Intelligent receiving method and device of communication signal

Abstract

The invention discloses an intelligent receiving method and device for communication signals. The method comprises the following steps: constructing a total communication data set of a communication area; performing clustering analysis processing on the total communication data set to obtain a data classification model and a communication data set of each communication type; obtaining a signal demodulation detection model corresponding to each communication type by using the communication data set of each communication type; performing classification processing on the position information of the communication receiver and the acquired environmental electromagnetic signals by using a data classification model to obtain a communication type of the communication receiver; and performing demodulation detection processing on the communication signal received by the communication receiver, the position information of the communication receiver and the environmental electromagnetic signal by using a signal demodulation detection model corresponding to the communication type of the communication receiver to obtain a detection signal. According to the invention, the problem of realizing high-reliability information transmission and accurate information receiving in dense multipath and complex electromagnetic scenes is solved.

Description

Technical Field

[0001] The present invention relates to the fields of communication and artificial intelligence, and particularly relates to an intelligent receiving method and device for communication signals. Background Art

[0002] With the development of wireless communication technology in the Internet of Things era, more and more communication terminals will be widely used in the future. Communication in dense multipath scenarios such as indoors will become increasingly important. Due to the ubiquitous presence of wireless devices, the electromagnetic environment of communication scenarios has become increasingly complex. In dense multipath and complex electromagnetic scenarios, how to achieve high-reliability information transmission and accurate information reception is an urgent problem to be solved currently. Summary of the Invention

[0003] The present invention mainly solves the problem of how to achieve high-reliability information transmission and accurate information reception in dense multipath and complex electromagnetic scenarios, and discloses an intelligent receiving method and device for communication signals.

[0004] In the first aspect of the embodiments of the present application, an intelligent receiving method for communication signals is disclosed, including: S1, constructing a total communication data set of a communication area; the total communication data set includes communication node data information; the communication node data information includes the position information, standard signal, received signal, and environmental electromagnetic signal of a communication node; the communication node is a node that receives communication signals in the communication area; the standard signals in all communication node data information are the same; S2, performing clustering analysis processing on the total communication data set to obtain a data classification model and a communication data set for each communication type; S3, using the communication data set for each communication type to perform training processing on a preset signal demodulation detection model to obtain a signal demodulation detection model corresponding to each communication type; S4, using the data classification model to perform classification processing on the position information of a communication receiver and the collected environmental electromagnetic signal to obtain the communication type of the communication receiver; S5, using the signal demodulation detection model corresponding to the communication type of the communication receiver to perform demodulation detection processing on the communication signal received by the communication receiver, the position information of the communication receiver, and the environmental electromagnetic signal to obtain a detection signal.

[0005] The performing clustering analysis processing on the total communication data set to obtain a data classification model and a communication data set for each communication type includes: representing the position information and environmental electromagnetic signal of the communication node in each communication node data information in the total communication data set as a node vector; the elements of the node vector are the position information and environmental electromagnetic signal of the communication node; Perform clustering analysis on all node vectors to obtain the type information of the node vectors and the node vectors included in each type; Use the communication node data information corresponding to all node vectors of the same type to construct a communication data set of the corresponding communication type; For all node vectors of the same type, perform central point calculation and boundary value calculation respectively to obtain the intermediate point value and boundary value of the corresponding communication type of the type; Use the intermediate point values and boundary values of all communication types to construct a data classification model.

[0006] The expression for the central point calculation is: where, is the j-th element of the i-th node vector of the same type, N is the number of node vectors included in the type, and are the preset first weighting factor and second weighting factor respectively, is the j-th element of the central point of the corresponding communication type of the type; The expression for the boundary value calculation is: , where, is the extreme difference of the j-th elements of all node vectors of the same type, , and are the mean, variance and median value of the j-th elements of all node vectors of the same type respectively, is the boundary value of the j-th element of the node vector of the corresponding communication type of the type.

[0007] The discriminant expression of the data classification model is: , where, is the j-th element of the node vector to be classified, M is the total number of elements included in the node vector, is the discriminant expression corresponding to the j-th element of the node vector; When each element of the node vector to be classified satisfies the corresponding discriminant expression, it is determined that the node vector to be classified belongs to the communication type corresponding to the intermediate point value and the boundary value.

