Method and device for determining signal detection network

Abstract

The present disclosure relates to a method and apparatus for determining a signal detection network. The method includes: determining sample communication parameters for communication between a sample transmitter and a sample receiver via a sample intelligent reflector surface (IRS) (S101); and training an initial neural network based on a training sample set composed of the sample communication parameters to obtain a signal detection network, wherein the input of the initial neural network is the sample communication parameters, and the output of the initial neural network is an estimate of the transmitted signal of the sample transmitter (S102). According to the present disclosure, the initial neural network can be trained based on the training sample set to obtain a signal detection network. Since the neural network is not a linear algorithm and is not limited to operating on linear relationships, it can be effectively used for signal detection even in complex communication environments with many nonlinear factors, and a high-precision estimate of the transmitted signal can be obtained.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a method for determining a signal detection network, an apparatus for determining a signal detection network, a communication apparatus, and a computer-readable storage medium. Background Art

[0002] When a base station communicates with a terminal, the receiving end needs to perform signal detection on the transmission signal of the transmitting end so as to perform subsequent operations according to the estimated transmission signal.

[0003] Currently, the main method used for signal detection is linear algorithm, such as Minimum Mean Square Error Estimate (MMSE). Based on this method, the decoding matrix can be determined based on the channel matrix from the transmitter to the receiver. The transmitted signal of the transmitter is then estimated based on the decoding matrix and the received signal of the receiver.

[0004] However, with the development of communication technology, the channel environment has become increasingly complex during the communication process, and the nonlinear factors in the channel have also increased. The accuracy of signal detection through the current linear algorithm will be greatly affected, seriously affecting the accuracy of signal detection. Summary of the Invention

[0005] In view of this, embodiments of the present disclosure provide a method for determining a signal detection network, an apparatus for determining a signal detection network, a communication apparatus, and a computer-readable storage medium to solve technical problems in related technologies.

[0006] According to a first aspect of an embodiment of the present disclosure, a method for determining a signal detection network is provided, including:

[0007] Determine sample communication parameters for communication between a sample transmitter and a sample receiver via a sample intelligent reflecting surface (IRS); train an initial neural network based on a training sample set consisting of the sample communication parameters to obtain a signal detection network, wherein the input of the initial neural network is the sample communication parameters, and the output of the initial neural network is an estimated value of the transmitted signal of the sample transmitter.

[0008] In one embodiment, the sample communication parameters include at least one of the following:

[0009] A first channel matrix from the sample transmitter to the sample IRS; a phase matrix of the sample IRS;

[0010] a second channel matrix from the sample IRS to the sample receiving end; a third channel matrix from the sample transmitting end to the sample receiving end; and a sample receiving signal at the sample receiving end.

[0011] In one embodiment, the initial neural network includes multiple cascaded update units, and the inputs of the update units include unit common inputs and unit-related inputs; the method further includes: determining the relationship between the unit-related inputs and the update values of the unit-related inputs according to the gradient descent method; determining the unit common input according to the parameters used to characterize the update value in the relationship, and determining the output of the update unit according to the update value; wherein the output of the update unit serves as the unit-related input of the next update unit in the cascade.

[0012] In one embodiment, the update unit includes two unit common inputs; the first unit common input of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix and the third channel matrix; the second unit common input of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix, the third channel matrix and the sample received signal.

[0013] In one embodiment, the update unit includes three fully connected layers, and the three fully connected layers include an input layer, a hidden layer, and an output layer.

[0014] In one embodiment, the update unit further includes a short-circuit direct connection structure, wherein the starting point of the short-circuit direct connection structure is the unit-related input and the end point is the hidden layer.

[0015] In one embodiment, the network parameters of the fully connected layer include unit-related weights, and at least part of the unit-related weights in the update unit are related to the ranking of the update unit in the multiple cascaded update units; wherein, the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit.

[0016] In one embodiment, among the update units ranked higher than a preset order, the unit-related weight is a preset value;

[0017] In the update units whose ranking is lower than or equal to the preset order, the unit-related weight is less than the preset value, and the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit.

[0018] According to a second aspect of an embodiment of the present disclosure, a signal detection method is proposed, comprising: in response to receiving a receive signal from an IRS, wherein the receive signal is a signal after a transmit signal emitted by a transmitter is converted by the IRS, determining the transmit signal by a signal detection network according to the above-mentioned determination method of the signal detection network.

[0019] According to a third aspect of an embodiment of the present disclosure, a device for determining a signal detection network is provided, including:

[0020] A parameter determination module is configured to determine sample communication parameters for communication between a sample transmitting end and a sample receiving end via a sample intelligent reflecting surface (IRS); a network training module is configured to train an initial neural network based on a training sample set consisting of the sample communication parameters to obtain a signal detection network, wherein the input of the initial neural network is the sample communication parameters, and the output of the initial neural network is an estimated value of the transmitted signal of the sample transmitting end.

[0021] In one embodiment, the sample communication parameters include at least one of the following: a first channel matrix from the sample transmitting end to the sample IRS; a phase matrix of the sample IRS; a second channel matrix from the sample IRS to the sample receiving end; a third channel matrix from the sample transmitting end to the sample receiving end; and a sample received signal at the sample receiving end.

[0022] In one embodiment, the initial neural network includes multiple cascaded update units, wherein the inputs of the update units include unit-common inputs and unit-dependent inputs. The apparatus further includes: a relationship determination module configured to determine the relationship between the unit-dependent inputs and the updated values of the unit-dependent inputs based on a gradient descent method; an input-output determination module configured to determine the unit-common input based on a parameter in the relationship that characterizes the updated value, and to determine the output of the update unit based on the updated value; wherein the output of the update unit serves as the unit-dependent input of the next update unit in the cascade.

