Signaling regulation method and device, computer equipment, storage medium and program product

Abstract

The invention relates to the technical field of communication networks, and discloses a signaling regulation method and device, computer equipment, a storage medium and a program product. The method is executed by a signaling normalizing application server in a mobile communication network, and the mobile communication network further comprises a core network. The signaling regulation application server is in communication connection with the core network; the method comprises the following steps: receiving an external signaling sent by external equipment; comparing the external signaling with a preset internal standard signaling so as to carry out regular processing on the external signaling; sending the structured external signaling to a core network, so that the core network responds to the structured external signaling to generate a feedback message; and receiving a feedback message sent by the core network, and forwarding the feedback message to the external equipment. The scheme is high in efficiency, good in accuracy, convenient and fast when the signaling regulation function is realized.

Description

Technical Field

[0001] The present invention relates to the field of communication network technology, and in particular to a signaling regularization method, device, computer equipment, storage medium and program product. Background Art

[0002] Signaling, as the core mechanism for controlling information exchange in mobile communication networks, undertakes key tasks such as connection establishment, maintenance and release, ensuring that users can smoothly make calls, surf the Internet and other operations. With the expansion of network scale and the evolution of technology, the signaling format and content of core network components from different manufacturers may be inconsistent, making it impossible for core network components to properly parse signaling, resulting in service interruption, network performance degradation, and even data leakage in severe cases; differences in signaling protocol implementation by different mobile device manufacturers may also cause problems in signaling interaction between mobile devices and the network.

[0003] In related technologies, signaling from different vendors is processed differently. When new signaling compatibility issues arise in the network, relevant technicians manually reproduce the problem scenario based on the monitored anomalies, locate the specific cause of the problem through detailed log records and data analysis, and develop targeted software patches to be deployed in the production environment.

[0004] However, the above solutions rely on the subjective judgment of relevant technical personnel, have high labor costs and thresholds, and are time-consuming, highly complex, and have low accuracy. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a signaling regularization method, device, computer equipment, storage medium and program product to solve the problems of long time consumption, high complexity and low accuracy in processing signaling compatibility issues.

[0006] In a first aspect, the present invention provides a signaling regularization method, which is executed by a signaling regularization application server in a mobile communication network; the mobile communication network also includes a core network; the signaling regularization application server is communicatively connected to the core network; the method comprises:

[0007] Receive external signaling sent by external devices;

[0008] Comparing the external signaling with a preset internal standard signaling to perform regular processing on the external signaling;

[0009] Sending the processed external signaling to the core network, so that the core network can generate a feedback message in response to the processed external signaling;

[0010] Receive the feedback message sent by the core network, and forward it to the external device.

[0011] In an optional implementation manner, comparing the external signaling with a preset internal standard signaling to perform regular processing on the external signaling includes:

[0012] Parsing the external signaling and performing preprocessing;

[0013] By means of the agent network, the pre-processed external signaling is compared with the preset internal standard signaling to generate a regularization strategy corresponding to the pre-processed external signaling;

[0014] The pre-processed external signaling is regularized according to the regularization strategy.

[0015] In an optional implementation manner, parsing the external signaling and performing preprocessing includes:

[0016] Parse the external signaling, split the external signaling into a header field and a header field corresponding value, convert the characters in the header field corresponding value into ASCII code values, and convert the parameters in the header field corresponding value into a tensor format.

[0017] In an optional implementation, the comparing the pre-processed external signaling with the preset internal standard signaling through the agent network to generate a regularization strategy corresponding to the pre-processed external signaling includes:

[0018] The pre-processed external signaling is used as input data of the intelligent agent network, so that the intelligent agent network generates a regularization strategy according to the pre-processed external signaling; wherein the intelligent agent network is pre-trained by the internal standard signaling; the regularization strategy includes a header field operation mode value, a header field name to be operated, an operation value, a value of whether the operation is completed, and whether the original signaling value is changed;

[0019] The step of regularizing the pre-processed external signaling according to the regularization strategy includes:

[0020] Determine whether the value of "whether to modify the original signaling" is true, and if so, parse the value of the operation mode of the header field;

[0021] If the header field operation mode value is a first value, the rule policy is determined to delete the header field corresponding to the header domain name to be operated; if the header field operation mode value is a second value, the rule policy is determined to use the operation value to replace the header field corresponding value corresponding to the header domain name to be operated; if the header field operation mode value is a third value, the rule policy is determined to add the operation value as the header field corresponding value to the header domain name to be operated.

