Method and device for determining signal detection network

Abstract

The invention relates to a method and a device for determining a signal detection network. The method comprises the following steps: determining sample communication parameters of a sample transmitting end and a sample receiving end communicating through a sample intelligent reflecting surface (IRS) (S101); and training an initial neural network based on a training sample set formed by the sample communication parameters to obtain a signal detection network, the input of the initial neural network being the sample communication parameters, and the output of the initial neural network being an estimated value of a transmission signal of the sample transmitting end (S102). According to the method and the device, the initial neural network can be trained based on the training sample set to obtain the signal detection network, and the neural network is a nonlinear algorithm and is not limited to operation of a linear relation, so that the method and the device can be effectively used for signal detection even in a complex communication environment with more nonlinear factors; and a high-precision estimation result is obtained for a transmitted signal.

Description

[0001] Divisional Application Instructions

[0002] This application is a divisional application of Chinese Patent Application No. 202180000927.3, filed on April 16, 2021, entitled "Method and Apparatus for Determining Signal Detection Network". Technical Field

[0003] This disclosure relates to the field of communication technology, and more specifically, to a method for determining a signal detection network, an apparatus for determining a signal detection network, a communication device, and a computer-readable storage medium. Background Technology

[0004] When a base station communicates with a terminal, the receiving end needs to detect the transmitted signal from the transmitting end in order to perform subsequent operations based on the estimated transmitted signal.

[0005] Currently, the main methods used for signal detection are linear algorithms, such as Minimum Mean Square Error Estimate (MMSE). Based on this method, the decoding matrix can be determined according to the channel matrix from the transmitter to the receiver, and then the transmitted signal of the transmitter can be estimated according to the decoding matrix and the received signal at the receiver.

[0006] However, with the development of communication technology, the channel environment is becoming increasingly complex during communication, and nonlinear factors in the channel are also increasing. The accuracy of signal detection using current linear algorithms will be greatly affected, seriously impacting the accuracy of signal detection. Summary of the Invention

[0007] 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 device, and a computer-readable storage medium to solve the technical problems in the related art.

[0008] According to a first aspect of the present disclosure, a method for determining a signal detection network is provided, comprising:

[0009] The sample communication parameters for communication between the sample transmitter and the sample receiver via the intelligent reflective surface (IRS) are determined. An initial neural network is trained 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.

[0010] In one embodiment, 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 from the sample receiver.

[0011] In one embodiment, the initial neural network includes multiple cascaded update units, the inputs of which include unit common inputs and unit-related inputs; the method further includes: determining the relationship between the unit-related inputs and their update values ​​using gradient descent; determining the unit common inputs based on parameters characterizing the update values ​​in the relationship; and determining the output of the update unit based on the update values; wherein the output of the update unit serves as the unit-related input of the next cascaded update unit.

[0012] In one embodiment, the update unit includes two common unit inputs; the first common unit input is determined based on the first channel matrix, the phase matrix, the second channel matrix, and the third channel matrix; the second common unit input 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 a three-layer fully connected layer, which includes 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 ending point is the hidden layer.

[0015] In one embodiment, the network parameters of the fully connected layer include cell-related weights, and at least some of the cell-related weights in the update cells are related to the order of the update cells in the plurality of cascaded update cells; wherein, the earlier the update cell is ordered in the plurality of cascaded update cells, the greater the cell-related weight in the update cell.

[0016] In one embodiment, in update units ranked above a preset order, the unit-related weight is a preset value; in update units ranked below or equal to the preset order, the unit-related weight is less than the preset value, and the earlier the update unit is ranked among the multiple cascaded update units, the greater the unit-related weight in the update unit.

[0017] According to a second aspect of the present disclosure, a signal detection method is provided, comprising: in response to receiving a received signal from an IRS, wherein the received signal is a signal converted by the IRS from a transmitted signal emitted by a transmitter, determining a signal detection network to determine the transmitted signal according to the above-described method for determining a signal detection network.

[0018] According to a third aspect of the present disclosure, a device for determining a signal detection network is provided, comprising:

[0019] The parameter determination module is configured to determine the sample communication parameters for communication between the sample transmitter and the sample receiver through the sample intelligent reflective surface IRS; the network training module is 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 estimate of the transmitted signal of the sample transmitter.

[0020] In one embodiment, 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 from the sample receiver.

[0021] In one embodiment, the initial neural network includes multiple cascaded update units, the inputs of which include unit common inputs and unit-related inputs. The apparatus further includes: a relation determination module configured to determine a relationship between the unit-related inputs and their updated values ​​using gradient descent; and an input-output determination module configured to determine the unit common inputs based on parameters characterizing the updated values ​​in the relation, and to determine the outputs of the update units based on the updated values; wherein the output of the update unit serves as the unit-related input of the next cascaded update unit.

