A Web-based installation and debugging method for remote serial ports of communication equipment

Abstract

The present invention discloses a Web-based installation and debugging method for a remote serial port of a communication device, which relates to the technical field of installation and debugging of remote serial ports of communication devices. The method comprises the following steps: collecting power output current, electromagnetic interference data and debugging data during installation and debugging of the remote serial port of the communication device, preprocessing the collected data, constructing a power output current monitoring model using a random forest algorithm, constructing an electromagnetic interference intensity monitoring model by combining an electromagnetic interference intensity output model with a convolutional neural network algorithm, and constructing a scheduling management model using a neural network algorithm. The decision tree algorithm modeling technology, random forest algorithm modeling technology, multivariate linear regression algorithm modeling technology, convolutional neural network algorithm modeling technology and neural network algorithm modeling technology in the method of the present invention are closely combined with modern information technology to achieve real-time monitoring of power supply conditions and electromagnetic interference conditions of communication equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of installation and debugging of remote serial ports of communication equipment, and in particular to a method for installing and debugging a remote serial port of a communication equipment based on a Web. Background Art

[0002] Web-based remote management mode has gradually become the mainstream. Combining Web technology with serial port communication of communication equipment to achieve remote serial port control can greatly improve management efficiency. On the one hand, enterprises can monitor and debug communication equipment distributed in different regions anytime and anywhere through the network, discover and solve problems in time, and reduce losses caused by equipment failures. On the other hand, for some application scenarios that require real-time data interaction, Web-based remote serial port communication can ensure timely transmission and processing of data, providing a strong guarantee for the stable operation of the system. However, the current related installation and debugging methods are not perfect enough. Therefore, studying a Web-based communication equipment remote serial port installation and debugging method has important practical significance.

[0003] Although the existing technology has made great progress in the installation and debugging of remote serial ports of Web-based communication equipment, there are still some problems that need to be optimized. During the installation and debugging of remote serial ports of Web-based communication equipment, there may be unstable power supply current and electromagnetic interference. Among them, unstable power supply current may cause damage to the communication equipment and failure to start. Electromagnetic interference may cause data packet loss during the debugging process, resulting in errors in the debugging results. The existing technology is unable to monitor the power supply situation and electromagnetic interference in real time, and take corresponding measures to solve the problems of unstable power supply current and electromagnetic interference, which increases the difficulty of installing and debugging remote serial ports of Web-based communication equipment. Summary of the Invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: A Web-based installation and debugging method for a remote serial port of a communication device, comprising the following steps:

[0005] Step 1: Collect power output current, electromagnetic interference data, and debugging data during the installation and debugging of the remote serial port of the communication equipment, and pre-process the collected data to provide data support for the subsequent steps;

[0006] Step 2: Based on the pre-processed power supply output current data and combined with the decision tree algorithm, a power supply output current partitioning model is constructed;

[0007] Step 3: Based on the output results of the power output current partitioning model, analyze the impact of the power output current on the communication equipment, and build a power output current monitoring model in combination with the random forest algorithm to monitor the power output current.

[0008] Step 4: Analyze the packet loss rate of transmitted data using the pre-processed debugging data. Combined with the multivariate linear regression algorithm, an electromagnetic interference intensity output model is constructed based on the magnetic field intensity and electric field intensity, providing a data basis for constructing an electromagnetic interference intensity monitoring model.

[0009] Step 5: Based on the output of the electromagnetic interference intensity output model and the convolutional neural network algorithm, an electromagnetic interference intensity monitoring model is constructed to monitor the electromagnetic interference intensity of the communication equipment environment.

[0010] Build an electromagnetic interference intensity monitoring model based on electromagnetic interference lightness and packet loss;

[0011] Step 6: Using the output results of the power output current monitoring model and the electromagnetic interference intensity monitoring model, a scheduling management model is constructed;

[0012] Step 7: Combined with the output results of the scheduling management model, the corresponding power supply output current scheduling instructions and electromagnetic interference scheduling instructions are matched and executed, which solves the problem that the existing technology cannot monitor the power supply situation and electromagnetic interference in real time, and takes corresponding measures to solve the problem of unstable power supply current and electromagnetic interference, which increases the difficulty of installing and debugging the remote serial port of the Web-based communication equipment.

[0013] A further improvement of the technical solution of the present invention is that in step 1, the process of collecting power supply output current, electromagnetic interference data and debugging data includes:

[0014] Deploy data collection equipment to collect power output current, electromagnetic interference data, and debugging data during remote serial port installation and debugging of communication equipment, wherein the data collection equipment includes an ammeter, an electric field strength tester, a gauss meter, and a network tester;

[0015] The electromagnetic interference data includes the electric field strength and magnetic field strength of the communication equipment environment, and the debugging data includes the number of lost transmission data packets and the total number of transmission data packets;

[0016] Use an ammeter to collect the power supply output current; use an electric field strength tester to collect the electric field strength of the communication equipment environment; use a gauss meter to collect the magnetic field strength of the communication equipment environment; use a network tester to collect the number of transmission data packet losses and the total number of transmission data packets.

