Communication method and device and electronic equipment

Abstract

The invention discloses a communication method and device and electronic equipment. The method comprises the following steps: receiving a first request message sent by a server to base station equipment; determining a connection state between the base station equipment and the server; under the condition that the connection state between the base station equipment and the server is abnormal, a prediction response message of the base station equipment is simulated through a target machine learning model, the target machine learning model is deployed in a simulator, the server is connected with the base station equipment through the simulator, and the prediction response message is a response message of the first request message; and sending the prediction response message to the server. According to the method and the device, the technical problem that error data is easily generated due to the fact that a method for simulating base station communication in related technologies cannot simulate real response during equipment operation is solved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a communication method, device and electronic equipment. Background Art

[0002] The base station network management automatic configuration server system in development iteration needs to be connected to the base station equipment for joint debugging, testing and acceptance. The traditional method uses the base station equipment to directly connect to the network management server, which is easily restricted by conditions such as network environment and network security policy, resulting in the base station equipment being unable to access the network management server or unstable communication with the network management server. Therefore, it is necessary to simulate the base station equipment and the network management server for interactive communication.

[0003] The methods for simulating base station communication in related technologies are all based on capturing packets to obtain communication message templates, and then modifying the message templates manually or automatically to communicate with the network management server. This simulation method cannot simulate the real response of the device during operation and is prone to generate erroneous data.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a communication method, an apparatus and an electronic device to at least solve the technical problem that the method of simulating base station communication in the related art cannot simulate the actual response of the device during operation and is prone to generate erroneous data.

[0006] According to one aspect of an embodiment of the present application, a communication method is provided, including: receiving a first request message sent by a server to a base station device; determining the connection status between the base station device and the server; when the connection status between the base station device and the server is an abnormal connection, simulating a predicted response message of the base station device through a target machine learning model, wherein the target machine learning model is deployed in a simulator, the server is connected to the base station device through the simulator, and the predicted response message is a response message of the first request message; and sending the predicted response message to the server.

[0007] Optionally, the target machine learning model is determined in the following manner: obtaining historical communication messages between the server and the base station device, wherein the historical communication messages include historical request messages and historical response messages; training the machine learning model based on the historical communication messages to obtain the target machine learning model.

[0008] Optionally, before obtaining the historical communication messages between the server and the base station device, the method also includes: obtaining the configuration status of the interface protocol of the simulator; when the configuration status is unconfigured, generating a prompt message to notify the target object to configure the interface protocol of the simulator; when the configuration status is configuration completed, determining whether the server and the base station device are configured with simulator information; when both the server and the base station device are configured with simulator information, obtaining the historical communication messages between the server and the base station device through the simulator.

[0009] Optionally, after obtaining the historical communication messages between the server and the base station device, the method also includes: obtaining a first identifier of a first communication message, wherein the first communication message is used to represent any historical communication message; determining a second communication message corresponding to the first identifier from a message library, wherein the message library is used to store historical communication messages between the server and the base station device; and associating the first communication message and the second communication message.

[0010] Optionally, before training the machine learning model based on historical communication messages, the method also includes: obtaining the message type and instruction type of the communication message; when the message type and instruction type cover all message types and all instruction types supported by the interface protocol, training the machine learning model based on the historical communication messages.

[0011] Optionally, after obtaining the target machine learning model, the method also includes: using a verification data set to verify the target machine learning model to obtain a verification result, wherein the verification data set includes all message types and all instruction types supported by the interface protocol of the coverage simulator; when the accuracy of the verification result is less than a preset threshold, the target machine learning model is not saved; when the accuracy of the verification result is greater than or equal to the preset threshold, the target machine learning model is saved and the preset threshold is updated.

[0012] Optionally, determining the connection status between the base station device and the server includes: starting a monitoring service of the simulator; when the connection between the base station device and the simulator is normal, performing a session timeout check and a periodic task timeout check on the base station device according to the monitoring service to obtain a first check result and a second check result; when the first check result indicates that a session timeout exists in the base station device or the second check result indicates that a periodic task timeout exists in the base station device, determining that the connection status between the base station device and the server is an abnormal connection; when the first check result indicates that no session timeout exists in the base station device and the second check result indicates that no periodic task timeout exists in the base station device, determining that the connection status between the base station device and the server is a normal connection.