[0023] In one embodiment, the update unit includes two unit common inputs; the first unit common input of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix and the third channel matrix; the second unit common input of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix, the third channel matrix and the sample received signal.

[0024] In one embodiment, the three fully connected layers include an input layer, a hidden layer, and an output layer.

[0025] In one embodiment, the update unit further includes a short-circuit direct connection structure, wherein the starting point of the short-circuit direct connection structure is the unit-related input and the end point is the hidden layer.

[0026] In one embodiment, the network parameters of the fully connected layer include unit-related weights, and at least part of the unit-related weights in the update unit are related to the ranking of the update unit in the multiple cascaded update units; wherein, the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit.

[0027] In one embodiment, in the update units ranked higher than the preset order, the unit-related weight is a preset value; in the update units ranked lower than or equal to the preset order, the unit-related weight is less than the preset value, and the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit.

[0028] According to a fourth aspect of an embodiment of the present disclosure, a signal detection device is proposed, comprising: a signal estimation module, configured to respond to receiving a receive signal from an IRS, wherein the receive signal is a signal after the transmit signal emitted by the transmitter is converted by the IRS, and determine the transmit signal according to a signal detection network determined by a determination device of the above-mentioned signal detection network.

[0029] According to a fifth aspect of an embodiment of the present disclosure, a communication device is proposed, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the above-mentioned method for determining a signal detection network.

[0030] According to a sixth aspect of an embodiment of the present disclosure, a communication device is proposed, comprising: a processor; and a memory for storing a computer program; wherein, when the computer program is executed by the processor, the above-mentioned signal detection method is implemented.

[0031] According to a seventh aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided for storing a computer program, which implements the steps in the above-mentioned method for determining a signal detection network when executed by a processor.

[0032] According to an eighth aspect of an embodiment of the present disclosure, a computer-readable storage medium is proposed for storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned signal detection method are implemented.

[0033] According to the embodiments of the present disclosure, an initial neural network can be trained based on a training sample set to obtain a signal detection network. Since the neural network is not a linear algorithm, it is not limited to operating on linear relationships. Even in a complex communication environment with many nonlinear factors, it can be effectively used for signal detection and obtain high-precision estimation results for the transmitted signal.

[0034] In addition, since the training sample set is constructed based on the sample communication parameters of the sample transmitter and the sample receiver communicating through the sample IRS, the signal detection network trained based on the training samples is more suitable for the scenario where the receiver and the transmitter communicate through the IRS, and can accurately perform signal detection for this scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0036] Figure 1 It is a schematic flowchart of a method for determining a signal detection network according to an embodiment of the present disclosure.

[0037] Figure 2 It is a schematic flow chart showing an application of the signal detection network according to an embodiment of the present disclosure.

[0038] Figure 3 is a schematic flowchart of another method for determining a signal detection network according to an embodiment of the present disclosure.

[0039] Figure 4A 1 is a schematic diagram of a local structure of an initial neural network according to an embodiment of the present disclosure.

[0040] Figure 4B 1 is a schematic diagram of a local structure of another initial neural network according to an embodiment of the present disclosure.

[0041] Figure 5A It is a schematic diagram of a partial structure of an update unit according to an embodiment of the present disclosure.

[0042] Figure 5B It is a partial structural diagram of another updating unit according to an embodiment of the present disclosure.

[0043] Figure 5C 2 is a partial structural diagram of another updating unit according to an embodiment of the present disclosure.

[0044] Figure 6 It is a schematic block diagram of a determination device for a signal detection network according to an embodiment of the present disclosure.

[0045] Figure 7 It is a schematic block diagram of another signal detection network determination device according to an embodiment of the present disclosure.

[0046] Figure 8 This is a schematic block diagram of an apparatus for determining a signal detection network according to an embodiment of the present disclosure.

[0047] Figure 9 It is a schematic block diagram of another apparatus for determining a signal detection network according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0048] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present disclosure.

[0049] Figure 1 This is a schematic flow chart illustrating a method for determining a signal detection network according to an embodiment of the present disclosure. The determination method illustrated in this embodiment can be used to determine a signal detection network, which can be used by a receiving end to perform signal detection. For example, after a transmitting end sends a transmit signal, the receiving end can receive a corresponding receive signal, and the receiving end can estimate the transmit signal based on the signal detection network.

[0050] In one embodiment, the transmitting end and the receiving end may be communication devices such as a terminal, a base station, a satellite, an unmanned aerial vehicle, a core network, etc. The following embodiments mainly illustrate the present disclosure in the case where the transmitting end is a base station and the receiving end is a terminal.

[0051] In one embodiment, the terminal includes but is not limited to mobile phones, tablet computers, wearable devices, sensors, Internet of Things devices and other communication devices. The terminal can communicate with a base station as a user equipment, and the base station includes but is not limited to a 4G base station, a 5G base station, and a 6G base station.

[0052] like Figure 1 As shown, the method for determining the signal detection network may include the following steps:

[0053] In step S101, sample communication parameters for communication between a sample transmitting end and a sample receiving end via a sample intelligent reflecting surface (IRS) are determined;

[0054] In step S102, an initial neural network is trained based on a training sample set consisting of the sample communication parameters to obtain a signal detection network, wherein the input of the initial neural network is the sample communication parameters, and the output of the initial neural network is an estimated value of the transmitted signal of the sample transmitting end.

