Signaling message sending method and device, equipment and storage medium

Abstract

The invention relates to the technical field of communication, and discloses a signaling message sending method, device and equipment and a storage medium, and the signaling message sending method comprises the steps: analyzing a received current signaling through a pre-constructed time sequence analysis model, and obtaining an analysis result; the analysis result comprises whether the current signaling has a prepositive message or not, and predicting the next signaling; according to an analysis result, the current signaling is matched with a predicted signaling set, the predicted next signaling is matched with a to-be-forwarded signaling set, and the predicted signaling set stores various signalings which are obtained through historical prediction and are not sent; each received and unsent signaling is stored in the to-be-forwarded signaling set; and determining whether to perform signaling forwarding according to a matching result, if the matching is successful, performing signaling message forwarding, and if the matching is unsuccessful, temporarily storing the signaling message. By analyzing the timestamps and message contents of the signaling messages, wrong-sequence messages are automatically detected and corrected, and it is ensured that the signaling messages are transmitted according to a correct sequence.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a signaling message sending method, device, equipment and storage medium. Background Art

[0002] In cross-operator scenarios, IP Multimedia Subsystem (IMS) signaling needs to pass through multiple network nodes and border gateways, which are managed and maintained by different operators. Each operator's network architecture, equipment performance, and management strategy may be significantly different, which leads to multiple challenges in the transmission of signaling messages, such as network latency and jitter. This can cause varying degrees of delay in the transmission of signaling messages, or even misordering.

[0003] For the above-mentioned signaling message misordering problem, existing solutions are generally based on protocol stack implementation, relying on sequence number mechanism and retransmission mechanism. Although this method can be used to detect and correct the order of messages, it can improve the reliable transmission of messages to a certain extent. However, in large-scale network environments with high load or extremely poor network conditions, due to the large number of messages and complex network paths, existing solutions cannot completely avoid message loss caused by network congestion, and also bring additional network overhead and delay.

[0004] Therefore, there is an urgent need for a signaling message sending method that can make up for the defects of the message reordering mechanism based on the protocol stack, which can be independent of the sequence number of the signaling message and improve the efficiency and accuracy of signaling message processing. Summary of the invention

[0005] In view of this, the present application provides a signaling message sending method, device, equipment and storage medium, so that the signaling message is transmitted in the correct order, and the efficiency and accuracy of signaling message processing are improved. The technical solution is as follows.

[0006] In a first aspect, the present invention provides a method for sending a signaling message, the method comprising:

[0007] The received current signaling is analyzed by using a pre-built timing analysis model to obtain an analysis result; the analysis result includes whether the current signaling has a preceding message and a predicted next signaling.

[0008] When there is a preceding message in the current signaling, the current signaling is matched with the predicted signaling set to obtain a first matching result, and the predicted next signaling is matched with the signaling set to be forwarded to obtain a second matching result; the predicted signaling set stores various signaling that has been historically predicted and not sent; the signaling set to be forwarded stores various signaling that has been received and not sent.

[0009] When the first matching result is a successful match and the second matching result is a successful match, the successful match signaling indicated by the second matching result is taken out from the signaling set to be forwarded, and the successful match signaling is forwarded after forwarding the current signaling; when the first matching result is a successful match and the second matching result is a failed match, the current signaling is forwarded and the predicted next signaling is stored in the predicted signaling set.

[0010] The signaling message sending method provided by the present invention has the following advantages.