[0013] According to another aspect of an embodiment of the present application, a communication device is also provided, including: a receiving module for receiving a first request message sent by a server to a base station device; a determining module for determining the connection status between the base station device and the server; a simulation module for simulating a predicted response message of the base station device through a target machine learning model when the connection status between the base station device and the server is an abnormal connection, wherein the target machine learning model is deployed in a simulator, the server is connected to the base station device through the simulator, and the predicted response message is a response message to the first request message; and a sending module for sending the predicted response message to the server.

[0014] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including: a memory for storing program instructions; a processor, connected to the memory, for executing program instructions to implement the following functions: receiving a first request message sent by a server to a base station device; determining the connection status between the base station device and the server; when the connection status between the base station device and the server is an abnormal connection, simulating a predicted response message of the base station device through a target machine learning model, wherein the target machine learning model is deployed in a simulator, and the server is connected to the base station device through the simulator; sending a predicted response message to the server, the predicted response message being a response message to the first request message.

[0015] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned communication method by running the computer program.

[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including computer instructions, which implement the above communication method when executed by a processor.

[0017] In an embodiment of the present application, a first request message sent by a server to a base station device is received; the connection status between the base station device and the server is determined; when the connection status between the base station device and the server is an abnormal connection, a predicted response message of the base station device is simulated by a target machine learning model, wherein the target machine learning model is deployed in a simulator, and the server is connected to the base station device through the simulator, and the predicted response message is a response message of the first request message; the predicted response message is sent to the server, thereby achieving the purpose of ensuring that the server can continue to receive response messages, thereby achieving the technical effect of the server being able to maintain normal communication even when the base station device connection is unstable or disconnected, thereby solving the technical problem that the method of simulating base station communication in the related technology cannot simulate the real response during device operation, and is prone to generate erroneous data. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a hardware structure block diagram of a computer terminal for implementing a communication method according to an embodiment of the present application;

[0020] Figure 2 is a flow chart of a communication method according to an embodiment of the present application;

[0021] Figure 3 It is a structural diagram of a communication device according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] First, some nouns or terms that appear in the process of explaining the embodiments of the present application are subject to the following explanations:

[0025] Network management: ACS (Automatic Configuration Server) is one of the core components in the base station network management system. ACS is responsible for remote management and configuration of base stations and related network equipment, including but not limited to base transceiver stations (BTS), base station controllers (BSC), and wireless access points. It establishes communication connections with these devices to achieve key management functions such as parameter setting, status monitoring, fault diagnosis, and software upgrades.

[0026] The methods for simulating base station communication in related technologies are all based on obtaining communication message templates by packet capture, and then modifying the message templates manually or automatically to communicate with the network management server. This simulation method has the following defects: 1. The simulated message depends on the message template, and can only send message contents of fixed event types and instruction types, which has poor flexibility; 2. It is separated from the data processing of the real device, and it is impossible to judge whether to reply to normal messages or abnormal messages, and it is impossible to simulate the real response of the device during operation; 3. The simulated message is prone to generate erroneous data, and it is easy to generate conflicting data when used with the real device at the same time, resulting in data distortion.

[0027] In order to solve the problems existing in the related art, the present application embodiment provides a communication method, which can be run on Figure 1 In the computer terminal shown, the computer terminal is explained below.

[0028] The communication method embodiment provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a communication method. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions connected via a wired and / or wireless network. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0029] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0030] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the communication method in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned communication method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 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.

[0031] The transmission module 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0033] It should be noted that, in some optional embodiments, the above Figure 1 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.

[0034] In the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a communication method. 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.

[0035] Figure 2 is a flow chart of a communication method according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0036] Step S202: receiving a first request message sent by the server to the base station device.

[0037] In the above step S202, the simulator receives a first request message sent by a server to a base station device. The server may be, for example, a base station network management server. The simulator receives and parses the first request message to understand the content and purpose of the first request message.

[0038] Step S204: determine the connection status between the base station device and the server.

[0039] In the above step S204, the simulator monitors the connection status between the base station device and the server, determines whether there is a session supermarket, a periodic task is not executed, or a reverse address request fails, so as to determine whether the connection status is abnormal.