[0055] In one embodiment, the transmitter and receiver can communicate directly or through an intelligent reflecting surface (IRS). The method for determining a signal detection network described in the embodiments of the present disclosure can be applied in a scenario where the transmitter and receiver communicate through an IRS.

[0056] Among them, the smart reflective surface is a planar array composed of a large number of reconfigurable passive components. For the incident signal incident on the smart reflective surface, each passive component can independently produce a certain amount of phase shift on the incident signal, so that the reflected signal reflected by the smart reflective surface changes the propagation characteristics relative to the incident signal, such as changing the phase, direction, etc.

[0057] In one embodiment, in order to train and obtain a signal detection network, an initial neural network and a training sample set may be constructed, and the initial neural network may be trained based on the training sample set to obtain the signal detection network.

[0058] Among them, the deep learning algorithm used in the training process can be selected as needed, for example, the Adam optimization algorithm and the end-to-end learning method can be selected.

[0059] In one embodiment, a large number of sample transmitters, sample receivers, and sample IRSs can be pre-determined. The sample transmitters can then communicate with the sample receivers via the sample IRSs. Specifically, the transmitted signals from the sample transmitters can be transmitted to the sample receivers via the sample IRSs. In this case, sample communication parameters for communication between the sample transmitters and the sample receivers via the sample IRSs can be determined, and a training sample set can be constructed based on these sample communication parameters.

[0060] In one embodiment, the sample communication parameters include at least one of the following:

[0061] A first channel matrix H1 from the sample transmitting end to the sample IRS;

[0062] The phase matrix Φ of the sample IRS;

[0063] A second channel matrix H2 from the sample IRS to the sample receiving end;

[0064] A third channel matrix H3 from the sample transmitting end to the sample receiving end;

[0065] The sample receiving signal y of the sample receiving end.

[0066] These sample communication parameters are all known quantities for the sample receiving end. For example, the sample received signal y is the signal received by the sample receiving end from the sample transmitting end. The first channel matrix H1 and the second channel matrix H2 can be determined based on the channel state information (Channel State Information, CSI) of the channel used by the sample transmitting end to transmit signals to the sample receiving end through the sample IRS. The third channel matrix H3 can be determined based on the CSI of the channel used by the sample transmitting end to directly transmit signals to the sample receiving end. The phase matrix Φ of the sample IRS can be determined before or during the communication between the transmitting end and the receiving end, and can be specifically determined based on the state of the passive components in the sample IRS.

[0067] According to the embodiments of the present disclosure, an initial neural network can be trained based on a training sample set to obtain a signal detection network. Since the neural network is not a linear algorithm, it is not limited to operating on linear relationships. Even in a complex communication environment with many nonlinear factors, it can be effectively used for signal detection and obtain high-precision estimation results for the transmitted signal.

[0068] In addition, since the training sample set is constructed based on the sample communication parameters of the sample transmitter and the sample receiver communicating through the sample IRS, the signal detection network trained based on the training samples is more suitable for the scenario where the receiver and the transmitter communicate through the IRS, and can accurately perform signal detection for this scenario.

[0069] In one embodiment, before training, the data in the training sample set can also be split into three sets. The first set is used as a sample set for training, the second set is used as a test set for testing the training results, and the third set is used as a verification set for verifying the training results. For example, the ratio of samples in the first set, the second set, and the third set can be 96:2:2.

[0070] Figure 2 FIG. 1 is a schematic flow chart showing an application of the signal detection network according to an embodiment of the present disclosure. Figure 2 As shown, in step S201, in response to the receiving end receiving a receiving signal from the IRS, the receiving signal is a signal after the transmitting signal sent by the transmitting end is converted by the IRS, and the transmitting signal is determined according to the signal detection network.

[0071] In one embodiment, after the signal detection network is determined, in a subsequent scenario where the receiving end and the transmitting end actually communicate through the IRS, signal detection can be performed through the signal detection network to determine the transmission signal sent by the transmitting end.

[0072] For example, each time the IRS adjusts its passive components, it can inform the receiver of the overall IRS phase matrix, allowing the receiver to determine the IRS phase matrix. The receiver can also determine the channel matrix from the transmitter to the IRS and the channel matrix from the IRS to the receiver based on the channel state information of the channel used by the transmitter to transmit signals to the receiver via the IRS. It can also determine the channel matrix from the sample transmitter to the sample receiver based on the channel state information of the channel used by the transmitter to transmit signals directly to the receiver. The receiver can then determine the input quantity based on the received signal, the above-mentioned phase matrix, and the three channel matrices, and input it into the signal detection network determined in the above embodiment to obtain an estimate of the signal transmitted by the transmitter.

[0073] Figure 3 FIG. 1 is a schematic flow chart of another method for determining a signal detection network according to an embodiment of the present disclosure. Figure 3 As shown, in some embodiments, the initial neural network includes a plurality of cascaded update units, and the input of the update unit includes a unit common input and a unit related input;

[0074] The method further comprises:

[0075] In step S301, a relationship between the unit-related input and an updated value of the unit-related input is determined according to a gradient descent method;

[0076] In step S302, the unit common input is determined according to the parameter used to characterize the update value in the relationship, and the output of the update unit is determined according to the update value;

[0077] The output of the update unit serves as the unit-related input of the next update unit in the cascade.

[0078] In one embodiment, multiple cascaded update units can be configured to form an initial neural network. The inputs of the update units include unit-common inputs and unit-specific inputs. The unit-common inputs remain constant as inputs to each update unit, while the unit-specific inputs vary based on the update unit.