[0017] A further improvement of the technical solution of the present invention is that in step 1, the process of preprocessing the collected data includes:

[0018] Perform data cleaning and data standardization on the collected power supply output current, electric field strength of the communication equipment environment, magnetic field strength of the communication equipment environment, number of transmission data packet losses, and total number of transmission data packets;

[0019] Timestamps are added to the electric field strength of the communication device environment, the magnetic field strength of the communication device environment, the number of transmission data packet losses, and the total number of transmission data packets, respectively. By adjusting the timestamps, the collection times of the electric field strength of the communication device environment, the magnetic field strength of the communication device environment, the number of transmission data packet losses, and the total number of transmission data packets are synchronized.

[0020] A further improvement of the technical solution of the present invention is that in step 2, the process of constructing the power supply output current division model includes:

[0021] A1. Divide the power supply output current and its impact on the communication equipment into three levels based on the rated current of the communication equipment, where the three levels are low current impact range, normal current impact range, and high current impact range.

[0022] Specifically, the power output current below 95% of the rated current of the communication equipment is classified as a low current impact range, the power output current between 95% and 105% of the rated current of the communication equipment is classified as a normal current impact range, and the power output current above 105% of the rated current of the communication equipment is classified as a high current impact range, thereby obtaining the impact range of the power output current on the communication equipment;

[0023] A2. The power supply output current and its impact on the communication equipment are used as the first data set, and divided into a training set and a test set in a ratio of 7:3;

[0024] Using training set data and decision tree algorithm, the power supply output current is taken as input, and the impact range of the power supply output current on the communication equipment is taken as output. 95% of the rated current of the communication equipment is used as the first judgment threshold. If the input power supply output current is lower than 95% of the rated current of the communication equipment, the power supply output current is input into the left subtree, and the low current impact range is output in the tree node of the left subtree; if the input power supply output current is higher than 95% of the rated current of the communication equipment, the power supply output current is input into the right subtree for judgment, and 105% of the rated current of the communication equipment is set as the second judgment threshold. If the input power supply output current is lower than 105% of the rated current of the communication equipment, the normal current impact range is output in the tree node of the right subtree; if the input power supply output current is higher than 105% of the rated current of the communication equipment, the high current impact range is output in the tree node of the right subtree. The nonlinear relationship between the power supply output current and its impact range on the communication equipment is learned, and the power supply output current partitioning model is trained.

[0025] A further improvement of the technical solution of the present invention is that in step 3, the process of analyzing the impact of the power supply output current on the communication device includes:

[0026] Inputting the power supply output current into the power supply output current partitioning model to obtain the impact range of the power supply output current on the communication equipment;

[0027] According to the impact range of the power output current on the communication equipment, when the power output current is within the low current impact range, it indicates that the power supply is insufficient and the communication equipment cannot start; when the power output current is within the normal current impact range, it indicates that the power current is normal and the communication equipment operates normally; when the power output current is within the high current impact range, it indicates that the power current is too large and the communication equipment is damaged. The impact results of the power output current on the communication equipment are obtained.

[0028] A further improvement of the technical solution of the present invention is that in step 3, the process of constructing the power supply output current monitoring model includes:

[0029] The power supply output current and its impact on the communication equipment are used as the second data set, which is divided into a training set and a test set in a ratio of 8:2;

[0030] Using training data and a random forest algorithm, the power supply output current is used as input and the impact of the power supply output current on the communication equipment is used as output. The nonlinear relationship between the power supply output current and its impact on the communication equipment is automatically learned to train the power supply output current monitoring model.

[0031] Input the test set data into the power output current monitoring model, compare the output results of the power output current monitoring model with the impact of the actual power output current on the communication equipment, evaluate the performance of the power output current monitoring model, adjust the parameters of the power output current monitoring model, optimize the power output current monitoring model, and obtain the final power output current monitoring model.

[0032] A further improvement of the technical solution of the present invention is that in step 4, the process of calculating the transmission data packet loss rate and constructing the electromagnetic interference intensity output model includes:

[0033] The transmission data packet loss rate is obtained by calculating the ratio of the number of transmission data packet losses to the total number of transmission data packets;

[0034] The electric field strength and magnetic field strength of the communication equipment environment are used as the third data set, and divided into a training set and a test set in a ratio of 8:2;

[0035] Combining training set data with a multivariate linear regression algorithm, taking the electric field strength and magnetic field strength of the communication equipment environment as input and the electromagnetic interference strength of the communication equipment environment as output, adjusting the intercept term, the regression coefficient of the electric field strength of the communication equipment environment, and the regression coefficient of the magnetic field strength of the communication equipment environment, learning the linear relationship between the electric field strength, magnetic field strength, and electromagnetic interference strength of the communication equipment environment, and training the electromagnetic interference strength output model;

[0036] The test set data is input into the electromagnetic interference intensity output model, the performance of the electromagnetic interference intensity output model is evaluated, the intercept term and regression coefficient of the electromagnetic interference intensity output model are adjusted, the electromagnetic interference intensity output model is optimized, and the final electromagnetic interference intensity output model is obtained.