[0022] In an optional implementation, the regularizing the pre-processed external signaling according to the regularization strategy further includes:

[0023] Performing a first regularization process on the preprocessed external signaling according to the regularization strategy;

[0024] Determine whether the operation completion value is true. If not, re-compare the external signaling after the first regularization processing with the preset internal standard signaling, and generate a regularization strategy corresponding to the external signaling after the first regularization processing, until the operation completion value is true.

[0025] In an optional embodiment, the method further includes:

[0026] Reading network parameters of the agent network and pre-stored historical experience data;

[0027] Using the to-be-trained intelligent agent network model to read the network parameters of the intelligent agent network, and training the to-be-trained intelligent agent network model through the historical experience data to obtain new network parameters;

[0028] Updating the agent network by new network parameters;

[0029] The method further comprises:

[0030] After generating a regularization strategy corresponding to the preprocessed external signaling, the regularization strategy is stored as historical experience data.

[0031] In a second aspect, the present invention provides a signaling regularization device, which is executed by a signaling regularization application server in a mobile communication network; the mobile communication network also includes a core network; the signaling regularization application server is communicatively connected to the core network; the device includes:

[0032] A signaling receiving module, used for receiving external signaling sent by an external device;

[0033] A regularization processing module, used for comparing the external signaling with a preset internal standard signaling to perform regularization processing on the external signaling;

[0034] A signaling sending module, used for sending the external signaling after regular processing to the core network, so that the core network generates a feedback message in response to the external signaling after regular processing;

[0035] The feedback forwarding module is used to receive the feedback message sent by the core network and forward it to the external device.

[0036] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the signaling regularization method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0037] 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 regularization method of the first aspect or any corresponding embodiment thereof.

[0038] 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 regularization method of the above-mentioned first aspect or any corresponding embodiment thereof.

[0039] The technical solution provided by the present invention may include the following beneficial effects:

[0040] The signaling regularization method provided by the present invention is executed by a signaling regularization application server in a mobile communication network, and the mobile communication network also includes a core network, and the signaling regularization application server is connected to the core network. The signaling regularization method first receives the external signaling sent by the external device, then compares the external signaling with the preset internal standard signaling to regularize the external signaling, and then sends the regularized external signaling to the core network, so that the core network can respond to the regularized external signaling to generate a feedback message, and finally receives the feedback message sent by the core network and forwards it to the external device. The above scheme, through the signaling regularization application server, uniformly regularizes the external signaling and then sends it to the core network, ensures that the core network can smoothly parse the external signaling, avoids service interruption, network performance degradation, data leakage and other problems caused by the inability to parse the external signaling, does not need to rely on manual judgment, has high efficiency, good accuracy, convenience and speed, thereby improving the efficiency and accuracy of the interaction between the external device and the core network, and improving the overall performance of the system and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] 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.

[0042] Figure 1 is a flow chart of a signaling regularization method according to an embodiment of the present invention;

[0043] Figure 2is a flowchart of another signaling regularization method according to an embodiment of the present invention;

[0044] Figure 3 is a schematic diagram of a working scenario of a signaling regularization application server according to an embodiment of the present invention;

[0045] Figure 4 is a schematic diagram of the structure of a signaling regularization application server according to an embodiment of the present invention;

[0046] Figure 5 is a flowchart of another signaling regularization method according to an embodiment of the present invention;

[0047] Figure 6 is a flow chart of agent network training according to an embodiment of the present invention;

[0048] Figure 7 is a structural block diagram of a signaling regularization device according to an embodiment of the present invention;

[0049] Figure 8 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0051] The rapid development of the fifth generation mobile communication network has not only brought unprecedented data transmission rates and low latency characteristics, but also greatly expanded the number of connections and the range of service types. However, the technological development has also brought increasingly complex challenges, especially those involving signaling processing in the core network. Signaling, as the core mechanism for controlling information exchange in mobile communication networks, undertakes key tasks such as connection establishment, maintenance and release, ensuring that users can smoothly make calls, surf the Internet and other operations. With the expansion of network scale and the evolution of technology, core network components (such as MME, SGW, PGW, etc.) from different manufacturers may have slight differences in following standards or have innovations in implementation, resulting in inconsistencies in signaling format and content, making it possible for core network components to fail to properly parse or respond to signaling messages, resulting in user service interruption, such as sudden disconnection during a call or failure to establish a data connection. Signaling errors may also cause network performance degradation and affect user experience, including increased call establishment failure rate and slow data transmission speed. More seriously, inappropriate signaling processing methods may be maliciously exploited, leading to security risks such as illegal access and data leakage. Differences in the implementation of signaling protocols by different mobile device manufacturers may also cause problems in the signaling interaction between mobile devices and the network. For example, some mobile phones may experience errors when sending or receiving specific types of signaling messages, affecting users' normal use of communication services.

