Synchronization method and device and storage medium

Abstract

The invention provides a synchronization method and device and a storage medium, and the method comprises the steps that receiving end equipment determines a power density spectrum based on a received signal and a local sequence; inputting the power density spectrum into an artificial intelligence (AI) model to obtain synchronization information output by the AI model; wherein the AI model is obtained based on training of a sample power density spectrum with a synchronization information label.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to a synchronization method, device and storage medium. Background Art

[0002] In the sixth generation of mobile communication technology (6-Generation, 6G), a huge number of terminals will access the network, which may have new synchronization requirements, including the need for more main synchronization sequences to support dense heterogeneous networks, the need to combat stronger multipath fading, the need to combat stronger Doppler effects, the need to combat stronger time offset / frequency offset problems, etc. Traditional synchronization schemes based on sequence correlation operations may not be applicable, and it is necessary to consider introducing synchronization schemes that can effectively adapt to harsh channel environments, effectively combat nonlinear distortion, and achieve low complexity. Summary of the invention

[0003] In view of the problems existing in the prior art, the present application provides a synchronization method, device and storage medium.

[0004] In a first aspect, the present application provides a synchronization method, applied to a receiving device, comprising:

[0005] determining a power density spectrum based on the received signal and the local sequence;

[0006] The power density spectrum is input into an artificial intelligence AI model to obtain synchronization information output by the AI ​​model; wherein the AI ​​model is trained based on a sample power density spectrum with synchronization information labels.

[0007] In some embodiments, determining a power density spectrum based on a received signal and a local sequence includes:

[0008] multiplying the first signal and the first sequence to obtain a product sequence;

[0009] Determine a power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence;

[0010] The first signal is a received signal, or a signal obtained by transforming the received signal;

[0011] The first sequence is a local sequence, or a sequence obtained by transforming the local sequence.

[0012] In some embodiments, performing transformation processing on the received signal includes:

[0013] The received signal is subjected to at least one of time shift, frequency domain transformation and conjugate transformation.

[0014] In some embodiments, the local sequence is transformed, including:

[0015] Perform at least one of frequency shift and frequency domain transformation on the local sequence.

[0016] In some embodiments, determining the power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence includes:

[0017] The product sequence or the time-frequency domain transformation sequence of the product sequence is summed over some parameters to obtain a summation sequence;

[0018] Based on the summed sequence, a power density spectrum is determined.

[0019] In some embodiments, the partial parameters are summed, including one or more of the following:

[0020] Sum time domain parameters or frequency domain parameters;

[0021] summing the time-shifted parameters;

[0022] The frequency shift parameters are summed.

[0023] In some embodiments, summing the time-shift parameters comprises:

[0024] Determine a first target sequence from the sequence to be time-shifted and parameter summed according to a first threshold;

[0025] The first target sequence is summed over the time-shift parameter.

[0026] In some embodiments, summing the frequency shift parameters comprises:

[0027] Determine a second target sequence from the sequence to be subjected to frequency shift parameter summation according to a second threshold;

[0028] The second target sequence is summed over the frequency shift parameter.

[0029] In some embodiments, the synchronization information includes one or more of a sequence identifier, a time synchronization parameter, and a frequency synchronization parameter.

[0030] In some embodiments, the local sequence is a ZC sequence or an m-sequence.

[0031] In some embodiments, the method further comprises:

[0032] receiving model input instruction information;

[0033] Based on the model input indication information, determine the power density spectrum type of the input AI model.

[0034] In a second aspect, the present application also provides a synchronization method, applied to a transmitting end device, comprising:

[0035] The model input indication information is sent to the receiving device, where the model input indication information is used to indicate the power density spectrum type of the input artificial intelligence AI model, and the AI ​​model is used to output synchronization information based on the input power density spectrum.

[0036] In a third aspect, the present application also provides a receiving end device, including a memory, a transceiver, and a processor;

[0037] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0038] determining a power density spectrum based on the received signal and the local sequence;

[0039] The power density spectrum is input into an artificial intelligence AI model to obtain synchronization information output by the AI ​​model; wherein the AI ​​model is trained based on a sample power density spectrum with synchronization information labels.

[0040] In some embodiments, determining a power density spectrum based on a received signal and a local sequence includes:

[0041] multiplying the first signal and the first sequence to obtain a product sequence;

[0042] Determine a power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence;

[0043] The first signal is a received signal, or a signal obtained by transforming the received signal;

[0044] The first sequence is a local sequence, or a sequence obtained by transforming the local sequence.

[0045] In some embodiments, performing transformation processing on the received signal includes:

[0046] The received signal is subjected to at least one of time shift, frequency domain transformation and conjugate transformation.

[0047] In some embodiments, the local sequence is transformed, including:

[0048] Perform at least one of frequency shift and frequency domain transformation on the local sequence.

[0049] In some embodiments, determining the power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence includes:

[0050] The product sequence or the time-frequency domain transformation sequence of the product sequence is summed over some parameters to obtain a summation sequence;

[0051] Based on the summed sequence, a power density spectrum is determined.

[0052] In some embodiments, the partial parameters are summed, including one or more of the following:

[0053] Sum time domain parameters or frequency domain parameters;

[0054] summing the time-shifted parameters;

[0055] The frequency shift parameters are summed.

[0056] In some embodiments, summing the time-shift parameters comprises:

[0057] Determine a first target sequence from the sequence to be time-shifted and parameter summed according to a first threshold;

[0058] The first target sequence is summed over the time-shift parameter.

[0059] In some embodiments, summing the frequency shift parameters comprises:

[0060] Determine a second target sequence from the sequence to be subjected to frequency shift parameter summation according to a second threshold;

[0061] The second target sequence is summed over the frequency shift parameter.

[0062] In some embodiments, the synchronization information includes one or more of a sequence identifier, a time synchronization parameter, and a frequency synchronization parameter.

[0063] In some embodiments, the local sequence is a ZC sequence or an m-sequence.

[0064] In some embodiments, the operations further include:

[0065] receiving model input instruction information;

[0066] Based on the model input indication information, determine the power density spectrum type of the input AI model.

[0067] In a fourth aspect, the present application also provides a transmitting end device, including a memory, a transceiver, and a processor;

[0068] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0069] The model input indication information is sent to the receiving device, where the model input indication information is used to indicate the power density spectrum type of the input artificial intelligence AI model, and the AI ​​model is used to output synchronization information based on the input power density spectrum.

[0070] In a fifth aspect, the present application further provides a synchronization device, including:

[0071] A first determining unit, configured to determine a power density spectrum based on a received signal and a local sequence;

[0072] An acquisition unit is used to input the power density spectrum into an artificial intelligence AI model to obtain synchronization information output by the AI ​​model; wherein the AI ​​model is trained based on a sample power density spectrum with a synchronization information label.

[0073] In some embodiments, determining a power density spectrum based on a received signal and a local sequence includes:

[0074] multiplying the first signal and the first sequence to obtain a product sequence;

[0075] Determine a power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence;

[0076] The first signal is a received signal, or a signal obtained by transforming the received signal;

[0077] The first sequence is a local sequence, or a sequence obtained by transforming the local sequence.

[0078] In some embodiments, performing transformation processing on the received signal includes:

[0079] The received signal is subjected to at least one of time shift, frequency domain transformation and conjugate transformation.

[0080] In some embodiments, the local sequence is transformed, including:

[0081] Perform at least one of frequency shift and frequency domain transformation on the local sequence.

