Signaling control method and device, computer device, storage medium and program product

Abstract

The application relates to a signaling control method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: performing prediction processing on a signaling load index parameter of a signaling processing network element in a next period according to a signaling load index parameter of the signaling processing network element in a current period, to obtain a predicted signaling load index parameter, wherein the signaling load index parameter is used to represent a signaling load condition of the signaling processing network element; determining whether the signaling processing network element will be overloaded in the next period according to the predicted signaling load index parameter; and if it is determined that the signaling processing network element will be overloaded in the next period, performing a signaling flow control process to reduce the signaling load of the signaling processing network element. By using the method, the signaling overload condition of the signaling processing network element can be predicted in advance, and a signaling flow control strategy can be adopted in advance to reduce the signaling load of the signaling processing network element, so that the signaling processing network element can be prevented from being overloaded, and the processing efficiency of the signaling overload can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and in particular to a signaling control method and device, a computer device, a storage medium and a program product. BACKGROUND

[0002] With the development of communication technology, the communication requirements of high speed, low latency and high reliability for network communication are becoming higher and higher. As a result, there are more and more registration requests for network communication. For a core network device, if a large number of registration requests initiated by terminals are received within a short time, the problem of signaling overload is likely to occur, forming a surge registration. Surge registration will cause abnormal service processing.

[0003] In the traditional technology, an operation and maintenance personnel manually sets a signaling capacity threshold of the core network device, and continuously monitors the actual signaling load of the core network device. In the case of signaling overload of the core network device, the operation and maintenance personnel manually intervenes to adjust the signaling capacity threshold.

[0004] However, the traditional processing method for signaling overload has the problem of low efficiency. SUMMARY

[0005] Therefore, it is necessary to provide a signaling control method, device, computer device, computer readable storage medium and computer program product capable of improving the processing efficiency of signaling overload in view of the above technical problems.

[0006] In a first aspect, the present application provides a signaling control method. The method comprises:

[0007] performing prediction processing on a signaling load index parameter of the signaling processing network element in a next time period according to a signaling load index parameter of the signaling processing network element in a current time period, to obtain a predicted signaling load index parameter, wherein the signaling load index parameter is used to represent a signaling load condition of the signaling processing network element;

[0008] determining whether the signaling processing network element will have signaling overload in the next time period according to the predicted signaling load index parameter;

[0009] if it is determined that the signaling processing network element will have signaling overload in the next time period, performing a signaling flow control process to reduce the signaling load of the signaling processing network element.

[0010] In one of the embodiments, the performing prediction processing on a signaling load index parameter of the signaling processing network element in a next time period according to a signaling load index parameter of the signaling processing network element in a current time period, to obtain a predicted signaling load index parameter, comprises:

[0011] The signaling processing network element inputs the signaling load index parameter of the signaling processing network element in the current period into the preset signaling load prediction model, and performs prediction processing on the signaling load index parameter of the signaling processing network element in the next period through the preset signaling load prediction model to obtain a predicted signaling load index parameter. The preset signaling load prediction model is trained based on the signaling load index parameters of the signaling processing network element in each period.

[0012] In one of the embodiments, the signaling load index parameter includes at least one index parameter, and the signaling load prediction model includes an index parameter prediction model corresponding to each index parameter. The signaling processing network element inputs the signaling load index parameter of the signaling processing network element in the current period into the preset signaling load prediction model, and performs prediction processing on the signaling load index parameter of the signaling processing network element in the next period through the preset signaling load prediction model to obtain a predicted signaling load index parameter. The method includes the following steps:

[0013] For each index parameter in the signaling load index parameter, a target index parameter prediction model corresponding to the index parameter is determined.

[0014] The signaling processing network element inputs the index parameter of the signaling processing network element in the current period into the target index parameter prediction model, and performs prediction processing on the index parameter of the signaling processing network element in the next period through the target index parameter prediction model to obtain a predicted index parameter corresponding to the index parameter.

[0015] In one of the embodiments, the signaling processing network element determines whether the signaling processing network element will appear signaling overload in the next period according to the predicted signaling load index parameter, which includes the following steps:

[0016] According to the predicted index parameter corresponding to each index parameter and the index overload threshold corresponding to each index parameter, it is judged whether each index parameter will appear signaling overload in the next period to obtain a signaling overload result.

[0017] According to the signaling overload result of each index parameter in the next period, it is determined whether the signaling processing network element will appear signaling overload in the next period.

[0018] In one of the embodiments, the signaling processing network element determines whether the signaling processing network element will appear signaling overload in the next period according to the signaling overload result of each index parameter in the next period, which includes the following steps:

[0019] If there is at least one index parameter whose signaling overload result in the next period represents that signaling overload will appear, it is determined that the signaling processing network element will appear signaling overload in the next period.

[0020] In one of the embodiments, the index parameter includes a request message, and according to the predicted index parameter corresponding to each index parameter and the index overload threshold corresponding to each index parameter, it is judged whether each index parameter will appear signaling overload in the next period to obtain a signaling overload result, which includes the following steps:

[0021] For each request message, it is compared whether the predicted request message quantity corresponding to the request message is greater than or equal to the request message threshold corresponding to the request message;

[0022] If the predicted request message quantity corresponding to the request message is greater than or equal to the request message threshold corresponding to the request message, it is determined that the request message will cause signaling overload in the next time period, and a signaling overload result representing that the signaling overload will occur is obtained.

[0023] In one of the embodiments, the index parameters include active users, and according to the predicted index parameters corresponding to each index parameter and the index overload threshold corresponding to each index parameter, it is determined whether each index parameter will cause signaling overload in the next time period, and a signaling overload result is obtained, including:

[0024] For each active user, it is compared whether the predicted active user quantity corresponding to the active user is less than or equal to the active user threshold corresponding to the active user;

[0025] If the predicted active user quantity corresponding to the active user is less than or equal to the active user threshold corresponding to the active user, it is determined that the active user will cause signaling overload in the next time period, and a signaling overload result representing that the signaling overload will occur is obtained.