[0022] In one embodiment, the update unit includes two common unit inputs; the first common unit input is determined based on the first channel matrix, the phase matrix, the second channel matrix, and the third channel matrix; the second common unit input is determined based on the first channel matrix, the phase matrix, the second channel matrix, the third channel matrix, and the sample received signal.

[0023] In one embodiment, the three fully connected layers include an input layer, a hidden layer, and an output layer.

[0024] 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 ending point is the hidden layer.

[0025] In one embodiment, the network parameters of the fully connected layer include cell-related weights, and at least some of the cell-related weights in the update cells are related to the order of the update cells in the plurality of cascaded update cells; wherein, the earlier the update cell is ordered in the plurality of cascaded update cells, the greater the cell-related weight in the update cell.

[0026] In one embodiment, in update units ranked above a preset order, the unit-related weight is a preset value; in update units ranked below or equal to the preset order, the unit-related weight is less than the preset value, and the earlier the update unit is ranked among the multiple cascaded update units, the greater the unit-related weight in the update unit.

[0027] According to a fourth aspect of the present disclosure, a signal detection apparatus is provided, comprising: a signal estimation module configured to determine the transmitted signal according to a signal detection network determined by the signal detection network determination device described above, in response to receiving a received signal from an IRS, wherein the received signal is a signal converted by the IRS from a transmitted signal emitted by a transmitter.

[0028] According to a fifth aspect of the present disclosure, a communication device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the above-described method for determining a signal detection network.

[0029] According to a sixth aspect of the present disclosure, a communication device is provided, comprising: a processor; a memory for storing a computer program; wherein, when the computer program is executed by the processor, the above-described signal detection method is implemented.

[0030] According to a seventh aspect of the present disclosure, a computer-readable storage medium is provided for storing a computer program that, when executed by a processor, implements the steps in the method for determining the signal detection network described above.

[0031] According to an eighth aspect of the present disclosure, a computer-readable storage medium is provided for storing a computer program that, when executed by a processor, implements the steps in the above-described signal detection method.

[0032] According to embodiments of this 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 nonlinear algorithm, it is not limited to operating on linear relationships. Even in complex communication environments with many nonlinear factors, it can be effectively used for signal detection to obtain high-precision estimation results for transmitted signals.

[0033] In addition, since the training sample set is constructed based on the sample communication parameters of the sample transmitter and 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 transmitter communicate through the IRS, and can accurately detect signals for this scenario. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a schematic flowchart illustrating a method for determining a signal detection network according to an embodiment of the present disclosure.

[0036] Figure 2 This is a schematic flowchart illustrating an application of the signal detection network according to an embodiment of the present disclosure.

[0037] Figure 3 This is a schematic flowchart illustrating another method for determining a signal detection network according to embodiments of the present disclosure.

[0038] Figure 4A This is a schematic diagram of a partial structure of an initial neural network according to an embodiment of the present disclosure.

[0039] Figure 4B This is a schematic diagram of a partial structure of another initial neural network according to an embodiment of the present disclosure.

[0040] Figure 5A This is a partial structural schematic diagram of an update unit according to an embodiment of the present disclosure.

[0041] Figure 5B This is a partial structural schematic diagram of another update unit according to an embodiment of the present disclosure.

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

[0043] Figure 6 This is a schematic block diagram illustrating a determination device for a signal detection network according to an embodiment of the present disclosure.

[0044] Figure 7 This is a schematic block diagram of a determination device for another signal detection network according to embodiments of the present disclosure.

[0045] Figure 8 This is a schematic block diagram illustrating an apparatus for determining a signal detection network according to embodiments of the present disclosure.

[0046] Figure 9 This is a schematic block diagram illustrating another apparatus for determining a signal detection network according to embodiments of the present disclosure. Detailed Implementation

[0047] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this disclosure.

[0048] Figure 1 This is a schematic flowchart illustrating a method for determining a signal detection network according to an embodiment of the present disclosure. The determination method 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 transmitted signal, the receiving end can receive a corresponding received signal, and the receiving end can estimate the transmitted signal based on the signal detection network.

[0049] In one embodiment, the transmitting end and the receiving end can be communication equipment such as a terminal, a base station, a satellite, an unmanned aerial vehicle, or a core network. The following embodiments mainly illustrate this disclosure by way of example when the transmitting end is a base station and the receiving end is a terminal.

[0050] In one embodiment, the terminal includes, but is not limited to, communication devices such as mobile phones, tablets, wearable devices, sensors, and IoT devices. The terminal can communicate with a base station as a user equipment, and the base station includes, but is not limited to, 4G base stations, 5G base stations, and 6G base stations.

[0051] like Figure 1 As shown, the method for determining the signal detection network may include the following steps:

[0052] In step S101, the sample communication parameters for communication between the sample transmitter and the sample receiver through the sample intelligent reflective surface (IRS) are determined.

[0053] In step S102, an initial neural network is trained based on a training sample set composed of the sample communication parameters to obtain a signal detection network. 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.