[0011] The signaling message sending method of the present invention analyzes and predicts the received signaling message through a pre-constructed timing analysis model, and determines whether the current signaling message has a preceding message and the next signaling message of the current signaling message. The timing analysis model is obtained by training a preset neural network model. Specifically, based on a large number of training signals acquired within a certain time period, its label vector and input feature vector are calculated, thereby constructing a training data set, and the training data set is provided to train the neural network model to obtain a timing analysis model. The timing analysis model can determine whether the current signaling is the first signaling and the next signaling of the signaling according to the timestamp and message content of the signaling message. If the current signaling is the first signaling, it can be forwarded directly. If it is not the first signaling, the signaling is matched with the pre-stored signaling set. If the match is successful, it means that the current signaling sequence is correct and can be forwarded. If the match fails, it means that the current signaling sequence is wrong and needs to be temporarily stored in the signaling set to be forwarded to wait for the arrival of the preceding signaling. Then the predicted next signaling is matched with the signaling set to be forwarded. If the match is successful, it means that the post-signaling of the current signaling has arrived in advance, and it is necessary to take the signaling from the signaling set to be forwarded and forward the signaling immediately after forwarding the current signaling; if the match fails, the predicted next signaling message is stored in the predicted signaling set and waits for matching the next time the signaling is received. The prediction and matching method of the present invention can be used to predict and analyze the timestamp and message content of the signaling message without relying on the sequence number of the signaling, and the overall content of the message and the business process are used to predict and reorganize the message sequence, automatically detect and correct the misordered signaling messages, and more accurately determine the sending order of the signaling messages, even in the case of sequence number loss or conflict. It can effectively make up for the defects of the signaling message reordering mechanism based on the protocol stack, improve the efficiency and accuracy of message processing, enhance the real-time and responsiveness of the system, and improve the scalability and maintainability of the system.

[0012] In an optional implementation, the signaling message sending method further includes: when the first matching result is a matching failure, storing the current signaling into a to-be-forwarded signaling set, and storing the predicted next signaling into a predicted signaling set.

[0013] In an optional implementation, the signaling message sending method further includes: when the current signaling does not have a preceding message, forwarding the current signaling and storing the predicted next signaling in a predicted signaling set.

[0014] In an optional implementation, the time series analysis model is obtained by training a preset neural network model.

[0015] In an optional embodiment, the signaling message sending method also includes: obtaining training signaling within a set time period; obtaining a pre-signaling tag of the training signaling based on whether the training signaling contains a pre-signaling; obtaining information about the next signaling of each signaling in the training signaling, and obtaining the next signaling tag of the training signaling; calculating the arrival time difference between each signaling in the training signaling and the corresponding next signaling, and using the time difference as a deletion time according to a set multiple to obtain a deletion time tag of the training signaling; obtaining a label vector of the training signaling based on the pre-signaling tag, the next signaling tag and the deletion time tag; obtaining an input feature vector of the training signaling; constructing a training data set based on the label vector and the input feature vector; and training the preset neural network model based on the training data set to obtain the timing analysis model.

[0016] In an optional embodiment, the signaling message sending method also includes: when there is a signaling to be forwarded in the signaling set to be forwarded, obtaining the current system time; calculating the difference between the storage time of each signaling to be forwarded in the signaling set to be forwarded and the current system time; and deleting the signaling to be forwarded whose difference is greater than the time threshold.

[0017] The signaling message sending method of the present invention sets a signaling message clearing mechanism to prevent message backlog. The timing analysis model synchronously predicts the upper limit of the waiting time to clear the accumulated messages, regularly checks the messages in the buffer, clears the timeout and unreached messages, and avoids message backlog. It can solve the processing bottleneck under high load, the complexity of multi-path transmission, the lack of real-time and responsiveness, and the scalability and maintainability problems of traditional solutions.

[0018] In a second aspect, the present invention provides a signaling message sending device, the device comprising:

[0019] The signaling analysis module is used to analyze the received current signaling through a pre-built timing analysis model to obtain an analysis result; the analysis result includes whether the current signaling has a preceding message and the predicted next signaling;

[0020] A signaling matching module, used for, when there is a preceding message in the current signaling, matching the current signaling with a predicted signaling set to obtain a first matching result, and matching the predicted next signaling with a signaling set to be forwarded to obtain a second matching result; the predicted signaling set stores various signalings that have been historically predicted and not sent; the signaling set to be forwarded stores various signalings that have been received and not sent;

[0021] A signaling sending module is used to, when the first matching result is a successful match and the second matching result is a successful match, take out the successful match signaling indicated by the second matching result from the signaling set to be forwarded, and forward the successful match signaling after forwarding the current signaling; when the first matching result is a successful match and the second matching result is a failed match, forward the current signaling and store the predicted next signaling in the predicted signaling set.