[0040] Step S206, when the connection status between the base station device and the server is an abnormal connection, the predicted response message of the base station device is simulated through the target machine learning model, wherein the target machine learning model is deployed in the simulator, and the server is connected to the base station device through the simulator, and the predicted response message is a response message of the first request message.

[0041] In the above step S206, if the connection status is determined to be abnormal, the simulator will use the previously trained target machine learning model, which is based on historical communication data (or historical communication messages) and can learn and predict the response behavior of the base station device in various situations. The simulator inputs the parsed first request message into the target machine learning model, and the model generates a predicted response message based on its learned pattern to simulate the normal response of the base station device.

[0042] Step S208: Send the prediction response message to the server.

[0043] In the above step S208, the simulator sends the predicted response message to the server, so that the server can still receive a seemingly normal response when the base station device is actually unable to respond, thereby maintaining the stability of the system and the continuity of the test process.

[0044] Through the above steps S202 to S208, by introducing the target machine learning model, a predicted response can be intelligently generated according to the server's request, thereby more realistically simulating the behavior of the base station equipment, improving the accuracy and reliability of the simulation, avoiding the limitations and potential errors brought about by the use of fixed templates or manually set responses, and solving the flexibility and authenticity problems in traditional simulation methods.

[0045] In the above communication method, the target machine learning model is determined in the following manner: obtaining historical communication messages between the server and the base station device, wherein the historical communication messages include historical request messages and historical response messages; training the machine learning model based on the historical communication messages to obtain the target machine learning model.

[0046] In an embodiment of the present application, the process of determining the target machine learning model is based on historical communication messages between the server and the base station device, and specifically includes the following steps:

[0047] 1. Data collection: First, collect historical communication messages from the communication records between the server and the base station device. These messages include not only the request messages sent by the server to the base station device (historical request messages), but also the response messages made by the base station device to these requests (historical response messages). The more comprehensive the collected data is, the richer the communication scenarios covered, and the stronger the prediction ability of the model is.

[0048] 2. Data preprocessing: The acquired historical communication messages need to be preprocessed, including cleaning, formatting, feature extraction and other steps. For example, key parameters such as instruction type, parameter value, event code, etc., as well as metadata such as session information and timestamps are extracted from request and response messages. At the same time, data standardization or normalization is performed to enable the model to better understand and learn the data.

[0049] 3. Feature association: In the preprocessing stage, it is also necessary to establish the association between the request message and the response message. This association builds the foundation for model learning and helps the model understand how different requests lead to different responses.

[0050] 4. Model training: Use the preprocessed historical communication message data as a training set and input it into the machine learning model for training. The goal of the model is to learn the mapping relationship between request messages and response messages, that is, to be able to predict the possible response message for a given request message. During the training process, the model continuously adjusts its internal parameters to minimize the difference between the predicted response and the actual historical response. After the training is completed, the target machine learning model is obtained.

[0051] Through the above process, the target machine learning model can capture the complexity and diversity of the communication between the base station equipment and the server, so that when the connection status of the base station equipment is abnormal, it can intelligently generate a prediction response message to simulate the normal communication behavior of the base station equipment, ensuring the continuity and stability of the server during testing, monitoring or management. Compared with the traditional simulation method based on fixed templates, this method significantly improves the accuracy and flexibility of the simulation, and can better deal with uncertainties and abnormal situations in communication.

[0052] In the above steps, before obtaining the historical communication messages between the server and the base station device, the method also includes: obtaining the configuration status of the interface protocol of the simulator; when the configuration status is unconfigured, generating a prompt message to notify the target object to configure the interface protocol of the simulator; when the configuration status is configuration completed, determining whether the server and the base station device are configured with simulator information; when both the server and the base station device are configured with simulator information, obtaining the historical communication messages between the server and the base station device through the simulator.

[0053] In the embodiment of the present application, before obtaining the historical communication messages between the server and the base station device, it is necessary to ensure that the configuration is correct to ensure the accurate acquisition of subsequent communication data and the effectiveness of model training. The specific steps are as follows:

[0054] 1. Get the interface protocol configuration status of the simulator: First, check whether the simulator has been configured with the correct interface protocol information. The interface protocol (such as TR069, SNMP v3, etc.) is the basis for communication between the simulator and the server and base station equipment. The correct configuration status is the prerequisite for subsequent steps. The simulator needs to be configured with the interface protocol information used by the southbound interface (such as TR069 protocol, SNMP v3 protocol, or other interface protocols). After the configuration is completed, all base station devices using this interface protocol can connect to the simulation service without being restricted by the device type and model.

