Receiver data transmission method and system fused with multi-redundancy communication

Abstract

The invention discloses a receiver data transmission method and system fused with multi-redundancy communication, and the method comprises the steps: inputting the signal intensity of a communication network into a BP neural network model for training through integrating a wired network, a 4G / 5G mobile network, a Beidou short message and a wireless ad hoc network communication multi-redundancy communication mode in a receiver; the optimal communication priority of different communication modes can be rapidly output, the optimal transmission path can be obtained and switched, fusion and non-inductive switching of the multi-redundancy communication modes are achieved, data communication in different environments is adapted, uninterrupted data transmission is guaranteed, and continuity and stability of data transmission of a receiver are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of receiver data transmission, and in particular to a receiver data transmission method and system integrating multiple redundant communications. Background Art

[0002] Data communication technology is a new communication method that emerged in the 1950s with the rapid development of computer technology and communication technology. It is the product of the combination of computers and communications, and mainly studies the theories, methods and technologies of transmission, exchange, storage and processing of digital data in computers. The background of data communication technology can be traced back to the mutual penetration and combination of computer technology and communication technology. This combination makes data communication possible and realizes data transmission between computers, computers and terminals, and terminals.

[0003] With the continuous development of communication technology, more and more large data transmission services are carried by wired broadband networks and other wireless communication networks to meet the growing demand for information interaction. Whether in agriculture, industry, commerce or military, they have been widely used, especially in application scenarios that require real-time data transmission. Wired broadband networks include 100 / 1000M networks, optical fibers, etc., and wireless communication networks include 4G / 5G mobile networks, WIFI, satellite communications, wireless ad hoc networks, etc., providing a broad platform for data communication applications.

[0004] In some specific situations, such as the receiver data transmission of the Continuously Operating Reference System (CORS) base station, wired network transmission is required under the conditions of wired broadband or dedicated lines. In the absence of wired broadband and dedicated lines, wireless network transmission is required. Although wireless communication networks are developing very rapidly, they still face huge challenges. The dynamic and heterogeneous nature of wireless networks, high error rates, and unpredictability of transmission links all have a great impact on the data transmission quality of receivers. Some receivers are used in harsh environments, with weak infrastructure such as electricity, communications, and transportation, and have more stringent requirements on the stability of data transmission networks. The existing receiver data transmission methods can no longer meet the needs, and there are the following problems:

[0005] 1) The communication mode is single, and wired network or 4G mobile network is mostly used for data transmission. In areas where wired network laying conditions are not available, when the mobile network is unstable, there is a problem of data loss;

[0006] 2) When a communication method fails or is interrupted, manual intervention, system switching, and other assistance are required, and data transmission is delayed or interrupted.

[0007] How to improve the real-time, continuity and reliability of data transmission in a multi-redundant communication fusion environment is a difficult problem currently faced. Summary of the invention

[0008] The present application provides a receiver data transmission method and system integrating multiple redundant communications to solve the problems of the existing receiver data transmission method, such as single communication mode, easy data loss, and data transmission delay or interruption.

[0009] According to a first aspect, an embodiment provides a receiver data transmission method integrating multiple redundant communications, the method comprising:

[0010] Collect network signal quality data samples under various communication modes and perform preprocessing to obtain a sample data set;

[0011] Dividing the sample data set into a training set and a validation set, and training and validating a pre-built neural network model, wherein the output of the neural network model is a communication mode priority;

[0012] The network signal quality data collected in real time under different communication modes are pre-processed and input into the trained neural network model to obtain the priority results of different communication modes, and the communication mode with the highest priority is used for data transmission.

[0013] Furthermore, network signal quality data samples under various communication modes are collected and preprocessed to obtain sample data sets, specifically including:

[0014] Start different communication mode ports and collect network signal quality data samples under different external environments. The communication modes include wired network, 4G / 5G mobile network, Beidou short message and wireless ad hoc network communication.

[0015] Furthermore, network signal quality data samples under various communication modes are collected and preprocessed to obtain sample data sets, specifically including:

[0016] Extract characteristic parameters of network signal quality sample data, including signal strength, signal-to-noise ratio, and signal delay, and perform normalization to convert the data to the same scale;

[0017] According to the normalized characteristic parameter value, the communication priority of the corresponding communication mode is marked.