[0054] In one embodiment, the transmitter and receiver can communicate directly or via a smart reflector (IRS). The method for determining the signal detection network described in the embodiments of this disclosure can be applied to scenarios where the transmitter and receiver communicate via an IRS.

[0055] The intelligent reflector is a planar array composed of a large number of reconfigurable passive components. For the incident signal incident on the intelligent reflector, each passive component can independently generate a certain phase shift on the incident signal, thereby changing the propagation characteristics of the reflected signal from the intelligent reflector relative to the incident signal, such as changing the phase and direction.

[0056] In one embodiment, in order to train a signal detection network, an initial neural network and a training sample set can be constructed, and the initial neural network can be trained based on the training sample set to obtain the signal detection network.

[0057] The deep learning algorithms used during training can be selected as needed, such as the Adam optimization algorithm and the end-to-end learning method.

[0058] In one embodiment, a large number of sample transmitters, sample receivers, and sample IRSs can be predetermined. Then, the sample transmitters communicate with the sample receivers via the sample IRSs, meaning that 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 sample receivers via the sample IRSs can be determined, and a training sample set can be constructed based on these sample communication parameters.

[0059] In one embodiment, the sample communication parameters include at least one of the following:

[0060] The first channel matrix H1 from the sample transmitter to the sample IRS;

[0061] The phase matrix Φ of the sample IRS;

[0062] The second channel matrix H2 from the sample IRS to the sample receiver;

[0063] The third channel matrix H3 from the sample transmitter to the sample receiver;

[0064] The sample receiving signal y at the sample receiving end.

[0065] These sample communication parameters are known quantities for the sample receiver. For example, the sample received signal y is the signal received by the sample receiver from the sample transmitter. The first channel matrix H1 and the second channel matrix H2 can be determined based on the channel state information (CSI) of the channel used by the sample transmitter to transmit signals to the sample receiver through the sample IRS. The third channel matrix H3 can be determined based on the CSI of the channel used by the sample transmitter to transmit signals directly to the sample receiver. The phase matrix Φ of the sample IRS can be determined before or during communication between the transmitter and receiver, specifically based on the state of the passive components in the sample IRS.

[0066] According to embodiments of this 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 nonlinear algorithm, it is not limited to operating on linear relationships. Even in complex communication environments with many nonlinear factors, it can be effectively used for signal detection to obtain high-precision estimation results for transmitted signals.

[0067] In addition, since the training sample set is constructed based on the sample communication parameters of the sample transmitter and 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 transmitter communicate through the IRS, and can accurately detect signals for this scenario.

[0068] In one embodiment, before training, the data in the training sample set can 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 validation set for validating the training results. For example, the ratio of samples in the first, second, and third sets can be 96:2:2.

[0069] Figure 2 This is a schematic flowchart illustrating an application of the signal detection network according to an embodiment of this disclosure. Figure 2 As shown, in step S201, in response to the receiving end receiving a received signal from the IRS, the received signal is the signal converted by the IRS from the transmitted signal emitted by the transmitting end, and the transmitted signal is determined according to the signal detection network.

[0070] In one embodiment, after the signal detection network is determined, signal detection can be performed through the signal detection network in subsequent scenarios where the receiver and transmitter communicate via IRS to determine the transmitted signal emitted by the transmitter.

[0071] For example, after each adjustment of a passive component within the IRS, the overall phase matrix of the IRS can be communicated to the receiver, allowing the receiver to determine the phase matrix of the IRS. 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 send a signal to the receiver via the IRS. Furthermore, it can 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 send a signal directly to the receiver. Then, the receiver can determine the input quantity based on the received signal, the aforementioned phase matrix, and the three channel matrices, and input it into the signal detection network defined in the above embodiment to obtain an estimate of the transmitted signal.

[0072] Figure 3 This is a schematic flowchart illustrating another method for determining a signal detection network according to embodiments of the present disclosure. Figure 3 As shown, in some embodiments, the initial neural network includes multiple cascaded update units, and the input of the update unit includes unit common input and unit related input;

[0073] The method further includes:

[0074] In step S301, the relationship between the cell-related input and the updated value of the cell-related input is determined according to the gradient descent method;

[0075] In step S302, the common input of the unit is determined according to the parameters used to characterize the updated value in the relation, and the output of the update unit is determined according to the updated value;

[0076] The output of the update unit serves as the unit-related input for the next update unit in the cascade.

[0077] In one embodiment, multiple cascaded update units can be configured to form the initial neural network. The inputs of the update units include common unit inputs and unit-specific inputs. The common unit inputs, which serve as the inputs for each update unit, remain constant; the unit-specific inputs vary depending on the update unit.

[0078] In one embodiment, the output of the update unit can be the updated value of the unit-related input based on gradient descent. For example, for the i-th update unit out of n+1 update units, the unit-related input is x. i The output is x i +1, n≥0, 0≤i≤n.

[0079] The relationship between the received signal x at the receiving end and the transmitted signal y at the transmitting end is as follows:

[0080] y = Hx + n;

[0081] Here, n is Gaussian white noise, which is a random variable, and H is the channel matrix.