[0052] In the related technology, signaling of different manufacturers is processed differently. When new signaling compatibility problems occur in the network, the relevant technicians manually reproduce the problem scenario based on the monitored abnormal phenomena or abnormal reports, and then locate the specific cause of the problem through detailed log records and data analysis. Since the signaling protocol itself is very complex and the implementation details between different manufacturers are also very different, this process is cumbersome and time-consuming, requiring the relevant technicians to have deep professional knowledge and rich practical experience. The next step is to develop a software patch for the problem, and correct the signaling processing logic in specific situations by writing code to ensure that the system can respond correctly when encountering similar problems. In the process of developing patches, engineers need to test and debug repeatedly to ensure the effectiveness and security of the patches. After completing the test verification, the patch will be officially deployed to the production environment. After the deployment is completed, it is necessary to monitor for a period of time. If it is found that the problem still exists or new problems have occurred, the relevant technicians need to re-enter the cycle of problem location and patch development until the problem is completely solved.

[0053] Over time, this approach that relies on manual intervention and continuous patching has gradually shown its limitations and unsustainability. On the one hand, manually handling each signaling compatibility issue is extremely time-consuming and prone to omissions, resulting in very low efficiency of the entire processing process. On the other hand, the increasing number of accumulated patches not only increases the overall complexity of the system, but also greatly increases the difficulty of maintenance. In addition, the existing patch mechanism is often slow to respond to new problems or changes, lacking sufficient flexibility and the ability to adapt quickly.

[0054] Therefore, an embodiment of the present invention provides a signaling regularization method, which uses a signaling regularization application server to regularize external signaling sent by an external device, with high efficiency, good accuracy, convenience and speed.

[0055] According to an embodiment of the present invention, a signaling regularization method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0056] In this embodiment, a signaling regularization method is provided, which is executed by a signaling regularization application server in a mobile communication network. The mobile communication network also includes a core network. The signaling regularization application server is in communication connection with the core network. Figure 1 is a flow chart of a signaling regularization method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0057] Step S101: receiving external signaling sent by an external device.

[0058] The external device can be a mobile device in a mobile communication network, such as a mobile phone, tablet computer, laptop computer, desktop computer, etc., or it can be a core network of another operator. The external device is connected to the signaling regularization application server. The core network is the main core network in the mobile communication network. When the external device needs to establish interaction with the core network, for example, when it needs to establish a communication session with the core network, it first sends an external signaling to the signaling regularization application server. The external signaling is generated by the external device using its own signaling format to indicate the required interactive content.

[0059] Step S102, comparing the external signaling with a preset internal standard signaling to regularize the external signaling.

[0060] The internal standard signaling is used to indicate the standard signaling format that the core network can parse. Specifically, the core network can send the internal standard signaling to the signaling regularization application server in advance, and the signaling regularization application server stores the received internal standard signaling. When the internal standard signaling is updated, the core network can send the updated internal standard signaling to the signaling regularization application server in a timely manner, and the signaling regularization application server stores the new internal standard signaling in a timely manner.

[0061] After the signaling regularization application server receives the external signaling sent by the external device, it can compare the difference between the external signaling and the internal standard signaling, and adjust the format of the external signaling based on the internal standard signaling to regularize the external signaling. The external signaling after regularization can be smoothly parsed by the core network, avoiding the problem that the external signaling generated by the external device may not be parsed by the core network due to the difference in format from the internal standard signaling, resulting in the failure of the interaction between the external device and the core network.

[0062] Step S103, sending the regularized external signaling to the core network, so that the core network generates a feedback message in response to the regularized external signaling.

[0063] The external signaling after regular processing can be successfully parsed by the core network. The core network can respond according to the interactive information contained in the external signaling after regular processing, and generate a feedback message to send to the signaling regularization application server.

[0064] Step S104: receiving a feedback message sent by the core network, and forwarding the feedback message to the external device.

[0065] The signaling regularization application server acts as a transit device between external devices and the core network, forwarding the feedback messages received from the core network to the corresponding external devices, completing the interaction between the external devices and the core network.