[0018] Furthermore, the pre-built neural network model is trained and verified, including:

[0019] The neural network model adopts the BP neural network model.

[0020] Furthermore, the method for constructing the BP neural network model includes:

[0021] Determine the number of layers and nodes in each layer of the neural network model. The number of layers is 3, including an input layer, a hidden layer and an output layer. After experimental verification, the number of nodes in each layer is set as follows: input layer: 12 nodes; hidden layer: 32 nodes; output layer: 16 nodes;

[0022] Determine the initialization parameters of the BP neural network model, determine the bias and weight, and build the BP neural network model.

[0023] Furthermore, the pre-built neural network model is trained and verified, including:

[0024] The expected error of the neural network model training is analyzed by calculating the loss function, and it is determined whether the difference between the output value and the expected value is within the preset error range. If it exceeds the range, the error value is reversely propagated, and the parameters of the neural network model are adjusted based on this, and re-training is performed until the error range is met or the preset number of training iterations is reached. The neural network model training is completed and the final result is output.

[0025] Furthermore, the loss function adopts the mean square error MSE. By back-propagating the calculated error value, the gradient of each weight and bias is calculated from the output layer, hidden layer, and input layer in turn, and the weights and bias of the model are continuously updated using the gradient descent method. The training is then re-performed until the MSE value converges to a preset range or reaches a preset number of iterations. The training ends and the final result is output.

[0026] Furthermore, the network signal quality data collected in real time under different communication modes are pre-processed and input into the trained BP neural network model to obtain the priority results of different communication modes, and the communication mode with the highest priority is used for data transmission, which specifically includes:

[0027] The network signal quality of different communication modes is collected in real time, and characteristic parameters including signal strength, signal-to-noise ratio and signal delay are extracted and normalized, and then input into the trained neural network model to output the priority of the communication mode;

[0028] The receiver switches the communication mode according to the optimal communication priority output by the neural network model, opens the communication mode with the highest priority, closes other communication modes, and transmits the receiver data according to the corresponding communication protocol.

[0029] According to a second aspect, an embodiment provides a receiver data transmission system integrating multiple redundant communications, the system comprising:

[0030] A data acquisition module is used to collect network signal quality data samples under various communication modes and perform preprocessing to obtain a sample data set;

[0031] A model training module, used for dividing the sample data set into a training set and a validation set, and training and validating a pre-built neural network model, wherein the output of the neural network model is a communication mode priority;

[0032] The data transmission module is used to pre-process the network signal quality data collected in real time under different communication modes and input it into the trained neural network model to obtain the priority results of different communication modes and use the communication mode with the highest priority for data transmission.

[0033] According to a third aspect, an embodiment provides an electronic device, the device comprising: a processor and a memory;

[0034] The memory is used to store one or more program instructions;

[0035] The processor is used to run one or more program instructions to execute the steps of a receiver data transmission method integrating multiple redundant communications as described in any one of the above items.

[0036] According to a fourth aspect, an embodiment provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of a receiver data transmission method integrating multiple redundant communications as described in any one of the above items are implemented.

[0037] The present application provides a receiver data transmission method and system integrating multiple redundant communications. By integrating multiple redundant communication modes of wired network, 4G / 5G mobile network, Beidou short message and wireless ad hoc network communication in the receiver, the communication network signal strength is input into a neural network model for training, and the optimal communication priority of different communication modes can be quickly output, thereby realizing real-time monitoring and seamless switching of the communication network by the receiver, greatly improving the continuity and stability of the receiver's data transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flowchart of a receiver data transmission method integrating multiple redundant communications provided by an embodiment of the present invention;

[0039] Figure 2 A specific implementation flow chart of a receiver data transmission method integrating multiple redundant communications provided by an embodiment of the present invention;

[0040] Figure 3 A schematic diagram of the logical structure of a receiver data transmission system integrating multiple redundant communications is provided in accordance with an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present application better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present application are not shown or described in the specification, this is to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0042] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0043] The first embodiment of the present invention provides a receiver data transmission method integrating multiple redundant communications, which collects network signal quality, uses BP neural network to establish a learning model, obtains the optimal transmission path and switches, realizes the integration and senseless switching of multiple redundant communication modes, adapts to data communication in different environments, and ensures uninterrupted data transmission. Figure 1 and Figure 2 Provide detailed explanation.