[0008] The signal demodulation detection model includes: a signal feature extraction network, a signal feature detection network and a signal feature fusion network; The signal feature extraction network includes a first input module, a first two-dimensional convolution module, a first activation module, a first residual module, and a first normalization module; the input end of the first input module is the input end of the signal feature extraction network for receiving input data; in the signal feature extraction network, the first input module, the first two-dimensional convolution module, the first activation module, the first residual module, and the first normalization module are connected in sequence; the output end of the first normalization module is the output end of the signal feature extraction network and is connected to the input end of the second input module; The signal feature detection network includes a second input module, a random permutation module, a second two-dimensional convolution module, a second activation module, and a second residual module; the input end of the signal feature detection network is the input end of the second input module; the output end of the signal feature detection network is the output end of the second residual module and is connected to the input end of the third input module; in the signal feature detection network, the second input module, the random permutation module, the second two-dimensional convolution module, the second activation module, and the second residual module are connected in sequence; The signal feature fusion network includes: a third input module, a first convolution module, a second convolution module, a third convolution module, a first pooling module, a fourth convolution module, a first fully-connected module, and a second fully-connected module; The input end of the third input module of the signal feature fusion network is connected to the output end of the second residual module; the output end of the third input module of the signal feature fusion network is connected to the input end of the first convolution module of the signal feature fusion network; the output end of the first convolution module of the signal feature fusion network is connected to the input end of the second convolution module of the signal feature fusion network; the output end of the second convolution module of the signal feature fusion network is connected to the input end of the third convolution module of the signal feature fusion network; the output end of the third convolution module of the signal feature fusion network is connected to the input end of the first pooling module of the signal feature fusion network; the output end of the first pooling module of the signal feature fusion network is connected to the input end of the fourth convolution module of the signal feature fusion network; the output end of the fourth convolution module of the signal feature fusion network is connected to the input end of the first fully-connected module of the signal feature fusion network; the output end of the first fully-connected module of the signal feature fusion network is connected to the input end of the second fully-connected module of the signal feature fusion network; the output end of the second fully-connected module is used to output a detection signal for the input signal.

[0009] Training a preset signal demodulation detection model using the communication data set of each communication type to obtain a signal demodulation detection model corresponding to each communication type includes: For a communication data set of a communication type, initialize the value of the training iteration count; during the training process, use the location information, received signal, and environmental electromagnetic signal of the communication data set corresponding to the communication type as training data; use the standard signal corresponding to the training data as label information; Use the training data in the communication data set as input data and input it into a signal demodulation and detection model corresponding to a communication type; Use the signal demodulation and detection model to process the input data to obtain a detection signal; Perform a difference calculation process on the obtained detection signal and the label information corresponding to the input data to obtain a difference value; Determine whether the difference value satisfies the convergence condition to obtain a first judgment result; When the first judgment result is no, determine whether the value of the training iteration count is equal to the training count threshold to obtain a second judgment result; When the second judgment result is no, determine that the model training status does not meet the termination training condition; When the second judgment result is yes, determine that the model training status meets the termination training condition; When the first judgment result is yes, determine that the model training status meets the termination training condition; When the model training status does not meet the termination training condition, use a parameter update model to update the parameters of the signal demodulation and detection model, increase the value of the training iteration count by 1, and trigger the execution of using the training data in the communication data set as input data and inputting it into the signal demodulation and detection model; When the model training status meets the termination training condition, complete the training process of the signal demodulation and detection model to obtain a trained signal demodulation and detection model; Use the communication data set of each communication type to perform a training process on a preset signal demodulation and detection model to obtain a signal demodulation and detection model corresponding to each communication type.

[0010] The parameter update model is: , ; In the formula, is the difference value calculated for the i-th training data in the communication data set, is the parameter update value, is the parameter of the signal demodulation and detection model, is the initial parameter learning rate, is the momentum angle parameter, , represents for the variable Find the partial derivative.

[0011] In the second aspect of the embodiments of the present application, an intelligent receiving device for communication signals is disclosed. The device includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent receiving method for communication signals described above.