[0066] The signaling regularization method provided in this embodiment is executed by a signaling regularization application server in a mobile communication network, and the mobile communication network also includes a core network, and the signaling regularization application server is connected to the core network in communication. The signaling regularization method first receives the external signaling sent by the external device, then compares the external signaling with the preset internal standard signaling to regularize the external signaling, and then sends the regularized external signaling to the core network, so that the core network can respond to the regularized external signaling to generate a feedback message, and finally receives the feedback message sent by the core network and forwards it to the external device. The above scheme, through the signaling regularization application server, uniformly regularizes the external signaling and then sends it to the core network, ensures that the core network can smoothly parse the external signaling, avoids service interruption, network performance degradation, data leakage and other problems caused by the inability to parse the external signaling, does not need to rely on manual judgment, is efficient, accurate, convenient and fast, thereby improving the efficiency and accuracy of the interaction between the external device and the core network, and improving the overall performance and user experience of the system.

[0067] In this embodiment, a signaling regularization method is provided, which is executed by a signaling regularization application server in a mobile communication network. The mobile communication network also includes a core network. The signaling regularization application server is in communication connection with the core network. Figure 2 is a flow chart of a signaling regularization method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0068] Step S201: receiving external signaling sent by an external device.

[0069] For example, Figure 3 is a schematic diagram of a working scenario of a signaling regularization application server according to an embodiment of the present invention, such as Figure 3 As shown, the external device can be user equipment UE1, user equipment UE2, core network CN-i of other operators, etc. When the external device needs to establish interaction with the core network CN, the external signaling is uniformly sent to the signaling regulation application server SRAS (Signal regulation application server), and then the signaling regulation application server regulates the external signaling and forwards it to the core network.

[0070] Step S202, comparing the external signaling with the preset internal standard signaling to regularize the external signaling.

[0071] Specifically, the above step S202 includes:

[0072] Step S2021, parse the external signaling and perform preprocessing.

[0073] Optionally, parse the external signaling, split the external signaling into a header field and a corresponding value of the header field, convert the characters in the corresponding value of the header field into ASCII code values, and convert the parameters in the corresponding value of the header field into a tensor format.

[0074] The header field is a component of the external signaling, and the corresponding value of the header field is the value of the specific information contained in the header field, such as IP address, port number, protocol identifier, device identifier, call identifier, timestamp, etc. Since the header field needs to be processed accordingly when the signaling is subsequently regularized, the header field of the external signaling is first split out in the preprocessing stage, and the characters and parameters in the corresponding value of the header field are modified to a format that is easy to process.

[0075] Step S2022, through the intelligent agent network, compare the pre-processed external signaling with the preset internal standard signaling, and generate a regularization strategy corresponding to the pre-processed external signaling.

[0076] The pre-processed external signaling is used as input data of the intelligent agent network, so that the intelligent agent network generates a regularization strategy according to the pre-processed external signaling. The intelligent agent network is pre-trained by the internal standard signaling, and can make decisions on the regularization strategy of the external signaling based on the internal standard signaling. The regularization strategy includes a header field operation mode value, a header field name to be operated, an operation value, a value of whether the operation is completed, and a value of whether to change the original signaling. The header field operation mode value is used to indicate how to operate the header field of the external signaling.

[0077] Optionally, the intelligent agent network can be updated regularly, or it can be updated every time the internal standard signaling is updated. Specifically, when updating the intelligent agent network, the network parameters of the intelligent agent network and the pre-stored historical experience data are first read. The historical experience data includes the previous internal standard signaling and the corresponding regularization strategy generated by the intelligent agent network for each external signaling. Then, the network parameters of the intelligent agent network are read using the intelligent agent network model to be trained, and the intelligent agent network model to be trained is trained with the historical experience data to obtain new network parameters. The intelligent agent network model to be trained corresponds to the intelligent agent network and is a replica of the intelligent agent network specifically used for training. The network parameters of the intelligent agent network are read through the intelligent agent network model to be trained, so that the state of the intelligent agent network model to be trained is consistent with the intelligent agent network, and then the intelligent agent network model to be trained is trained with the historical experience data to obtain new network parameters. Finally, the intelligent agent network is updated with the new network parameters so that the regularization strategy generated by the intelligent agent network is more in line with current needs. By timely updating the intelligent network, the signaling regularization application server can automatically adjust and optimize the signaling regularization strategy according to the constantly changing external signaling data and environmental conditions during actual operation, better respond to new problems or changes that may arise, and maintain the stability and reliability of the system.

[0078] Optionally, after generating a regularization strategy corresponding to the preprocessed external signaling, the regularization strategy is stored as historical experience data to expand the training set, improve the accuracy of the training, and thereby improve the accuracy of the regularization strategy generated by the intelligent agent network.

[0079] Step S2023: regularize the pre-processed external signaling according to the regularization strategy.