[0044] like Figure 1 As shown, in step S100, network signal quality data samples under a plurality of different communication modes are collected and preprocessed to obtain a sample data set.

[0045] The above steps specifically include:

[0046] S110, the system is started and initialized. All communication modules including wired network, 4G / 5G mobile network, Beidou short message and wireless ad hoc network are started normally. Under different environments, the CPU collects and stores signal quality data samples of each communication network through the serial port. This step aims to collect as many signal quality data samples as possible under different latitude and longitude, altitude, air pressure, temperature and humidity, and geographical environment conditions during the testing phase.

[0047] S120, extract characteristic parameters of the sample data, including signal strength, signal-to-noise ratio and signal delay, perform normalization preprocessing, convert the sample data of the four communication modes to the same scale, obtain 12 different data, and then compare the data samples in different environments through manual labeling to obtain the communication priorities of different communication modes;

[0048] Among them, the normalization process uses a linear function conversion method to convert the data value to the range of (0, 1). The specific formula is as follows:

[0049] y=(x-MinValue) / (MaxValue-MinValue)

[0050] Among them, x and y are the values ​​before and after the conversion, respectively, and MaxValue and MinValue are the maximum and minimum values ​​of the sample data, respectively;

[0051] After calculating through the above formula, 12 kinds of data are obtained, including y of wired network 1-1 ,y 1-2 ,y 1-3 , 4G / 5G mobile network 2-1 ,y 2-2 ,y 2-3 , Beidou short message y 3-1 ,y 3-2 ,y 3-3 , wireless ad hoc network y4-1 ,y 4-2 ,y 4-3 , these data are used as input for the neural network model.

[0052] like Figure 1 As shown, in step S200, the sample data set is divided into a training set and a verification set, and a pre-built neural network model is trained and verified, and the output of the neural network model is the communication mode priority.

[0053] The above steps specifically include:

[0054] S210, divide the processed sample data into two parts, a training set and a validation set, according to a preset ratio; the training set is used to train the parameters of the network model so that the model can recognize and learn the rules and patterns in the sample data and minimize the prediction error of the model on the training set; the validation set is used to verify the trained model and adjust the parameters of the model to improve the generalization performance of the model. The ratios of the training set and the validation set are set here to 80% and 20% respectively.

[0055] S220, inputting the processed sample data into the BP neural network model for network model training, and continuously optimizing the parameters through iterative training to obtain a machine learning model with the minimum budget error, which specifically includes the following steps:

[0056] S230, determining the number of layers and the number of nodes in each layer of the neural network model, wherein the number of layers is 3, including an input layer, a hidden layer, and an output layer. After experimental verification, the number of nodes in each layer is set as follows:

[0057] Input layer: 12 nodes

[0058] Hidden layer: 32 nodes

[0059] Output layer: 16 nodes

[0060] S240, determining the initialization parameters of the neural network model, determining the bias and weight, and constructing the BP neural network model, the input data is the signal strength, signal-to-noise ratio and signal delay of the four communication networks, and the output data is the priority of the communication mode;

[0061] S250, inputting the training set of sample data into the constructed BP neural network model for training, thereby obtaining a trained machine learning model;

[0062] S260, after the network model training is completed, the model has reached the optimal state in processing the data of the training set. In order to train the model's ability to process new data, the verification set of the sample data is input into the trained machine learning model so that the prediction error of the output communication mode priority is minimized, thereby obtaining the output value of the communication mode priority;

[0063] S270, analyze the expected error of network model training, determine whether the difference between the output value and the expected value is within the preset error range, if it exceeds the range, reverse propagate the error value, and use it as a basis to adjust the parameters of the neural network model, return to step S250 and retrain until the error range is met or the preset number of training iterations is reached, the machine model training is completed, and the final result is output.

[0064] Preferably, the loss function is calculated to determine whether the difference between the output value and the expected value is within a preset error range. The loss function uses the mean square error (MSE), and its calculation formula is as follows:

[0065]

[0066] Among them, N represents the number of samples, y_i represents the true value of the i-th sample, y_pred represents the predicted value, and Σ represents the sum of all samples.