[0037] A further improvement of the technical solution of the present invention is that in step 5, the process of constructing the electromagnetic interference intensity monitoring model includes:

[0038] Inputting the electric field strength and the magnetic field strength of the communication equipment environment into the electromagnetic interference strength output model, the electromagnetic interference strength output model outputs the electromagnetic interference strength of the communication equipment environment;

[0039] The electromagnetic interference intensity and transmission data packet loss rate of the communication equipment environment are used as the fourth data set, which is divided into a training set and a test set in a ratio of 7:3;

[0040] By combining training data with a convolutional neural network algorithm, the electromagnetic interference intensity of the communication equipment environment is used as input and the packet loss rate of transmitted data is used as output. The nonlinear relationship between the electromagnetic interference intensity of the communication equipment environment and the packet loss rate of transmitted data is learned, and an electromagnetic interference intensity monitoring model is trained.

[0041] The test set data is input into the electromagnetic interference intensity monitoring model, and the actual transmission data packet loss rate is compared with the transmission data packet loss rate output by the electromagnetic interference intensity monitoring model to evaluate the performance of the electromagnetic interference intensity monitoring model. The electromagnetic interference intensity monitoring model parameters are updated through the Adam optimizer to optimize the electromagnetic interference intensity monitoring model and obtain the final electromagnetic interference intensity monitoring model.

[0042] A further improvement of the technical solution of the present invention is that in step 6, the construction process of the scheduling management model includes:

[0043] S1. Inputting the power output current into a power output current monitoring model, which outputs the impact of the power output current on the communication device; inputting the electromagnetic interference intensity of the communication device environment into the electromagnetic interference intensity monitoring model, which outputs the transmission data packet loss rate;

[0044] S2. Based on the impact of the power output current on the communication equipment, when the power supply is insufficient and the communication equipment cannot start, switch to the backup power supply to provide startup current for the communication equipment; when the power output current is within the normal current influence range, monitor the power output current in real time; when the power current is too large and the communication equipment is damaged, use the power management chip to intelligently limit the power output current, issue a power output current alarm signal, allocate power output current scheduling instructions, and number different power output current scheduling instructions;

[0045] S3. Based on the transmission data packet loss rate, when the transmission data packet loss rate is lower than 0.1, the transmission data packet loss rate is monitored in real time; when the transmission data packet loss rate is between 0.1 and 0.25, the communication equipment and cables are wrapped with metal casings, and the ground wires are reconnected to achieve low-impedance grounding and reduce the intensity of electromagnetic interference; when the transmission data packet loss rate is higher than 0.25, the abnormally working communication equipment is immediately deactivated, an electromagnetic interference alarm signal is issued, and electromagnetic interference scheduling instructions are assigned, and different electromagnetic interference scheduling instructions are numbered respectively;

[0046] S4. The fifth data set is divided into a training set and a test set in a ratio of 7:3 using the results of the impact of the power output current on the communication device, the transmission data packet loss rate, the power output current scheduling instruction number, and the electromagnetic interference scheduling instruction number.

[0047] Using training set data and a neural network algorithm, the impact of power output current on communication equipment and the transmission data packet loss rate are used as input, and the power output current scheduling instruction number and the electromagnetic interference scheduling instruction number are used as output. The nonlinear relationship between the impact of power output current on communication equipment and the power output current scheduling instruction number, as well as the nonlinear relationship between the transmission data packet loss rate and the electromagnetic interference scheduling instruction number, is learned to train the scheduling management model;

[0048] The test set data is input into the scheduling management model, and the MSE function is used to evaluate the error between the power output current scheduling instruction number output by the scheduling management model and the actual power output current scheduling instruction number, as well as the error between the electromagnetic interference scheduling instruction number output by the scheduling management model and the actual electromagnetic interference scheduling instruction number. According to the evaluation results, the parameters of the scheduling management model are adjusted, the performance of the scheduling management model is optimized, and the final scheduling management model is obtained.

[0049] A further improvement of the technical solution of the present invention is that in step seven, the process of matching and executing the corresponding power supply output current scheduling instructions and electromagnetic interference scheduling instructions in combination with the output results of the scheduling management model includes:

[0050] The impact of the power output current on the communication equipment and the transmission data packet loss rate are input into the scheduling instruction generation model. The scheduling instruction generation model outputs the power output current scheduling instruction number and the electromagnetic interference scheduling instruction number. According to the power output current scheduling instruction number, the corresponding power output current scheduling instruction is matched and the power output current scheduling instruction is executed; according to the electromagnetic interference scheduling instruction number, the corresponding electromagnetic interference scheduling instruction is matched and the electromagnetic interference scheduling instruction is executed.