[0082] In some embodiments, determining the power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence includes:

[0083] The product sequence or the time-frequency domain transformation sequence of the product sequence is summed over some parameters to obtain a summation sequence;

[0084] Based on the summed sequence, a power density spectrum is determined.

[0085] In some embodiments, the partial parameters are summed, including one or more of the following:

[0086] Sum time domain parameters or frequency domain parameters;

[0087] summing the time-shifted parameters;

[0088] The frequency shift parameters are summed.

[0089] In some embodiments, summing the time-shift parameters comprises:

[0090] Determine a first target sequence from the sequence to be time-shifted and parameter summed according to a first threshold;

[0091] The first target sequence is summed over the time-shift parameter.

[0092] In some embodiments, summing the frequency shift parameters comprises:

[0093] Determine a second target sequence from the sequence to be subjected to frequency shift parameter summation according to a second threshold;

[0094] The second target sequence is summed over the frequency shift parameter.

[0095] In some embodiments, the synchronization information includes one or more of a sequence identifier, a time synchronization parameter, and a frequency synchronization parameter.

[0096] In some embodiments, the local sequence is a ZC sequence or an m-sequence.

[0097] In some embodiments, the apparatus further comprises:

[0098] A receiving unit, used for receiving model input indication information;

[0099] The second determination unit is used to determine the power density spectrum type of the input AI model based on the model input indication information.

[0100] In a sixth aspect, the present application further provides a synchronization device, including:

[0101] The sending unit is used to send model input indication information to the receiving device, where the model input indication information is used to indicate the power density spectrum type of the input artificial intelligence AI model, and the AI ​​model is used to output synchronization information based on the input power density spectrum.

[0102] In the seventh aspect, the present application also provides a non-transitory readable storage medium, which stores a computer program, and the computer program is used to enable a processor to execute the synchronization method described in the first aspect as described above, or execute the synchronization method described in the second aspect as described above.

[0103] In an eighth aspect, the present application further provides a communication device, in which a computer program is stored, and the computer program is used to enable the communication device to execute the synchronization method described in the first aspect as described above, or execute the synchronization method described in the second aspect as described above.

[0104] In a ninth aspect, the present application also provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, wherein the computer program is used to enable the processor to execute the synchronization method described in the first aspect as described above, or to execute the synchronization method described in the second aspect as described above.

[0105] In the tenth aspect, the present application also provides a chip product, in which a computer program is stored, and the computer program is used to enable the chip product to execute the synchronization method described in the first aspect as described above, or execute the synchronization method described in the second aspect as described above.

[0106] The synchronization method, apparatus, and storage medium provided in the present application are such that, after the receiving device receives the synchronization signal, it first determines the power density spectrum based on the received signal and the local sequence, and then inputs the power density spectrum into a pre-trained AI model to directly obtain the synchronization information, thereby being able to meet the synchronization requirements in complex 6G scenarios while reducing the complexity of implementing the synchronization solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0107] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the following is a brief introduction to the drawings required for use in the embodiments or the related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0108] Figure 1 One of the flowcharts of the synchronization method provided in the embodiment of the present application;

[0109] Figure 2 A second flowchart of the synchronization method provided in an embodiment of the present application;

[0110] Figure 3 An example diagram of a synchronization method provided in an embodiment of the present application;

[0111] Figure 4 An example diagram of the RESNet neural network structure provided in an embodiment of the present application;

[0112] Figure 5 A schematic diagram of the structure of a receiving device provided in an embodiment of the present application;

[0113] Figure 6 A schematic diagram of the structure of a transmitting end device provided in an embodiment of the present application;

[0114] Figure 7 One of the structural schematic diagrams of the synchronization device provided in the embodiment of the present application;

[0115] Figure 8 The second structural diagram of the synchronization device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0116] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0117] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0118] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0119] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0120] The synchronization schemes of the traditional Long Term Evolution (LTE) system and the New Radio (NR) system both use correlation operations at the receiving end to obtain synchronization information. For 6G scenarios, the synchronization schemes of LTE and NR either fail to meet the performance indicators of one-shot communication or are too complex to implement. Therefore, it is necessary to consider introducing a synchronization scheme that can effectively adapt to harsh channel environments, effectively combat nonlinear distortion, and achieve low complexity.

[0121] This application uses a receiving-end synchronization algorithm based on artificial intelligence (AI) to achieve performance that meets the one-shot indicator while reducing implementation complexity in complex 6G scenarios.

[0122] Figure 1 One of the flow charts of the synchronization method provided in the embodiment of the present application is applied to a receiving device, such as Figure 1 As shown, the method comprises the following steps:

[0123] Step 100: Determine a power density spectrum based on a received signal and a local sequence.

[0124] Step 101: input the power density spectrum into an artificial intelligence AI model to obtain synchronization information output by the AI ​​model; wherein the AI ​​model is trained based on a sample power density spectrum with a synchronization information label.

[0125] Specifically, the embodiment of the present application is based on the synchronization scheme of the AI ​​model (or AI engine, AI mechanism, AI algorithm, etc.). After the receiving device receives the synchronization signal, it first determines the power density spectrum based on the received signal and the local sequence, and then inputs the power density spectrum into the pre-trained AI model to directly obtain the synchronization information. Compared with the situation where the traditional synchronization scheme is enhanced to meet the 6G requirements, the synchronization scheme provided by the embodiment of the present application can implement many kinds of complex combinations with the AI ​​model, thereby significantly reducing the implementation complexity of the synchronization scheme.

[0126] In some embodiments, the local sequence is a ZC sequence or an m sequence. That is, the synchronization scheme provided in the embodiment of the present application can select a ZC sequence or an m sequence as a synchronization sequence. In practice, a ZC sequence or an m sequence of appropriate length can be designed according to dense heterogeneous network scenarios, multipath fading, Doppler effect, time offset / frequency offset strength, etc., to obtain the best overall performance.

[0127] In some embodiments, the transmitting device can select a ZC sequence (or m-sequence) based on the identity (ID) of the transmitting device and the length of the predetermined ZC sequence (or m-sequence). Then, the selected ZC sequence (or m-sequence) is sent out on the predetermined resources. After receiving the signal, the receiving device can use the AI ​​model to perform reasoning operations based on the received signal and the local sequence to obtain the output of the model, that is, the synchronization information, so as to complete the synchronization.

[0128] In some embodiments, the synchronization information includes one or more of a sequence identifier (ID), a time synchronization parameter, and a frequency synchronization parameter, wherein the time synchronization parameter refers to a parameter used for time synchronization, and the frequency synchronization parameter refers to a parameter used for frequency synchronization.

[0129] Before using the AI ​​model for synchronous reasoning, a large number of training samples are needed to train the model parameters. The data of each training sample is (PDP, synchronization information), where PDP refers to the power density profile (Power Density Profile), the specific type of the power density profile input to the AI ​​model, and the synchronization information includes the sequence ID, time synchronization parameters, and frequency synchronization parameters. Which one or more of them can be flexibly changed according to the needs of the AI ​​model. In some embodiments, a large amount of sample data can be obtained through a simulation program.

[0130] In the embodiments of the present application, the AI ​​model can use any AI model, such as a convolutional neural network (CNN) model, a residual network (ReSNet) model, a deep reinforcement learning (DRL) model, etc.

[0131] In some embodiments, the receiving device is a terminal or a network device (e.g., a base station); the transmitting device is a network device or a terminal. This actually includes synchronization mechanisms in four situations: network device sends - network device receives, network device sends - terminal receives, terminal sends - network device receives, and terminal sends - terminal receives.