[0082] When considering communication between the transmitter and receiver via an IRS, for example, communication between the sample transmitter and the sample receiver via a sample IRS, 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.

[0083] H = H2ΦH1 + H3;

[0084] Then y = (H2ΦH1 + H3)x + n;

[0085] In practical applications, the receiver cannot directly determine the transmitted signal x; instead, it needs to estimate it through signal detection. The embodiments disclosed herein are primarily for the purpose of obtaining Make x and The gap between them should be as small as possible.

[0086] In order to find a value closer to x Gradient descent method can be used to... In this embodiment, the input is updated via an update unit. To perform an update, for example, for the i-th update unit, it is possible to... Update to obtain Compared to It is closer to the actual transmitted signal x emitted by the transmitter.

[0087] Based on gradient descent and The relationship between them is:

[0088]

[0089] in, η i For the i-th update unit pair The step size for updating. Values ​​preset as needed.

[0090] Expanding Formula 1 yields and The relationship between them is:

[0091]

[0092] As can be seen from Formula 2, the i-th update unit pair Update to obtain Need to be based on

[0093] (H2ΦΗ1+H3) T y and (H2ΦH1+H3) T The three quantities (H2ΦH1+H3) are used for calculation, so these three quantities can be used as the input quantities 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, therefore it can be used as a common input for the units. It will change with i and will be different for each update unit, so it can be used as a unit-related input.

[0094] Figure 4A This is a schematic diagram of a partial structure of an initial neural network according to an embodiment of the present disclosure. Figure 4B This is a schematic diagram of a partial 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+1)th update unit U i+1 Input And so on, until the result is obtained.

[0096] like Figure 4B As shown, it can also be found in Figure 4A Based on the structure shown, the i-th update unit U i Input With output Weighted summation (the weights used in the weighting of each update unit can be preset as needed), and the weighted summation result is used as the (i+1)th 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 from the previous unit can be introduced into the input of the next update unit, which helps to avoid excessively large update increments that would deviate significantly from the expected value.

[0097] In one embodiment, the update unit includes two units with a common input;

[0098] The first common input of the two units 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 Formula 2 above. T (H2ΦH1+H3);

[0099] The second common input of the two units 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 Formula 2 above. T y.

[0100] According to embodiments of this disclosure, each update unit in the initial neural network requires only 3 inputs. The small number of inputs results in fewer connections in the network, which helps reduce network complexity and makes the network suitable for complex channel environments, while also enabling faster output of results.

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

[0102] In one embodiment, the update unit can 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, the i-th update unit U is mainly illustrated. i The input layer and hidden layers in the diagram, where the weights of the input layer are w. i1 The corresponding bias is b i1 The corresponding activation function is ρ; the weights of the hidden layer are w. i2 The corresponding bias is b i2 The corresponding activation function is ψ.

[0104] The input to the input layer is primarily determined by the transmitted signal. Concatenation (or concatenation method) refers to a method that can concatenate strings, arrays, vectors, etc., in the input.

[0105] (H2ΦH1+H3) T (H2ΦH1+H3) and The result of the multiplication, and (H2ΦH1+H3) T If you concatenate the three inputs (y, y, and y) using the concatenation method (Concat), you will get the concatenated result.

[0106] 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. Correspondingly, It's 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 concatenating the three results in a 3M*1 vector. Therefore, the input layer can be set to have 3M*1 inputs.

[0107] The input passes through w in the input layer i1 Multiply and then add b i1 The sums are then passed through the activation function ρ and output to the hidden layer. The activation function ρ can be the sigmoid function.

[0108] The number of inputs to the hidden layer can be set as needed, generally greater than or equal to the number of inputs to the input layer, for example, 4M * 1. The inputs in the hidden layer are processed by w... i2 Multiply and then add b i2 The sums are then passed through an activation function ψ before being output. The activation function ψ can be a tanh function.

[0109] The output layer has M*1 outputs, which can form an M*1 vector input to the next update unit.

[0110] It should be noted that the activation function is not limited to the examples given in the above embodiments. The specific activation function can be selected according to the needs. For example, the ReLU function can also be selected as the activation function.

[0111] Figure 5B This is a partial structural schematic diagram of another updating unit according to an embodiment of the present disclosure. For example... 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 ending point is the hidden layer.

[0112] In one embodiment, relying solely on a fully connected network makes it difficult to fully exploit the nonlinear relationships in complex channel environments during training. Therefore, it is possible to... Figure 5B As shown, in Figure 5A Based on the update unit shown, a short-cut structure is added to the fully connected layer. The starting point of the short-cut structure is the relevant input of the unit, and the ending point is the hidden layer. This allows the... The result is added to the output of the input layer (either directly or by weighted summation), and then used as the input to the hidden layer.

[0113] Therefore, it is convenient to fully explore the nonlinear relationships in complex channel environments during training, and it can alleviate the gradient divergence effect caused by multiple update units being cascaded, which helps to ensure the rationality of training results.