[0022] In an optional implementation, the signaling matching module is further used to: when the current signaling does not have a preceding message, forward the current signaling and store the predicted next signaling into the predicted signaling set.

[0023] In an optional implementation, the signaling sending module is further used to: when the first matching result is a matching failure, store the current signaling into the to-be-forwarded signaling set, and store the predicted next signaling into the predicted signaling set.

[0024] In an optional embodiment, the signaling message sending device also includes: a signaling cleaning module, which is used to obtain the current system time when there is a signal to be forwarded in the signaling set to be forwarded; calculate the difference between the storage time of each signal to be forwarded in the signaling set to be forwarded and the current system time; and delete the signal to be forwarded whose difference is greater than the time threshold.

[0025] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the signaling message sending method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0026] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the signaling message sending method of the first aspect or any corresponding embodiment thereof.

[0027] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the signaling message sending method of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 It is a flow chart of a signaling message sending method provided by an embodiment of the present invention.

[0030] Figure 2 The figure is a schematic diagram of an application scenario of a method for sending a signaling message according to an exemplary embodiment.

[0031] Figure 3 It is a logic block diagram of a timing analysis signaling reassembly server according to an exemplary embodiment.

[0032] Figure 4 The figure is a flowchart of a method for sending a signaling message according to an exemplary embodiment.

[0033] Figure 5 The figure is a flow chart of a signaling message clearing method according to an exemplary embodiment.

[0034] Figure 6 It is a structural diagram of a signaling message sending device provided in an embodiment of the present application.

[0035] Figure 7 It is a structural schematic diagram of a computer device provided by an optional embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution 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 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 those skilled in the art without making creative work are within the scope of protection of this application.

[0037] It should be understood that the "indication" mentioned in the embodiments of the present application can be a direct indication, an indirect indication, or an indication of an association relationship. For example, A indicates B, which can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association relationship between A and B.

[0038] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between two items, or an association relationship between the two items, or a relationship between indication and being indicated, configuration and being configured, and the like.

[0039] In an embodiment of the present application, "predefinition" can be achieved by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including a terminal device and a network device). The present application does not limit its specific implementation method.

[0040] First, the terms involved in this application are introduced.

[0041] IMS: (IP Multimedia Subsystem) IP Multimedia Subsystem;

[0042] SIP: (Session Initiation Protocol) Session Initiation Protocol;

[0043] QoS: (Quality of Service) service quality;

[0044] TSASRS: (Time series analysis signaling reassembly server) time series analysis signaling reassembly server;

[0045] CSeq: (Command Sequence Number) command sequence number;

[0046] P-CSCF: (Proxy-Call Session Control Function) Proxy call session control function, P-CSCF is the first entity that users contact in the IMS system, and plays the role of a unified entry point for IMS access networks. From the perspective of SIP, it is an outbound / inbound SIP proxy server. All SIP signaling, whether from user equipment (UE) or sent to UE, must pass through P-CSCF.

[0047] In modern communication networks, IP Multimedia Subsystem (IMS) has become an important infrastructure for providing high-quality multimedia communication services. IMS manages and controls multimedia sessions through the Session Initiation Protocol (SIP) and supports multiple communication forms such as voice, video, and instant messaging. However, when IMS signaling is transmitted between networks of different operators, network fluctuations and latency become a problem that cannot be ignored.

[0048] In cross-operator scenarios, IMS signaling needs to pass through multiple network nodes and border gateways, which are managed and maintained by different operators. The network architecture, equipment performance, and management strategies of each operator may vary significantly, which leads to multiple challenges in the transmission of signaling messages. Network fluctuations are usually manifested as network delays and jitters, which can cause varying degrees of delay in the transmission of signaling messages, or even misordering.

[0049] The existing solutions to message misordering are mainly based on protocol stack implementation. Take the SIP (Session Initiation Protocol) protocol stack as an example. The SIP protocol is one of the most commonly used signaling protocols in IMS, used to establish, modify and terminate multimedia sessions. The CSeq (Command Sequence Number) field in the SIP protocol is used to identify the sequence number of each request message. The receiver can determine the order of the messages based on the CSeq field.