[0026] In one of the embodiments, if it is determined that the signaling processing network element will cause signaling overload in the next time period, a signaling flow control process is performed to reduce the signaling load of the signaling processing network element, including:

[0027] If it is determined that the signaling processing network element will cause signaling overload in the next time period, a first signaling flow control request is sent to the signaling forwarding network element to instruct the signaling forwarding network element to reduce the signaling data sent to the signaling processing network element;

[0028] A second signaling flow control request is sent to the entry network element to instruct the entry network element to reduce the signaling data sent to the signaling processing network element.

[0029] In one of the embodiments, the first signaling flow control request includes an outflow control value of the signaling forwarding network element per unit time, the second signaling flow control request includes an outflow control value of the entry network element per unit time, and the outflow control value per unit time is negatively correlated with the signaling overload degree.

[0030] In one of the embodiments, the entry network element includes a 4G entry network element, a 5G entry network element and a VoLTE entry network element, and the signaling flow control priority of the VoLTE entry network element is greater than the signaling flow control priority of the 4G entry network element and the 5G entry network element.

[0031] In a second aspect, the present application also provides a signaling control device. The device includes:

[0032] The prediction module is configured to perform prediction processing on the signaling load index parameter of the signaling processing network element in the next time period according to the signaling load index parameter of the signaling processing network element in the current time period, to obtain a predicted signaling load index parameter, wherein the signaling load index parameter is used to represent the signaling load condition of the signaling processing network element.

[0033] The determination module is configured to determine whether the signaling processing network element will be overloaded in the next time period according to the predicted signaling load index parameter.

[0034] The execution module is configured to perform a signaling flow control process to reduce the signaling load of the signaling processing network element if it is determined that the signaling processing network element will be overloaded in the next time period.

[0035] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor. The memory stores a computer program. The processor implements the steps of the signaling control method in the first aspect when executing the computer program.

[0036] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps of the signaling control method in the first aspect.

[0037] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program. The computer program is executed by a processor to implement the steps of the signaling control method in the first aspect.

[0038] The signaling control method, device, computer device, storage medium and computer program product described above, the server performs prediction processing on the signaling load index parameter of the signaling processing network element in the next time period according to the signaling load index parameter of the signaling processing network element in the current time period, to obtain a predicted signaling load index parameter; then, according to the predicted signaling load index parameter, it is determined whether the signaling processing network element will appear signaling overload in the next time period; if it is determined that the signaling processing network element will appear signaling overload in the next time period, a signaling flow control process is performed to reduce the signaling load of the signaling processing network element; wherein the signaling load index parameter is used to represent the signaling load condition of the signaling processing network element. That is, in the present application, when processing the signaling overload of the signaling processing network element, the predicted signaling load index parameter in the next time period is predicted through the signaling load index parameter of the signaling processing network element in the current time period, and whether the signaling overload condition will appear in the next time period is judged based on the predicted signaling load index parameter in the next time period; that is, in the present application, the signaling overload condition of the signaling processing network element can be predicted in advance, and when it is predicted that the signaling processing network element will appear signaling overload in the next time period, the signaling flow control strategy is taken in advance to reduce the signaling load of the signaling processing network element, so as to avoid the signaling processing network element from appearing signaling overload; compared with the way of taking the signaling flow control strategy when the signaling processing network element has appeared signaling overload, the early prediction method of the present application can greatly reduce the probability of the signaling processing network element appearing signaling overload, and even can ensure that the signaling processing network element no longer appears signaling overload condition; so as to ensure the stable and efficient operation of the signaling processing network element, and greatly improve the processing efficiency of the signaling overload of the signaling processing network element.

[0039] In addition, by using the method in the present application, in the process of network communication, the operation and maintenance personnel do not need to participate, and the operation and maintenance personnel do not need to monitor the signaling processing network element in real time, which reduces the human input; and compared with the method of artificially judging signaling overload and artificially adjusting signaling capacity, the method of the present application can also greatly improve the processing efficiency of signaling overload. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 It is a traditional signaling overload control schematic diagram;

[0041] Figure 2 It is an application environment diagram of the signaling control method in one embodiment;

[0042] Figure 3 It is a flowchart of the signaling control method in one embodiment;

[0043] Figure 4 It is a flowchart of the signaling control method in another embodiment;

[0044] Figure 5Flowchart of signaling control method in another embodiment

[0045] Figure 6 Signaling control flowchart proposed in the present application

[0046] Figure 7 Signaling flow control flowchart proposed in the present application

[0047] Figure 8 Structural block diagram of signaling control device in one embodiment

[0048] Figure 9 Internal structural diagram of computer device in one embodiment DETAILED DESCRIPTION

[0049] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0050] The signaling control method proposed in the embodiments of the present application is suitable for the field of communication technology, especially for the field of network technology and security, and can be applied to 4G / 5G / VoLTE core network scenarios.

[0051] Due to reasons such as recovery of network interruption or disaster recovery switching, batch Internet of Things terminals being configured to access the network at the same time, etc., a large number of terminals will simultaneously initiate registration requests in a short period of time, forming a surge of registration, which brings a large amount of signaling load to the Home Subscriber Server (HSS) in the 4G core network / Unified Data Management (UDM) in the 5G core network; if the signaling load exceeds the upper limit of the processing capacity of the HSS / UDM, a large number of service messages will fail or be discarded, resulting in persistent user 4G / 5G signal loss or data / call / sms service abnormalities, etc.

[0052] Reference Figure 1 As shown, the existing method in the industry is usually to estimate the network processing capacity by the operation and maintenance personnel, configure a "static" signaling capacity threshold at the entry network element, and prevent surge registration. However, the estimation accuracy of the "static" threshold is low, and it cannot adapt to the dynamic changes of network processing capacity (such as the decrease of processing capacity caused by network element failure, etc.), so the operation and maintenance personnel need to continuously observe the HSS / UDM signaling load index data, and manually intervene to adjust the signaling capacity threshold when necessary.