[0114] Furthermore, based on the above embodiments, it can be seen that in and The relationship consists of three items, two of which contain Therefore, relative to other inputs, right The impact is greater, and by adding a short-circuit direct connection in the fully connected layer, it makes... (i.e. It can be used not only as the initial input to a fully connected layer, but also as the input to hidden layers within the fully connected layer, ensuring... The updated unit can have a greater influence, and and The relationship is compatible, which also helps to ensure the rationality of the training results.

[0115] In one embodiment, a signal detection network can be obtained by training the initial neural network composed of cascaded update units in the above embodiment based on the training sample set.

[0116] The deep learning algorithm used during training can be selected as needed, such as the Adam optimization algorithm and an end-to-end learning approach; the loss function used during training can also be set as needed, for example, it can be set to... That is, from i=1 to i=n, ​​for Perform a weighted summation, with the weight value being lgi.

[0117] In some embodiments, the network parameters of the fully connected layer include cell-related weights, and at least some of the cell-related weights in the update cells are related to the order of the update cells in the plurality of cascaded update cells; wherein, the earlier the update cell is ordered in the plurality of cascaded update cells, the larger the cell-related weight in the update cell, and the later the update cell is ordered in the plurality of cascaded update cells, the smaller the cell-related weight in the update cell.

[0118] In one embodiment, unit-related weights, i.e. weights associated with the update unit, can be introduced into the input layer of the update unit.

[0119] Figure 5C This is a partial structural schematic diagram of another updating unit according to an embodiment of the present disclosure. For example... Figure 5C As shown, the i-th update unit U iThe unit-related weight is β i For at least some update units, U i In the n cascaded update units, the earlier the i is sorted, that is, the smaller i is, the better β is. i The larger it is.

[0120] It should be noted that the unit-related weight is β. i The position of the fully connected layer can be set as needed. Generally, it can be placed in the input layer and / or hidden layers. For example, if placed in the input layer, it could be like this: Figure 5C The setting shown is in w i1 Afterwards, the input passes through w in the input layer. i1 The results of the multiplication are then multiplied further, and if set in a hidden layer, they can be set in w. i2 Afterwards, the input passes through w in the hidden layer. i2 The results of multiplication are then multiplied again.

[0121] Because of the gradient descent algorithm update At the same time, earlier updates have a greater impact on the overall update process than later updates. Therefore, when updating through multiple update units... When updating, relatively large unit-related weights can be set for the update units that are ranked higher, while relatively small unit-related weights can be set for the update units that are ranked lower, which helps to reduce the complexity of the training process.

[0122] It should be noted that the content regarding the unit-related weights is not limited to, for example... Figure 5C As shown, it is applied in Figure 5B Based on the illustrated embodiment, it can also be directly applied to Figure 5A Based on the embodiment shown.

[0123] In one embodiment, in update units ranked above a preset order, the unit-related weight is a preset value. In update units ranked below or equal to the preset order, the unit-related weight is less than the preset value, and the earlier the update unit is ranked in the plurality of cascaded update units, the greater the unit-related weight in the update unit; the later the update unit is ranked in the plurality of cascaded update units, the smaller the unit-related weight in the update unit.

[0124] In one embodiment, the cell correlation can be configured to keep some update cells unchanged, while only other update cells change with the sorting. For example, for update cells sorted above a preset order, the cell correlation weight remains unchanged at a preset value, while for update cells sorted below or equal to the preset order, the cell correlation weight can be configured to decrease as the sorting progresses.

[0125] Therefore, while ensuring the importance of the update units that rank higher, we can reduce the changes to the weights of some units, which helps to reduce the complexity of the training process.

[0126] For example, the unit correlation weight β i It can be a semi-exponential function that updates the sorting of unit i, and its form can be as follows:

[0127]

[0128] That is, in n update units, the unit-related weights in the first half of the update units can remain unchanged, while the unit-related weights in the second half of the update units can decrease as the order of the update units i progresses later.

[0129] The embodiments of this disclosure also propose a signal detection method, which can be implemented by the receiving end during the communication process between the transmitting end and the receiving end.

[0130] In one embodiment, the transmitting end and the receiving end can be communication equipment such as a terminal, a base station, a satellite, an unmanned aerial vehicle, or a core network. For example, in the communication process between a base station and a terminal, the receiving end can be either a base station or a terminal. For instance, if the transmitting end is a base station, then the receiving end is a terminal; if the transmitting end is a terminal, then the receiving end is a base station.

[0131] In one embodiment, the terminal includes, but is not limited to, communication devices such as mobile phones, tablets, wearable devices, sensors, and IoT devices. The terminal can communicate with a base station as a user equipment, and the base station includes, but is not limited to, 4G base stations, 5G base stations, and 6G base stations.