[0050] Although the message reordering mechanism based on the protocol stack has solved the problem of misordered signaling to a certain extent, it still has significant defects in cross-operator scenarios. The misordered message discovery mechanism based on CSeq is only effective when CSeq is less than the previous message. When messages are missed or missing, the mechanism cannot solve the problem and will still cause session abnormalities due to processing messages in the wrong sequence. In addition, under cross-operator conditions, message misordering is common. After the traditional CSeq mechanism discovers the misorder and temporarily stores the signaling, it is difficult to effectively sort the signaling, and there is a lack of a message cleanup mechanism. At the same time, the message processing mechanism is rigid, resulting in the inability to sort successfully in time even after the resent message arrives, resulting in a backlog of internally stored signaling and low reordering efficiency.

[0051] Therefore, an embodiment of the present invention provides a signaling message sending method that does not rely on sequence numbers, but uses the overall content of the message and the business process to predict the reorganized message sequence and clearing time. By analyzing the message body, the message sending order can be more accurately determined, and even in the case of sequence number loss or conflict, the message can be correctly sorted. At the same time, in order to prevent message backlogs, the timing prediction scheme synchronously predicts the upper limit of the waiting time to clear the accumulated messages, regularly checks the messages in the buffer, clears the messages that have timed out and have not arrived, and avoids message backlogs. The process of the signaling message sending method of the embodiment of the present invention is as follows: Figure 1 As shown, the following steps are included.

[0052] S101. Analyze the received current signaling through a pre-built timing analysis model to obtain an analysis result; the analysis result includes whether the current signaling has a preceding message and a predicted next signaling.

[0053] Specifically, in step S101, judging whether there is a preceding message in the current signaling is to judge whether the current signaling is the first message. If there is no preceding message, it indicates that the current signaling is the first message and can be directly forwarded without sorting, which simplifies the process of sorting signaling messages. The predicted next signaling message can be the next signaling message itself or the identifier of the next signaling message.

[0054] Optionally, in step S101, the timing analysis model is obtained by training a preset neural network model. The specific process of the training includes: obtaining training signaling within a set time period; obtaining a pre-signaling label of the training signaling according to whether the training signaling contains a pre-signaling; obtaining the information of the next signaling of each signaling in the training signaling, and obtaining the next signaling label of the training signaling; calculating the arrival time difference between each signaling in the training signaling and the corresponding next signaling, and using the time difference as a set multiple as the deletion time to obtain the deletion time label of the training signaling; obtaining a label vector of the training signaling based on the pre-signaling label, the next signaling label and the deletion time label; obtaining the input feature vector of the training signaling; constructing a training data set according to the label vector and the input feature vector; training the preset neural network model according to the training data set to obtain the timing analysis model.

[0055] S102. When there is a preceding message in the current signaling, the current signaling is matched with the predicted signaling set to obtain a first matching result, and the predicted next signaling is matched with the signaling set to be forwarded to obtain a second matching result; the predicted signaling set stores various signalings that have been historically predicted and not sent; the signaling set to be forwarded stores various signalings that have been received and not sent.

[0056] Specifically, in step S102, matching is only required when there is a preceding message in the current signaling message. The predicted signaling set stores signaling messages obtained by historical prediction, and the signaling set to be forwarded stores received signaling. Both signaling sets contain signaling messages that have not yet been forwarded. If a signaling message is forwarded after a successful match, the corresponding signaling messages in the two signaling sets need to be deleted.

[0057] Optionally, in step S102, when there is no preceding message for the current signaling, the current signaling is forwarded and the predicted next signaling is stored in a predicted signaling set.

[0058] S103. When the first matching result is a successful match and the second matching result is a successful match, take out the successful match signaling indicated by the second matching result from the signaling set to be forwarded, and forward the successful match signaling after forwarding the current signaling; when the first matching result is a successful match and the second matching result is a failed match, forward the current signaling and store the predicted next signaling in the predicted signaling set.