[0051] The beneficial effects of the present invention are as follows: a Web-based installation and debugging method for a remote serial port of a communication device in the present invention, compared with a traditional Web-based installation and debugging method for a remote serial port of a communication device, the decision tree algorithm modeling technology, random forest algorithm modeling technology, multivariate linear regression algorithm modeling technology, convolutional neural network algorithm modeling technology and neural network algorithm modeling technology in the method of the present invention are closely integrated with modern information technology, and through an ammeter, an electric field strength tester, a gauss meter and a network tester, the data such as the power supply output current, the electric field strength of the communication equipment environment, the magnetic field strength of the communication equipment environment, the number of transmission data packet losses and the total number of transmission data packets are accurately captured, the influence range is divided for the power supply output current, the transmission data packet loss rate is calculated using the debugging data, the power supply output current division model is constructed using the decision tree model, and the power supply output current monitoring model is constructed using the random forest algorithm, thereby realizing the power supply output current monitoring. Monitoring of power supply conditions, through the multivariate linear regression algorithm, constructing an electromagnetic interference intensity output model, combining the electromagnetic interference intensity output model with the convolutional neural network algorithm, constructing an electromagnetic interference intensity monitoring model, achieving the monitoring of electromagnetic interference conditions of communication equipment, through the neural network algorithm, integrating the power output current monitoring model and the electromagnetic interference intensity monitoring model, constructing a scheduling management model, solving the problem that the existing technology is difficult to monitor power supply conditions and electromagnetic interference conditions in real time, resulting in difficulty in taking corresponding measures to solve the problem of unstable power current and electromagnetic interference, ensuring that the method in the present invention can refine the dynamic monitoring standards for a Web-based communication equipment remote serial port installation and debugging method within a more precise range, so that the monitored data becomes a more accurate indicator under the same conditions. The development and application of this method significantly enhances the level of intelligence in the installation and debugging process of the Web-based communication equipment remote serial port. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0053] Figure 1A logic diagram of a Web-based installation and debugging method for a remote serial port of a communication device according to the present invention;

[0054] Figure 2 It is the logic diagram of power supply output current data flow;

[0055] Figure 3 This is the logic diagram of electromagnetic interference data and debugging data flow. DETAILED DESCRIPTION

[0056] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0057] like Figure 1 As shown, the present invention provides a Web-based installation and debugging method for a remote serial port of a communication device, which consists of the following steps:

[0058] Step 1: Collect power output current, electromagnetic interference data, and debugging data during the installation and debugging of the remote serial port of the communication equipment, and pre-process the collected data to provide data support for the subsequent steps;

[0059] Step 2: Based on the pre-processed power supply output current data and combined with the decision tree algorithm, a power supply output current partitioning model is constructed;

[0060] Step 3: Based on the output results of the power output current partitioning model, analyze the impact of the power output current on the communication equipment, and build a power output current monitoring model in combination with the random forest algorithm to monitor the power output current.

[0061] Step 4: Analyze the packet loss rate of transmitted data using the pre-processed debugging data. Combined with the multivariate linear regression algorithm, an electromagnetic interference intensity output model is constructed based on the magnetic field intensity and electric field intensity, providing a data basis for constructing an electromagnetic interference intensity monitoring model.

[0062] Step 5: Based on the output of the electromagnetic interference intensity output model and the convolutional neural network algorithm, an electromagnetic interference intensity monitoring model is constructed to monitor the electromagnetic interference intensity of the communication equipment environment.

[0063] Build an electromagnetic interference intensity monitoring model based on electromagnetic interference lightness and packet loss;

[0064] Step 6: Using the output results of the power output current monitoring model and the electromagnetic interference intensity monitoring model, a scheduling management model is constructed;

[0065] Step 7: Combined with the output results of the scheduling management model, the corresponding power supply output current scheduling instructions and electromagnetic interference scheduling instructions are matched and executed, which solves the problem that the existing technology cannot monitor the power supply situation and electromagnetic interference in real time, and takes corresponding measures to solve the problem of unstable power supply current and electromagnetic interference, which increases the difficulty of installing and debugging the remote serial port of the Web-based communication equipment.

[0066] Preferably, in step 1, the process of collecting power supply output current, electromagnetic interference data, and debugging data includes:

[0067] Deploy data collection equipment to collect power output current, electromagnetic interference data, and debugging data during remote serial port installation and debugging of communication equipment. The data collection equipment includes ammeters, electric field strength testers, gauss meters, and network testers.

[0068] Among them, electromagnetic interference data includes the electric field strength and magnetic field strength of the communication equipment environment, and debugging data includes the number of lost transmission data packets and the total number of transmission data packets;

[0069] Use an ammeter to collect the power supply output current; use an electric field strength tester to collect the electric field strength of the communication equipment environment; use a gauss meter to collect the magnetic field strength of the communication equipment environment; use a network tester to collect the number of transmission data packet losses and the total number of transmission data packets.