[0132] The signal detection method may include the following steps:

[0133] In response to receiving a received signal from the IRS, wherein the received signal is the signal converted by the IRS from the transmitted signal emitted by the transmitter, the transmitted signal is determined by the signal detection network determined according to the method described in any of the above embodiments.

[0134] In one embodiment, after the signal detection network is determined based on the foregoing embodiments, signal detection can be performed through the signal detection network in subsequent scenarios where the receiver and transmitter communicate via IRS to determine the transmitted signal emitted by the transmitter.

[0135] For example, after each adjustment of a passive component within the IRS, the overall phase matrix of the IRS can be communicated to the receiver, allowing the receiver to determine the phase matrix of the IRS. 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. Furthermore, it can 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. Then, the receiver can determine the input quantity (e.g., based on the received signal, the aforementioned phase matrix, and the three channel matrices). Figure 4A Figure 4B The three input quantities corresponding to the three input quantities in the illustrated embodiment are input into the signal detection network determined in the above embodiment to obtain an estimate of the transmitted signal at the transmitting end.

[0136] 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 this disclosure do not limit this. For example, if it is performed by other devices, then the signal detection network can be sent to the receiving end after it is obtained.

[0137] Corresponding to the aforementioned embodiments of the method for determining a signal detection network, this disclosure also provides embodiments of a device for determining a signal detection network.

[0138] Figure 6 This is a schematic block diagram illustrating a signal detection network determination apparatus according to an embodiment of the present disclosure. The determination apparatus 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 transmitted signal, the receiving end can receive a corresponding received signal, and the receiving end can estimate the transmitted signal based on the signal detection network.

[0139] In one embodiment, the transmitting end and the receiving end can be communication equipment such as a terminal, a base station, a satellite, an unmanned aerial vehicle, or a core network. The following embodiments mainly illustrate this disclosure by way of example when the transmitting end is a base station and the receiving end is a terminal.

[0140] In one embodiment, the terminal includes, but is not limited to, communication devices such as mobile phones, tablets, wearable devices, sensors, and IoT devices. The terminal can communicate with a base station as a user equipment, and the base station includes, but is not limited to, 4G base stations, 5G base stations, and 6G base stations.

[0141] like Figure 6As shown, the signal detection network determination device may include: a parameter determination module 601, configured to determine sample communication parameters for communication between the sample transmitter and the sample receiver via the sample intelligent reflective surface IRS; and 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 estimate of the transmitted signal of the sample transmitter.

[0142] 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 from the sample receiver.

[0143] Figure 7 This is a schematic block diagram illustrating another signal detection network determination device according to embodiments of the present disclosure. Figure 7 As shown, the initial neural network includes multiple cascaded update units, and the input of each update unit includes common unit input and unit-related input.

[0144] The apparatus further 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; and an input-output determination module 702, configured to determine the unit common input according to the parameters used to characterize the updated value in the relationship, and to 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 cascaded update unit.

[0145] In some embodiments, the update unit includes two common unit inputs; the first common unit input is determined based on the first channel matrix, the phase matrix, the second channel matrix, and the third channel matrix; the second common unit input is determined based on the first channel matrix, the phase matrix, the second channel matrix, the third channel matrix, and the sample received signal.

[0146] In some embodiments, the update unit includes a three-layer fully connected layer, which includes an input layer, a hidden layer, and an output layer.

[0147] 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 ending point is the hidden layer.

[0148] In some embodiments, the network parameters of the fully connected layer include cell-related weights, and at least some of the cell-related weights in the update cells are related to the order of the update cells in the plurality of cascaded update cells;

[0149] The earlier the update unit is ranked among the multiple cascaded update units, the greater the unit-related weight of the update unit; conversely, the later the update unit is ranked among the multiple cascaded update units, the smaller the unit-related weight of the update unit.

[0150] In some embodiments, in update units that are ranked higher than a preset order, the unit-related weight is a preset value;

[0151] In update units whose sorting order is lower than or equal to a preset order, the unit-related weight is less than the preset value. Furthermore, the earlier the update unit is sorted among the multiple cascaded update units, the greater the unit-related weight in the update unit. The later the update unit is sorted among the multiple cascaded update units, the smaller the unit-related weight in the update unit.

[0152] Embodiments of this disclosure also propose a signal detection device that can be applied to the receiving end during communication between the transmitting end and the receiving end.

[0153] In one embodiment, the transmitting end and the receiving end can be communication equipment such as a terminal, a base station, a satellite, an unmanned aerial vehicle, or a core network. For example, in the communication process between a base station and a terminal, the receiving end can be either a base station or a terminal. For instance, if the transmitting end is a base station, then the receiving end is a terminal; if the transmitting end is a terminal, then the receiving end is a base station.

[0154] In one embodiment, the terminal includes, but is not limited to, communication devices such as mobile phones, tablets, wearable devices, sensors, and IoT devices. The terminal can communicate with a base station as a user equipment, and the base station includes, but is not limited to, 4G base stations, 5G base stations, and 6G base stations.