[0055] 2. Check the configuration status: After obtaining the configuration status, determine whether the interface protocol of the simulator has been configured. If the configuration status is "Not configured", it means that the simulator cannot receive and parse communication data normally. At this time, a prompt message will be generated to notify the relevant target object (usually the system administrator) to perform the necessary interface protocol configuration.

[0056] 3. Determine the configuration status of the server and base station equipment: After confirming that the simulator itself has been configured, further check whether the server and base station equipment have been configured with simulator information. Specifically, the server side needs to change the base station connection information (such as the reverse address), and the base station equipment side needs to modify the network management information (such as the network management server address). After the base station equipment and the server are configured with simulator information, the communication messages between the server and the base station equipment will be forwarded via the simulator.

[0057] 4. Configure simulator information: If the server and base station equipment are not configured with simulator information, prompt information needs to be generated to notify the target object to configure it. For example, the server needs to know the address and port of the simulator in order to send the request message to the simulator; and the base station equipment needs to configure the simulator as the agent of its network management service to ensure that all communications are carried out through the simulator.

[0058] 5. Obtain historical communication messages: After ensuring that the server, base station equipment and simulator are correctly configured, the simulator begins to receive and record all communication messages between the server and the base station equipment, including historical request messages and historical response messages. These messages will be used for subsequent machine learning model training so that the model can learn and understand the response behavior of the base station equipment under different requests. Specifically, different methods are used to parse the acquired communication messages or data. Communication data refers to the data nodes in the message that record key information such as session information, device information, instruction information, parameter information, etc.

[0059] For example, the message message of the TR069 protocol: (1) DeviceId: a structure that uniquely identifies the device, including attributes such as the manufacturer (Manufacturer), device type (ProductClass) and serial number (SerialNumber). (2) Event: one or more event structures (EventStruct) that represent the event that triggered the event. Each EventStruct contains attributes such as the event code (EventCode) and command key (CommandKey). (3) ParameterList: a parameter list containing multiple parameter value structures (ParameterValueStruct), which is used to report the device status in the Inform message or set the device parameters in the SetParameterValues ​​message. The protocol message of the SNMP v3 protocol: first obtain each OID and the corresponding value, and then obtain the device information and device parameter information according to the values ​​corresponding to different OIDs. Other interface protocol types also need to parse communication data through similar methods.

[0060] Through the above steps, it is ensured that the simulator can correctly intervene in the communication process between the server and the base station equipment and accurately obtain the communication data, which provides the necessary conditions for the subsequent model training and the implementation of the adaptive simulation service of the base station equipment. This series of configuration checks and prompt mechanisms helps to prevent data acquisition failures caused by configuration errors and ensures the smooth and effective operation of the entire simulation system.

[0061] In the above steps, after obtaining the historical communication messages between the server and the base station device, the method also includes: obtaining a first identifier of the first communication message, wherein the first communication message is used to represent any historical communication message; determining a second communication message corresponding to the first identifier from a message library, wherein the message library is used to store historical communication messages between the server and the base station device; and associating the first communication message and the second communication message.

[0062] In the embodiment of the present application, after obtaining the historical communication messages between the server and the base station device, in order to better understand and process these communication messages, especially to train the machine learning model to accurately predict the response, the method also includes the following steps to establish the correlation between the request and response messages:

[0063] 1. Obtain the first identifier of the first communication message: First, for each historical communication message, a unique identifier needs to be extracted, which can help identify and track a specific communication event or session. The first communication message can be a request sent by the server to the base station device, or any communication message sent by the base station device to the server, and the first identifier can be a timestamp, session ID, request ID, or a composite identifier that combines device information and communication type.