[0080] After the intelligent agent network generates a regularization strategy, it parses the regularization strategy to regularize the pre-processed external signaling. Specifically, first determine whether the value of the original signaling should be changed is true. If so, parse the value of the header field operation mode; if not (for example, whether the value of the original signaling should be changed is false), it is determined that the pre-processed external signaling does not need to be modified, and the pre-processed external signaling is reorganized and restored to the original external signaling to be sent to the core network.

[0081] Next, in the case of whether to change the original signaling value is true, if the value of the header field operation mode is the first value, the rule strategy is determined to delete the header field corresponding to the header domain name to be operated; if the value of the header field operation mode is the second value, the rule strategy is determined to use the operation value to replace the header field corresponding value corresponding to the header domain name to be operated; if the value of the header field operation mode is the third value, the rule strategy is determined to add the operation value as the header field corresponding value to the header field corresponding to the header domain name to be operated. The first value, the second value, and the third value can be set according to actual needs, for example, set to 1, 2, and 3 respectively. By performing detailed signaling checks on external signaling and automatically supplementing missing key information, the integrity and accuracy of external signaling are ensured, and there is no need to rely on manual judgment. It can more accurately identify and process inconsistencies in external signaling, thereby improving the overall performance and user experience of the system.

[0082] In actual application scenarios, it may happen that after a round of regularization, the external signaling still cannot be modified to the required format. Therefore, a whether the operation is completed value is also set in the rule strategy, and whether the external signaling is modified to the required format after the current round of regularization can be determined based on the whether the operation is completed value. Specifically, the pre-processed external signaling is first regularized according to the regularization strategy (i.e., the regularization strategy of the current round), and then it is determined whether the whether the operation is completed value is true. If not, the external signaling after the first regularization is compared with the preset internal standard signaling again, and a regularization strategy corresponding to the external signaling after the first regularization is generated. The external signaling after the first regularization is subjected to a second regularization according to the regularization strategy corresponding to the external signaling after the first regularization, and then it is determined whether the whether the operation is completed value is true, and so on, until the whether the operation is completed value is true, the regularization step is completed, and the external signaling after the regularization is obtained.

[0083] Step S203, sending the regularized external signaling to the core network, so that the core network generates a feedback message in response to the regularized external signaling.

[0084] The regularized external signaling is reassembled and restored and sent to the core network. The core network can respond according to the interactive information carried in the regularized external signaling, generate a feedback message and send it to the signaling regularization application server.

[0085] Step S204: receiving a feedback message sent by the core network, and forwarding the feedback message to the external device.

[0086] For details, please see Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0087] The signaling regularization method provided in this embodiment is executed by a signaling regularization application server in a mobile communication network, and the mobile communication network also includes a core network, and the signaling regularization application server is connected to the core network in communication. The signaling regularization method first receives the external signaling sent by the external device, then compares the external signaling with the preset internal standard signaling to regularize the external signaling, and then sends the regularized external signaling to the core network, so that the core network can respond to the regularized external signaling to generate a feedback message, and finally receives the feedback message sent by the core network and forwards it to the external device. The above scheme, through the signaling regularization application server, uniformly regularizes the external signaling and then sends it to the core network, ensures that the core network can smoothly parse the external signaling, avoids service interruption, network performance degradation, data leakage and other problems caused by the inability to parse the external signaling, does not need to rely on manual judgment, is efficient, accurate, convenient and fast, thereby improving the efficiency and accuracy of the interaction between the external device and the core network, and improving the overall performance and user experience of the system.

[0088] As one or more specific application embodiments of the embodiments of the present invention, the optimal implementation scheme or the scheme that the inventor most wants to embody is described below in combination with specific application scenarios.

[0089] Figure 4 is a schematic diagram of the structure of a signaling regularization application server according to an embodiment of the present invention. Figure 4 As shown, the signaling regularization application server includes a proxy server PROXY, a central controller, an intelligent agent network, a training center and an experience database. The proxy server is respectively connected to the external device, the central controller and the core network. The central controller is respectively connected to the intelligent agent network, the training center and the experience database. The training center is respectively connected to the intelligent agent network and the experience database.

[0090] Specifically, the core network can send internal standard signaling to the proxy server through the Y2 interface, and the proxy server forwards the internal standard signaling to the central controller through the X1 interface. The external device can send external signaling to the proxy server through the Y1 interface. After receiving the external signaling, the proxy server forwards the external signaling to the central controller through the X1 interface. The central controller parses the received external signaling and performs preprocessing, and then sends the preprocessed external signaling to the intelligent network through the X2 interface. The intelligent network generates a regularization strategy based on the preprocessed external signaling and sends it to the central controller through the X2 interface. The central controller parses the regularization strategy to regularize the preprocessed external signaling, and sends the regularized external signaling to the proxy server through the X1 interface. The proxy server forwards the regularized external signaling to the core network through the Y2 interface. The core network generates a feedback message based on the regularized external signaling and sends the feedback message to the proxy server through the Y2 interface. The proxy server then forwards the feedback message to the external device through the Y1 interface. The core network can also evaluate whether the external signaling after regular processing meets the analysis requirements, and send the evaluation results to the proxy server through the Y2 interface. The proxy server feeds back the evaluation results to the experience database through the X4 interface so that the experience database can store the evaluation results as historical experience data.