[0132] The synchronization method provided in the embodiment of the present application is that after the receiving device receives the synchronization signal, the power density spectrum is first determined based on the received signal and the local sequence, and then the power density spectrum is input into a pre-trained AI model to directly obtain the synchronization information, thereby meeting the synchronization requirements in complex 6G scenarios while reducing the complexity of implementing the synchronization solution.

[0133] In some embodiments, determining a power density spectrum based on a received signal and a local sequence includes:

[0134] multiplying the first signal and the first sequence to obtain a product sequence;

[0135] Determine a power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence;

[0136] The first signal is a received signal, or a signal obtained by transforming the received signal;

[0137] The first sequence is a local sequence, or a sequence obtained by transforming the local sequence.

[0138] Specifically, the receiving device can transform and multiply the received signal and the local sequence, that is, transform the received signal and then multiply it with the local sequence, or transform the local sequence and then multiply it with the received signal, or transform both the received signal and the local sequence and then multiply them, to obtain a product sequence, which is used to determine the power density spectrum of the input AI model.

[0139] In some embodiments, the product sequence can be directly used as the input of the AI ​​model, or the product sequence can be used as the input of the AI ​​model after time-frequency domain transformation. Time-frequency domain transformation of the product sequence refers to converting the product sequence to the time domain or to the frequency domain.

[0140] For example, the product sequence is a time domain product sequence, and the product sequence can be directly used as the input of the AI ​​model, or the product sequence can be converted into the frequency domain and used as the input of the AI ​​model.

[0141] For example, the product sequence is a frequency domain product sequence, and the product sequence can be directly used as the input of the AI ​​model, or the product sequence can be converted into the time domain and used as the input of the AI ​​model.

[0142] In some embodiments, the product sequence or the time-frequency domain transformation sequence of the product sequence may be further processed before being used as input to the AI ​​model.

[0143] In some embodiments, the time-frequency domain transformation can be implemented by Fast Fourier Transform (FFT) or Inverse Fast Fourier Transform (IFFT).

[0144] In some embodiments, performing transformation processing on the received signal includes:

[0145] The received signal is subjected to at least one of time shift, frequency domain transformation and conjugate transformation.

[0146] For example, the received signal is first time-shifted and then transformed into the frequency domain, and then conjugate transformed. After the conjugate transformation, it is multiplied with the frequency domain transformation sequence of the local sequence to obtain a product sequence.

[0147] For example, time synchronization has been completed in advance, and the received signal does not need to be time-shifted. It is directly transformed into the frequency domain and then conjugate transformed. After the conjugate transformation, it is multiplied with the frequency domain transformation sequence of the local sequence to obtain a product sequence.

[0148] For example, the received signal is time-shifted and then directly multiplied with the transformed sequence of the local sequence to obtain a product sequence.

[0149] For example, the received signal is time-shifted and conjugated and then multiplied with the local sequence to obtain a product sequence.

[0150] In some embodiments, the local sequence is transformed, including:

[0151] Perform at least one of frequency shift and frequency domain transformation on the local sequence.

[0152] For example, the local sequence is first transformed into the frequency domain and then frequency shifted, and then multiplied with the conjugate of the frequency domain transformed sequence of the received signal to obtain a product sequence.

[0153] For example, frequency synchronization has been completed in advance, and the local sequence does not need frequency shifting, but is directly transformed into the frequency domain, and then multiplied with the conjugate of the frequency domain transformed sequence of the received signal to obtain a product sequence.

[0154] For example, the local sequence is directly multiplied with the transformed sequence of the received signal after frequency shifting to obtain a product sequence.

[0155] In some embodiments, determining the power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence includes:

[0156] The product sequence or the time-frequency domain transformation sequence of the product sequence is summed over some parameters to obtain a summation sequence;

[0157] Based on the summed sequence, a power density spectrum is determined.

[0158] Specifically, after obtaining the product sequence, the product sequence or the time-frequency domain transformation sequence of the product sequence can be further processed to obtain a summation sequence, and then the power density spectrum of the input AI model is determined based on the summation sequence.

[0159] In some embodiments, the resulting summed sequence may be used as input to an AI model.

[0160] In some embodiments, the partial parameters are summed, including one or more of the following:

[0161] Sum time domain parameters or frequency domain parameters;

[0162] summing the time-shifted parameters;

[0163] The frequency shift parameters are summed.

[0164] Specifically, summing the time domain parameters refers to performing a time domain summation operation on the product sequence or the time-frequency domain transformation sequence of the product sequence.

[0165] Summing the frequency domain parameters refers to performing a frequency domain summation operation on the product sequence or the time-frequency domain transformation sequence of the product sequence.

[0166] Summing the time shift parameters refers to performing a multipath summation operation on the product sequence or the time-frequency domain transformation sequence of the product sequence.

[0167] Summing the frequency shift parameters refers to performing a Doppler summation operation on the product sequence or the time-frequency domain transformation sequence of the product sequence.

[0168] For example, if the product sequence is a time-domain product sequence, a time-domain summation operation may be performed on the time-domain product sequence to obtain a time-domain summation sequence.

[0169] For example, if the product sequence is a frequency domain product sequence, the frequency domain product sequence may be subjected to a frequency domain summation operation to obtain a frequency domain summation sequence.

[0170] For example, a multipath summation operation may be performed on the product sequence to obtain a multipath summation sequence.

[0171] For example, a Doppler summation operation may be performed on the product sequence to obtain a Doppler summation sequence.

[0172] For example, a time-domain summation operation may be performed on the product sequence, and then a multipath summation operation may be performed to obtain a time-domain multipath summation sequence.

[0173] For example, a time-domain summation operation may be performed on the product sequence, and then a Doppler summation operation may be performed to obtain a time-domain Doppler summation sequence.

[0174] For example, a frequency domain summation operation may be performed on the product sequence, and then a multipath summation operation may be performed to obtain a frequency domain multipath summation sequence.

[0175] For example, a frequency domain summation operation may be performed on the product sequence, and then a Doppler summation operation may be performed to obtain a frequency domain Doppler summation sequence.

[0176] For example, a time-domain summation operation may be performed on the product sequence, followed by a multipath summation operation, and then a Doppler summation operation to obtain a time-domain multipath Doppler summation sequence.

[0177] For example, a time-domain summation operation may be performed on the product sequence, followed by a Doppler summation operation, and then a multipath summation operation to obtain a time-domain Doppler multipath summation sequence.

[0178] For example, a frequency domain summation operation may be performed on the product sequence, followed by a multipath summation operation, and then a Doppler summation operation to obtain a frequency domain multipath Doppler summation sequence.

[0179] For example, a frequency domain summation operation may be performed on the product sequence, followed by a Doppler summation operation, and then a multipath summation operation to obtain a frequency domain Doppler multipath summation sequence.

[0180] For the time-frequency domain transformation sequence of the product sequence, there are also similar examples as above, which can be cross-referenced with the examples of the product sequence and will not be described in detail here.

[0181] The summation in each embodiment of the present application can be in many different forms, which are not limited here. For example, one form of summation is Wherein, x represents the parameter to be summed, PDP(x) represents the sequence to be summed for the parameter x (such as a product sequence, a sequence after time domain summation, a sequence after multipath summation, etc.), N x Indicates the number of different values ​​that the parameter x can take.