[0053] Specifically, an operation and maintenance personnel estimates the overall processing capacity of the network according to operation and maintenance experience, configures a signaling capacity threshold at an entry network element of Voice over Long-Term Evolution (VoLTE), 4G Evolved Packet Core (EPC), and 5G Core (5GC), limits the registration signaling passing through per unit time to prevent surge registration impact, then the operation and maintenance personnel observes the signaling load related index values of HSS and UDM to determine whether signaling overload occurs, and if signaling overload occurs, the operation and maintenance personnel should intervene in an emergency to adjust the signaling capacity threshold at the entry network element of VoLTE, EPC, and 5GC.

[0054] However, the traditional way of manually monitoring signaling and processing signaling overload by operation and maintenance personnel has the problem of low processing efficiency, which is not conducive to the efficient operation of the network.

[0055] Based on this, the embodiment of the present application proposes a signaling control method, which protects surge registration of HSS / UDM based on Network Data Analytics Function (NWDAF), without manual intervention, and can improve the processing efficiency of signaling overload.

[0056] The signaling control method provided by the embodiment of the present application can be applied to an application environment as shown in Figure 2 . The terminal 102 communicates with the server 104 through the network, the server 104 can be a core network server, and the data storage system can store data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0057] In one embodiment, as shown in Figure 3 , a signaling control method is provided, which is taken as an example to illustrate the server in Figure 2 , including the following steps:

[0058] Step 302, according to the signaling load index parameter of the signaling processing network element in the current period, the signaling load index parameter of the signaling processing network element in the next period is predicted and processed to obtain the predicted signaling load index parameter.

[0059] The signaling load indicator parameter is used to represent the signaling load of the signaling processing network element. For example, the signaling load indicator parameter can include, but is not limited to, the request message received by the signaling processing network element, the active user, and the like. The signaling processing network element can include an HSS, a UDM, and the like.

[0060] For example, the server can obtain the signaling load indicator parameters of the signaling processing network element in the current period, and perform prediction processing on the signaling load indicator parameters of the signaling processing network element in the next period according to the signaling load indicator parameters, to obtain the predicted signaling load indicator parameters corresponding to the signaling load indicator parameters, respectively.

[0061] For each signaling load indicator parameter, the server can perform prediction on the signaling load indicator parameter in the next period according to the signaling load indicator parameter in the current period and the signaling load indicator parameters in the historical periods, to obtain the predicted signaling load indicator parameter corresponding to the signaling load indicator parameter.

[0062] Optionally, for each signaling load indicator parameter, the server can construct a preset signaling load prediction model corresponding to the signaling load indicator parameter according to the signaling load indicator parameters in the historical periods. For example, an initial deep learning time series prediction (Temporal Fusion Transformers, TFT for short) algorithm can be trained based on the signaling load indicator parameters in the historical periods, to obtain the preset signaling load prediction model corresponding to the signaling load indicator parameter, to form an indicator inference prediction capability.

[0063] Based on this, the server can input the signaling load indicator parameters of the signaling processing network element in the current period into the preset signaling load prediction model, and perform prediction processing on the signaling load indicator parameters of the signaling processing network element in the next period by the preset signaling load prediction model, to obtain the predicted signaling load indicator parameters.

[0064] Further, in a case where the signaling load indicator parameter comprises at least one indicator parameter, the signaling load prediction model comprises an indicator parameter prediction model corresponding to each indicator parameter; then, the server, when inputting the signaling load indicator parameter of the signaling processing network element in the current time period into the preset signaling load prediction model, and performing prediction processing on the signaling load indicator parameter of the signaling processing network element in the next time period by using the preset signaling load prediction model to obtain the predicted signaling load indicator parameter, can comprise: determining, for each indicator parameter in the signaling load indicator parameter, a target indicator parameter prediction model corresponding to the indicator parameter, and then inputting the indicator parameter of the signaling processing network element in the current time period into the target indicator parameter prediction model corresponding to the indicator parameter, and performing prediction processing on the indicator parameter of the signaling processing network element in the next time period by using the target indicator parameter prediction model to obtain the predicted indicator parameter corresponding to the indicator parameter.

[0065] In step 304, whether the signaling processing network element will be overloaded in the next time period is determined according to the predicted signaling load indicator parameter.

[0066] For example, the server can determine whether the predicted signaling load indicator parameter satisfies a preset signaling overload condition corresponding to the signaling load indicator parameter based on the preset signaling overload condition; if the predicted signaling load indicator parameter satisfies the preset signaling overload condition, it can be determined that the signaling processing network element will be overloaded in the next time period; if the predicted signaling load indicator parameter does not satisfy the preset signaling overload condition, it can be determined that the signaling processing network element will not be overloaded in the next time period.

[0067] In a case where the signaling load indicator parameter comprises multiple indicator parameters, for each indicator parameter, a corresponding preset signaling overload condition can be set; then, in one implementation, if there is a predicted signaling load indicator parameter that satisfies the preset signaling overload condition corresponding thereto, it can be determined that the signaling processing network element will be overloaded in the next time period; in another implementation, if there are multiple predicted signaling load indicator parameters that simultaneously satisfy the preset signaling overload conditions corresponding thereto, it can be determined that the signaling processing network element will be overloaded in the next time period.

[0068] It should be noted that the plurality of predicted signaling load indicator parameters can include a plurality of predicted signaling load indicator parameters under the same type of signaling load indicator parameter, such as a plurality of different request messages under the request message type; or can include a plurality of predicted signaling load indicator parameters under different types of signaling load indicator parameters, such as at least one request message under the request message type and at least one active user under the active user type. In addition, whether the plurality of predicted signaling load indicator parameters under the same type of signaling load indicator parameter or the plurality of predicted signaling load indicator parameters under different types of signaling load indicator parameters, can include a plurality of predicted signaling load indicator parameters of the same signaling processing network element, such as a plurality of predicted signaling load indicator parameters of the HSS network element; or can include a plurality of predicted signaling load indicator parameters of different signaling processing network elements, such as at least one predicted signaling load indicator parameter of the HSS network element and at least one predicted signaling load indicator parameter of the UDM network element; the type combination of each predicted signaling load indicator parameter involved in the signaling overload judgment of the plurality of predicted signaling load indicator parameters in the embodiment of the present application is not limited.