[0067] The smaller the MSE value is, the higher the prediction accuracy of the model is. The calculated error value is back-propagated, and the gradient of each weight and bias is calculated from the output layer, hidden layer, and input layer in turn. The weight and bias of the model are continuously updated using the gradient descent method, and the training is returned to step S250 for retraining until the MSE value converges to a preset range. This value can be set according to the actual working conditions. Considering that after multiple iterations of training, the output result has been infinitely close to the expected result, in order to avoid meaningless training in the later stage, after experimental verification, the number of iterations is set to 1000 here. After the number of iterations is reached, the training ends and the final result is output.

[0068] In the gradient descent method, the weight update formula is:

[0069]

[0070] Where w is the weight, η is the learning rate, is the gradient of the weight. The learning rate η is set to an empirical value of 0.1.

[0071] The bias update formula is:

[0072]

[0073] Where L is the bias, η is the learning rate, is the gradient of the bias. The learning rate η is set to an empirical value of 0.1.

[0074] Through the above steps, the neural network model has completed training and reached the optimal state, preparing for subsequent real-time data processing.

[0075] like Figure 1 As shown, in step S300, the network signal quality data collected in real time under different communication modes are preprocessed and input into the trained neural network model to obtain the priority results of different communication modes, and the communication mode with the highest priority is used for data transmission.

[0076] The above steps specifically include:

[0077] S310: During the operation of the receiver function, the network signal quality of four communication modes is collected in real time, three characteristic parameters, namely signal strength, signal-to-noise ratio and signal delay data, are extracted, and input into the trained machine learning model to output the current optimal communication priority.

[0078] S320, the receiver switches the communication mode according to the optimal communication priority output by the network model, opens the communication mode with the highest priority, closes other communication modes, and transmits the receiver data according to the corresponding communication protocol.

[0079] Corresponding to the above-disclosed receiver data transmission method integrating multiple redundant communications, the embodiment of the present invention further discloses a receiver data transmission system integrating multiple redundant communications, such as Figure 3 As shown, it specifically includes:

[0080] A data acquisition module is used to collect network signal quality data samples under various communication modes and perform preprocessing to obtain a sample data set;

[0081] A model training module, used for dividing the sample data set into a training set and a validation set, and training and validating a pre-built neural network model, wherein the output of the neural network model is a communication mode priority;

[0082] The data transmission module is used to pre-process the network signal quality data collected in real time under different communication modes and input it into the trained neural network model to obtain the priority results of different communication modes and use the communication mode with the highest priority for data transmission.

[0083] It should be noted that, for a detailed description of a receiver data transmission system integrating multiple redundant communications provided in an embodiment of the present invention, reference may be made to the relevant description of a receiver data transmission method integrating multiple redundant communications provided in an embodiment of the present application, which will not be repeated here.

[0084] In addition, an embodiment of the present invention further provides an electronic device, comprising: a processor and a memory; the memory is used to store one or more program instructions; the processor is used to run one or more program instructions to execute the steps of a receiver data transmission method integrating multiple redundant communications as described in any one of the above items.

[0085] It should be noted that, for the detailed description of an electronic device provided in an embodiment of the present invention, reference may be made to the relevant description of a receiver data transmission method integrating multiple redundant communications provided in an embodiment of the present application, which will not be repeated here.

[0086] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of a receiver data transmission method integrating multiple redundant communications as described in any one of the above items are implemented.

[0087] It should be noted that, for a detailed description of a computer-readable storage medium provided in an embodiment of the present invention, reference may be made to the relevant description of a receiver data transmission method integrating multiple redundant communications provided in an embodiment of the present application, which will not be repeated here.

[0088] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above-mentioned embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above-mentioned functions can be implemented. In addition, when all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and can be downloaded or copied and saved in the memory of the local device, or the system of the local device is updated, and when the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0089] The above specific examples are used to illustrate the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the art, according to the concept of the present invention, some simple deductions, modifications or substitutions can be made.