[0064] 2. Determine the second communication message corresponding to the first identifier from the message library: After the historical communication messages are collected and stored in the message library, the library is queried and the first identifier extracted in the first step is used to find the second communication message associated therewith. The second communication message is usually a direct response to the first communication message or a subsequent series of responses. For example, if the first communication message is a request for a status report of a base station device, then the second communication message may be a status report response sent by the base station device.

[0065] 3. Associating the first communication message with the second communication message: Associating the first communication message with the second communication message is crucial to establishing a causal relationship between the request and the response. By establishing this association, a sequence of communication events can be constructed. When training the machine learning model, the model will learn what kind of response a specific request will result in, and how the base station equipment will respond in different situations (such as normal operation, failure, abnormal events, etc.). The construction of this correlation data provides a basis for model training, enabling the model to more accurately predict the possible response of the base station equipment under a given request.

[0066] Through the above steps, not only historical communication messages are collected, but more importantly, the correlation between these messages is established, providing a structured and meaningful data set for subsequent data analysis and machine learning model training. This identifier-based matching and association mechanism ensures the accuracy of data processing and the reliability of system operation.

[0067] In the above steps, before training the machine learning model based on historical communication messages, the method also includes: obtaining the message type and instruction type of the communication message; when the message type and instruction type cover all message types and all instruction types supported by the interface protocol, training the machine learning model based on the historical communication messages.

[0068] In an embodiment of the present application, the message type and instruction type of each message are extracted from the collected historical communication messages. The message type generally refers to the category of the communication message, such as status report, parameter setting request, event notification, etc.; while the instruction type specifically describes the execution content or purpose of the message, such as querying the device status, modifying parameter settings, reporting fault events, etc. The extracted message type and instruction type are compared with all the message types and instruction types supported by the interface protocol. Among them, the interface protocol (such as TR069, SNMP v3) defines the rules and standards for communication between base station equipment and servers, including all possible message types and instruction types. By checking, it is confirmed whether the historical communication messages contain all possible communication scenarios specified by the interface protocol. If the message type and instruction type of the historical communication message cover all message types and all instruction types supported by the interface protocol, including communication under normal and abnormal conditions, then the data set can be considered to be comprehensive, covering all possible communication events and device responses. This step ensures that the machine learning model can learn the behavior patterns of base station equipment in various situations, thereby improving the prediction and generalization capabilities of the model. After confirming that the historical communication messages cover all necessary message types and instruction types, these message data are used to train the machine learning model. The training process involves adjusting the model parameters to minimize the difference between the predicted response and the actual historical response. Comprehensive and diverse training data helps the model better understand and predict the device response in different situations, improving its accuracy and reliability in practical applications.

[0069] The machine learning model in the embodiment of the present application can use a supervised learning model, such as a decision tree, a random forest, and other supervised learning models. The method of triggering training can be set by itself, such as triggering by a scheduled task, or triggering after a certain number of training data sets are added. In another optional embodiment, the machine learning model can be replaced by a gradient boosting machine model.

[0070] Through the above steps, it is possible to ensure that the data set before the machine learning model training is sufficient and can cover all possible scenarios of communication between base station equipment and servers. This not only improves the training effect of the model, but also ensures the comprehensiveness and accuracy of the model when simulating the behavior of real base station equipment. In the case of incomplete data sets, it may be necessary to supplement data or adjust the data collection strategy to achieve the coverage required for training.

[0071] In the above steps, after obtaining the target machine learning model, the method also includes: using a verification data set to verify the target machine learning model to obtain a verification result, wherein the verification data set includes all message types and all instruction types supported by the interface protocol of the coverage simulator; when the accuracy of the verification result is less than a preset threshold, the target machine learning model is not saved; when the accuracy of the verification result is greater than or equal to the preset threshold, the target machine learning model is saved and the preset threshold is updated.

[0072] In an embodiment of the present application, in order to ensure the reliability and performance of the model, the method also includes the steps of model verification and optimization preservation. This process ensures that the model can accurately predict the response of the base station equipment in practical applications, and provides a mechanism for the continuous improvement of the model. Specifically, the verification data set is data independent of the training data set, which is used to evaluate the generalization ability of the model, that is, the performance of the model on unseen data. The verification data set in the embodiment of the present application is specially designed to cover all message types and all instruction types supported by the simulator interface protocol, including normal and abnormal communication scenarios. This means that the verification data set not only contains common communication requests and instructions, but also contains communication events under specific conditions (such as equipment failure, network interruption, etc.), ensuring the comprehensiveness and robustness of the model.