[0079] In one embodiment, the output of the update unit may be an updated value of the unit-dependent input of the update unit based on the gradient descent method. For example, for the i-th update unit among the n+1 update units, the unit-dependent input is x i , the output is x i +1, n≥0, 0≤i≤n.

[0080] The relationship between the received signal x received by the receiver and the transmitted signal y sent by the transmitter is:

[0081] y=Hx+n;

[0082] Here n is Gaussian white noise, which is a random variable, and H is the channel matrix.

[0083] In the case where the transmitter and receiver communicate through the IRS, for example, the sample transmitter communicates with the sample receiver through the sample IRS, then the channel matrix H in the above formula can be determined based on the first channel matrix H1 from the sample transmitter to the sample IRS, the phase matrix Φ of the sample IRS, the second channel matrix H2 from the sample IRS to the sample receiver, and the third channel matrix H3 from the sample transmitter to the sample receiver:

[0084] H=H2ΦH1+H3;

[0085] Then y=(H2ΦH1+H3)x+n;

[0086] In practical applications, the receiving end cannot directly determine the transmitted signal x, but needs to estimate it through signal detection. The embodiment of the present disclosure is mainly to obtain So that x and The gap between them should be as small as possible.

[0087] In order to get closer to x According to the gradient descent method, To update, in this embodiment, the input For example, for the i-th update unit, Update to get Relative to It is closer to the actual transmitted signal x sent by the transmitter.

[0088] Based on the gradient descent method, and The relationship between them is:

[0089]

[0090] in, η i is the i-th update unit pair The update step size, It is a value that is preset as needed.

[0091] Expanding formula 1 yields and The relationship between them is:

[0092]

[0093] Based on formula 2, we can see that the i-th update unit pair Update to get Need to be based on (H2ΦH1+H3) T y and (H2ΦH1+H3) T (H2ΦH1+H3) are calculated, so these three quantities can be used as the input of the i-th update unit, where (H2ΦH1+H3) T y and (H2ΦH1+H3) T (H2ΦH1+H3) does not change with i and is the same for each update unit, so it can be used as a common input for the unit. It will change with i and will be different for each update unit, so it can be used as a unit-dependent input.

[0094] Figure 4A 1 is a schematic diagram of a local structure of an initial neural network according to an embodiment of the present disclosure. Figure 4B 1 is a schematic diagram of a local structure of another initial neural network according to an embodiment of the present disclosure.

[0095] like Figure 4A As shown, for the i-th update unit U i , the input is The output is You can directly As the next update unit, that is, the i+1th update unit U i+1 Input And so on, until we get

[0096] like Figure 4B As shown, you can also Figure 4A Based on the structure shown, the i-th update unit U i Input With output Weighted summation (the weight used by each update unit in the weighting can be pre-set as needed), and the weighted summation result is used as the i+1th update unit U i+1 Input Although Figure 4B The structure shown is relative to Figure 4A The structure shown is relatively complex, but more factors of the previous unit can be introduced into the input of the next update unit, which helps to avoid the update amplitude being too large each time and seriously deviating from the expected value.

[0097] In one embodiment, the update unit comprises two unit common inputs;

[0098] The first unit common input of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix and the third channel matrix, such as (H2ΦH1+H3) in the above formula 2. T (H2ΦH1+H3);

[0099] The second common input of the two common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix, the third channel matrix and the sample received signal, such as (H2ΦH1+H3) in the above formula 2. T y.

[0100] According to the embodiments of the present disclosure, each update unit in the initial neural network only requires 3 inputs. The small number of inputs reduces the number of connections in the network, which is beneficial to reducing the complexity of the network, making the network suitable for complex channel environments and capable of outputting results faster.

[0101] Figure 5A FIG2 is a partial structural diagram of an update unit according to an embodiment of the present disclosure. In some embodiments, the update unit includes three fully connected layers, each of which includes an input layer, a hidden layer, and an output layer.

[0102] In one embodiment, the update unit may be designed to include three fully connected layers, which may specifically include an input layer, a hidden layer, and an output layer.

[0103] like Figure 5A As shown, it mainly shows the i-th update unit U i The input layer and hidden layer in , where the weight corresponding to the input layer is w i1 , the corresponding bias is b i1 , the corresponding activation function is ρ; the weight corresponding to the hidden layer is w i2 , the corresponding bias is b i2 , the corresponding activation function is ψ.

[0104] The input of the input layer is mainly determined by the transmitted signal. Concat refers to the concatenation method, which can concatenate the strings, arrays, vectors, etc. (H2ΦH1+H3) T (H2ΦH1+H3) and The result of multiplication, and (H2ΦH1+H3) T If you input the three y in series and use Concat, you can get the concatenation result of the three.

[0105] For example, if the number of antennas at the transmitting end is M (known at the receiving end), the transmitted signal can be an M*1 vector. Accordingly, It is an M*1 vector, (H2ΦH1+H3) T (H2ΦH1+H3) and The result of multiplication is also an M*1 vector, (H2ΦH1+H3) T y is also an M*1 vector, so the result of concatenating the three is a 3M*1 vector, so the input layer can be set to 3M*1 inputs.

[0106] The input passes through the input layer and w i1 After multiplication, add b i1 The sum is added, and then after passing through the activation function ρ, it is output to the hidden layer, where the activation function ρ can be a sigmoid function.

[0107] The number of inputs in the hidden layer can be set as needed, which is generally greater than or equal to the number of inputs in the input layer, for example, 4M*1. i2 After multiplication, add b i2 The sum is added, and then output to the output after passing through the activation function ψ, where the activation function ψ can be a tanh function.