[0070] Preferably, in step 1, the process of preprocessing the collected data includes:

[0071] Perform data cleaning and data standardization on the collected power supply output current, electric field strength of the communication equipment environment, magnetic field strength of the communication equipment environment, number of transmission data packet losses, and total number of transmission data packets;

[0072] Timestamps are added to the electric field strength of the communication device environment, the magnetic field strength of the communication device environment, the number of transmission data packet losses, and the total number of transmission data packets, respectively. By adjusting the timestamps, the collection times of the electric field strength of the communication device environment, the magnetic field strength of the communication device environment, the number of transmission data packet losses, and the total number of transmission data packets are synchronized.

[0073] Preferably, in step 2, the process of constructing the power supply output current division model includes:

[0074] A1. Based on the rated current of the communication equipment, the power supply output current and its impact range on the communication equipment are divided into three levels, namely low current impact range, normal current impact range and high current impact range;

[0075] Specifically, the power output current below 95% of the rated current of the communication equipment is classified as a low current impact range, the power output current between 95% and 105% of the rated current of the communication equipment is classified as a normal current impact range, and the power output current above 105% of the rated current of the communication equipment is classified as a high current impact range, thereby obtaining the impact range of the power output current on the communication equipment;

[0076] A2. The power supply output current and its impact on the communication equipment are used as the first data set, and divided into a training set and a test set in a ratio of 7:3;

[0077] Using training set data and decision tree algorithm, the power supply output current is taken as input, and the impact range of the power supply output current on the communication equipment is taken as output. 95% of the rated current of the communication equipment is used as the first judgment threshold. If the input power supply output current is lower than 95% of the rated current of the communication equipment, the power supply output current is input into the left subtree, and the low current impact range is output in the tree node of the left subtree; if the input power supply output current is higher than 95% of the rated current of the communication equipment, the power supply output current is input into the right subtree for judgment, and 105% of the rated current of the communication equipment is set as the second judgment threshold. If the input power supply output current is lower than 105% of the rated current of the communication equipment, the normal current impact range is output in the tree node of the right subtree; if the input power supply output current is higher than 105% of the rated current of the communication equipment, the high current impact range is output in the tree node of the right subtree. The nonlinear relationship between the power supply output current and its impact range on the communication equipment is learned, and the power supply output current partitioning model is trained.

[0078] Preferably, in step 3, the process of analyzing the impact of the power output current on the communication device includes:

[0079] Inputting the power supply output current into the power supply output current partitioning model to obtain the impact range of the power supply output current on the communication equipment;

[0080] According to the impact range of the power output current on the communication equipment, when the power output current is within the low current impact range, it indicates that the power supply is insufficient and the communication equipment cannot start; when the power output current is within the normal current impact range, it indicates that the power current is normal and the communication equipment operates normally; when the power output current is within the high current impact range, it indicates that the power current is too large and the communication equipment is damaged. The impact results of the power output current on the communication equipment are obtained.

[0081] Preferably, in step 3, the process of constructing the power supply output current monitoring model includes:

[0082] The power supply output current and its impact on the communication equipment are used as the second data set, which is divided into a training set and a test set in a ratio of 8:2;

[0083] Using training data and a random forest algorithm, the power supply output current is used as input and the impact of the power supply output current on the communication equipment is used as output. The nonlinear relationship between the power supply output current and its impact on the communication equipment is automatically learned to train the power supply output current monitoring model.

[0084] Input the test set data into the power output current monitoring model, compare the output results of the power output current monitoring model with the impact of the actual power output current on the communication equipment, evaluate the performance of the power output current monitoring model, adjust the parameters of the power output current monitoring model, optimize the power output current monitoring model, and obtain the final power output current monitoring model.

[0085] Preferably, in step 4, the process of analyzing the packet loss rate of transmitted data and constructing an electromagnetic interference intensity output model includes:

[0086] The transmission data packet loss rate is obtained by calculating the ratio of the number of transmission data packet losses to the total number of transmission data packets;

[0087] The electric field strength and magnetic field strength of the communication equipment environment are used as the third data set, and divided into a training set and a test set in a ratio of 8:2;

[0088] Combining training set data with a multivariate linear regression algorithm, taking the electric field strength and magnetic field strength of the communication equipment environment as input and the electromagnetic interference strength of the communication equipment environment as output, adjusting the intercept term, the regression coefficient of the electric field strength of the communication equipment environment, and the regression coefficient of the magnetic field strength of the communication equipment environment, learning the linear relationship between the electric field strength, magnetic field strength, and electromagnetic interference strength of the communication equipment environment, and training the electromagnetic interference strength output model;

[0089] The test set data is input into the electromagnetic interference intensity output model, the performance of the electromagnetic interference intensity output model is evaluated, the intercept term and regression coefficient of the electromagnetic interference intensity output model are adjusted, the electromagnetic interference intensity output model is optimized, and the final electromagnetic interference intensity output model is obtained.