[0059] Specifically, in step S103, if the current signaling successfully matches the predicted signaling set, it indicates that the current signaling message sequence is correct and can be directly forwarded. If the match fails, it indicates that the current signaling message sequence is incorrect and needs to be temporarily stored in the signaling set to be forwarded and wait for the arrival of the preceding signaling. If the predicted next signaling successfully matches the signaling set to be forwarded, it indicates that the next signaling of the current signaling has arrived in advance, and the signaling is taken out from the signaling set to be forwarded and forwarded immediately after the current signaling is forwarded. If the match fails, the predicted next signaling message is stored in the predicted signaling set and waits for matching when the next signaling is received.

[0060] Optionally, in step S103, when the first matching result is a matching failure, the current signaling is stored in a set of signalings to be forwarded, and the predicted next signaling is stored in a set of predicted signalings.

[0061] In an optional implementation, the signaling sending method provided in this embodiment is further provided with a signaling clearing mechanism. Specifically, when there are signals to be forwarded in the signaling set to be forwarded, the current system time is obtained; the difference between the storage time of each signal to be forwarded in the signaling set to be forwarded and the current system time is calculated; and the signals to be forwarded whose difference is greater than the time threshold are deleted. By periodically checking the messages in the buffer, the messages that have timed out and have not arrived are cleared to avoid message backlog. The processing bottlenecks under high load, the complexity of multi-path transmission, the lack of real-time and responsiveness, and the scalability and maintainability problems of the traditional solution can be solved.

[0062] In summary, the signaling message sending method provided by the embodiment of the present invention analyzes and predicts the received signaling message through a pre-constructed timing analysis model, and determines whether the current signaling message has a preceding message and the next signaling message of the current signaling message. The timing analysis model is obtained by training a preset neural network model. Specifically, based on a large number of training signals acquired within a certain time period, its label vector and input feature vector are calculated, thereby constructing a training data set, and the training data set is provided to train the neural network model to obtain a timing analysis model. The timing analysis model can determine whether the current signaling is the first signaling and the next signaling of the signaling according to the timestamp and message content of the signaling message. If the current signaling is the first signaling, it can be forwarded directly. If it is not the first signaling, the signaling is matched with the pre-stored signaling set. If the match is successful, it means that the current signaling sequence is correct and can be forwarded. If the match fails, it means that the current signaling sequence is wrong and needs to be temporarily stored in the signaling set to be forwarded to wait for the arrival of the preceding signaling. Then the predicted next signaling is matched with the signaling set to be forwarded. If the match is successful, it means that the post-signaling of the current signaling has arrived in advance, and it is necessary to take the signaling from the signaling set to be forwarded and forward the signaling immediately after forwarding the current signaling; if the match fails, the predicted next signaling message is stored in the predicted signaling set and waits for the next signaling to be received for matching. Through the prediction and matching method of the present invention, it is possible to not rely on the sequence number of the signaling, but to perform prediction and analysis through the timestamp and message content of the signaling message, use the overall content of the message and the business process to predict and reorganize the message sequence, automatically detect and correct the misordered signaling messages, and more accurately determine the sending order of the signaling messages, even in the case of sequence number loss or conflict. It can effectively make up for the defects of the signaling message reordering mechanism based on the protocol stack mode, improve the efficiency and accuracy of message processing, enhance the real-time and responsiveness of the system, and improve the scalability and maintainability of the system. At the same time, a signaling message cleaning mechanism is set to regularly clear the signaling messages that have timed out and have not arrived, effectively prevent the backlog of signaling messages, and maintain the efficient operation of the system.

[0063] Based on the above embodiment, a specific example will be used to illustrate the signaling sending method of the embodiment of the present invention. The application scenario of this example is as follows: Figure 2 As shown, it includes: a signaling reorganization server based on timing analysis and a timing analysis model.