[0012] In the third aspect of the embodiments of the present application, a computer-readable storage medium is disclosed. The computer-readable storage medium stores computer instructions, which are used to execute the intelligent receiving method for communication signals when called by a computer.

[0013] In the fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed. The information data processing terminal is used to implement the intelligent receiving method for communication signals described above.

[0014] The beneficial effects of the present invention are as follows: The present invention discloses an intelligent receiving method and device for communication signals, which solves the problem of how to achieve high-reliability information transmission and accurate information reception in dense multipath and complex electromagnetic scenarios.

[0015] Before formal communication, the present invention first constructs a total communication data set for the communication area, obtains the electromagnetic signals of each communication node and the received signals for the standard signal; by classifying the received signals and environmental signals of each node, a classification model for communication is established, and a corresponding signal demodulation and detection model is constructed for each type of scenario, improving the matching between demodulation and scenarios.

[0016] The present invention realizes the demodulation and detection of signals by establishing a signal demodulation and detection model and using three networks: a signal feature extraction network, a signal feature detection network, and a signal feature fusion network, achieving the accuracy and real-time performance of demodulation and detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flowchart of the implementation of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] To better understand the content of the present invention, an embodiment is given here.

[0019] Figure 1 It is a flowchart of the implementation of the method of the present invention.

[0020] In the first aspect of the embodiments of the present application, an intelligent receiving method for communication signals is disclosed, including: S1. Construct the total communication data set of the communication area; the total communication data set includes communication node data information; the communication node data information includes the location information, standard signal, received signal, and environmental electromagnetic signal of the communication node; the communication node is a node that receives communication signals within the communication area; the standard signal is the signal sent to the communication receiver at the location of the communication node, the received signal is the signal corresponding to the standard signal received by the communication receiver at the location of the communication node; the electromagnetic signal is the environmental electromagnetic signal collected by the communication receiver at the location of the communication node; the standard signals in all communication node data information are the same; the environmental electromagnetic signal is the electromagnetic signal of the background environment collected by the communication receiver of the communication node when there is no received signal. The standard signal in the total communication data set is a unified information signal sent by nodes within the communication area. The received signal in the total communication data set is the received signal corresponding to the standard signal of nodes within the communication area.

[0021] S2. Perform clustering analysis on the total communication data set to obtain a data classification model and the communication data set of each communication type. S3. Use the communication data set of each communication type to train a preset signal demodulation detection model to obtain a signal demodulation detection model corresponding to each communication type. S4. Use the data classification model to classify the location information of the communication receiver and the collected environmental electromagnetic signal to obtain the communication type of the communication receiver. S5. Use the signal demodulation detection model corresponding to the communication type of the communication receiver to perform demodulation detection on the received communication signal of the communication receiver to obtain a detection signal. The performing clustering analysis on the total communication data set to obtain a data classification model and the communication data set of each communication type includes: Represent the location information and environmental electromagnetic signal of the communication node in each communication node data information in the total communication data set as a node vector; the elements of the node vector are the location information and environmental electromagnetic signal of the communication node. Perform clustering analysis on all node vectors to obtain the type information of the node vectors and the node vectors included in each type. Use the communication node data information corresponding to all node vectors of the same type to construct the communication data set of the corresponding communication type. Perform centroid calculation and boundary value calculation on all node vectors of the same type to obtain the midpoint value and boundary value of the corresponding communication type. Use the midpoint values and boundary values of all communication types to construct a data classification model. The expression for calculating the center point is as follows: Where, is the j-th element of the i-th node vector of the same type, N is the number of node vectors included in the type, and are the preset first weighting factor and second weighting factor respectively, is the j-th element of the center point of the communication type corresponding to the type; The expression for calculating the center point comprehensively uses the geometric mean and weighted logarithmic operations, and takes into account both the overall product relationship and relative proportion relationship of the elements in the node vectors of the same type. For complex data such as the location information of communication nodes and environmental electromagnetic signals, it can extract key features from multiple dimensions, avoid losing important information due to a single calculation method, and more accurately depict the core trend of data distribution.