[0073] The verification data set is input into the target machine learning model, and the model predicts the response message based on the pattern it has learned. Then, the response predicted by the model is compared with the known correct response in the verification data set, and the accuracy of the model prediction, i.e., the verification result, is calculated. If the accuracy of the verification result is less than the preset threshold, this indicates that the model performs poorly on the verification data set and may not accurately predict the response of all types of messages and instructions, so the model will not be saved. This step ensures that low-quality or poorly performing models will not be used to simulate the response of the base station, avoiding potential prediction errors and system instability. If the accuracy of the verification result is greater than or equal to the preset threshold, the model has reached the expected performance standard, and the model is saved at this time as the basis for subsequent simulation of the base station response. In addition, an update mechanism for the preset threshold is also designed in the embodiment of the present application, that is, after the model is verified, the preset threshold can be appropriately increased to prompt the subsequent trained model to reach a higher accuracy standard and continuously optimize the model quality.

[0074] Through the above steps, not only the performance of the model is verified, but also a mechanism for model quality control and continuous improvement is provided, ensuring that the deployed machine learning model can accurately and reliably simulate the response of base station equipment, thus providing a solid foundation for the base station adaptive simulation system. This method not only ensures the accuracy of model prediction, but also improves the overall stability and efficiency of the system.

[0075] In step S204 of the above communication method, the connection status between the base station device and the server is determined, including: starting the monitoring service of the simulator; when the connection between the base station device and the simulator is normal, performing a session timeout check and a periodic task timeout check on the base station device according to the monitoring service to obtain a first check result and a second check result; when the first check result indicates that the base station device has a session timeout or the second check result indicates that the base station device has a periodic task timeout, determining that the connection status between the base station device and the server is an abnormal connection; when the first check result indicates that the base station device does not have a session timeout, and when the second check result indicates that the base station device does not have a periodic task timeout, determining that the connection status between the base station device and the server is a normal connection.

[0076] In an embodiment of the present application, the simulator starts its built-in monitoring service, which is responsible for monitoring and checking the connection status between the base station device and the simulator (and indirectly, with the server). When the connection between the base station device and the simulator is confirmed to be normal, the monitoring service will regularly perform a session timeout check. The session timeout check involves recording the time each time the base station device initiates or responds to a server request, and comparing it with the preset session timeout time. If the base station device does not respond to the server request within the session timeout time, the monitoring service will obtain a first check result, indicating that the base station device has a session timeout. The monitoring service is also responsible for periodic task timeout checks, such as whether the base station device has normally performed periodic communication tasks such as heartbeat detection. The periodic task timeout check involves recording the execution time and period of the periodic task, and determining whether the base station device has performed these tasks within the specified period. If the base station device fails to complete the task within the period, the monitoring service will obtain a second check result, indicating that the base station device has a periodic task timeout.

[0077] According to the first inspection result and the second inspection result, the monitoring service can determine the connection status between the base station device and the server. If the first inspection result indicates that there is a session timeout, or the second inspection result indicates that there is a periodic task timeout, the monitoring service will determine that the connection status between the base station device and the server is abnormal. When the connection is abnormal, the simulator is required to simulate the base station device to generate a predicted response message and return the predicted response message to the server. On the contrary, if the first inspection result indicates that there is no session timeout for the base station device, and the second inspection result also indicates that there is no periodic task timeout for the base station device, the monitoring service will determine that the connection status between the base station device and the server is normal. This indicates that the base station device can stably receive and respond to the server's request, and the communication status is good. At this time, the simulator is only responsible for forwarding the message sent by the base station device to the server.

[0078] Through the above steps, the monitoring service can monitor the communication status between the base station equipment and the server in real time, and promptly detect and report abnormal conditions, which is crucial to ensure that the server can accurately judge the health of the base station equipment and adopt appropriate communication strategies in normal and abnormal conditions. When the connection status is abnormal, the server can generate a predicted response using the trained machine learning model through the simulator, thereby maintaining the stable operation of the system and avoiding system interruptions or errors caused by the instability of the real base station equipment.