[0069] Step 306, if it is determined that the signaling processing network element will be overloaded in the next period, a signaling flow control process is performed to reduce the signaling load of the signaling processing network element.

[0070] The signaling flow control process is used to limit the signaling received by the signaling processing network element to reduce the signaling load of the signaling processing network element. Illustratively, the signaling flow control process can include modifying the signaling capacity threshold of the entry network element in the core network to reduce the signaling flow output by the entry network element, thereby reducing the signaling flow received by the signaling processing network element and reducing the signaling load of the signaling processing network element.

[0071] Illustratively, the server can execute the signaling flow control process and send a signaling flow control request to the entry network element in the core network to instruct the entry network element to reduce the signaling flow sent to the signaling processing network element in the case of determining that the signaling processing network element will be overloaded in the next period.

[0072] In the signaling control method, the server performs prediction processing on the signaling load index parameter of the signaling processing network element in the next time period according to the signaling load index parameter of the signaling processing network element in the current time period, to obtain a predicted signaling load index parameter; then, according to the predicted signaling load index parameter, it is determined whether the signaling processing network element will be overloaded in the next time period; if it is determined that the signaling processing network element will be overloaded in the next time period, a signaling flow control process is performed to reduce the signaling load of the signaling processing network element; wherein the signaling load index parameter is used to represent the signaling load condition of the signaling processing network element. That is, in the present application, when processing the signaling overload of the signaling processing network element, the predicted signaling load index parameter in the next time period is predicted through the signaling load index parameter in the current time period of the signaling processing network element, and whether the signaling overload will occur in the next time period is judged based on the predicted signaling load index parameter in the next time period; that is, the signaling overload condition of the signaling processing network element can be predicted in advance in the present application, and when it is predicted that the signaling processing network element will be overloaded in the next time period, the signaling flow control strategy is taken in advance to reduce the signaling load of the signaling processing network element, so as to avoid the signaling overload of the signaling processing network element; compared with the way of taking the signaling flow control strategy when the signaling processing network element has been overloaded, the prediction method of the present application can greatly reduce the probability of the signaling overload of the signaling processing network element, and even can ensure that the signaling processing network element no longer appears the signaling overload condition; so as to ensure the stable and efficient operation of the signaling processing network element, and greatly improve the processing efficiency of the signaling overload of the signaling processing network element.

[0073] In addition, by using the method in the present application, the operation and maintenance personnel do not need to participate in the process of network communication, and the operation and maintenance personnel do not need to monitor the signaling processing network element in real time, which reduces the labor input; and compared with the method of artificially judging the signaling overload and artificially adjusting the signaling capacity, the method in the present application can also greatly improve the processing efficiency of the signaling overload.

[0074] Figure 4 The flowchart of the signaling control method in another embodiment is shown. The present embodiment relates to an optional implementation process of determining whether the signaling processing network element will be overloaded in the next time period according to the predicted signaling load index parameter, which is based on the above-mentioned embodiment, as shown in Figure 4 The step 304 includes:

[0075] In step 402, according to the predicted index parameter corresponding to each index parameter and the index overload threshold value corresponding to each index parameter, it is determined whether each index parameter will be overloaded in the next time period, to obtain a signaling overload result.

[0076] The prediction index parameter can be used to represent the signaling load of the signaling processing network element in the next period. For example, the prediction index parameter can include the number of request messages in the next period, the number of active users in the next period, etc. The more the number of request messages, the greater the signaling load in the next period, and signaling overload can occur. The fewer the number of active users, the greater the signaling load in the next period, and signaling overload can occur.

[0077] Optionally, different index overload thresholds can be set for different index parameters, which are used to determine signaling overload for different prediction index parameters.

[0078] Based on this, for each index parameter, the server can determine whether the index parameter will have signaling overload in the next period according to the prediction index parameter corresponding to the index parameter and the index overload threshold corresponding to the index parameter, thereby obtaining a signaling overload result.

[0079] For example, when the index parameter includes request messages, the server can compare the prediction request message quantity corresponding to each request message with the request message threshold corresponding to the request message. If the prediction request message quantity corresponding to the request message is greater than or equal to the request message threshold corresponding to the request message, it can be determined that the request message will have signaling overload in the next period, and a signaling overload result representing that signaling overload will occur is obtained.

[0080] For example, when the index parameter includes active users, the server can compare the prediction active user quantity corresponding to each active user with the active user threshold corresponding to the active user. If the prediction active user quantity corresponding to the active user is less than or equal to the active user threshold corresponding to the active user, it can be determined that the active user will have signaling overload in the next period, and a signaling overload result representing that signaling overload will occur is obtained.

[0081] Step 404: According to the signaling overload results of each index parameter in the next period, it is determined whether the signaling processing network element will have signaling overload in the next period.

[0082] For example, the server can determine whether the signaling processing network element will have signaling overload in the next period according to the signaling overload results of each index parameter in the next period. If at least one index parameter in the signaling overload results in the next period represents that signaling overload will occur, it can be determined that the signaling processing network element will have signaling overload in the next period.

[0083] Exemplarily, the server can also determine that the signaling processing network element will appear signaling overload in the next time period according to the signaling overload result of each index parameter in the next time period, in a case that there are a preset number of index parameters whose signaling overload result in the next time period represents that signaling overload will appear. That is, in a case that there are multiple index parameters whose signaling overload result in the next time period represents that signaling overload will appear, it is determined that the signaling processing network element will appear signaling overload in the next time period.

[0084] In this embodiment, the server determines whether signaling overload will appear in the next time period for each index parameter according to the predicted index parameter corresponding to each index parameter and the index overload threshold corresponding to each index parameter, to obtain a signaling overload result; and determines whether signaling overload will appear in the next time period for the signaling processing network element according to the signaling overload result of each index parameter in the next time period. That is, the signaling overload of each index parameter is determined respectively, and whether signaling overload will appear in the next time period for the signaling processing network element is further determined according to the signaling overload result of each index parameter; by using this method, multiple index parameters can be determined respectively, more granular signaling overload determination is achieved, and the determination accuracy of signaling overload is improved.