[0155] The signal detection device may include:

[0156] The signal estimation module is configured to determine the transmitted signal according to the signal detection network determined by the device described in any of the above embodiments in response to receiving a received signal from the IRS, the received signal being a transmitted signal from the transmitter converted by the IRS.

[0157] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments of the relevant methods, and will not be elaborated upon here.

[0158] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0159] Embodiments of this disclosure also provide a communication device, comprising: a processor; a memory for storing a computer program; wherein, when the computer program is executed by the processor, it implements the method for determining a signal detection network as described in any of the above embodiments.

[0160] Embodiments of this disclosure also provide a communication device, including: a processor; a memory for storing a computer program; wherein, when the computer program is executed by the processor, it implements the signal detection method described in the above embodiments.

[0161] Embodiments of this disclosure also provide a computer-readable storage medium for storing a computer program that, when executed by a processor, implements the steps in the method for determining a signal detection network as described in any of the foregoing embodiments.

[0162] Embodiments of this disclosure also propose a computer-readable storage medium for storing a computer program that, when executed by a processor, implements the steps of the signal detection method as described in the above embodiments.

[0163] like Figure 8 As shown, Figure 8 This is a schematic block diagram illustrating another apparatus 800 for determining a signal detection network according to embodiments of the present disclosure. Apparatus 800 can be provided as a base station. (Refer to...) Figure 8 The device 800 includes a processing component 822, a wireless transmitting / receiving component 824, an antenna component 826, and a signal processing section 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 the signal detection network as described in any of the above embodiments.

[0164] When the device 800 is used as a receiving end, one of the processors in the processing component 822 can be configured to implement the signal detection steps based on the signal detection network described in the above embodiments.

[0165] Figure 9This is a schematic block diagram illustrating an apparatus 900 for determining a signal detection network according to embodiments of the present disclosure. For example, apparatus 900 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0166] Reference Figure 9 The device 900 may include one or more of the following components: a processing component 902, a memory 904, a power supply 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.

[0167] Processing component 902 typically controls the overall operation of device 900, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 902 may include one or more processors 920 to execute instructions to perform all or part of the steps of the method for determining the signal detection network described above. When device 900 is acting as a receiving end, processor 920 may also execute instructions to perform the steps of signal detection based on the signal detection network described in the embodiments.

[0168] Furthermore, 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.

[0169] Memory 904 is configured to store various types of data to support the operation of device 900. Examples of this data include instructions for any application or method operating on device 900, contact data, phonebook data, messages, pictures, videos, etc. 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 storage, flash memory, magnetic disk, or optical disk.

[0170] Power supply component 906 provides power to various components of device 900. Power supply component 906 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to device 900.

[0171] 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 may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 908 includes a front-facing camera and / or a rear-facing camera. When the device 900 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0172] Audio component 910 is configured to output and / or input audio signals. For example, audio component 910 includes a microphone (MIC) configured to receive external audio signals when device 900 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 904 or transmitted via communication component 916. In some embodiments, audio component 910 also includes a speaker for outputting audio signals.

[0173] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0174] Sensor assembly 914 includes one or more sensors for providing status assessments of various aspects of device 900. For example, sensor assembly 914 may detect the on / off state of device 900, the relative positioning of components such as the display and keypad of device 900, changes in position of device 900 or a component of device 900, the presence or absence of user contact with device 900, orientation or acceleration / deceleration of device 900, and temperature changes of device 900. Sensor assembly 914 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. 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, sensor assembly 914 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0175] Communication component 916 is configured to facilitate wired or wireless communication between device 900 and other devices. Device 900 can access wireless networks based on communication standards, such as WiFi, 2G or 3G, 4G LTE, 5G NR, or combinations thereof. In one exemplary embodiment, communication component 916 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 916 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0176] 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 method for determining the signal detection network described above.

[0177] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 904 including instructions, which can be executed by a processor 920 of the device 900 to complete the method for determining the signal detection network. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0178] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0179] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

[0180] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0181] The methods and apparatus provided in the embodiments of this disclosure have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this disclosure. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this disclosure. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this disclosure. Therefore, the content of this specification should not be construed as a limitation of this disclosure.

Claims

1. A method for determining a signal detection network, characterized in that, include: Determine the sample communication parameters for communication between the sample transmitter and the sample receiver via the sample intelligent reflective surface IRS; The initial neural network is trained using a training sample set composed of the sample communication parameters to obtain a signal detection network. 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.

2. The method according to claim 1, characterized in that, The sample communication parameters include at least one of the following: The first channel matrix from the sample transmitter to the sample IRS; The phase matrix of the sample IRS; The second channel matrix from the sample IRS to the sample receiver; The third channel matrix from the sample transmitter to the sample receiver; and The sample receiving signal of the sample receiving end.