[0090] Preferably, in step 5, the process of constructing the electromagnetic interference intensity monitoring model includes:

[0091] Inputting the electric field strength and the magnetic field strength of the communication equipment environment into the electromagnetic interference strength output model, the electromagnetic interference strength output model outputs the electromagnetic interference strength of the communication equipment environment;

[0092] The electromagnetic interference intensity and transmission data packet loss rate of the communication equipment environment are used as the fourth data set, which is divided into a training set and a test set in a ratio of 7:3;

[0093] By combining training data with a convolutional neural network algorithm, the electromagnetic interference intensity of the communication equipment environment is used as input and the packet loss rate of transmitted data is used as output. The nonlinear relationship between the electromagnetic interference intensity of the communication equipment environment and the packet loss rate of transmitted data is learned, and an electromagnetic interference intensity monitoring model is trained.

[0094] The test set data is input into the electromagnetic interference intensity monitoring model, and the actual transmission data packet loss rate is compared with the transmission data packet loss rate output by the electromagnetic interference intensity monitoring model to evaluate the performance of the electromagnetic interference intensity monitoring model. The electromagnetic interference intensity monitoring model parameters are updated through the Adam optimizer to optimize the electromagnetic interference intensity monitoring model and obtain the final electromagnetic interference intensity monitoring model.

[0095] Preferably, in step six, the process of building the scheduling management model includes:

[0096] S1. Inputting the power output current into a power output current monitoring model, which outputs the impact of the power output current on the communication device; inputting the electromagnetic interference intensity of the communication device environment into the electromagnetic interference intensity monitoring model, which outputs the transmission data packet loss rate;

[0097] S2. Based on the impact of the power output current on the communication equipment, when the power supply is insufficient and the communication equipment cannot start, switch to the backup power supply to provide startup current for the communication equipment; when the power output current is within the normal current influence range, monitor the power output current in real time; when the power current is too large and the communication equipment is damaged, use the power management chip to intelligently limit the power output current, issue a power output current alarm signal, allocate power output current scheduling instructions, and number different power output current scheduling instructions;

[0098] S3. Based on the transmission data packet loss rate, when the transmission data packet loss rate is lower than 0.1, the transmission data packet loss rate is monitored in real time; when the transmission data packet loss rate is between 0.1 and 0.25, the communication equipment and cables are wrapped with metal casings, and the ground wires are reconnected to achieve low-impedance grounding and reduce the intensity of electromagnetic interference; when the transmission data packet loss rate is higher than 0.25, the abnormally working communication equipment is immediately deactivated, an electromagnetic interference alarm signal is issued, and electromagnetic interference scheduling instructions are assigned, and different electromagnetic interference scheduling instructions are numbered respectively;

[0099] S4. The fifth data set is divided into a training set and a test set in a ratio of 7:3 using the results of the impact of the power output current on the communication device, the transmission data packet loss rate, the power output current scheduling instruction number, and the electromagnetic interference scheduling instruction number.

[0100] Using training set data and a neural network algorithm, the impact of power output current on communication equipment and the transmission data packet loss rate are used as input, and the power output current scheduling instruction number and the electromagnetic interference scheduling instruction number are used as output. The nonlinear relationship between the impact of power output current on communication equipment and the power output current scheduling instruction number, as well as the nonlinear relationship between the transmission data packet loss rate and the electromagnetic interference scheduling instruction number, is learned to train the scheduling management model;

[0101] The test set data is input into the scheduling management model, and the MSE function is used to evaluate the error between the power output current scheduling instruction number output by the scheduling management model and the actual power output current scheduling instruction number, as well as the error between the electromagnetic interference scheduling instruction number output by the scheduling management model and the actual electromagnetic interference scheduling instruction number. According to the evaluation results, the parameters of the scheduling management model are adjusted, the performance of the scheduling management model is optimized, and the final scheduling management model is obtained.

[0102] Preferably, in step seven, the process of matching and executing the corresponding power supply output current scheduling instruction and electromagnetic interference scheduling instruction in combination with the output result of the scheduling management model includes:

[0103] The impact of the power output current on the communication equipment and the transmission data packet loss rate are input into the scheduling instruction generation model. The scheduling instruction generation model outputs the power output current scheduling instruction number and the electromagnetic interference scheduling instruction number. According to the power output current scheduling instruction number, the corresponding power output current scheduling instruction is matched and the power output current scheduling instruction is executed; according to the electromagnetic interference scheduling instruction number, the corresponding electromagnetic interference scheduling instruction is matched and the electromagnetic interference scheduling instruction is executed.