[0085] Figure 5 The flowchart of the signaling control method in another embodiment is shown. This embodiment relates to an optional implementation process of performing a signaling flow control process to reduce the signaling load of the signaling processing network element in a case that it is determined that the signaling processing network element will appear signaling overload in the next time period, on the basis of the above embodiment. As shown in Figure 5 The step 306 includes:

[0086] In step 502, if it is determined that the signaling processing network element will appear signaling overload in the next time period, a first signaling flow control request is sent to the signaling forwarding network element to instruct the signaling forwarding network element to reduce the signaling data sent to the signaling processing network element.

[0087] The signaling forwarding network element can be a network element that is in communication connection with the signaling processing network element and used to send signaling data to the signaling processing network element; that is, the signaling forwarding network element can be used to receive the signaling data sent by the ingress network element and forward the signaling data to the signaling processing network element. Exemplarily, the signaling forwarding network element can include a functional network element (Diameter Route Agent, DRA) in a 3G or 4G (such as LTE) network.

[0088] For the first signaling flow control request, it can be used to instruct the signaling forwarding network element to reduce the signaling data sent to the signaling processing network element; for example, the signaling forwarding network element can reduce the outgoing flow control value of itself according to the current outgoing flow control value of the signaling forwarding network element and a preset flow control reduction value, to obtain a reduced outgoing flow control value, which can be used as the outgoing flow control value of the signaling forwarding network element in the next period; wherein, the preset flow control reduction value can be a preset value in the signaling forwarding network element, or a flow control reduction value sent by the server to the signaling forwarding network element based on the signaling overload condition of the signaling processing network element.

[0089] That is, the preset flow control reduction value can be carried in the first signaling flow control request, so that the signaling forwarding network element can determine the reduced outgoing flow control value based on the preset flow control reduction value carried in the first signaling flow control request and the current outgoing flow control value. Alternatively, the preset flow control reduction value carried in the first signaling flow control request can be determined by the server based on the signaling overload condition of the signaling processing network element, that is, the higher the signaling overload degree of the signaling processing network element, the larger the corresponding preset flow control reduction value, so that the outgoing flow control value of the signaling forwarding network element in the next period is smaller; that is, the preset flow control reduction value is positively correlated with the signaling overload degree.

[0090] For example, the first signaling flow control request can also include the outgoing flow control value of the signaling forwarding network element per unit time, that is, in this example, the server can directly inform the signaling forwarding network element of its outgoing flow control value in the next period; in this way, the signaling forwarding network element does not need to additionally calculate the outgoing flow control value in the next period, thereby reducing the data processing amount of the signaling forwarding network element. Alternatively, the outgoing flow control value per unit time of the signaling forwarding network element carried in the first signaling flow control request can also be determined by the server based on the signaling overload condition of the signaling processing network element, that is, the higher the signaling overload degree of the signaling processing network element, the smaller the corresponding outgoing flow control value per unit time, that is, the outgoing flow control value per unit time is negatively correlated with the signaling overload degree.

[0091] Step 504, sending a second signaling flow control request to the ingress network element to instruct the ingress network element to reduce the signaling data sent to the signaling processing network element.

[0092] The ingress network element can be connected with the terminal in communication and used to receive signaling data sent by the terminal. The ingress network element sends the signaling data sent by the terminal to the signaling forwarding network element and forwards the signaling data to the signaling processing network element through the signaling forwarding network element. For example, the ingress network element can include a 4G ingress network element, a 5G ingress network element, a VoLTE ingress network element, and the like, such as a Mobility Management Entity (MME) network element in an EPC, an Access and Mobility management Function (AMF) network element in a 5GC, and a Proxy Session Border Controller (PSBC) network element corresponding to VoLTE.

[0093] The second signaling flow control request can be used to instruct the ingress network element to reduce the signaling data sent to the signaling processing network element. For example, when the second signaling flow control request is received, the ingress network element can reduce the outflow control value of the ingress network element according to the current outflow control value of the ingress network element and a preset flow control reduction value, to obtain a reduced outflow control value. The reduced outflow control value can be used as the outflow control value of the ingress network element in the next period. The preset flow control reduction value can be a preset value in the ingress network element or a flow control reduction value sent by the server to the ingress network element based on the signaling overload condition of the signaling processing network element.

[0094] That is, the preset flow control reduction value can be carried in the second signaling flow control request, so that the ingress network element can determine the reduced outflow control value based on the preset flow control reduction value carried in the second signaling flow control request and the current outflow control value. Alternatively, the preset flow control reduction value carried in the second signaling flow control request can be determined by the server based on the signaling overload condition of the signaling processing network element. That is, the higher the signaling overload degree of the signaling processing network element, the larger the corresponding preset flow control reduction value, so that the outflow control value of the ingress network element in the next period is smaller. That is, the preset flow control reduction value is positively correlated with the signaling overload degree.

[0095] Exemplarily, the outflow control value of the ingress network element per unit time can also be included in the second signaling flow control request, that is, in the example, the server can directly inform the ingress network element of the outflow control value of the ingress network element in the next time period; in this way, the ingress network element does not need to additionally calculate the outflow control value of the next time period, thereby reducing the data processing amount of the ingress network element. Alternatively, the outflow control value of the ingress network element per unit time carried in the second signaling flow control request can also be determined by the server based on the signaling overload condition of the signaling processing network element, that is, the higher the signaling overload degree of the signaling processing network element, the smaller the outflow control value per unit time, that is, the outflow control value per unit time is negatively correlated with the signaling overload degree.