[0182] For example, a summation of the form

[0183] For example, a summation of the form

[0184] In some embodiments, summing the time-shift parameters comprises:

[0185] Determine a first target sequence from the sequence to be time-shifted and parameter summed according to a first threshold;

[0186] The first target sequence is summed over the time-shift parameter.

[0187] Specifically, when performing time shift parameter summation (ie, multipath summation operation), a first threshold may be used to first screen a sequence for which time shift parameter summation is to be performed to obtain a first target sequence.

[0188] The first threshold is a pre-set threshold, and its value can be flexibly set without specific limitation.

[0189] For example, a first threshold may be set in advance, and a sequence whose modulus value is greater than the first threshold in the sequence to be summed for time-shift parameters is determined as a first target sequence, and the time-shift parameters of the first target sequence are summed. Example of summation form: Where τ represents the time shift parameter, Th 1 represents the first threshold, N τ is the number of stronger paths in the channel multipath, that is, |PDP(τ)|>Th 1 The number of different values ​​of τ in PDP(τ).

[0190] For example, a first threshold may be set in advance, and a sequence whose square of the modulus value is greater than the first threshold in the sequence to be summed for time-shift parameters is determined as a first target sequence, and the time-shift parameters of the first target sequence are summed. Example of summation form: It should be noted that N τ It is also the number of stronger paths in the channel multipath, but it satisfies |PDP(τ)| 2 >Th 1 The number of different values ​​of τ in PDP(τ).

[0191] In some embodiments, summing the frequency shift parameters comprises:

[0192] Determine a second target sequence from the sequence to be subjected to frequency shift parameter summation according to a second threshold;

[0193] The second target sequence is summed over the frequency shift parameter.

[0194] Specifically, when performing frequency shift parameter summation (ie, Doppler summation operation), the second threshold value can be used to filter the sequence to be summed to obtain the second target sequence. The second threshold value is a pre-set threshold value, and its value can be flexibly set and is not specifically limited.

[0195] For example, a second threshold may be set in advance, and a sequence whose modulus value is greater than the second threshold in the sequence to be summed with frequency shift parameters is determined as a second target sequence, and the frequency shift parameters of the second target sequence are summed. Example of summation form: Where Δ represents the frequency shift parameter, Th 2 represents the second threshold, N Δ is the number of stronger Dopplers in the channel Doppler, that is, satisfying |PDP(Δ)|>Th 2 The number of different values ​​of Δ in PDP(Δ).

[0196] For example, a second threshold may be set in advance, and a sequence whose square of the modulus value is greater than the second threshold in the sequence to be summed for frequency shift parameters is determined as the second target sequence, and the frequency shift parameters of the second target sequence are summed. Example of summation form: It should be noted that N Δ It is also the number of stronger Dopplers in the channel Doppler, but it satisfies |PDP(Δ)| 2 >Th 2 The number of different values ​​of Δ in PDP(Δ).

[0197] In some embodiments, the method further comprises:

[0198] receiving model input instruction information;

[0199] Based on the model input indication information, determine the power density spectrum type of the input AI model.

[0200] Specifically, the transmitting device can send model input indication information to the receiving device, and the indication information is used to indicate the type of power density spectrum input to the AI ​​model. For example, the indication information indicates that the type of power density spectrum input to the AI ​​model is one of a time domain product sequence, a frequency domain product sequence, a time domain summation sequence, a frequency domain summation sequence, a time domain multipath summation sequence, a frequency domain multipath summation sequence, a time domain Doppler summation sequence, a frequency domain Doppler summation sequence, a time domain multipath Doppler summation sequence, a frequency domain multipath Doppler summation sequence, a time domain Doppler multipath summation sequence, a frequency domain Doppler multipath summation sequence, etc. The receiving device calculates the corresponding power density spectrum according to the indication information, and then inputs the AI ​​model for inference to obtain synchronization information.

[0201] The power density spectrum of the input AI model has different types, and the calculation complexity is different, and the corresponding AI model reasoning accuracy is also different. For example, the higher the calculation complexity of the power density spectrum of the input AI model (the more preprocessing processes), the higher the accuracy of the synchronization information output by the corresponding AI model.

[0202] Figure 2 The second flowchart of the synchronization method provided in the embodiment of the present application is applied to a transmitting device, such as Figure 2 As shown, the method comprises the following steps:

[0203] Step 200: Send model input indication information to the receiving device, where the model input indication information is used to indicate the type of power density spectrum input to the artificial intelligence AI model, and the AI ​​model is used to output synchronization information based on the input power density spectrum.

[0204] Specifically, the embodiment of the present application is based on a synchronization scheme of an AI model (or AI engine, AI mechanism, AI algorithm, etc.). The transmitting device can send model input indication information to the receiving device, and the indication information is used to indicate the power density spectrum type of the input AI model. For example, the indication information indicates that the power density spectrum type of the input AI model is one of a time domain product sequence, a frequency domain product sequence, a time domain summation sequence, a frequency domain summation sequence, a time domain multipath summation sequence, a frequency domain multipath summation sequence, a time domain Doppler summation sequence, a frequency domain Doppler summation sequence, a time domain multipath Doppler summation sequence, a frequency domain multipath Doppler summation sequence, a time domain Doppler multipath summation sequence, a frequency domain Doppler multipath summation sequence, etc. The receiving device calculates the corresponding power density spectrum according to the indication information, and then inputs the AI ​​model for inference to obtain synchronization information.

[0205] In the embodiments of the present application, the AI ​​model can use any AI model, such as a CNN model, a ReSNet model, a DRL model, etc.

[0206] In some embodiments, the transmitting device can select a ZC sequence (or m-sequence) based on the ID of the transmitting device and the length of the predetermined ZC sequence (or m-sequence). Then, the selected ZC sequence (or m-sequence) is sent out on the predetermined resources. After receiving the signal, the receiving device can use the AI ​​model to perform inference operations based on the received signal and the local sequence to obtain the output of the model, that is, the synchronization information, so as to complete the synchronization.

[0207] In some embodiments, the receiving device is a terminal or a network device (e.g., a base station); the transmitting device is a network device or a terminal. This actually includes synchronization mechanisms in four situations: network device sends - network device receives, network device sends - terminal receives, terminal sends - network device receives, and terminal sends - terminal receives.

[0208] According to the synchronization method provided in the embodiment of the present application, the transmitting device can send model input indication information to the receiving device, indicating the power density spectrum type of the input AI model, so that the receiving device can perform power density spectrum operations of different complexities according to the instructions of the network side, thereby improving the flexibility of implementing the synchronization scheme.

[0209] The methods provided in the embodiments of the present application are based on the same application concept, so the implementation of each method can refer to each other, and the repeated parts will not be repeated.

[0210] The following describes the methods provided in the above embodiments of the present application by using examples of specific application scenarios.

[0211] Figure 3 An example diagram of the synchronization method provided in the embodiment of the present application is shown in FIG. Figure 3 As shown, in the 6G scenario, the terminal usually has AI capabilities. The general process of the AI-based synchronization method is as follows: the receiving device performs preprocessing based on the received signal and the local sequence, and then inputs the preprocessed sequence (or power density spectrum) into the AI ​​model for inference operation to obtain synchronization information. The following is an example of various AI model inputs and AI models.

[0212] Example 1: The input of the AI ​​model is a frequency domain product sequence.

[0213] The main steps of the synchronization process are as follows:

[0214] Step 1: FFT operation, for the kth local sequence and the τth received signal in the time domain sliding window Do FFT to get the frequency domain sequence Receive signal in frequency domain Where k = 1, 2, ..., K, K represents the number of local sequences; N s is the sequence length; i represents the time domain parameter, n represents the frequency domain parameter, and τ represents the time shift parameter.