[0064] The structure of the signaling reorganization server based on timing analysis is as follows Figure 3As shown, it includes: a central controller, an alternative message area, a waiting message area and several interfaces, through which signaling messages are received and sent. Specifically, the X1 interface is used by the central controller to transmit the pre-processed message vector to the neural network, and at the same time, the neural network is used to transmit the predicted result to the central controller; the X2 interface is used by the central controller to transmit the current signaling to the alternative message area to determine whether it is disordered, and at the same time, the alternative message area is used to send a confirmation message to the central controller to control the central controller to forward the current signaling; the X3 interface is used by the central controller to transmit the predicted next signaling feature to the waiting buffer area, from the waiting buffer area, and at the same time, the waiting buffer area sends a confirmation message and the signaling to be forwarded to the central controller to control the central controller to forward the forwarding signaling; the Y1 interface is used by the external domain network to send signaling to the central controller for signaling reorganization, and at the same time, the external domain network is used to send the network status to the central controller to predict the arrival of the next signaling; the Y2 interface is used by the central controller to send the reorganized sending signaling to the external domain network.

[0065] exist Figure 2 In the scenario, when the IMS network receives signaling, it first analyzes the signaling through timing analysis to reorganize the server. It analyzes the current signaling in real time based on the business process through timing analysis to determine whether there is a message disorder.

[0066] Specifically, the processing flow is as follows Figure 4 As shown. When the IMS network receives the signaling, it first passes it to the timing analysis signaling reassembly server. After receiving the signaling, the server immediately performs timing analysis, analyzes the timestamp, message header and other key information of the signaling through the timing analysis model, predicts the arrival time, sequence number and method name of the next signaling, and determines whether the current signaling is the first message of a certain service. If the current signaling is not the first message, the server sends it to the candidate message area for matching. In the candidate message area, the server tries to match the current signaling with the existing signaling. If the match is successful, it means that the current signaling sequence is correct and can be processed directly. If the match fails, the server considers the signaling to be a misordered message and sends it to the waiting buffer area to wait for the arrival of the preceding message. In the waiting buffer area, the server continues to monitor the arrival of the signaling. At the same time, the server sends it to the waiting buffer area for matching according to the predicted next signaling information. If the match is successful, it means that the subsequent signaling arrives in advance. At this time, the server first sends the current signaling, and then immediately sends the matched subsequent signaling to ensure the correctness of the message sequence.

[0067] In addition, there is a cleaning timer inside the timing analysis signaling reassembly server to regularly clean up the timed-out signaling in the waiting buffer. The cleaning process is as follows: Figure 5As shown, when the cleaning timer times out, start checking the status of the waiting buffer; if there is a signaling to be forwarded in the waiting buffer, record the current system time as the reference time; traverse all the signaling to be forwarded in the waiting buffer, and calculate the difference between the storage time of each signaling and the current system time; if the time difference exceeds the predicted cleaning time, delete the signaling to be forwarded; after traversing all the signaling to be forwarded, restart the cleaning timer. If there is no signaling to be forwarded in the waiting buffer, restart the cleaning timer directly. In this way, the server can maintain good performance, avoid processing delays and resource waste caused by signaling backlogs, provide more reliable protection for IMS signaling transmission across networks, and ensure high-quality multimedia communication services.

[0068] The signaling sending process of this example relies on a timing analysis model to perform predictive analysis on the currently received signaling. The timing analysis model is obtained by training a neural network model. The specific training process takes the SIP protocol as an example and includes the following steps.

[0069] Use the signaling tracking method to track the SIP signaling for a certain period of time as the original data set for TSASRS training. According to the actual business, extract the signaling at the beginning of each business, and set it to 0 if there is a preceding signaling, and set the vector of the remaining signaling to 1 to obtain the preceding signaling label. Calculate the feature label of the next signaling: extract the [from, to, cseq, call-id, type] of each signaling next signaling, where [from, to, cseq, call-id] are all corresponding header field data, time is the arrival timestamp, and type is the message type. The corresponding mapping relationship is shown in the mapping relationship table in Table 1. Calculate the time difference Δt between this signaling and its post-vector, and use twice the time as the deletion time label.