[0096] Exemplarily, in the case where the ingress network element includes a 4G ingress network element, a 5G ingress network element and a VoLTE ingress network element, considering the practical habits of users, many current application programs APP can replace voice contact, and therefore, the PSBC network element can be preferentially and mainly suppressed to realize the preferential recovery of data services. That is, the signaling flow control priority of the VoLTE ingress network element can be greater than the signaling flow control priorities of the 4G ingress network element and the 5G ingress network element, that is, when the second signaling flow control request is sent to the ingress network element, the second signaling flow control request can be first sent to the VoLTE ingress network element (such as the PSBC network element), and then, after a preset interval, the second signaling flow control request is sent to the 4G ingress network element and the 5G ingress network element.

[0097] In the embodiment, when it is determined that the signaling processing network element will be overloaded in the next time period, the first signaling flow control request can be first sent to the signaling forwarding network element to instruct the signaling forwarding network element to reduce the signaling data sent to the signaling processing network element; and then, the second signaling flow control request is sent to the ingress network element to instruct the ingress network element to reduce the signaling data sent to the signaling processing network element. That is, in the embodiment, the outflow control value of the signaling forwarding network element connected to the signaling processing network element can be first controlled to directly reduce the signaling impact of the signaling forwarding network element on the signaling processing network element, so as to ensure that the signaling processing network element is not seriously overloaded under the signaling impact; and then, the outflow control value of the ingress network element is controlled, thereby relieving the signaling processing pressure of the signaling processing network element from the signaling source, solving the signaling overload problem of the signaling processing network element; thereby improving the processing efficiency and processing effect of the signaling overload.

[0098] In one embodiment, a complete embodiment of a signaling control method is provided. In this embodiment, the signaling control method can be applied to a server, and in the server, a network data analytics function (NWDAF) network element can be included, and by means of the NWDAF network element, the prediction of the signaling load indicator parameters of the signaling processing network element in the next period is realized, so as to realize the early prediction and protection of the signaling overload of the signaling processing network element.

[0099] Exemplarily, reference is made to Figure 6 The signaling control method can include the following steps:

[0100] ① Through the NWDAF network element, the signaling load indicator parameters of the signaling processing network element HSS / UDM in the current period and the historical signaling load indicator parameters of each period are obtained from the HSS network element and the UDM network element; wherein the signaling load indicator parameters can include the number of "request messages" and the number of "active users" and other indicator parameters;

[0101] ② Through the MTLF (training) component in the NWDAF network element, on the basis of a deep learning algorithm such as a temporal prediction algorithm (Temporal Fusion Transformers, TFT), the model training is carried out according to the historical indicator parameters of each period for each indicator parameter, so as to obtain the indicator parameter prediction model corresponding to each indicator parameter respectively, and form the indicator reasoning prediction capability;

[0102] ③ Through the ANLF (reasoning) component in the NWDAF network element, the indicator parameter prediction model provided by the MTLF (training) component is used to reason the indicator parameters of the next period according to the indicator parameters of the current period, and the predicted indicator parameters of the signaling processing network element HSS / UDM in the next period are predicted, and a prediction analysis report is provided to the "HSS / UDM signaling load intelligent control application";

[0103] ④ The "HSS / UDM signaling load intelligent control application" obtains the prediction indicator parameter analysis report of the HSS / UDM sent by the NWDAF network element, and judges whether the signaling processing network element HSS / UDM will appear signaling overload;

[0104] ⑤ If it is judged that the signaling processing network element HSS / UDM will appear signaling overload, the "HSS / UDM signaling load intelligent control application" executes the signaling flow control process to reduce the signaling load of the signaling processing network element HSS / UDM.

[0105] Among them, regarding the signaling load index parameter, the NWDAF network element can collect the statistical index parameter data of the request message and active user of the HSS network element and the UDM network element, and then train a machine learning (ML) model based on a deep learning TFT algorithm to predict and infer each index to use artificial intelligence methods to perceive changes in signaling load in advance.

[0106] Referring to Table 1, some signaling load index parameters and signaling overload judgment conditions are shown.

[0107] Table 1

[0108]

[0109]

[0110] For the "HSS / UDM signaling load intelligent control application", it can continuously obtain each prediction index parameter of the HSS network element and the UDM network element from the NWDAF network element, and when the prediction index parameter meets the signaling overload condition, it can be predicted in advance that the signaling processing network element HSS / UDM has signaling overload, and at this time, appropriate signaling flow control strategies can be issued to the DRA, PSBC, MME, AMF and other network elements.

[0111] Regarding the signaling flow control strategy, refer to Figure 7 , which includes the following steps:

[0112] ① When the "HSS / UDM signaling load intelligent control application" judges that the signaling processing network element HSS / UDM will have signaling overload, the signaling flow control strategy can be issued; first, reduce the outflow control value of the signaling transmission network element DRA, which can directly reduce the signaling impact of DRA on HSS / UDM, thereby protecting HSS and UDM from serious overload under signaling impact;

[0113] ② The "HSS / UDM signaling load intelligent control application" issues the flow control strategy to the entry network element PSBC, MME and AMF to limit the number of initial registration passes per unit time, thereby reducing the registration of new users to the 4G / 5G / VoLTE domain; It can further relieve the signaling pressure of HSS / UDM from the signaling source. In addition, considering the practical habits of users, many application programs APP can replace voice contact, so PSBC network element can also be preferentially inhibited to realize the preferential recovery of data services.

[0114] In this embodiment, the NWDAF network element collects the "request message" and "active user" index data of the HSS network element and the UDM network element; and based on the deep learning TFT algorithm, the NWDAF network element uses the collected historical index data of each period to train an index prediction model to form an index reasoning and prediction capability; then, the "HSS / UDM signaling load intelligent control application" obtains the index prediction value from the NWDAF network element, and judges whether the HSS / UDM signaling overload caused by the surge registration occurs; further, in the case where the signaling overload occurs, the "HSS / UDM signaling load intelligent control application" issues a signaling flow control policy to the DRA, SBC, MME and AMF network elements, and finally relieves the signaling pressure of the HSS / UDM.