[0215] Step 2: Frequency domain cyclic shift, for the kth local frequency domain sequence Perform a cyclic shift of Δ subcarrier intervals to obtain a frequency domain shift sequence Wherein, Δ represents the frequency shift parameter.

[0216] Step 3: Frequency domain correlation operation, Receive signal in frequency domain The conjugate of is point-multiplied in the frequency domain to obtain the power density spectrum PDP(k,τ,Δ,n), which is the frequency domain product sequence.

[0217] Step 4: AI model reasoning, taking PDP (k, τ, Δ, n) as the input of the AI ​​model, and after AI reasoning operation, obtaining the output of the AI ​​model, that is, the main synchronization information, including the sequence ID Time synchronization parameters Frequency synchronization parameters

[0218] Example 2: The input of the AI ​​model is a time-domain product sequence.

[0219] The main steps of the synchronization process are as follows:

[0220] Step 1: FFT operation, for the kth local sequence and the τth received signal in the time domain sliding window Do FFT to get the frequency domain sequence Receive signal in frequency domain

[0221] Step 2: Frequency domain cyclic shift, for the kth local frequency domain sequence Perform a cyclic shift of Δ subcarrier intervals to obtain a frequency domain shift sequence

[0222] Step 3: Frequency domain correlation operation, Receive signal in frequency domain The conjugate of is multiplied in the frequency domain to obtain the power density spectrum PDP(k,τ,Δ,n).

[0223] Step 4: IFFT operation. Perform IFFT on PDP(k,τ,Δ,n) to obtain PDP(k,τ,Δ,i), which is the time domain product sequence.

[0224] Step 5: AI model reasoning, taking PDP (k, τ, Δ, i) as the input of the AI ​​model, and after AI reasoning operation, obtaining the output of the AI ​​model, that is, the main synchronization information, including the sequence ID Time synchronization parameters Frequency synchronization parameters

[0225] Example 3: The input of the AI ​​model is a time-domain correlation value (a time-domain summation sequence).

[0226] The main steps of the synchronization process are as follows:

[0227] Step 1: FFT operation, for the kth local sequence and the τth received signal in the time domain sliding window Do FFT to get the frequency domain sequence Receive signal in frequency domain

[0228] Step 2: Frequency domain cyclic shift, for the kth local frequency domain sequence Perform a cyclic shift of Δ subcarrier intervals to obtain a frequency domain shift sequence

[0229] Step 3: Frequency domain correlation operation, Receive signal in frequency domain The conjugate of is multiplied in the frequency domain to obtain the power density spectrum PDP(k,τ,Δ,n).

[0230] Step 4: IFFT operation. Perform IFFT on PDP(k,τ,Δ,n) to obtain PDP(k,τ,Δ,i).

[0231] Step 5: Time domain summation operation, sum the parameter i and get That is, the time-domain summation sequence.

[0232] Step 6: AI model reasoning, taking PDP (k, τ, Δ) as the input of the AI ​​model, and after AI reasoning operation, obtaining the output of the AI ​​model, namely the main synchronization information, including the sequence ID Time synchronization parameters Frequency synchronization parameters

[0233] Example 4: The input of the AI ​​model is the correlation value after time domain multipath processing (time domain multipath summation sequence).

[0234] The main steps of the synchronization process are as follows:

[0235] Step 1: FFT operation, for the kth local sequence and the τth received signal in the time domain sliding window Do FFT to get the frequency domain sequence Receive signal in frequency domain

[0236] Step 2: Frequency domain cyclic shift, for the kth local frequency domain sequence Perform a cyclic shift of Δ subcarrier intervals to obtain a frequency domain shift sequence

[0237] Step 3: Frequency domain correlation operation, Receive signal in frequency domain The conjugate of is multiplied in the frequency domain to obtain the power density spectrum PDP(k,τ,Δ,n).

[0238] Step 4: IFFT operation. Perform IFFT on PDP(k,τ,Δ,n) to obtain PDP(k,τ,Δ,i).

[0239] Step 5: Time domain summation operation, sum the parameter i and get

[0240] Step 6: Multipath summation operation, based on a given threshold Th 1 , summing the parameter τ, we get where τ 0 is the τ corresponding to the maximum value of |PDP(k,τ,Δ)| with τ as the variable. Here each pair (k,Δ) corresponds to a τ 0 . Nτ is the number of stronger paths in the channel multipath.

[0241] Step 7: AI model reasoning, PDP(k,τ 0 ,Δ) as the input of the AI ​​model, after AI reasoning operation, the output of the AI ​​model is obtained, that is, the main synchronization information, including the sequence ID Time synchronization parameters Frequency synchronization parameters

[0242] Example 5: The input of the AI ​​model is the time-domain Doppler processed correlation value (time-domain Doppler summation sequence).

[0243] The main steps of the synchronization process are as follows:

[0244] Step 1: FFT operation, for the kth local sequence and the τth received signal in the time domain sliding window Do FFT to get the frequency domain sequence Receive signal in frequency domain

[0245] Step 2: Frequency domain cyclic shift, for the kth local frequency domain sequence Perform a cyclic shift of Δ subcarrier intervals to obtain a frequency domain shift sequence

[0246] Step 3: Frequency domain correlation operation, Receive signal in frequency domain The conjugate of is multiplied in the frequency domain to obtain the power density spectrum PDP(k,τ,Δ,n).

[0247] Step 4: IFFT operation. Perform IFFT on PDP(k,τ,Δ,n) to obtain PDP(k,τ,Δ,i).

[0248] Step 5: Time domain summation operation, sum the parameter i and get

[0249] Step 6: Doppler summation operation, based on the pre-given threshold Th 2 , summing the parameter Δ, we get where Δ 0 is the Δ corresponding to the maximum value of |PDP(k,τ,Δ)| with Δ as the variable. Here each pair (k,τ) corresponds to a Δ 0 . N Δ is the number of stronger Doppler frequencies in the channel Doppler.

[0250] Step 7: AI model reasoning, PDP(k,τ,Δ 0) as the input of the AI ​​model, and after AI reasoning operation, the output of the AI ​​model is obtained, that is, the main synchronization information, including the sequence ID Time synchronization parameters Frequency synchronization parameters

[0251] Example 6: The input of the AI ​​model is the correlation value after time domain multipath Doppler processing (time domain multipath Doppler summation sequence).

[0252] The main steps of the synchronization process are as follows:

[0253] Step 1: FFT operation, for the kth local sequence and the τth received signal in the time domain sliding window Do FFT to get the frequency domain sequence Receive signal in frequency domain

[0254] Step 2: Frequency domain cyclic shift, for the kth local frequency domain sequence Perform a cyclic shift of Δ subcarrier intervals to obtain a frequency domain shift sequence

[0255] Step 3: Frequency domain correlation operation, Receive signal in frequency domain The conjugate of is multiplied in the frequency domain to obtain the power density spectrum PDP(k,τ,Δ,n).

[0256] Step 4: IFFT operation. Perform IFFT on PDP(k,τ,Δ,n) to obtain PDP(k,τ,Δ,i).

[0257] Step 5: Time domain summation operation, sum the parameter i and get

[0258] Step 6: Multipath summation operation, based on a given threshold Th 1 , summing the parameter τ, we get where τ 0 is the τ corresponding to the maximum value of |PDP(k,τ,Δ)| with τ as the variable. Here each pair (k,Δ) corresponds to a τ 0 .