[0108] The output number of the output layer is M*1, which can form an M*1 vector input to the next update unit.

[0109] It should be noted that the activation function is not limited to the examples given in the above embodiments, and can be selected as needed. For example, the relu function can also be selected as the activation function.

[0110] Figure 5B FIG is a partial structural diagram of another updating unit according to an embodiment of the present disclosure. Figure 5B As shown, in some embodiments, the update unit further includes a short-circuit direct connection structure, wherein the starting point of the short-circuit direct connection structure is the unit-related input and the end point is the hidden layer.

[0111] In one embodiment, it is difficult to fully exploit the nonlinear relationship in a complex channel environment during training by relying solely on a fully connected network. Figure 5B As shown, in Figure 5A On the basis of the update unit shown in the figure, a short-circuit direct connection (short cut, which can also be translated as direct connection or shortcut) structure is added to the fully connected layer. The starting point of the short-circuit direct connection structure is the relevant input of the unit and the end point is the hidden layer. That is, Add it to the output of the input layer (either directly or by weighted summation), and use the result of the addition as the input of the hidden layer.

[0112] Based on this, it is convenient to fully explore the nonlinear relationship in the complex channel environment during the training process, and it can alleviate the gradient divergence effect caused by the cascade of multiple update units, which is conducive to ensuring the rationality of the training results.

[0113] In addition, based on the above embodiments, it can be seen that and In the relationship, it consists of three terms, two of which include Therefore, relative to other inputs, right The impact of is greater, and by adding short-circuit direct connections in the fully connected layer, (i.e. ) is not only used as the initial input of the fully connected layer, but also as the input of the hidden layer in the fully connected layer, ensuring Update units can have a greater impact, with and The relationship between the two is consistent, which is also conducive to ensuring the rationality of the training results.

[0114] In one embodiment, the initial neural network formed by the cascade connection of update units in the above embodiment is trained based on a training sample set to obtain a signal detection network.

[0115] The deep learning algorithm used in the training process can be selected as needed, for example, the Adam optimization algorithm and the end-to-end learning method can be selected; the loss function used in the training process can also be set as needed, for example, it can be set to That is, from i=1 to i=n, Perform weighted summation with the weight value being lgi.

[0116] In some embodiments, the network parameters of the fully connected layer include unit-related weights, and at least part of the unit-related weights in the update unit are related to the ranking of the update unit in the multiple cascaded update units; wherein, the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit, and the later the ranking of the update unit in the multiple cascaded update units, the smaller the unit-related weight in the update unit.

[0117] In one embodiment, unit-related weights, that is, weights related to the update unit, may be introduced into the input layer of the update unit.

[0118] Figure 5C FIG. 1 is a partial structural diagram of another updating unit according to an embodiment of the present disclosure. Figure 5C As shown, the i-th update unit U i The unit-related weight is β i, for at least some update units, U i The higher the ranking among the n cascaded update units, that is, the smaller i is, the higher the β i The bigger it is.

[0119] It should be noted that the unit-related weight is β i The position in the fully connected layer can be set as needed, and can generally be set in the input layer and / or hidden layer. For example, if it is set in the input layer, it can be as follows Figure 5C The settings shown are in w i1 After that, the input passes through the input layer and w i1 The result of the multiplication is further multiplied, and if it is set in the hidden layer, it can be set in w i2 After that, the input passes through the hidden layer with w i2 The result of the multiplication is further multiplied.

[0120] Since the gradient descent algorithm is used to update When updating, the earlier updates have a greater impact on the overall update process than the later updates. When updating, relatively large unit-related weights can be set for update units with higher rankings, while relatively small unit-related weights can be set for update units with lower rankings, which helps reduce the complexity of the training process.

[0121] It should be noted that the content of unit-related weights is not limited to Figure 5C As shown, the application Figure 5B Based on the embodiment shown, it can also be directly applied to Figure 5A Based on the shown embodiment.

[0122] In one embodiment, for update units ranked higher than a preset order, the unit-related weight is a preset value. For update units ranked lower than or equal to the preset order, the unit-related weight is less than the preset value. The higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight of the update unit, and the lower the ranking of the update unit in the multiple cascaded update units, the smaller the unit-related weight of the update unit.

[0123] In one embodiment, the unit correlation can be set to remain unchanged for some update units, and only change with the ranking for another part of the update units. For example, for update units ranked higher than a preset order, the unit correlation weight remains unchanged at the preset value, while for update units ranked lower than or equal to the preset order, the unit correlation weight can be set to decrease as the ranking becomes later.

[0124] Accordingly, on the basis of ensuring the importance of the updated units ranked higher, the changes in the weights related to some units can be reduced, which is conducive to reducing the complexity of the training process.

[0125] For example, the unit-related weight β i It can be a semi-exponential function of the update unit ranking i, and its form can be, for example, as shown below:

[0126]

[0127] That is, among the n update units, the unit-related weights in the first half of the update units may remain unchanged, while the unit-related weights in the second half of the update units may decrease as the ranking i of the update units becomes later.

[0128] The embodiments of the present disclosure further provide a signal detection method, which can be implemented by a receiving end during communication between a transmitting end and a receiving end.

[0129] In one embodiment, the transmitting end and the receiving end may be communication devices such as a terminal, a base station, a satellite, an unmanned aerial vehicle, a core network, etc. For example, in the communication process between a base station and a terminal, the receiving end may be either a base station or a terminal. For example, when the transmitting end is a base station, the receiving end is a terminal, and when the transmitting end is a terminal, the receiving end is a base station.