[0070] Message Type INVITE ACK BYE CANCEL OPTIONS REGISTER Mapping ID 0 1 2 3 4 5 Message Type INFO REFER MESSAGE SUBSCRIBE NOTIFY PUBLISH Mapping ID 6 7 8 9 10 11 Message Type PRACK Mapping ID 12

[0071] Table 1 Mapping relationship table

[0072] The above signaling data is normalized to avoid the influence of some vectors. The previous signaling label, the next signaling label and the deletion time label are integrated to obtain the label vector, which is expressed as:

[0073] y i =[first_message,from,to,cseq,call-id,type,ΔT];

[0074] Where: first_message is whether there is a pre-signaling tag, [from, to, cseq, call-id] are all corresponding header field data, type is the message type, and ΔT is the deletion time.

[0075] After obtaining the label vector, the input vector needs to be processed to extract the features [from, to, cseq, call-id, type, time] in the SIP signaling message header, where [from, to, cseq, call-id, type] is consistent with the next signaling, and time is the relative arrival time of the signaling. The input feature vector is obtained by integration, and the expression is:

[0076] x i =[from,to,cseq,call-id,type,time];

[0077] Integrate the feature vector and label vector into a training data set, the expression is:

[0078] D L ={(x1,y1),(x2,y2),...,(x m ,y m )};

[0079] The neural network model is trained based on the training data set, and the prediction expression of the neural network model is:

[0080]

[0081] Based on the prediction expression, the loss function is calculated as follows:

[0082]

[0083] Based on the loss function, the gradient is updated through the back propagation algorithm, and the expression is:

[0084]

[0085] Where θ is the neural network parameter and α is the learning rate.

[0086] In summary, the signaling message sending method provided in this example does not rely on the sequence number of the signaling, but performs predictive analysis through the timestamp and message content of the signaling message, and uses the overall content of the message and the business process to predict and reorganize the message sequence, automatically detect and correct the misordered signaling messages, and can more accurately determine the sending order of the signaling messages, even in the case of sequence number loss or conflict. It can effectively make up for the defects of the signaling message reordering mechanism based on the protocol stack, improve the efficiency and accuracy of message processing, enhance the real-time and responsiveness of the system, and improve the scalability and maintainability of the system. At the same time, a signaling message cleaning mechanism is set up to regularly clear signaling messages that have timed out and have not arrived, effectively preventing the backlog of signaling messages and maintaining the efficient operation of the system.

[0087] In the embodiment of the present application, a signaling message sending device is also provided, and the device is used to implement the above-mentioned embodiment and preferred implementation mode, and the description has been made no further. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0088] The present application provides a signaling message sending device. Figure 6 : is a structural diagram of a signaling message sending device provided in an embodiment of the present application, the device comprising:

[0089] The signaling analysis module 601 is used to analyze the received current signaling through a pre-built timing analysis model to obtain an analysis result; the analysis result includes whether the current signaling has a preceding message and the predicted next signaling;

[0090] The signaling matching module 602 is used to match the current signaling with a predicted signaling set to obtain a first matching result when there is a preceding message in the current signaling, and to match the predicted next signaling with a signaling set to be forwarded to obtain a second matching result; the predicted signaling set stores various signalings that have been historically predicted and not sent; and the signaling set to be forwarded stores various signalings that have been received and not sent;

[0091] The signaling sending module 603 is used to, when the first matching result is a successful match and the second matching result is a successful match, take out the successful match signaling indicated by the second matching result from the signaling set to be forwarded, and forward the successful match signaling after forwarding the current signaling; when the first matching result is a successful match and the second matching result is a failed match, forward the current signaling and store the predicted next signaling in the predicted signaling set.

[0092] In an optional implementation, the signaling matching module 602 is further used to: when the current signaling does not have a preceding message, forward the current signaling and store the predicted next signaling into the predicted signaling set.

[0093] In an optional implementation, the signaling sending module 603 is further used to: when the first matching result is a matching failure, store the current signaling into the to-be-forwarded signaling set, and store the predicted next signaling into the predicted signaling set.

[0094] In an optional embodiment, the signaling message sending device also includes: a signaling cleaning module 604, which is used to obtain the current system time when there is a signal to be forwarded in the signaling set to be forwarded; calculate the difference between the storage time of each signal to be forwarded in the signaling set to be forwarded and the current system time; and delete the signal to be forwarded whose difference is greater than the time threshold.