[0259] Step 7: Doppler summation operation, based on the pre-given threshold Th 2 , summing the parameter Δ, we get where Δ 0 is |PDP(k,τ) with Δ as the variable 0 ,Δ)| corresponds to the maximum value of Δ. Here, each pair (k,τ 0 ) corresponds to a Δ 0.

[0260] Step 8: AI model reasoning, PDP(k,τ 0 ,Δ 0 ) as the input of the AI ​​model, and after AI reasoning operation, the output of the AI ​​model is obtained, that is, the main synchronization information, including the sequence ID Time synchronization parameters Frequency synchronization parameters

[0261] Example 7: The input of the AI ​​model is the correlation value after time domain Doppler multipath processing (time domain Doppler multipath summation sequence).

[0262] The main steps of the synchronization process are as follows:

[0263] Step 1: FFT operation, for the kth local sequence and the τth received signal in the time domain sliding window Do FFT to get the frequency domain sequence Receive signal in frequency domain

[0264] Step 2: Frequency domain cyclic shift, for the kth local frequency domain sequence Perform a cyclic shift of Δ subcarrier intervals to obtain a frequency domain shift sequence

[0265] Step 3: Frequency domain correlation operation, Receive signal in frequency domain The conjugate of is multiplied in the frequency domain to obtain the power density spectrum PDP(k,τ,Δ,n).

[0266] Step 4: IFFT operation. Perform IFFT on PDP(k,τ,Δ,n) to obtain PDP(k,τ,Δ,i).

[0267] Step 5: Time domain summation operation, sum the parameter i and get

[0268] Step 6: Doppler summation operation, based on the pre-given threshold Th 2 , summing the parameter Δ, we get where Δ 0 is the Δ corresponding to the maximum value of |PDP(k,τ,Δ)| with Δ as the variable. Here each pair (k,τ) corresponds to a Δ 0 .

[0269] Step 7: Multipath summation operation, based on a given threshold Th 1 , summing the parameter τ, we get where τ 0is |PDP(k,τ,Δ 0 )| corresponds to the maximum value of τ. Here, each pair (k,Δ 0 ) corresponds to a τ 0 .

[0270] Step 8: AI model reasoning, PDP(k,τ 0 ,Δ 0 ) as the input of the AI ​​model, and after AI reasoning operation, the output of the AI ​​model is obtained, that is, the main synchronization information, including the sequence ID Time synchronization parameters Frequency synchronization parameters

[0271] Example 8: AI model.

[0272] The choice of AI model can be any AI model, including CNN, ReSNet, DRL, etc. Figure 4 This is an example diagram of the RESNet neural network structure provided in the embodiment of the present application. Figure 4 Take the RESNet shown in the figure as an example to illustrate. Assume that the input of the AI ​​model is the time domain correlation value PDP (k, τ, Δ), and the input dimension is k = 3, τ = 224, Δ = 224. Figure 4 The input data dimension in is 3×224×224.

[0273] Figure 4 In the figure, ks represents the convolution edge length kernel_size, s represents the step length stride, and p represents the border padding.

[0274] For the first convolution layer, the convolution side length kernel_size = 7, the number of output channels output_channel = 64, the step length stride = 2, and the border padding = 3. The side length of the output matrix can be obtained as output_size = (224-7+3×2) / 2+1 = 112, so a feature matrix of 64×112×112 is output.

[0275] The output of the first convolutional layer is pooled with 3×3, stride=2, and border padding=1, and the side length of the output matrix can be obtained as output_size=(112-3+2) / 2+1=56, so the output feature matrix is ​​64×56×56.

[0276] Then it goes through 8 two-layer block structures.

[0277] The first and second block structures both contain two convolutional layers. The convolution edge length of each convolutional layer is kernel_size=3, the number of output channels is output_channel=64, the step length is stride=1, and the border padding is 1. The output matrix edge length is output_size=(56-3+1×2) / 1+1=56, so the output is a 64×56×56 feature matrix. The input of each block structure will add the input to the output to achieve a residual structure.

[0278] The third block structure contains two convolutional layers. The first convolutional layer kernel_size = 3, the number of output channels output_channel = 128, the stride = 2, and the border padding = 1. The side length of the output matrix can be obtained as output_size = (56-3 + 1 × 2) / 2 + 1 = 28, so the output feature matrix is ​​128 × 28 × 28. The second convolutional layer kernel_size = 3, the number of output channels output_channel = 128, the stride = 1, the border padding = 1, and the output feature matrix is ​​128 × 28 × 28. In this block structure, in order to achieve dimensional alignment, the input is downsampled to 128 × 28 × 28 and then added to the output.

[0279] The fourth block structure contains two convolutional layers. Each convolutional layer has kernel_size=3, output channel number output_channel=128, stride=1, border padding=1, and outputs a 128×28×28 feature matrix.

[0280] The fifth block structure is similar to the third block structure, except that the number of output channels output_channel = 256. The sixth block structure is similar to the fourth block structure, except that the number of output channels output_channel = 256. The seventh block structure is similar to the third block structure, except that the number of output channels output_channel = 512. The eighth block structure is similar to the fourth block structure, except that the number of output channels output_channel = 512.

[0281] Then, average pooling is performed to obtain a 512×1×1 output.

[0282] Finally, after passing through a 512×3 fully connected (FC) layer, the sequence ID is output Time synchronization parameters Frequency synchronization parameters The value of .

[0283] The methods and devices provided in the various embodiments of the present application are based on the same application concept. Since the methods and devices solve problems based on similar principles, the implementation of the devices and methods can refer to each other, and the repeated parts will not be repeated.

[0284] Figure 5 A schematic diagram of the structure of a receiving device provided in an embodiment of the present application, such as Figure 5 As shown, the receiving end device includes a memory 520, a transceiver 510 and a processor 500; wherein the processor 500 and the memory 520 may also be arranged physically separately.

[0285] The memory 520 is used to store computer programs; the transceiver 510 is used to send and receive data under the control of the processor 500.

[0286] Specifically, the transceiver 510 is used to receive and send data under the control of the processor 500 .

[0287] Among them, Figure 5 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 500 and memory represented by memory 520. The bus architecture may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described in this application. The bus interface provides an interface. The transceiver 510 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which may include a wireless channel, a wired channel, an optical cable, and other transmission media.

[0288] The processor 500 is responsible for managing the bus architecture and general processing, and the memory 520 can store data used by the processor 500 when performing operations.

[0289] The processor 500 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0290] The processor 500 calls the computer program stored in the memory 520 to execute any of the methods provided in the embodiments of the present application according to the obtained executable instructions, for example: determining the power density spectrum based on the received signal and the local sequence; inputting the power density spectrum into the artificial intelligence AI model to obtain the synchronization information output by the AI ​​model; wherein the AI ​​model is trained based on the sample power density spectrum with the synchronization information label.

[0291] In some embodiments, determining a power density spectrum based on a received signal and a local sequence includes:

[0292] multiplying the first signal and the first sequence to obtain a product sequence;

[0293] Determine a power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence;

[0294] The first signal is a received signal, or a signal obtained by transforming the received signal;

[0295] The first sequence is a local sequence, or a sequence obtained by transforming the local sequence.

[0296] In some embodiments, performing transformation processing on the received signal includes:

[0297] The received signal is subjected to at least one of time shift, frequency domain transformation and conjugate transformation.