[0130] In one embodiment, the terminal includes but is not limited to mobile phones, tablet computers, wearable devices, sensors, Internet of Things devices and other communication devices. The terminal can communicate with a base station as a user equipment, and the base station includes but is not limited to a 4G base station, a 5G base station, and a 6G base station.

[0131] The signal detection method may include the following steps:

[0132] In response to receiving a receive signal from the IRS, the receive signal is a signal obtained by converting a transmit signal sent by a transmitter through the IRS, and the transmit signal is determined by a signal detection network determined according to the method described in any one of the above embodiments.

[0133] In one embodiment, after the signal detection network is determined based on the aforementioned embodiment, in a subsequent scenario where the receiving end and the transmitting end actually communicate through the IRS, signal detection can be performed through the signal detection network to determine the transmission signal sent by the transmitting end.

[0134] For example, each time the IRS adjusts its passive components, it can inform the receiving end of the overall phase matrix of the IRS, so that the receiving end can determine the phase matrix of the IRS. The receiving end can also determine the channel matrix from the transmitting end to the IRS and the channel matrix from the IRS to the receiving end based on the channel state information of the channel used by the transmitting end to transmit signals to the receiving end through the IRS, and determine the channel matrix from the sample transmitting end to the sample receiving end based on the channel state information of the channel used by the transmitting end to transmit signals directly to the receiving end. The receiving end can then determine the input quantity output (for example, with Figure 4A Figure 4B The three input quantities corresponding to the input quantities of the embodiment shown are input into the signal detection network determined in the above embodiment to obtain an estimated value of the signal transmitted by the transmitting end.

[0135] It should be noted that the operation of determining the signal detection network can be performed by the receiving end or by other devices. The embodiments of the present disclosure do not limit this. For example, if it is performed by other devices, the signal detection network can be sent to the receiving end after obtaining it.

[0136] Corresponding to the aforementioned embodiment of the method for determining a signal detection network, the present disclosure further provides an embodiment of an apparatus for determining a signal detection network.

[0137] Figure 6 This is a schematic block diagram of a device for determining a signal detection network according to an embodiment of the present disclosure. The device shown in this embodiment can be used to determine a signal detection network, which can be used by a receiving end to perform signal detection. For example, after a transmitting end sends a transmit signal, the receiving end can receive a corresponding receive signal, and the receiving end can estimate the transmit signal based on the signal detection network.

[0138] In one embodiment, the transmitting end and the receiving end may be communication devices such as a terminal, a base station, a satellite, an unmanned aerial vehicle, a core network, etc. The following embodiments mainly illustrate the present disclosure in the case where the transmitting end is a base station and the receiving end is a terminal.

[0139] In one embodiment, the terminal includes but is not limited to mobile phones, tablet computers, wearable devices, sensors, Internet of Things devices and other communication devices. The terminal can communicate with a base station as a user equipment, and the base station includes but is not limited to a 4G base station, a 5G base station, and a 6G base station.

[0140] like Figure 6As shown, the determination device of the signal detection network may include: a parameter determination module 601, configured to determine sample communication parameters for communication between a sample transmitting end and a sample receiving end through a sample intelligent reflecting surface IRS; a network training module 602, configured to train an initial neural network based on a training sample set composed of the sample communication parameters to obtain a signal detection network, wherein the input of the initial neural network is the sample communication parameters, and the output of the initial neural network is an estimated value of the transmitted signal of the sample transmitting end.

[0141] In some embodiments, the sample communication parameters include at least one of the following: a first channel matrix from the sample transmitter to the sample IRS; a phase matrix of the sample IRS; a second channel matrix from the sample IRS to the sample receiver; a third channel matrix from the sample transmitter to the sample receiver; and a sample received signal at the sample receiver.

[0142] Figure 7 FIG. 1 is a schematic block diagram of another signal detection network determination device according to an embodiment of the present disclosure. Figure 7 As shown, the initial neural network includes multiple cascaded update units, and the input of the update unit includes unit common input and unit related input.

[0143] The device also includes: a relationship determination module 701, configured to determine the relationship between the unit-related input and the updated value of the unit-related input according to the gradient descent method; an input-output determination module 702, configured to determine the unit common input according to the parameter used to characterize the updated value in the relationship, and determine the output of the update unit according to the updated value; wherein the output of the update unit serves as the unit-related input of the next update unit in the cascade.

[0144] In some embodiments, the update unit includes two unit common inputs; the first unit common input of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix and the third channel matrix; the second unit common input of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix, the third channel matrix and the sample received signal.

[0145] In some embodiments, the update unit includes three fully connected layers, and the three fully connected layers include an input layer, a hidden layer, and an output layer.

[0146] In some embodiments, the update unit further includes a short-circuit direct connection structure, wherein a starting point of the short-circuit direct connection structure is the unit-related input and an end point is the hidden layer.

[0147] In some embodiments, the network parameters of the fully connected layer include unit-related weights, and at least some of the unit-related weights in the update unit are related to the order of the update unit in the plurality of cascaded update units;

[0148] Among them, the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit, and the lower the ranking of the update unit in the multiple cascaded update units, the smaller the unit-related weight in the update unit.

[0149] In some embodiments, among update units ranked higher than a preset order, the unit-related weight is a preset value;

[0150] In the update units whose ranking is lower than or equal to the preset order, the unit-related weight is less than the preset value, and the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit, and the lower the ranking of the update unit in the multiple cascaded update units, the smaller the unit-related weight in the update unit.