[0091] The proxy server can also send internal specification signaling to the experience database through the X4 interface. When the intelligent agent network needs to be updated, the central controller sends a training start signal to the training center through the X3 interface. The training center reads the historical experience data stored in the experience database through the X5 interface and reads the network parameters of the intelligent agent network through the X6 interface. After the training center completes the training and obtains the new network parameters, it sends the core network parameters to the intelligent agent network through the X6 interface for the intelligent agent network to update. The central controller can also send the regularization strategy generated by the intelligent agent network to the experience database for storage through the X7 interface.

[0092] By considering the compatibility of different signaling formats and protocols and providing a complete interface design, the signaling regularization application server can communicate with different network components and devices in the mobile communication network, receive and send signaling, and ensure that the signaling regularization application server can work effectively in a diverse network environment.

[0093] Figure 5It is a flow chart of the signaling regularization method according to an embodiment of the present invention. After receiving the external signaling sent by the external device, the proxy server forwards it to the central controller, the central controller parses the external signaling and performs preprocessing, and then sends the preprocessed external signaling to the intelligent network for decision-making, obtains the regularization strategy, and the central controller parses the regularization strategy again, and performs regularization based on the header field operation mode value A0, the header field name to be operated A1, the operation value A2, the operation completion value A3, and the original signaling value A4.

[0094] Optionally, the agent network includes a value network and a policy network. The value network is used to score the actions selected by the agent network in the current state, and the policy network is used to make decisions on the regularization strategy during the signal regularization process. The output α of the policy network of the agent network k It can be defined by the following formula:

[0095] a k =π(s k |θ)

[0096] Among them, π(s k |θ) represents the strategy of the policy network at time step k, and s k is the state tensor of the policy network at time step k, and θ is the network parameter of the policy network.

[0097] The output of the policy network is k Specifically, it is the action vector [a1, a2, a3, a4], where a1 corresponds to the header domain name to be operated A1, a2 corresponds to the operation value A2, a3 corresponds to whether the operation is completed value A3, and a4 corresponds to whether the original signaling value is changed A4.

[0098] The specific meanings and value ranges of the header field operation mode value A0, the header field name to be operated A1, the operation value A2, the whether the operation is completed value A3, and the whether to change the original signaling value A4 are as follows:

[0099] Table 1: Regularization strategy information table.

[0100]

[0101] Specifically, whether the external signaling needs to be modified is determined based on whether the original signaling value A4 is changed. If the original signaling value A4 is changed = False (value is 0), no modification is required, and the signaling is reassembled and restored to wait for forwarding; if the original signaling value A4 is changed = True (value is 1), different processing is performed according to the value of the header field operation mode value A0. If the header field operation mode value A0 = 0, the header field corresponding to the header field A1 to be operated in the signaling is deleted. If the header field operation mode value A0 = 1, the header field value corresponding to the header field A1 to be operated is replaced with the value of the operation value A2. If the header field operation mode value A0 = 2, the header field corresponding to the header field A1 to be operated is added to the external signaling, and the corresponding value of the header field is the operation value A2. Whether the regularization processing is terminated is determined based on the value of the operation completion value A3. If the operation completion value A3 = False, the modified external signaling is used as input to make a new decision, and so on until the operation completion value A3 is true.

[0102] Figure 6 is a flow chart of agent network training according to an embodiment of the present invention. First, the central controller uses the X3 interface to send a training request to the training center. The training center receives the training request and starts the training process. Then, the training center reads the agent network parameters through the X6 interface and learns the agent historical strategy based on the current network parameters. The training center can also read historical experience from the experience database through the X5 interface to learn historical experience data. The training center can also compare the state s at the current time t t and the state s at the next time t+1 t+1 Corresponding core network evaluation results, rewards will be given according to the core network evaluation results:

[0103]

[0104] Among them, r punish Signaling discard penalty. If the external signaling after regular processing is discarded by the core network, this policy penalty I is given. punish ,as follows:

[0105]

[0106] r net is the network status reward. If there is no network fluctuation inside the core network after the strategy is executed, a network status reward is given. The reward value is positively correlated with the network status net. net =f(net). The difference between the speed at which the network element receiving the external signaling executes the external signaling and the average signaling processing speed is used to evaluate whether there is an abnormality in the regularized external signaling. Among them, t i is the time taken by network element i to process the external signaling, is the average time for network element i to process signaling.