[0115] Compared with the traditional signaling overload processing mode, the signaling overload control scheme in this embodiment has the following advantages:

[0116] (1) By combining the NWDAF network element capability and predicting the index value based on deep learning, the signaling overload is predicted in advance to avoid the hysteresis of the traditional "detection and judgment of signaling overload according to the actual index value", and the signaling overload problem of the HSS / UDM is predicted early;

[0117] (2) The "HSS / UDM signaling load intelligent control application" can automatically judge and handle the signaling overload of the HSS / UDM, and after the signaling overload, the signaling flow control is automatically performed in the signaling transmission network element DRA to directly relieve the signaling pressure of the HSS / UDM, and the signaling flow control is performed in the entry network element (MME, AMF, PSBC) of the 4G / 5G / VoLTE domain to reduce the signaling request of the HSS / UDM from the signaling source, so as to timely cope with and avoid the further spread of the signaling overload.

[0118] It should be understood that although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0119] Based on the same inventive concept, the embodiments of the present application also provide a signaling control device for implementing the signaling control method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more signaling control device embodiments provided below can be referred to the limitations of the signaling control method in the above, which will not be described here.

[0120] In one embodiment, as shown in Figure 8 A signaling control device is provided, comprising: a prediction module 802, a determination module 804 and an execution module 806, wherein:

[0121] The prediction module 802 is configured to perform prediction processing on the signaling load index parameter of the signaling processing network element in the next period according to the signaling load index parameter of the signaling processing network element in the current period, to obtain a predicted signaling load index parameter, wherein the signaling load index parameter is used to represent the signaling load condition of the signaling processing network element.

[0122] The determination module 804 is configured to determine whether the signaling processing network element will have signaling overload in the next period according to the predicted signaling load index parameter.

[0123] The execution module 806 is configured to perform a signaling flow control process to reduce the signaling load of the signaling processing network element if it is determined that the signaling processing network element will have signaling overload in the next period.

[0124] In one embodiment, the prediction module 802 is configured to input the signaling load index parameter of the signaling processing network element in the current period into a preset signaling load prediction model, and perform prediction processing on the signaling load index parameter of the signaling processing network element in the next period by the preset signaling load prediction model, to obtain the predicted signaling load index parameter; the preset signaling load prediction model is trained based on the historical signaling load index parameters of the signaling processing network element in each period.

[0125] In one embodiment, the signaling load index parameter comprises at least one index parameter, and the signaling load prediction model comprises an index parameter prediction model corresponding to each index parameter; the prediction module 802 comprises:

[0126] A first determination sub-module is configured to determine, for each index parameter in the signaling load index parameter, a target index parameter prediction model corresponding to the index parameter.

[0127] A prediction sub-module is configured to input the index parameter of the signaling processing network element in the current period into the target index parameter prediction model, and perform prediction processing on the index parameter of the signaling processing network element in the next period by the target index parameter prediction model, to obtain a predicted index parameter corresponding to the index parameter.

[0128] In one of the embodiments, the determining module 804 comprises:

[0129] The judging sub-module is configured to judge whether the signaling overload will occur in the next time period according to the predicted index parameter corresponding to each index parameter and the index overload threshold corresponding to each index parameter, and obtain a signaling overload result.

[0130] The second determining sub-module is configured to determine whether the signaling processing network element will occur signaling overload in the next time period according to the signaling overload result of each index parameter in the next time period.

[0131] In one of the embodiments, the second determining sub-module is configured to determine that the signaling processing network element will occur signaling overload in the next time period if at least one index parameter in the next time period has a signaling overload result representing that the signaling overload will occur.

[0132] In one of the embodiments, the index parameter comprises a request message, and the judging sub-module comprises:

[0133] The first comparison unit is configured to compare whether the predicted request message quantity corresponding to each request message is greater than or equal to the request message threshold corresponding to the request message.

[0134] The first determining unit is configured to determine that the request message will occur signaling overload in the next time period if the predicted request message quantity corresponding to the request message is greater than or equal to the request message threshold corresponding to the request message, and obtain a signaling overload result representing that the signaling overload will occur.

[0135] In one of the embodiments, the index parameter comprises an active user, and the judging sub-module comprises:

[0136] The second comparison unit is configured to compare whether the predicted active user quantity corresponding to each active user is less than or equal to the active user threshold corresponding to the active user.

[0137] The second determining unit is configured to determine that the active user will occur signaling overload in the next time period if the predicted active user quantity corresponding to the active user is less than or equal to the active user threshold corresponding to the active user, and obtain a signaling overload result representing that the signaling overload will occur.

[0138] In one of the embodiments, the executing module 806 comprises:

[0139] The first sending sub-module is configured to send a first signaling flow control request to the signaling forwarding network element to instruct the signaling forwarding network element to reduce the signaling data sent to the signaling processing network element if it is determined that the signaling processing network element will occur signaling overload in the next time period.

[0140] The second sending sub-module is configured to send a second signaling flow control request to the ingress network element to instruct the ingress network element to reduce signaling data sent to the signaling processing network element.

[0141] In one of the embodiments, the first signaling flow control request comprises an outflow control value of the signaling forwarding network element per unit time, and the second signaling flow control request comprises an outflow control value of the ingress network element per unit time, and the outflow control value per unit time is negatively correlated with the signaling overload degree.

[0142] In one of the embodiments, the ingress network element comprises a 4G ingress network element, a 5G ingress network element and a VoLTE ingress network element, and the signaling flow control priority of the VoLTE ingress network element is higher than that of the 4G ingress network element and the 5G ingress network element.

[0143] The modules in the signaling control device can be realized by software, hardware and combinations thereof in whole or in part. The modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the modules.

[0144] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram thereof can be as shown in Figure 9 The computer device comprises a processor, a memory and a network interface connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store various index prediction models and various index data of various time periods. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a signaling control method.

[0145] Those skilled in the art can understand that Figure 9 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can comprise more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0146] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the signaling control method in any of the above embodiments.

[0147] In an embodiment, a computer readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, implements the steps of the signaling control method of any of the above embodiments.

[0148] In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the signaling control method of any of the above embodiments.