[0022] The expression for calculating the center point can, through the preset first weighting factor and second weighting factor, flexibly adjust the contribution degrees of the two calculation methods to the calculation of the center point according to the requirements of the actual communication scenario. For example, in a scenario with a drastic change in the electromagnetic environment, the weight of the second weighting factor can be increased to highlight the sensitivity of the logarithmic operation to data fluctuations, so that the center point can better reflect the characteristics of the environmental electromagnetic signals; while when the location information has a greater impact on signal reception, the weight of the first weighting factor can be increased to emphasize the comprehensive consideration of the geometric mean for the location distribution.

[0023] In the expression for calculating the center point, the logarithmic operation part is normalized by introducing a denominator component, effectively suppressing the interference of abnormal data to the calculation of the center point. In a complex electromagnetic environment, even if there are abnormal electromagnetic signal data collected by individual communication nodes, this expression can, through the characteristics of the logarithmic operation, reduce the impact of abnormal values and ensure the stability and reliability of the center point calculation result, thereby improving the accuracy of the data classification model.

[0024] The expression for calculating the boundary value is as follows: , Where, is the range difference of the j-th elements of all node vectors of the same type, , and are the mean value, variance and median value of the j-th elements of all node vectors of the same type respectively, is the boundary value of the j-th element of the node vector of the communication type corresponding to the type; The boundary value calculation expression incorporates the range, mean, variance of the data, and the maximum deviation of individual data from the reference value, comprehensively describing the distribution boundaries of node vector elements of the same type from multiple perspectives. The range reflects the degree of data dispersion, the mean and variance reflect the central tendency and fluctuation of the data, and the maximum deviation captures the extreme changes in the data. This combination of multiple indicators can accurately define the boundary range of communication type data, avoiding misclassification during classification; The boundary value calculation expression can adaptively adjust the boundary value according to the fluctuation characteristics of the data by introducing the ratio of the mean to the variance of the data. In a scenario where the electromagnetic environment is complex and variable, when the variance increases indicating increased data fluctuation, the ratio of the mean to the variance will be adjusted accordingly, enabling the boundary value to dynamically expand to accommodate more signal variation situations; conversely, when the data is relatively stable, the boundary value can also be tightened to improve the accuracy of classification, thereby enabling the data classification model to better adapt to different communication environments. By taking the maximum deviation value in the calculation, it is ensured that the boundary value can cover all possible extreme data situations. In a dense multipath and complex electromagnetic scenario, even if rare signal interference or abnormal received data occurs, the boundary value determined by this expression can include them, preventing these extreme situations from causing misclassification of communication types and effectively enhancing the robustness and fault tolerance of the data classification model.

[0025] The discriminant expression of the data classification model is: , where is the j-th element of the node vector to be classified, M is the total number of elements contained in the node vector, is the discriminant expression corresponding to the j-th element of the node vector; when each element of the node vector to be classified satisfies the corresponding discriminant expression, it is determined that the node vector to be classified belongs to the communication type corresponding to the intermediate point value and the boundary value; The signal demodulation and detection model includes: a signal feature extraction network, a signal feature detection network, and a signal feature fusion network; The signal feature extraction network includes a first input module, a first two-dimensional convolution module, a first activation module, a first residual module, and a first normalization module; the input end of the first input module is the input end of the signal feature extraction network for receiving input data; in the signal feature extraction network, the first input module, the first two-dimensional convolution module, the first activation module, the first residual module, and the first normalization module are connected in sequence; the output port of the first normalization module is the output port of the signal feature extraction network; The signal feature detection network includes a second input module, a random permutation module, a second two-dimensional convolutional module, a second activation module, and a second residual module; the input of the signal feature detection network is the input end of the second input module; the output of the signal feature detection network is the output end of the second residual module; in the signal feature detection network, the second input module, the random permutation module, the second two-dimensional convolutional module, the second activation module, and the second residual module are connected in sequence; The signal feature fusion network includes: a third input module, a first convolutional module, a second convolutional module, a third convolutional module, a first pooling module, a fourth convolutional module, a first fully-connected module, and a second fully-connected module; The input end of the third input module of the signal feature fusion network is connected to the output end of the second residual module; the output end of the third input module of the signal feature fusion network is connected to the input end of the first convolutional module of the signal feature fusion network; the output end of the first convolutional module of the signal feature fusion network is connected to the input end of the second convolutional module of the signal feature fusion network; the output end of the second convolutional module of the signal feature fusion network is connected to the input end of the third convolutional module of the signal feature fusion network; the output end of the third convolutional module of the signal feature fusion network is connected to the input end of the first pooling module of the signal feature fusion network; the output end of the first pooling module of the signal feature fusion network is connected to the input end of the fourth convolutional module of the signal feature fusion network; the output end of the fourth convolutional module of the signal feature fusion network is connected to the input end of the first fully-connected module of the signal feature fusion network; the output end of the first fully-connected module of the signal feature fusion network is connected to the input end of the second fully-connected module of the signal feature fusion network. The output end of the second fully-connected module is used to output the detection signal of the input signal; The clustering analysis can adopt density-based clustering, graph clustering, spectral clustering, etc.