[0104] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A Web-based method for installing and debugging a remote serial port of a communication device, characterized by: The following steps are involved: Step 1: Collect power output current, electromagnetic interference data, and debugging data during installation and debugging of the remote serial port of the communication equipment, and pre-process the collected data; Step 2: Based on the pre-processed power supply output current data and combined with the decision tree algorithm, a power supply output current partitioning model is constructed; Using training data and a decision tree algorithm, the power supply output current is used as input and the range of influence of the power supply output current on the communication device is used as output. The nonlinear relationship between the power supply output current and the range of influence on the communication device is learned, and the power supply output current partitioning model is trained. Step 3: Based on the output results of the power output current partitioning model, analyze the impact of the power output current on the communication equipment and build a power output current monitoring model by combining the random forest algorithm; Inputting the power supply output current into the power supply output current partitioning model to obtain the impact range of the power supply output current on the communication equipment; Based on the impact range of the power output current on the communication equipment, when the power output current is within the low current impact range, it indicates that the power supply is insufficient and the communication equipment cannot be started; when the power output current is within the normal current impact range, it indicates that the power current is normal and the communication equipment is operating normally; when the power output current is within the high current impact range, it indicates that the power current is too large and the communication equipment is damaged. Obtain the impact results of the power output current on the communication equipment; Using training data and a random forest algorithm, the power supply output current is used as input and the impact of the power supply output current on the communication equipment is used as output. The nonlinear relationship between the power supply output current and its impact on the communication equipment is automatically learned to train the power supply output current monitoring model. The power supply output current below 95% of the rated current of the communication equipment is classified as the low current impact range, the power supply output current between 95% and 105% of the rated current of the communication equipment is classified as the normal current impact range, and the power supply output current above 105% of the rated current of the communication equipment is classified as the high current impact range. The impact range of the power supply output current on the communication equipment is obtained. Step 4: Analyze the packet loss rate of transmitted data using the pre-processed debugging data, and build an electromagnetic interference intensity output model based on the magnetic field intensity and electric field intensity by combining the multivariate linear regression algorithm; Learn the linear relationship between the electric field strength, magnetic field strength, and electromagnetic interference strength of the communication equipment environment, and train the electromagnetic interference strength output model; Combining the training set data with a multiple linear regression algorithm, taking the electric field strength and the magnetic field strength of the communication equipment environment as inputs and the electromagnetic interference strength of the communication equipment environment as output, adjusting the intercept term, the regression coefficient of the electric field strength of the communication equipment environment, and the regression coefficient of the magnetic field strength of the communication equipment environment; Step 5: Using the output of the electromagnetic interference intensity output model and combining it with the convolutional neural network algorithm, an electromagnetic interference intensity monitoring model is constructed; Learn the nonlinear relationship between the electromagnetic interference intensity of the communication equipment environment and the packet loss rate of transmitted data, and train the electromagnetic interference intensity monitoring model; Construct an electromagnetic interference intensity monitoring model based on electromagnetic interference intensity and packet loss; Input the test set data into the electromagnetic interference intensity monitoring model, compare the actual transmission data packet loss rate with the transmission data packet loss rate output by the electromagnetic interference intensity monitoring model, evaluate the performance of the electromagnetic interference intensity monitoring model, update the electromagnetic interference intensity monitoring model parameters through the Adam optimizer, optimize the electromagnetic interference intensity monitoring model, and obtain the final electromagnetic interference intensity monitoring model; By combining training set data with a convolutional neural network algorithm, the electromagnetic interference intensity of the communication equipment environment is used as input, and the transmission data packet loss rate is used as output; Step 6: Using the output results of the power output current monitoring model and the electromagnetic interference intensity monitoring model, a scheduling management model is constructed; Using training set data and neural network algorithms, the impact of power output current on communication equipment and the transmission data packet loss rate are taken as input, and the power output current scheduling instruction number and electromagnetic interference scheduling instruction number are taken as output; Learn the nonlinear relationship between the impact of power output current on communication equipment and the power output current scheduling instruction number, as well as the nonlinear relationship between the transmission data packet loss rate and the electromagnetic interference scheduling instruction number, and train the scheduling management model; Step 7: Combine the output results of the scheduling management model to match and execute the corresponding power supply output current scheduling instructions and electromagnetic interference scheduling instructions; The impact of the power output current on the communication equipment and the transmission data packet loss rate are input into the scheduling instruction generation model. The scheduling instruction generation model outputs the power output current scheduling instruction number and the electromagnetic interference scheduling instruction number. According to the power output current scheduling instruction number, the corresponding power output current scheduling instruction is matched and the power output current scheduling instruction is executed. According to the electromagnetic interference scheduling instruction number, the corresponding electromagnetic interference scheduling instruction is matched and the electromagnetic interference scheduling instruction is executed.

2. The method for installing and debugging a remote serial port of a Web-based communication device according to claim 1, wherein: In step 1, the process of collecting power supply output current, electromagnetic interference data, and debugging data includes: Deploy collection equipment to collect power output current, electromagnetic interference data, and debugging data during remote serial port installation and debugging of communication equipment, wherein the collection equipment includes an ammeter, an electric field strength tester, a gauss meter, and a network tester; The electromagnetic interference data includes the electric field strength and magnetic field strength of the communication equipment environment, and the debugging data includes the number of lost transmission data packets and the total number of transmission data packets.