[0298] In some embodiments, the local sequence is transformed, including:

[0299] Perform at least one of frequency shift and frequency domain transformation on the local sequence.

[0300] In some embodiments, determining the power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence includes:

[0301] The product sequence or the time-frequency domain transformation sequence of the product sequence is summed over some parameters to obtain a summation sequence;

[0302] Based on the summed sequence, a power density spectrum is determined.

[0303] In some embodiments, the partial parameters are summed, including one or more of the following:

[0304] Sum time domain parameters or frequency domain parameters;

[0305] summing the time-shifted parameters;

[0306] The frequency shift parameters are summed.

[0307] In some embodiments, summing the time-shift parameters comprises:

[0308] Determine a first target sequence from the sequence to be time-shifted and parameter summed according to a first threshold;

[0309] The first target sequence is summed over the time-shift parameter.

[0310] In some embodiments, summing the frequency shift parameters comprises:

[0311] Determine a second target sequence from the sequence to be subjected to frequency shift parameter summation according to a second threshold;

[0312] The second target sequence is summed over the frequency shift parameter.

[0313] In some embodiments, the synchronization information includes one or more of a sequence identifier, a time synchronization parameter, and a frequency synchronization parameter.

[0314] In some embodiments, the local sequence is a ZC sequence or an m-sequence.

[0315] In some embodiments, the method further comprises:

[0316] receiving model input instruction information;

[0317] Based on the model input indication information, determine the power density spectrum type of the input AI model.

[0318] Figure 6 A schematic diagram of the structure of the transmitting end device provided in the embodiment of the present application, such as Figure 6 As shown, the transmitting end device includes a memory 620, a transceiver 610 and a processor 600; wherein the processor 600 and the memory 620 may also be arranged physically separately.

[0319] The memory 620 is used to store computer programs; the transceiver 610 is used to send and receive data under the control of the processor 600.

[0320] Specifically, the transceiver 610 is used to receive and send data under the control of the processor 600 .

[0321] Among them, Figure 6 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 600 and memory represented by memory 620. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described in this application. The bus interface provides an interface. The transceiver 610 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which may include a wireless channel, a wired channel, an optical cable, and other transmission media.

[0322] The processor 600 is responsible for managing the bus architecture and general processing, and the memory 620 can store data used by the processor 600 when performing operations.

[0323] The processor 600 may be a CPU, an ASIC, an FPGA or a CPLD, and the processor may also adopt a multi-core architecture.

[0324] The processor 600 calls the computer program stored in the memory 620 to execute any of the methods provided in the embodiments of the present application according to the obtained executable instructions, for example: sending model input indication information to the receiving device, the model input indication information is used to indicate the power density spectrum type input to the artificial intelligence AI model, and the AI ​​model is used to output synchronization information based on the input power density spectrum.

[0325] It should be noted here that the above-mentioned receiving device and transmitting device provided in the embodiments of the present application can implement all the method steps implemented in the above-mentioned method embodiments, and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those in the method embodiments will not be described in detail here.

[0326] Figure 7 One of the structural diagrams of the synchronization device provided in the embodiment of the present application is as follows: Figure 7 As shown, the device comprises:

[0327] A first determining unit 700 is configured to determine a power density spectrum based on a received signal and a local sequence;

[0328] The acquisition unit 710 is used to input the power density spectrum into the artificial intelligence AI model to obtain the synchronization information output by the AI ​​model; wherein the AI ​​model is trained based on the sample power density spectrum with the synchronization information label.

[0329] In some embodiments, determining a power density spectrum based on a received signal and a local sequence includes:

[0330] multiplying the first signal and the first sequence to obtain a product sequence;

[0331] Determine a power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence;

[0332] The first signal is a received signal, or a signal obtained by transforming the received signal;

[0333] The first sequence is a local sequence, or a sequence obtained by transforming the local sequence.

[0334] In some embodiments, performing transformation processing on the received signal includes:

[0335] The received signal is subjected to at least one of time shift, frequency domain transformation and conjugate transformation.

[0336] In some embodiments, the local sequence is transformed, including:

[0337] Perform at least one of frequency shift and frequency domain transformation on the local sequence.

[0338] In some embodiments, determining the power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence includes:

[0339] The product sequence or the time-frequency domain transformation sequence of the product sequence is summed over some parameters to obtain a summation sequence;

[0340] Based on the summed sequence, a power density spectrum is determined.

[0341] In some embodiments, the partial parameters are summed, including one or more of the following:

[0342] Sum time domain parameters or frequency domain parameters;

[0343] summing the time-shifted parameters;

[0344] The frequency shift parameters are summed.

[0345] In some embodiments, summing the time-shift parameters comprises:

[0346] Determine a first target sequence from the sequence to be time-shifted and parameter summed according to a first threshold;

[0347] The first target sequence is summed over the time-shift parameter.

[0348] In some embodiments, summing the frequency shift parameters comprises:

[0349] Determine a second target sequence from the sequence to be subjected to frequency shift parameter summation according to a second threshold;

[0350] The second target sequence is summed over the frequency shift parameter.

[0351] In some embodiments, the synchronization information includes one or more of a sequence identifier, a time synchronization parameter, and a frequency synchronization parameter.

[0352] In some embodiments, the local sequence is a ZC sequence or an m-sequence.

[0353] In some embodiments, the apparatus further comprises:

[0354] A receiving unit, used for receiving model input indication information;

[0355] The second determination unit is used to determine the power density spectrum type of the input AI model based on the model input indication information.

[0356] Figure 8 The second structural diagram of the synchronization device provided in the embodiment of the present application is as follows: Figure 8 As shown, the device comprises:

[0357] The sending unit 800 is used to send model input indication information to the receiving end device, where the model input indication information is used to indicate the power density spectrum type of the input artificial intelligence AI model, and the AI ​​model is used to output synchronization information based on the input power density spectrum.

[0358] It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0359] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0360] It should be noted here that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0361] On the other hand, an embodiment of the present application further provides a non-transitory readable storage medium, wherein the non-transitory readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the synchronization method provided by the above embodiments.

[0362] It should be noted here that the non-transitory readable storage medium provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0363] The non-transitory readable storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0364] The technical solution provided in the embodiment of the present application can be applicable to a variety of systems, especially 5G systems. For example, the applicable system can be a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (WCDMA) general packet radio service (GPRS) system, a long term evolution (LTE) system, a LTE frequency division duplex (FDD) system, a LTE time division duplex (TDD) system, an advanced long term evolution (LTE-A) system, a universal mobile telecommunication system (UMTS), a world-wide interoperability for microwave access (WiMAX) system, a 5G new air interface (NR) system, etc. These various systems include terminal equipment and network equipment. The system may also include a core network part, such as an evolved packet system (EPS), a 5G system (5GS), etc.

[0365] The terminal involved in the embodiment of the present application may be a device that provides voice and / or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem. In different systems, the name of the terminal may also be different. For example, in a 5G system, the terminal may be called a user equipment (UE). A wireless terminal device can communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or a "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges language and / or data with a wireless access network. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs) and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, and a user device, but is not limited in the embodiments of the present application.