[0095] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0096] The signaling message sending device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0097] The embodiment of the present invention also provides a computer device having the above Figure 6 The signaling message sending device shown.

[0098] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphic information in a graphical user interface on an external input / output device (such as a display device coupled to an interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0099] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0100] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0101] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0102] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0103] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0104] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0105] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0106] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for sending a signaling message, characterized in that: include: Analyze the received current signaling through the pre-built timing analysis model to obtain the analysis result; The analysis result includes whether the current signaling has a preceding message and the predicted next signaling; When there is a preceding message in the current signaling, the current signaling is matched with the predicted signaling set to obtain a first matching result, and the predicted next signaling is matched with the signaling set to be forwarded to obtain a second matching result; the predicted signaling set stores various signalings that have been historically predicted and not sent; the signaling set to be forwarded stores various signalings that have been received and not sent; When the first matching result is a successful match and the second matching result is a successful match, the successful match signaling indicated by the second matching result is taken out from the signaling set to be forwarded, and the successful match signaling is forwarded after forwarding the current signaling; when the first matching result is a successful match and the second matching result is a failed match, the current signaling is forwarded and the predicted next signaling is stored in the predicted signaling set.

2. The method according to claim 1, characterized in that The method further comprises: When the first matching result is a matching failure, the current signaling is stored in the to-be-forwarded signaling set, and the predicted next signaling is stored in the predicted signaling set.

3. The method according to claim 2, characterized in that The method further comprises: When the current signaling does not have a preceding message, the current signaling is forwarded and the predicted next signaling is stored in the predicted signaling set.

4. The method according to any one of claims 1 to 3, characterized in that: The time series analysis model is obtained by training a preset neural network model.

5. The method according to claim 4, characterized in that The method further comprises: Obtain training signaling within a set time period; Obtaining a pre-signaling tag of the training signaling according to whether the training signaling includes a pre-signaling; Obtain information about the next signaling of each signaling in the training signaling, and obtain a next signaling label of the training signaling; Calculate the arrival time difference between each signaling in the training signaling and the corresponding next signaling, use the time difference as a set multiple as the deletion time, and obtain the deletion time label of the training signaling; Obtaining a label vector of the training signaling based on the previous signaling label, the next signaling label, and the deletion time label; Obtaining an input feature vector of the training signaling; Constructing a training data set according to the label vector and the input feature vector; The preset neural network model is trained according to the training data set to obtain the time series analysis model.

6. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: When there is a signaling to be forwarded in the signaling set to be forwarded, obtaining the current system time; Calculating the difference between the storage time of each signaling to be forwarded in the signaling set to be forwarded and the current system time; The signaling to be forwarded whose difference is greater than the time threshold is deleted.

7. A signaling message sending device, characterized in that: include: The signaling analysis module is used to analyze the received current signaling through a pre-built timing analysis model to obtain analysis results; The analysis result includes whether the current signaling has a preceding message and the predicted next signaling; A signaling matching module, used for, when there is a preceding message in the current signaling, matching the current signaling with a predicted signaling set to obtain a first matching result, and matching the predicted next signaling with a signaling set to be forwarded to obtain a second matching result; the predicted signaling set stores various signalings that have been historically predicted and not sent; the signaling set to be forwarded stores various signalings that have been received and not sent; A signaling sending module is used to, when the first matching result is a successful match and the second matching result is a successful match, take out the successful match signaling indicated by the second matching result from the signaling set to be forwarded, and forward the successful match signaling after forwarding the current signaling; when the first matching result is a successful match and the second matching result is a failed match, forward the current signaling and store the predicted next signaling in the predicted signaling set.

8. The device according to claim 7, characterized in that The device also includes: The signaling cleaning module is used to obtain the current system time when there is a signaling to be forwarded in the signaling set to be forwarded; calculate the difference between the storage time of each signaling to be forwarded in the signaling set to be forwarded and the current system time; and delete the signaling to be forwarded whose difference is greater than the time threshold.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the signaling message sending method according to any one of claims 1 to 6 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the signaling message sending method according to any one of claims 1 to 6.

Images