[0026] The activation module is used to implement an activation function; the activation function can be a sigmoid function; The residual module can be implemented using a Resnet network; The normalization module can be implemented using the Quantile Normalization function in phthon.

[0027] The random permutation module is implemented using the shuffle function in python.

[0028] The ninth activation module is implemented using the tanh function; The quantization module has the following calculation formula: , where X is the input of the quantization module.

[0029] Using the communication data sets of each communication type to train a preset signal demodulation detection model to obtain a signal demodulation detection model corresponding to each communication type includes: For the communication data set of one communication type, initialize the training iteration count value; during training, use the location information, received signal, and environmental electromagnetic signal of the communication data set as training data; use the standard signal corresponding to the training data as label information; Use the training data in the communication data set as input data and input it into a signal demodulation detection model corresponding to one communication type; Use the signal demodulation detection model to process the input data to obtain a detection signal; Perform a difference calculation on the obtained detection signal and the label information corresponding to the input data to obtain a difference value; Determine whether the difference value satisfies the convergence condition to obtain a first judgment result; When the first judgment result is no, determine whether the training iteration count value is equal to the training count threshold to obtain a second judgment result; When the second judgment result is no, determine that the model training state does not meet the termination training condition; When the second judgment result is yes, determine that the model training state meets the termination training condition; When the first judgment result is yes, determine that the model training state meets the termination training condition; When the model training state does not meet the termination training condition, use a parameter update model to update the parameters of the signal demodulation detection model, increase the training iteration count value by 1, and trigger the execution of using the training data in the communication data set as input data and inputting it into the signal demodulation detection model; When the model training state meets the termination training condition, complete the training process of the signal demodulation detection model to obtain a trained signal demodulation detection model.

[0030] Use the communication data sets of each communication type to train a preset signal demodulation detection model to obtain a signal demodulation detection model corresponding to each communication type.

[0031] The difference value satisfying the convergence condition means that the difference value is less than a preset convergence threshold, such as 0.5; the difference value not satisfying the convergence condition means that the difference value is not less than the preset convergence threshold.

[0032] The above-mentioned difference calculation and processing can be implemented by using a loss function.

[0033] The loss function can be a cross-entropy loss function.

[0034] The parameter update model is as follows: , , In the formula, is the difference value calculated for the i-th training data in the communication dataset, is the parameter update value, is the parameter of the signal demodulation detection model, is the initial parameter learning rate, is the momentum angle parameter, , denotes taking the partial derivative with respect to the variable to find the partial derivative.

[0035] The above-mentioned use of the data classification model to classify the position information of the communication receiver and the collected environmental electromagnetic signals to obtain the communication type of the communication receiver includes: Represent the position information of the communication receiver and the collected environmental electromagnetic signals as node vectors; the elements of the node vectors are the position information of the communication nodes and the environmental electromagnetic signals; Use the data classification model to classify the node vectors to obtain the communication type of the communication receiver.