Claims

1. A receiver data transmission method integrating multiple redundant communications, characterized in that: The method comprises: Collect network signal quality data samples under various communication modes and perform preprocessing to obtain a sample data set; Dividing the sample data set into a training set and a validation set, and training and validating a pre-built neural network model, wherein the output of the neural network model is a communication mode priority; The network signal quality data collected in real time under different communication modes are pre-processed and input into the trained neural network model to obtain the priority results of different communication modes, and the communication mode with the highest priority is used for data transmission.

2. A receiver data transmission method integrating multiple redundant communications as claimed in claim 1, characterized in that: Collect network signal quality data samples under various communication modes and perform preprocessing to obtain sample data sets, including: Start different communication mode ports and collect network signal quality data samples under different external environments. The communication modes include wired network, 4G / 5G mobile network, Beidou short message and wireless ad hoc network communication.

3. A receiver data transmission method integrating multiple redundant communications as claimed in claim 2, characterized in that: Collect network signal quality data samples under various communication modes and perform preprocessing to obtain sample data sets, including: Extract characteristic parameters of network signal quality sample data, including signal strength, signal-to-noise ratio, and signal delay, and perform normalization to convert the data to the same scale; According to the normalized characteristic parameter value, the communication priority of the corresponding communication mode is marked.

4. A receiver data transmission method integrating multiple redundant communications as claimed in claim 1, characterized in that: Train and validate pre-built neural network models, including: The neural network model adopts the BP neural network model.

5. A receiver data transmission method integrating multiple redundant communications as claimed in claim 4, characterized in that: The construction method of BP neural network model includes: Determine the number of layers and nodes in each layer of the neural network model. The number of layers is 3, including an input layer, a hidden layer and an output layer. After experimental verification, the number of nodes in each layer is set as follows: input layer: 12 nodes; hidden layer: 32 nodes; output layer: 16 nodes; Determine the initialization parameters of the BP neural network model, determine the bias and weight, and build the BP neural network model.

6. A receiver data transmission method integrating multiple redundant communications as claimed in claim 1, characterized in that: Train and validate pre-built neural network models, including: The expected error of the neural network model training is analyzed by calculating the loss function, and it is determined whether the difference between the output value and the expected value is within the preset error range. If it exceeds the range, the error value is reversely propagated, and the parameters of the neural network model are adjusted based on this, and re-training is performed until the error range is met or the preset number of training iterations is reached. The neural network model training is completed and the final result is output.

7. A receiver data transmission method integrating multiple redundant communications as claimed in claim 6, characterized in that: The loss function uses the mean square error (MSE). The calculated error value is back-propagated, and the gradient of each weight and bias is calculated from the output layer, hidden layer, and input layer in turn. The weights and biases of the model are continuously updated using the gradient descent method, and the training is re-performed until the MSE value converges to a preset range or reaches a preset number of iterations. The training ends and the final result is output.

8. A receiver data transmission method integrating multiple redundant communications as claimed in claim 1, characterized in that: The network signal quality data collected in real time under different communication modes are pre-processed and input into the trained BP neural network model to obtain the priority results of different communication modes. The communication mode with the highest priority is used for data transmission, including: The network signal quality of different communication modes is collected in real time, and characteristic parameters including signal strength, signal-to-noise ratio and signal delay are extracted and normalized, and then input into the trained neural network model to output the priority of the communication mode; The receiver switches the communication mode according to the optimal communication priority output by the neural network model, opens the communication mode with the highest priority, closes other communication modes, and transmits the receiver data according to the corresponding communication protocol.

9. A receiver data transmission system integrating multiple redundant communications, characterized in that: The system comprises: A data acquisition module is used to collect network signal quality data samples under various communication modes and perform preprocessing to obtain a sample data set; A model training module, used for dividing the sample data set into a training set and a validation set, and training and validating a pre-built neural network model, wherein the output of the neural network model is a communication mode priority; The data transmission module is used to pre-process the network signal quality data collected in real time under different communication modes and input it into the trained neural network model to obtain the priority results of different communication modes and use the communication mode with the highest priority for data transmission.

10. An electronic device, characterized in that: The device comprises: a processor and a memory; The memory is used to store one or more program instructions; The processor is used to run one or more program instructions to execute the steps of a receiver data transmission method integrating multiple redundant communications as described in any one of claims 1 to 8.

Images