[0149] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0150] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to a memory, database or other medium used in the embodiments provided by the present application can include at least one of a non-volatile and volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive memory (ReRAM), a magnetoresistive random access memory (MRAM), a ferroelectric memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0151] The technical features of the above embodiments can be combined in any manner. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not contradict each other, they should be considered to be within the scope of the present disclosure.

[0152] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be pointed out that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method of signaling control, characterized by, The method comprises: According to the signaling load index parameter of the signaling processing network element in the current period, the signaling load index parameter of the signaling processing network element in the next period is predicted to obtain a predicted signaling load index parameter, wherein the signaling load index parameter is used to represent the signaling load of the signaling processing network element; According to the predicted signaling load index parameter, it is determined whether the signaling processing network element will be overloaded in the next period; If it is determined that the signaling processing network element will be overloaded in the next period, a signaling flow control process is performed to reduce the signaling load of the signaling processing network element, If it is determined that the signaling processing network element will be overloaded in the next period, a first signaling flow control request is sent to a signaling forwarding network element to instruct the signaling forwarding network element to reduce the signaling data sent to the signaling processing network element; A second signaling flow control request is sent to an entry network element to instruct the entry network element to reduce the signaling data sent to the signaling processing network element, The first signaling flow control request includes an outflow control value of the signaling forwarding network element per unit time, and the second signaling flow control request includes an outflow control value of the entry network element per unit time, and the outflow control value per unit time is negatively correlated with the degree of signaling overload. The method comprises:

2. The method of claim 1, wherein, The signaling load index parameter of the signaling processing network element in the current period is input into a preset signaling load prediction model, and the signaling load index parameter of the signaling processing network element in the next period is predicted by the preset signaling load prediction model to obtain a predicted signaling load index parameter; the preset signaling load prediction model is trained based on the historical signaling load index parameters of each period of the signaling processing network element. The signaling load index parameter comprises at least one index parameter, and the signaling load prediction model comprises an index parameter prediction model corresponding to each index parameter; the signaling load index parameter of the signaling processing network element in the current period is input into a preset signaling load prediction model, and the signaling load index parameter of the signaling processing network element in the next period is predicted by the preset signaling load prediction model to obtain a predicted signaling load index parameter, comprising:

3. The method of claim 2, wherein, For each index parameter in the signaling load index parameter, a target index parameter prediction model corresponding to the index parameter is determined; The index parameter of the signaling processing network element in the current period is input into the target index parameter prediction model, and the index parameter of the signaling processing network element in the next period is predicted by the target index parameter prediction model to obtain a predicted index parameter corresponding to the index parameter. ​ 4. The method of claim 3, wherein, The determining whether the signaling processing network element will appear signaling overload in the next time period according to the prediction signaling load index parameter comprises: determining whether each index parameter will appear signaling overload in the next time period according to the prediction index parameter corresponding to each index parameter and the index overload threshold corresponding to each index parameter, and obtaining a signaling overload result; determining whether the signaling processing network element will appear signaling overload in the next time period according to the signaling overload result of each index parameter in the next time period.

5. The method of claim 4, wherein, The determining whether the signaling processing network element will appear signaling overload in the next time period according to the prediction signaling load index parameter comprises: if there is at least one index parameter whose signaling overload result in the next time period represents that signaling overload will appear, it is determined that the signaling processing network element will appear signaling overload in the next time period.

6. The method of claim 4, wherein, The index parameter comprises a request message, and the determining whether each index parameter will appear signaling overload in the next time period according to the prediction index parameter corresponding to each index parameter and the index overload threshold corresponding to each index parameter, and obtaining a signaling overload result, comprises: for each request message, comparing whether the prediction request message quantity corresponding to the request message is greater than or equal to the request message threshold corresponding to the request message; if the prediction request message quantity corresponding to the request message is greater than or equal to the request message threshold corresponding to the request message, it is determined that the request message will appear signaling overload in the next time period, and a signaling overload result representing that signaling overload will appear is obtained.

7. The method of claim 4, wherein, The index parameter comprises an active user, and the determining whether each index parameter will appear signaling overload in the next time period according to the prediction index parameter corresponding to each index parameter and the index overload threshold corresponding to each index parameter, and obtaining a signaling overload result, comprises: for each active user, comparing whether the prediction active user quantity corresponding to the active user is less than or equal to the active user threshold corresponding to the active user; if the prediction active user quantity corresponding to the active user is less than or equal to the active user threshold corresponding to the active user, it is determined that the active user will appear signaling overload in the next time period, and a signaling overload result representing that signaling overload will appear is obtained.

8. The method of claim 1, wherein, The entry network element comprises a 4G entry network element, a 5G entry network element and a VoLTE entry network element, and the signaling flow control priority of the VoLTE entry network element is greater than that of the 4G entry network element and the 5G entry network element.

9. A signaling control device, characterized by The device comprises: a prediction module configured to perform prediction processing on signaling load index parameters of a signaling processing network element in a next time period according to signaling load index parameters of the signaling processing network element in a current time period, and obtain prediction signaling load index parameters, wherein the signaling load index parameters are used to represent signaling load conditions of the signaling processing network element; a determination module configured to determine whether the signaling processing network element will appear signaling overload in the next time period according to the prediction signaling load index parameters; and The execution module is configured to execute a signaling flow control process to reduce the signaling load of the signaling processing network element if it is determined that the signaling processing network element will be overloaded in the next time period, The execution module comprises: The first sending sub-module is configured to send a first signaling flow control request to the signaling forwarding network element to instruct the signaling forwarding network element to reduce the signaling data sent to the signaling processing network element if it is determined that the signaling processing network element will be overloaded in the next time period; The second sending sub-module is configured to send a second signaling flow control request to the entry network element to instruct the entry network element to reduce the signaling data sent to the signaling processing network element. The first signaling flow control request comprises an outflow control value of the signaling forwarding network element per unit time, and the second signaling flow control request comprises an outflow control value of the entry network element per unit time, and the outflow control value per unit time is negatively correlated with the signaling overload degree. 10.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-9. The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 8.

11. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 8.

12. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 8.

Images