[0036] The above-mentioned use of the signal demodulation detection model corresponding to the communication type of the communication receiver to perform demodulation detection processing on the received communication signal, the position information of the communication receiver, and the environmental electromagnetic signals to obtain a detection signal includes: Obtain the trained signal demodulation detection model corresponding to the communication type of the communication receiver; Use the signal demodulation detection model to perform demodulation detection processing on the received communication signal, the position information of the communication receiver, and the environmental electromagnetic signals to obtain a detection signal.

[0037] The extreme difference is the difference between the maximum value and the minimum value; For the communication node data information corresponding to all node vectors of each type, construct the communication datasets corresponding to the corresponding communication types respectively, so as to obtain the communication datasets of all communication types; In the second aspect of the embodiments of the present application, an intelligent receiving device for communication signals is disclosed. The device includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory and executes the intelligent receiving method of the communication signal.

[0038] In a third aspect of the embodiments of the present application, a computer-readable storage medium is disclosed. The computer-readable storage medium stores computer instructions, which are used to execute the intelligent receiving method of the communication signal when called by a computer.

[0039] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed. The information data processing terminal is used to implement the intelligent receiving method of the communication signal.

[0040] The above are only the embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. An intelligent receiving method for communication signals, characterized in that, Including: S1, constructing a total communication data set of a communication area; The total communication data set includes communication node data information; The communication node data information includes the location information, standard signal, received signal, and environmental electromagnetic signal of the communication node; the communication node is a node that receives communication signals within the communication area; The standard signals in all communication node data information are the same; S2, performing clustering analysis on the total communication data set to obtain a data classification model and a communication data set for each communication type; S3, using the communication data set for each communication type to train a preset signal demodulation detection model to obtain a signal demodulation detection model corresponding to each communication type; S4, using the data classification model to classify the location information of the communication receiver and the collected environmental electromagnetic signal to obtain the communication type of the communication receiver; S5, using the signal demodulation detection model corresponding to the communication type of the communication receiver to perform demodulation detection on the communication signal received by the communication receiver, the location information of the communication receiver, and the environmental electromagnetic signal to obtain a detection signal.

2. The intelligent receiving method of a communication signal according to claim 1, wherein The performing clustering analysis on the total communication data set to obtain a data classification model and a communication data set for each communication type includes: Representing the location information and environmental electromagnetic signal of the communication node in each communication node data information in the total communication data set as a node vector; the elements of the node vector are the location information and environmental electromagnetic signal of the communication node; Performing clustering analysis on all node vectors to obtain the type information of the node vectors and the node vectors included in each type; Using the communication node data information corresponding to all node vectors of the same type to construct a communication data set for the corresponding communication type; Performing central point calculation and boundary value calculation on all node vectors of the same type to obtain the intermediate point value and boundary value of the corresponding communication type; Using the intermediate point values and boundary values of all communication types to construct a data classification model.

3. The intelligent receiving method of a communication signal according to claim 2, characterized in that, The expression for the central point calculation is: Among them, is the j-th element of the i-th node vector of the same type, N is the number of node vectors included in the type, and are the preset first weighting factor and second weighting factor respectively, is the j-th element of the center point of the communication type corresponding to the said type; The expression for the boundary value calculation is: ， wherein, is the extreme difference value of the j-th element of all node vectors of the same type, , and are the mean value, variance value and median value of the j-th element of all node vectors of the same type respectively, is the boundary value of the j-th element of the node vector of the communication type corresponding to the said type.

4. The intelligent receiving method of a communication signal according to claim 3, wherein, The discriminant expression of the data classification model is: ， Among them, is the j-th element of the node vector to be classified, M is the total number of elements included in the node vector, is the discriminant expression corresponding to the j-th element of the node vector; When each element of the node vector to be classified satisfies the corresponding discriminant expression, it is determined that the node vector to be classified belongs to the communication type corresponding to the intermediate point value and the boundary value.