[0151] An embodiment of the present disclosure further provides a signal detection device, which can be applied to a receiving end during communication between a transmitting end and a receiving end.

[0152] In one embodiment, the transmitting end and the receiving end may be communication devices such as a terminal, a base station, a satellite, an unmanned aerial vehicle, a core network, etc. For example, in the communication process between a base station and a terminal, the receiving end may be either a base station or a terminal. For example, when the transmitting end is a base station, the receiving end is a terminal, and when the transmitting end is a terminal, the receiving end is a base station.

[0153] In one embodiment, the terminal includes but is not limited to mobile phones, tablet computers, wearable devices, sensors, Internet of Things devices and other communication devices. The terminal can communicate with a base station as a user equipment, and the base station includes but is not limited to a 4G base station, a 5G base station, and a 6G base station.

[0154] The signal detection device may include:

[0155] The signal estimation module is configured to respond to receiving a receive signal from the IRS, where the receive signal is a signal after the transmit signal sent by the transmitter is converted by the IRS, and determine the transmit signal according to the signal detection network determined by the device described in any of the above embodiments.

[0156] Regarding the apparatus in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments of the relevant methods and will not be elaborated on here.

[0157] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art can understand and implement it without paying any creative work.

[0158] An embodiment of the present disclosure further provides a communication device, comprising: a processor; and a memory for storing a computer program. When the computer program is executed by the processor, the method for determining a signal detection network described in any one of the above embodiments is implemented.

[0159] An embodiment of the present disclosure further provides a communication device, comprising: a processor; and a memory for storing a computer program; wherein, when the computer program is executed by the processor, the signal detection method described in the above embodiment is implemented.

[0160] An embodiment of the present disclosure further provides a computer-readable storage medium for storing a computer program. When the computer program is executed by a processor, the steps in the method for determining a signal detection network as described in any of the above embodiments are implemented.

[0161] An embodiment of the present disclosure further provides a computer-readable storage medium for storing a computer program. When the computer program is executed by a processor, the steps in the signal detection method described in the above embodiment are implemented.

[0162] like Figure 8 As shown, Figure 8 FIG. 8 is a schematic block diagram of another apparatus 800 for determining a signal detection network according to an embodiment of the present disclosure. The apparatus 800 may be provided as a base station. Figure 8 The apparatus 800 includes a processing component 822, a wireless transmitting / receiving component 824, an antenna component 826, and a signal processing portion specific to the wireless interface. The processing component 822 may further include one or more processors. One of the processors in the processing component 822 may be configured to implement the method for determining a signal detection network as described in any of the above embodiments.

[0163] When the apparatus 800 serves as a receiving end, one of the processors in the processing component 822 may be configured to implement the step of performing signal detection based on the signal detection network as described in the above embodiment.

[0164] Figure 91 is a schematic block diagram of an apparatus 900 for determining a signal detection network according to an embodiment of the present disclosure. For example, apparatus 900 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0165] Reference Figure 9 , the device 900 may include one or more of the following components: a processing component 902 , a memory 904 , a power component 906 , a multimedia component 908 , an audio component 910 , an input / output (I / O) interface 912 , a sensor component 914 , and a communication component 916 .

[0166] The processing component 902 generally controls the overall operation of the device 900, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 902 may include one or more processors 920 to execute instructions to complete all or part of the steps of the above-mentioned method for determining the signal detection network. When the device 900 is acting as a receiving end, the processor 920 may also execute instructions to complete the steps of performing signal detection based on the signal detection network described in the embodiment.

[0167] In addition, the processing component 902 may include one or more modules to facilitate interaction between the processing component 902 and other components. For example, the processing component 902 may include a multimedia module to facilitate interaction between the multimedia component 908 and the processing component 902.

[0168] The memory 904 is configured to store various types of data to support the operations of the device 900. Examples of such data include instructions for any application or method operating on the device 900, contact data, phone book data, messages, pictures, videos, etc. The memory 904 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0169] The power supply component 906 provides power to the various components of the device 900. The power supply component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 900.

[0170] The multimedia component 908 includes a screen that provides an output interface between the device 900 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 908 includes a front camera and / or a rear camera. When the device 900 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.

[0171] The audio component 910 is configured to output and / or input audio signals. For example, the audio component 910 includes a microphone (MIC), which is configured to receive external audio signals when the device 900 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 904 or transmitted via the communication component 916. In some embodiments, the audio component 910 also includes a speaker for outputting audio signals.

[0172] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0173] The sensor assembly 914 includes one or more sensors for providing various aspects of the status assessment of the device 900. For example, the sensor assembly 914 can detect the open / closed state of the device 900, the relative positioning of components, such as the display and keypad of the device 900. The sensor assembly 914 can also detect changes in the position of the device 900 or a component of the device 900, the presence or absence of user contact with the device 900, the orientation or acceleration / deceleration of the device 900, and temperature changes of the device 900. The sensor assembly 914 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 914 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 914 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0174] The communication component 916 is configured to facilitate wired or wireless communication between the device 900 and other devices. The device 900 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G LTE, 5G NR or a combination thereof. In an exemplary embodiment, the communication component 916 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 916 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0175] In an exemplary embodiment, the apparatus 900 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-mentioned method for determining the signal detection network.

[0176] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is further provided, such as a memory 904 including instructions. The instructions can be executed by the processor 920 of the apparatus 900 to implement the above-mentioned method for determining the signal detection network. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0177] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the disclosure herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0178] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

[0179] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0180] The above is a detailed introduction to the methods and devices provided in the embodiments of the present disclosure. Specific examples are used herein to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is only used to help understand the methods and core ideas of the present disclosure. At the same time, for those skilled in the art, according to the ideas of the present disclosure, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present disclosure.