3. The method for installing and debugging a remote serial port of a Web-based communication device according to claim 2, wherein: In step 1, the process of preprocessing the collected data includes: Perform data cleaning and data standardization on the collected power supply output current, electric field strength of the communication equipment environment, magnetic field strength of the communication equipment environment, number of transmission data packet losses, and total number of transmission data packets; Timestamps are added to the electric field strength of the communication device environment, the magnetic field strength of the communication device environment, the number of transmission data packet losses, and the total number of transmission data packets, respectively. By adjusting the timestamps, the collection times of the electric field strength of the communication device environment, the magnetic field strength of the communication device environment, the number of transmission data packet losses, and the total number of transmission data packets are synchronized.

4. The method for installing and debugging a remote serial port of a Web-based communication device according to claim 3, wherein: In the second step, the process of constructing the power supply output current division model includes: A1. Divide the power supply output current and its impact on the communication equipment into three levels based on the rated current of the communication equipment, where the three levels are low current impact range, normal current impact range, and high current impact range. A2. The power supply output current and its impact on the communication equipment are used as the first data set, and divided into a training set and a test set in a ratio of 7:3; Input the test set data into the power output current partitioning model, compare the output results of the power output current partitioning model with the impact range of the actual power output current on the communication equipment, evaluate the performance of the power output current partitioning model, adjust the parameters of the power output current partitioning model, optimize the power output current partitioning model, and obtain the final power output current partitioning model.

5. The method for installing and debugging a remote serial port of a Web-based communication device according to claim 4, wherein: In step 3, the process of analyzing the impact of the power supply output current on the communication device includes: In step 3, the process of constructing the power supply output current monitoring model includes: The power supply output current and its impact on the communication equipment are used as the second data set, which is divided into a training set and a test set in a ratio of 8:2; Input the test set data into the power output current monitoring model, compare the output results of the power output current monitoring model with the impact of the actual power output current on the communication equipment, evaluate the performance of the power output current monitoring model, adjust the parameters of the power output current monitoring model, optimize the power output current monitoring model, and obtain the final power output current monitoring model.

6. The method for installing and debugging a remote serial port of a Web-based communication device according to claim 5, wherein: In step 4, the process of analyzing the packet loss rate of transmitted data and constructing an electromagnetic interference intensity output model includes: The transmission data packet loss rate is obtained by calculating the ratio of the number of transmission data packet losses to the total number of transmission data packets; The electric field strength and magnetic field strength of the communication equipment environment are used as the third data set, and divided into a training set and a test set in a ratio of 8:2; The test set data is input into the electromagnetic interference intensity output model, the performance of the electromagnetic interference intensity output model is evaluated, the intercept term and regression coefficient of the electromagnetic interference intensity output model are adjusted, the electromagnetic interference intensity output model is optimized, and the final electromagnetic interference intensity output model is obtained.

7. The method for installing and debugging a remote serial port of a Web-based communication device according to claim 6, wherein: In step 5, the process of constructing the electromagnetic interference intensity monitoring model includes: Inputting the electric field strength and the magnetic field strength of the communication equipment environment into the electromagnetic interference strength output model, the electromagnetic interference strength output model outputs the electromagnetic interference strength of the communication equipment environment; The electromagnetic interference intensity and transmission data packet loss rate of the communication equipment environment are used as the fourth data set, which is divided into a training set and a test set in a ratio of 7:

3.

8. The method for installing and debugging a remote serial port of a Web-based communication device according to claim 7, wherein: In step 6, the construction process of the scheduling management model includes: S1. Inputting the power output current into a power output current monitoring model, which outputs the impact of the power output current on the communication device; inputting the electromagnetic interference intensity of the communication device environment into the electromagnetic interference intensity monitoring model, which outputs the transmission data packet loss rate; S2. Allocate power output current scheduling instructions according to the impact of the power output current on the communication device, and number different power output current scheduling instructions respectively; S3. Allocate electromagnetic interference scheduling instructions based on the transmission data packet loss rate, and number different electromagnetic interference scheduling instructions respectively; S4. The fifth data set is divided into a training set and a test set in a ratio of 7:3 using the results of the impact of the power output current on the communication device, the transmission data packet loss rate, the power output current scheduling instruction number, and the electromagnetic interference scheduling instruction number. The test set data is input into the scheduling management model, and the MSE function is used to evaluate the error between the power output current scheduling instruction number output by the scheduling management model and the actual power output current scheduling instruction number, as well as the error between the electromagnetic interference scheduling instruction number output by the scheduling management model and the actual electromagnetic interference scheduling instruction number. According to the evaluation results, the parameters of the scheduling management model are adjusted, the performance of the scheduling management model is optimized, and the final scheduling management model is obtained.

Images