5. The intelligent receiving method of a communication signal according to claim 4, wherein The signal demodulation detection model includes: a signal feature extraction network, a signal feature detection network, and a signal feature fusion network; The signal feature extraction network includes a first input module, a first two-dimensional convolution module, a first activation module, a first residual module, and a first normalization module; the input end of the first input module is the input end of the signal feature extraction network for receiving input data; in the signal feature extraction network, the first input module, the first two-dimensional convolution module, the first activation module, the first residual module, and the first normalization module are connected in sequence; the output end of the first normalization module is the output end of the signal feature extraction network and is connected to the input end of the second input module; The signal feature detection network includes a second input module, a random permutation module, a second two-dimensional convolution module, a second activation module, and a second residual module; the input end of the signal feature detection network is the input end of the second input module; the output end of the signal feature detection network is the output end of the second residual module, which is connected to the input end of the third input module; in the signal feature detection network, the second input module, the random permutation module, the second two-dimensional convolution module, the second activation module, and the second residual module are connected in sequence; The signal feature fusion network includes: a third input module, a first convolution module, a second convolution module, a third convolution module, a first pooling module, a fourth convolution module, a first fully connected module, and a second fully connected module; The input end of the third input module of the signal feature fusion network is connected to the output end of the second residual module; the output end of the third input module of the signal feature fusion network is connected to the input end of the first convolution module of the signal feature fusion network; the output end of the first convolution module of the signal feature fusion network is connected to the input end of the second convolution module of the signal feature fusion network; the output end of the second convolution module of the signal feature fusion network is connected to the input end of the third convolution module of the signal feature fusion network; the output end of the third convolution module of the signal feature fusion network is connected to the input end of the first pooling module of the signal feature fusion network; the output end of the first pooling module of the signal feature fusion network is connected to the input end of the fourth convolution module of the signal feature fusion network; the output end of the fourth convolution module of the signal feature fusion network is connected to the input end of the first fully connected module of the signal feature fusion network; the output end of the first fully connected module of the signal feature fusion network is connected to the input end of the second fully connected module of the signal feature fusion network; the output end of the second fully connected module is used to output the detection signal of the input signal.

6. The intelligent receiving method of a communication signal according to claim 5, wherein, Using the communication data set of each communication type to perform training processing on a preset signal demodulation detection model to obtain a signal demodulation detection model corresponding to each communication type includes: Initializing the training iteration number value for the communication data set of a communication type; during the training process, using the position information, received signal, and environmental electromagnetic signal of the communication data set corresponding to the communication type as training data; using the standard signal corresponding to the training data as label information; Using the training data in the communication data set as input data and inputting it into a signal demodulation detection model corresponding to a communication type; Using the signal demodulation detection model to process the input data to obtain a detection signal; Performing a difference calculation process on the obtained detection signal and the label information corresponding to the input data to obtain a difference value; Judging whether the difference value satisfies the convergence condition to obtain a first judgment result; When the first judgment result is no, judging whether the training iteration number value is equal to the training number threshold to obtain a second judgment result; When the second judgment result is negative, determine that the model training status does not meet the termination training condition; When the second judgment result is positive, determine that the model training status meets the termination training condition; When the first judgment result is positive, determine that the model training status meets the termination training condition; When the model training status does not meet the termination training condition, use the parameter update model to update the parameters of the signal demodulation detection model, increase the training iteration number value by 1, and trigger the execution of using the training data in the communication dataset as input data and inputting it into the signal demodulation detection model; When the model training status meets the termination training condition, complete the training process of the signal demodulation detection model to obtain a trained signal demodulation detection model; Use the communication datasets of each communication type to perform training processing on a preset signal demodulation detection model to obtain a signal demodulation detection model corresponding to each communication type.

7. The intelligent receiving method of a communication signal according to claim 6, characterized in that, The parameter update model is: ， ； Wherein, is the difference value calculated for the i-th training data in the communication dataset, is the parameter update value, is the parameter of the signal demodulation detection model, is the initial parameter learning rate, is the momentum angle parameter, , denotes taking the partial derivative with respect to the variable for partial derivative.

8. An intelligent receiving device for communication signals, characterized in that, The device includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent receiving method of communication signals according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which are used to execute the intelligent receiving method of communication signals according to any one of claims 1 to 7 when called by a computer.

10. An information data processing terminal, characterized in that, The information data processing terminal is used to implement the intelligent receiving method of communication signals according to any one of claims 1 to 7.

Images