[0079] Figure 3 is a structural diagram of a communication device according to an embodiment of the present application, such as Figure 3 As shown, the device comprises:

[0080] A receiving module 30, configured to receive a first request message sent by the server to the base station device;

[0081] A determination module 32, used to determine the connection status between the base station device and the server;

[0082] A simulation module 34 is used to simulate the predicted response message of the base station device through the target machine learning model when the connection state between the base station device and the server is abnormal connection, wherein the target machine learning model is deployed in the simulator, the server is connected to the base station device through the simulator, and the predicted response message is a response message of the first request message;

[0083] The sending module 36 is used to send the prediction response message to the server.

[0084] The above-mentioned communication device also includes a training module 38, which is used to train the target machine learning model. Specifically, the training module is used to obtain historical communication messages between the server and the base station device, wherein the historical communication messages include historical request messages and historical response messages; the machine learning model is trained based on the historical communication messages to obtain the target machine learning model.

[0085] The above-mentioned communication device also includes a processing module 40, which is used to obtain the configuration status of the interface protocol of the simulator before obtaining the historical communication messages between the server and the base station device; when the configuration status is not configured, generate a prompt message to notify the target object to configure the interface protocol of the simulator; when the configuration status is configuration completed, determine whether the server and the base station device are configured with simulator information; when both the server and the base station device are configured with simulator information, obtain the historical communication messages between the server and the base station device through the simulator.

[0086] In the above-mentioned communication device, the processing module is also used to obtain a first identifier of a first communication message, wherein the first communication message is used to represent any historical communication message; determine a second communication message corresponding to the first identifier from a message library, wherein the message library is used to store historical communication messages between a server and a base station device; and associate the first communication message and the second communication message.

[0087] In the above-mentioned communication device, the processing module is also used to obtain the message type and instruction type of the communication message; when the message type and instruction type cover all message types and all instruction types supported by the interface protocol, the machine learning model is trained based on historical communication messages.

[0088] In the above-mentioned communication device, the training module is also used to verify the target machine learning model using a verification data set after obtaining the target machine learning model, and obtain a verification result, wherein the verification data set includes all message types and all instruction types supported by the interface protocol of the coverage simulator; when the accuracy of the verification result is less than a preset threshold, the target machine learning model is not saved; when the accuracy of the verification result is greater than or equal to the preset threshold, the target machine learning model is saved and the preset threshold is updated.

[0089] In the determination module in the above-mentioned communication device, the determination module is used to start the monitoring service of the simulator; when the connection between the base station device and the simulator is normal, the session timeout check and the periodic task timeout check are respectively performed on the base station device according to the monitoring service to obtain a first check result and a second check result; when the first check result indicates that the base station device has a session timeout or the second check result indicates that the base station device has a periodic task timeout, it is determined that the connection status between the base station device and the server is an abnormal connection; when the first check result indicates that the base station device does not have a session timeout, and when the second check result indicates that the base station device does not have a periodic task timeout, it is determined that the connection status between the base station device and the server is a normal connection.

[0090] It should be noted that Figure 3 The communication device shown is used to perform Figure 2 The communication method shown, therefore the relevant explanations in the above communication method are also applicable to the communication device and will not be repeated here.

[0091] An embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory, and is used to execute program instructions to implement the following functions: receiving a first request message sent by a server to a base station device; determining the connection status between the base station device and the server; when the connection status between the base station device and the server is an abnormal connection, simulating a predicted response message of the base station device through a target machine learning model, wherein the target machine learning model is deployed in a simulator, and the server is connected to the base station device through the simulator; sending a predicted response message to the server, the predicted response message being a response message to the first request message.

[0092] It should be noted that the above electronic equipment is used to execute Figure 2 The communication method shown, therefore the relevant explanations in the above communication method are also applicable to the electronic device and will not be repeated here.

[0093] An embodiment of the present application also provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following communication method by running the computer program: receiving a first request message sent by a server to a base station device; determining the connection status between the base station device and the server; when the connection status between the base station device and the server is an abnormal connection, simulating a predicted response message of the base station device through a target machine learning model, wherein the target machine learning model is deployed in a simulator, and the server is connected to the base station device through the simulator; sending a predicted response message to the server, the predicted response message being a response message to the first request message.