3. The method according to claim 2, characterized in that, The initial neural network includes multiple cascaded update units, and the input of each update unit includes common unit input and unit-related input. The method further includes: The relationship between the cell-related input and its updated value is determined using the gradient descent method. The common input of the unit is determined based on the parameters used to characterize the updated value in the relationship, and the output of the update unit is determined based on the updated value. The output of the update unit serves as the unit-related input for the next update unit in the cascade.

4. The method according to claim 3, characterized in that, The update unit includes two units with a common input; The first common input of the two units is determined based on the first channel matrix, the phase matrix, the second channel matrix, and the third channel matrix; The second common input of the two units is determined based on the first channel matrix, the phase matrix, the second channel matrix, the third channel matrix, and the sample received signal.

5. The method according to claim 3, characterized in that, The update unit includes three fully connected layers, which consist of an input layer, a hidden layer, and an output layer.

6. The method according to claim 5, characterized in that, The update unit further includes a short-circuit direct connection structure, wherein the starting point of the short-circuit direct connection structure is the relevant input of the unit, and the ending point is the hidden layer.

7. The method according to claim 5, characterized in that, The network parameters of the fully connected layer include cell-related weights, and at least some of the cell-related weights in the update cells are related to the order of the update cells in the plurality of cascaded update cells; The earlier the update unit is ranked among the multiple cascaded update units, the greater the unit-related weight in the update unit.

8. The method according to claim 7, characterized in that, In update units that are ranked higher than a preset order, the unit-related weights are preset values; In update units whose sorting order is lower than or equal to a preset order, the unit-related weight is less than the preset value, and the earlier the update unit is sorted among the multiple cascaded update units, the greater the unit-related weight in the update unit.

9. A signal detection method, characterized in that, include: The method of any one of claims 1 to 8 determines the signal detection network to determine the transmitted signal, wherein the received signal is a signal converted by the IRS from the transmitted signal emitted by the transmitter.

10. A device for determining a signal detection network, characterized in that, include: The parameter determination module is configured to determine the sample communication parameters for communication between the sample transmitter and the sample receiver through the sample intelligent reflective surface IRS. The 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 estimate of the transmitted signal of the sample transmitter.

11. The apparatus according to claim 10, characterized in that, The sample communication parameters include at least one of the following: The first channel matrix from the sample transmitter to the sample IRS; The phase matrix of the sample IRS; The second channel matrix from the sample IRS to the sample receiver; The third channel matrix from the sample transmitter to the sample receiver; and The sample receiving signal of the sample receiving end.

12. The apparatus according to claim 11, characterized in that, The initial neural network includes multiple cascaded update units, and the input of each update unit includes common unit input and unit-related input. The device further includes: The relationship determination module is configured to determine the relationship between the cell-related input and the updated value of the cell-related input according to the gradient descent method; An input-output determination module is configured to determine the common input of the unit based on the parameters used to characterize the update value in the relation, and to determine the output of the update unit based on the update value. The output of the update unit serves as the unit-related input for the next update unit in the cascade.

13. The apparatus according to claim 12, characterized in that, The update unit includes two units with a common input; The first common input of the two units is determined based on the first channel matrix, the phase matrix, the second channel matrix, and the third channel matrix; The second common input of the two units is determined based on the first channel matrix, the phase matrix, the second channel matrix, the third channel matrix, and the sample received signal.

14. The apparatus according to claim 12, characterized in that, The three fully connected layers include an input layer, a hidden layer, and an output layer.

15. The apparatus according to claim 14, characterized in that, The update unit further includes a short-circuit direct connection structure, wherein the starting point of the short-circuit direct connection structure is the relevant input of the unit, and the ending point is the hidden layer.

16. The apparatus according to claim 14, characterized in that, The network parameters of the fully connected layer include cell-related weights, and at least some of the cell-related weights in the update cells are related to the order of the update cells in the plurality of cascaded update cells; The earlier the update unit is ranked among the multiple cascaded update units, the greater the unit-related weight in the update unit.

17. The apparatus according to claim 16, characterized in that, In update units that are ranked higher than a preset order, the unit-related weights are preset values; In update units whose sorting order is lower than or equal to a preset order, the unit-related weight is less than the preset value, and the earlier the update unit is sorted among the multiple cascaded update units, the greater the unit-related weight in the update unit.

18. A signal detection device, characterized in that, include: A signal estimation module is configured to determine the transmitted signal in response to receiving a received signal from an IRS, the received signal being a transmitted signal from a transmitter converted by the IRS, and the transmitted signal being determined by a signal detection network defined by the apparatus according to any one of claims 10 to 17.

19. A communication device, characterized in that, include: processor; Memory used to store computer programs; When the computer program is executed by a processor, it implements the method for determining the signal detection network as described in any one of claims 1 to 8.

20. A communication device, characterized in that, include: processor; Memory used to store computer programs; When the computer program is executed by the processor, it implements the signal detection method as described in claim 9.

21. A computer-readable storage medium for storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps in the method for determining a signal detection network as described in any one of claims 1 to 8.

22. A computer-readable storage medium for storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps in the signal detection method as described in claim 9.

Images