[0107] When training the agent network, the network parameters of the agent network are updated according to the network status reward obtained. By adjusting the parameters, the agent can gradually improve the accuracy of the generated regularization strategy. Optionally, the value network of the agent network is updated by the TD algorithm (Temporal Difference algorithm), and the formula is as follows:

[0108]

[0109] Among them, Q target is the target value, is the value estimate of the agent network at the next time step k+1, r is the reward value, γ is the discount factor, θ is the network parameter of the policy network, is the network parameter of the value network, is the value estimate of the value network at the current time step k, and L(θ) is the loss function of the value network.

[0110] Calculate the gradient of the policy network of the agent network using the gradient ascent algorithm The formula is as follows:

[0111]

[0112] in, is the expected return of the policy network.

[0113] The formula for updating network parameters is as follows:

[0114]

[0115] Finally, the training center updates the network parameters of the intelligent network through the X6 interface based on the network parameters obtained after the training is completed. The intelligent network not only processes the current external signaling, but also evaluates the effect of the regularization strategy and makes timely adjustments based on the feedback signals from the core network (such as signaling discard penalties, network status rewards, etc.). This closed-loop mechanism ensures that the intelligent network can continuously improve the process of generating regularization strategies to adapt to changes in the network environment and improve the accuracy of generating regularization strategies.

[0116] In this embodiment, a signaling regularization device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0117] This embodiment provides a signaling regularization device, which is executed by a signaling regularization application server in a mobile communication network; the mobile communication network also includes a core network; the signaling regularization application server is connected to the core network in communication; Figure 7 As shown, the device comprises:

[0118] The signaling receiving module 701 is used to receive external signaling sent by an external device;

[0119] A regularization processing module 702, used for comparing the external signaling with a preset internal standard signaling to perform regularization processing on the external signaling;

[0120] The signaling sending module 703 is used to send the external signaling after the regularization process to the core network, so that the core network generates a feedback message in response to the external signaling after the regularization process;

[0121] The feedback forwarding module 704 is used to receive the feedback message sent by the core network and forward it to the external device.

[0122] In an optional embodiment, the regularization processing module includes:

[0123] A preprocessing unit, used for parsing the external signaling and performing preprocessing;

[0124] A regularization strategy unit, used to compare the pre-processed external signaling with the preset internal standard signaling through the intelligent agent network, and generate a regularization strategy corresponding to the pre-processed external signaling;

[0125] The regularization processing unit is used to perform regularization processing on the pre-processed external signaling according to the regularization strategy.

[0126] In an optional implementation, the preprocessing unit is further used to: parse the external signaling, split the external signaling into a header field and a header field corresponding value, convert the characters in the header field corresponding value into ASCII code values, and convert the parameters in the header field corresponding value into a tensor format.

[0127] In an optional implementation, the regularization strategy unit is further used to: use the preprocessed external signaling as input data of the intelligent agent network, so that the intelligent agent network generates a regularization strategy according to the preprocessed external signaling; wherein the intelligent agent network is pre-trained by the internal specification signaling; the regularization strategy includes a header field operation mode value, a header field name to be operated, an operation value, a value of whether the operation is completed, and whether to change the original signaling value;

[0128] The regularization processing unit is further used to: determine whether the value of whether to change the original signaling is true, and if so, parse the header field operation mode value; if the header field operation mode value is a first value, determine the rule policy to delete the header field corresponding to the header domain name to be operated; if the header field operation mode value is a second value, determine the rule policy to use the operation value to replace the header field corresponding value corresponding to the header domain name to be operated; if the header field operation mode value is a third value, determine the rule policy to add the operation value as the header field corresponding value to the header field corresponding to the header domain name to be operated.

[0129] In an optional embodiment, the regularization processing unit is also used to: perform a first regularization processing on the pre-processed external signaling according to the regularization strategy; determine whether the operation completion value is true, and if not, re-compare the external signaling after the first regularization processing with the preset internal standard signaling, and generate a regularization strategy corresponding to the external signaling after the first regularization processing, until the operation completion value is true.

[0130] In an optional embodiment, the device further includes a training module, which is used to: read the network parameters of the intelligent agent network and the pre-stored historical experience data; use the intelligent agent network model to be trained to read the network parameters of the intelligent agent network, and train the intelligent agent network model to be trained by the historical experience data to obtain new network parameters; update the intelligent agent network by the new network parameters;

[0131] The device also includes a storage module, which is used to: after generating a regularization strategy corresponding to the pre-processed external signaling, store the regularization strategy as historical experience data.