[0094] An embodiment of the present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the communication method in each embodiment of the present application.

[0095] The embodiments of the present application also provide a computer program, which, when executed by a processor, implements the steps of the communication method in each embodiment of the present application.

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

[0097] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0102] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A communication method, characterized in that: include: Receiving a first request message sent by the server to the base station device; Determining a connection status between the base station device and the server; When the connection state between the base station device and the server is abnormal, simulating a predicted response message of the base station device through a target machine learning model, wherein the target machine learning model is deployed in a simulator, the server is connected to the base station device through the simulator, and the predicted response message is a response message of the first request message; The prediction response message is sent to the server.

2. The method according to claim 1, characterized in that The target machine learning model is determined by: Acquire historical communication messages between the server and the base station device, wherein the historical communication messages include historical request messages and historical response messages; A machine learning model is trained based on the historical communication messages to obtain the target machine learning model.

3. The method according to claim 2, characterized in that Before acquiring the historical communication messages between the server and the base station device, the method further includes: Obtaining the configuration status of the interface protocol of the simulator; In the case where the configuration state is unconfigured, generating prompt information to notify the target object to configure the interface protocol of the simulator; When the configuration status is configuration completed, determining whether the server and the base station device are configured with simulator information; In the case that both the server and the base station device are configured with simulator information, historical communication messages between the server and the base station device are obtained through the simulator.

4. The method according to claim 2, characterized in that: After acquiring historical communication messages between the server and the base station device, the method further includes: Acquire a first identifier of a first communication message, wherein the first communication message is used to represent any historical communication message; Determine a second communication message corresponding to the first identifier from a message library, wherein the message library is used to store historical communication messages between the server and the base station device; The first communication message and the second communication message are associated.

5. The method according to claim 3, characterized in that: Before training the machine learning model according to the historical communication messages, the method further includes: Obtaining a message type and an instruction type of the communication message; When the message type and the instruction type cover all message types and all instruction types supported by the interface protocol, the machine learning model is trained based on the historical communication messages.

6. The method according to claim 2, characterized in that After obtaining the target machine learning model, the method further includes: Verify the target machine learning model using a verification data set to obtain a verification result, wherein the verification data set includes all message types and all instruction types supported by the interface protocol of the simulator; If the accuracy of the verification result is less than a preset threshold, the target machine learning model is not saved; When the accuracy of the verification result is greater than or equal to the preset threshold, the target machine learning model is saved and the preset threshold is updated.

7. The method according to claim 1, characterized in that Determining a connection state between the base station device and the server includes: Starting the monitoring service of the simulator; When the connection between the base station device and the simulator is normal, performing a session timeout check and a periodic task timeout check on the base station device according to the monitoring service to obtain a first check result and a second check result; When the first inspection result indicates that a session timeout exists in the base station device or when the second inspection result indicates that a periodic task timeout exists in the base station device, determining that the connection state between the base station device and the server is abnormal; When the first check result indicates that the base station device does not have a session timeout, and when the second check result indicates that the base station device does not have a periodic task timeout, it is determined that the connection state between the base station device and the server is a normal connection.

8. A communication device, characterized in that: include: A receiving module, used to receive a first request message sent by the server to the base station device; A determination module, used to determine the connection status between the base station device and the server; a simulation module, configured to simulate, when the connection state between the base station device and the server is abnormal, a predicted response message of the base station device through a target machine learning model, wherein the target machine learning model is deployed in a simulator, the server is connected to the base station device through the simulator, and the predicted response message is a response message of the first request message; A sending module is used to send the prediction response message to the server.

9. An electronic device, characterized in that: include: A memory for storing program instructions; A processor, connected to the memory, is used to execute program instructions to implement the following functions: receiving a first request message sent by a server to a base station device; Determine the connection status between the base station device and the server; when the connection status between the base station device and the server is abnormal, simulate the prediction response message of the base station device through the target machine learning model, wherein the target machine learning model is deployed in a simulator, and the server is connected to the base station device through the simulator; send the prediction response message to the server, and the prediction response message is a response message of the first request message.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the communication method according to any one of claims 1 to 7 by running the computer program.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the communication method according to any one of claims 1 to 7 is implemented.

Images