Claims

1. A method for determining a signal detection network, characterized in that: include: Determine sample communication parameters for the sample transmitter and the sample receiver to communicate via the sample intelligent reflective surface IRS; Training an initial neural network based on a training sample set consisting of the sample communication parameters to obtain a signal detection network, wherein the input of the initial neural network is the sample communication parameters, and the output of the initial neural network is an estimated value of a transmitted signal of the sample transmitting end; The sample communication parameters include at least one of the following: a first channel matrix from the sample transmitting end to the sample IRS; a phase matrix of the sample IRS; a second channel matrix from the sample IRS to the sample receiving end; A third channel matrix from the sample transmitting end to the sample receiving end; and a sample receiving signal from the sample receiving end; The initial neural network includes a plurality of cascaded update units, wherein the input of the update unit includes a unit common input and a unit related input; the method further includes: determining a relationship between the unit-related input and an updated value of the unit-related input according to a gradient descent method; determining the unit common input according to the parameter used to characterize the update value in the relationship, and determining the output of the update unit according to the update value; wherein the output of the update unit serves as the unit-related input of the next update unit in the cascade; The update unit includes three fully connected layers, each of which includes an input layer, a hidden layer, and an output layer; the update unit also includes a short-circuit direct connection structure, wherein the starting point of the short-circuit direct connection structure is the unit-related input and the end point is the hidden layer; the network parameters of the fully connected layer include unit-related weights, and at least part of the unit-related weights in the update unit are related to the ranking of the update unit in the multiple cascaded update units; wherein, the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit.

2. The method according to claim 1, characterized in that The update unit includes two unit common inputs; A first unit common input of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix and the third channel matrix; A second one of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix, the third channel matrix, and the sample reception signal.

3. The method according to claim 1, characterized in that In the update units ranked higher than the preset order, the unit-related weight is the preset value; In the update units whose ranking is lower than or equal to the preset order, the unit-related weight is less than the preset value, and the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit.

4. A signal detection method, characterized in that: include: Receive a receiving signal from an IRS, where the receiving signal is a signal obtained by converting a transmitting signal sent by a transmitting end through the IRS, and determine the transmitting signal by a signal detection network according to the method according to any one of claims 1 to 3.

5. A device for determining a signal detection network, characterized in that: include: a parameter determination module configured to determine sample communication parameters for the sample transmitting end and the sample receiving end to communicate via the sample intelligent reflecting surface IRS; a network training module configured to train an initial neural network based on a training sample set consisting of the sample communication parameters to obtain a signal detection network, wherein the input of the initial neural network is the sample communication parameters and the output of the initial neural network is an estimated value of a transmitted signal of the sample transmitting end; The sample communication parameters include at least one of the following: a first channel matrix from the sample transmitting end to the sample IRS; a phase matrix of the sample IRS; a second channel matrix from the sample IRS to the sample receiving end; A third channel matrix from the sample transmitting end to the sample receiving end; and a sample receiving signal from the sample receiving end; The initial neural network includes a plurality of cascaded update units, wherein the input of the update unit includes a unit common input and a unit related input; the apparatus further includes: a relationship determination module configured to determine a relationship between the unit-related input and an updated value of the unit-related input according to a gradient descent method; an input-output determination module configured to determine the unit common input according to a parameter used to characterize the update value in the relationship, and determine the output of the update unit according to the update value; wherein the output of the update unit serves as the unit-related input of the next update unit in the cascade; The update unit includes three fully connected layers, each of which includes an input layer, a hidden layer, and an output layer; the update unit also includes a short-circuit direct connection structure, wherein the starting point of the short-circuit direct connection structure is the unit-related input and the end point is the hidden layer; the network parameters of the fully connected layer include unit-related weights, and at least part of the unit-related weights in the update unit are related to the ranking of the update unit in the multiple cascaded update units; wherein, the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit.

6. The device according to claim 5, characterized in that The update unit includes two unit common inputs; A first unit common input of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix and the third channel matrix; A second one of the two unit common inputs is determined based on the first channel matrix, the phase matrix, the second channel matrix, the third channel matrix, and the sample reception signal.

7. The device according to claim 5, characterized in that In the update units ranked higher than the preset order, the unit-related weight is the preset value; In the update units whose ranking is lower than or equal to the preset order, the unit-related weight is less than the preset value, and the higher the ranking of the update unit in the multiple cascaded update units, the greater the unit-related weight in the update unit.

8. A signal detection device, characterized in that: include: The signal estimation module is configured to determine the transmission signal in response to receiving a reception signal from the IRS, wherein the reception signal is a signal after the transmission signal sent by the transmitting end is converted by the IRS, and the transmission signal is determined according to the signal detection network determined by the device according to any one of claims 5 to 7.

9. A communication device, characterized in that: include: processor; memory for storing computer programs; When the computer program is executed by a processor, the method for determining a signal detection network according to any one of claims 1 to 3 is implemented.

10. A communication device, characterized in that: include: processor; memory for storing computer programs; When the computer program is executed by a processor, the signal detection method according to claim 4 is implemented.

11. A computer-readable storage medium for storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for determining a signal detection network according to any one of claims 1 to 3 are implemented.

12. A computer-readable storage medium for storing a computer program, characterized in that: When the computer program is executed by a processor, the steps in the signal detection method according to claim 4 are implemented.

Images