[0132] 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.

[0133] The signaling regularization 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.

[0134] The embodiment of the present invention also provides a computer device having the above Figure 7 The signaling regularization device shown.

[0135] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 8As 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 the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the 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 8 A processor 10 is taken as an example.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.

[0141] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0142] 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.

[0143] 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.

[0144] 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 shall all fall within the scope of protection of the present invention.

Claims

1. A signaling regularization method, characterized in that: The method is executed by a signaling regularization application server in a mobile communication network; the mobile communication network also includes a core network; the signaling regularization application server is in communication connection with the core network; the method includes: Receive external signaling sent by external devices; Comparing the external signaling with a preset internal standard signaling to perform regular processing on the external signaling; Sending the processed external signaling to the core network, so that the core network can generate a feedback message in response to the processed external signaling; Receive the feedback message sent by the core network, and forward it to the external device.

2. The method according to claim 1, characterized in that The comparing the external signaling with the preset internal standard signaling to perform regular processing on the external signaling includes: Parsing the external signaling and performing preprocessing; By means of the agent network, the pre-processed external signaling is compared with the preset internal standard signaling to generate a regularization strategy corresponding to the pre-processed external signaling; The pre-processed external signaling is regularized according to the regularization strategy.

3. The method according to claim 2, characterized in that The parsing of the external signaling and preprocessing includes: Parse the external signaling, split the external signaling into a header field and a header field corresponding value, convert the characters in the header field corresponding value into ASCII code values, and convert the parameters in the header field corresponding value into a tensor format.

4. The method according to claim 3, characterized in that: The method of comparing the pre-processed external signaling with the preset internal standard signaling through the agent network to generate a regularization strategy corresponding to the pre-processed external signaling includes: The pre-processed external signaling is used as input data of the intelligent agent network, so that the intelligent agent network generates a regularization strategy according to the pre-processed external signaling; wherein the intelligent agent network is pre-trained by the internal standard signaling; the regularization strategy includes a header field operation mode value, a header field name to be operated, an operation value, a value of whether the operation is completed, and whether the original signaling value is changed; The step of regularizing the pre-processed external signaling according to the regularization strategy includes: Determine whether the value of "whether to modify the original signaling" is true, and if so, parse the value of the operation mode of the header field; If the header field operation mode value is a first value, the rule policy is determined to delete the header field corresponding to the header domain name to be operated; if the header field operation mode value is a second value, the rule policy is determined to use the operation value to replace the header field corresponding value corresponding to the header domain name to be operated; if the header field operation mode value is a third value, the rule policy is determined to add the operation value as the header field corresponding value to the header domain name to be operated.

5. The method according to claim 4, characterized in that The step of regularizing the pre-processed external signaling according to the regularization strategy further includes: Performing a first regularization process on the pre-processed external signaling according to the regularization strategy; Determine whether the operation completion value is true. If not, re-compare the external signaling after the first regularization processing with the preset internal standard signaling, and generate a regularization strategy corresponding to the external signaling after the first regularization processing, until the operation completion value is true.

6. The method according to any one of claims 2 to 5, characterized in that: The method further comprises: Reading network parameters of the agent network and pre-stored historical experience data; Using the to-be-trained intelligent agent network model to read the network parameters of the intelligent agent network, and training the to-be-trained intelligent agent network model through the historical experience data to obtain new network parameters; Updating the agent network by new network parameters; The method further comprises: After generating a regularization strategy corresponding to the preprocessed external signaling, the regularization strategy is stored as historical experience data.

7. A signaling regularization device, characterized in that: The signaling regularization application server in the mobile communication network is executed; the mobile communication network also includes a core network; the signaling regularization application server is connected to the core network in communication; the device includes: A signaling receiving module, used for receiving external signaling sent by an external device; A regularization processing module, used for comparing the external signaling with a preset internal standard signaling to perform regularization processing on the external signaling; A signaling sending module, used for sending the external signaling after regular processing to the core network, so that the core network generates a feedback message in response to the external signaling after regular processing; The feedback forwarding module is used to receive the feedback message sent by the core network and forward it to the external device.

8. 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 regularization method described in any one of claims 1 to 6 by executing the computer instructions.

9. 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 regularization method described in any one of claims 1 to 6.

10. A computer program product, characterized in that It comprises computer instructions, and the computer instructions are used to make a computer execute the signaling regularization method described in any one of claims 1 to 6.

Images