[0366] The network device involved in the embodiment of the present application may be a base station, which may include multiple cells providing services for the terminal. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in the access network that communicates with the wireless terminal device through one or more sectors on the air interface, or other names. The network device may be used to interchange received air frames with Internet Protocol (IP) packets, and serve as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present application may be a network device (Base Transceiver Station, BTS) in the Global System for Mobile communications (Global System for Mobile communications, GSM) or Code Division Multiple Access (Code Division Multiple Access, CDMA), or a network device (NodeB) in Wide-band Code Division Multiple Access (WCDMA), or an evolutionary network device (evolutional Node B, eNB or e-NodeB) in the long term evolution (long term evolution, LTE) system, a 5G base station (gNB) in the 5G network architecture (next generation system), or a home evolved Node B (Home evolved Node B, HeNB), a relay node, a home base station (femto), a pico base station (pico), etc., which is not limited in the embodiments of the present application. In some network structures, the network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be arranged geographically separately.

[0367] Network devices and terminals can each use one or more antennas for multiple-input multiple-output (MIMO) transmission. MIMO transmission can be single-user MIMO (SU-MIMO) or multi-user MIMO (MU-MIMO). Depending on the form and number of antenna combinations, MIMO transmission can be 2D-MIMO, 3D-MIMO, FD-MIMO or massive-MIMO, or it can be diversity transmission, precoded transmission or beamforming transmission, etc.

[0368] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0369] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0370] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0371] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0372] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A synchronization method, It is characterized in that Applied to receiving devices, including: determining a power density spectrum based on the received signal and the local sequence; The power density spectrum is input into an artificial intelligence AI model to obtain synchronization information output by the AI ​​model; wherein the AI ​​model is trained based on a sample power density spectrum with a synchronization information label.

2. The synchronization method according to claim 1, It is characterized in that The step of determining a power density spectrum based on a received signal and a local sequence comprises: multiplying the first signal and the first sequence to obtain a product sequence; Determine a power density spectrum based on the product sequence or a time-frequency domain transformation sequence of the product sequence; The first signal is the received signal, or a signal obtained by transforming the received signal; The first sequence is the local sequence, or a sequence obtained by transforming the local sequence.

3. The synchronization method according to claim 2, It is characterized in that The step of transforming the received signal comprises: The received signal is subjected to at least one of time shift, frequency domain transformation and conjugate transformation.

4. The synchronization method according to claim 2, It is characterized in that The transforming process of the local sequence includes: Perform at least one of frequency shift and frequency domain transformation on the local sequence.

5. The synchronization method according to claim 2, It is characterized in that The determining of the power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence includes: Sum some parameters of the product sequence or the time-frequency domain transformation sequence of the product sequence to obtain a summation sequence; Based on the summation sequence, a power density spectrum is determined.

6. The synchronization method according to claim 5, It is characterized in that The summing of some parameters includes one or more of the following: Sum time domain parameters or frequency domain parameters; summing the time-shifted parameters; The frequency shift parameters are summed.

7. The synchronization method according to claim 6, It is characterized in that The step of summing the time-shift parameters comprises: Determine a first target sequence from the sequence to be time-shifted and parameter summed according to a first threshold; The first target sequence is summed with respect to a time shift parameter.

8. The synchronization method according to claim 6, It is characterized in that The summing of the frequency shift parameters comprises: Determine a second target sequence from the sequence to be subjected to frequency shift parameter summation according to a second threshold; The second target sequence is summed with respect to the frequency shift parameter.

9. The synchronization method according to any one of claims 1 to 8, It is characterized in that The synchronization information includes one or more of a sequence identifier, a time synchronization parameter, and a frequency synchronization parameter.

10. The synchronization method according to any one of claims 1 to 8, It is characterized in that The local sequence is a ZC sequence or an m sequence.

11. The synchronization method according to any one of claims 1 to 8, It is characterized in that The method further comprises: receiving model input instruction information; Based on the model input indication information, determine the power density spectrum type input into the AI ​​model.

12. A synchronization method, It is characterized in that Applicable to transmitter equipment, including: Model input indication information is sent to a receiving device, where the model input indication information is used to indicate the type of power density spectrum input to an artificial intelligence (AI) model, and the AI ​​model is used to output synchronization information based on the input power density spectrum.

13. A receiving device, It is characterized in that Including memory, transceiver, processor; A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: determining a power density spectrum based on the received signal and the local sequence; The power density spectrum is input into an artificial intelligence AI model to obtain synchronization information output by the AI ​​model; wherein the AI ​​model is trained based on a sample power density spectrum with a synchronization information label.

14. The receiving device according to claim 13, It is characterized in that The step of determining a power density spectrum based on a received signal and a local sequence comprises: multiplying the first signal and the first sequence to obtain a product sequence; Determine a power density spectrum based on the product sequence or a time-frequency domain transformation sequence of the product sequence; The first signal is the received signal, or a signal obtained by transforming the received signal; The first sequence is the local sequence, or a sequence obtained by transforming the local sequence.

15. The receiving device according to claim 14, It is characterized in that The step of transforming the received signal comprises: The received signal is subjected to at least one of time shift, frequency domain transformation and conjugate transformation.

16. The receiving device according to claim 14, It is characterized in that The transforming process of the local sequence includes: Perform at least one of frequency shift and frequency domain transformation on the local sequence.

17. The receiving device according to claim 14, It is characterized in that The determining of the power density spectrum based on the product sequence or the time-frequency domain transformation sequence of the product sequence includes: Sum some parameters of the product sequence or the time-frequency domain transformation sequence of the product sequence to obtain a summation sequence; Based on the summation sequence, a power density spectrum is determined.

18. The receiving device according to claim 17, It is characterized in that The summing of some parameters includes one or more of the following: Sum time domain parameters or frequency domain parameters; summing the time-shifted parameters; The frequency shift parameters are summed.

19. The receiving device according to claim 18, It is characterized in that The step of summing the time-shift parameters comprises: Determine a first target sequence from the sequence to be time-shifted and parameter summed according to a first threshold; The first target sequence is summed with respect to a time shift parameter.

20. The receiving device according to claim 18, It is characterized in that The summing of the frequency shift parameters comprises: Determine a second target sequence from the sequence to be subjected to frequency shift parameter summation according to a second threshold; The second target sequence is summed with respect to the frequency shift parameter.

21. The receiving device according to any one of claims 13 to 20, It is characterized in that The synchronization information includes one or more of a sequence identifier, a time synchronization parameter, and a frequency synchronization parameter.

22. The receiving device according to any one of claims 13 to 20, It is characterized in that The local sequence is a ZC sequence or an m sequence.

23. The receiving device according to any one of claims 13 to 20, It is characterized in that The operations also include: receiving model input instruction information; Based on the model input indication information, determine the power density spectrum type input into the AI ​​model.

24. A transmitting device, It is characterized in that Including memory, transceiver, processor; A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Model input indication information is sent to a receiving device, where the model input indication information is used to indicate the type of power density spectrum input to an artificial intelligence (AI) model, and the AI ​​model is used to output synchronization information based on the input power density spectrum.

25. A synchronization device, It is characterized in that include: A first determining unit, configured to determine a power density spectrum based on a received signal and a local sequence; An acquisition unit is used to input the power density spectrum into an artificial intelligence AI model to obtain synchronization information output by the AI ​​model; wherein the AI ​​model is trained based on a sample power density spectrum with a synchronization information label.

26. A synchronization device, It is characterized in that include: A sending unit is used to send model input indication information to a receiving end device, wherein the model input indication information is used to indicate the power density spectrum type of an input artificial intelligence AI model, and the AI ​​model is used to output synchronization information based on the input power density spectrum.

27. A non-transitory readable storage medium, It is characterized in that The non-transitory readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the method according to any one of claims 1 to 11.

28. A non-transitory readable storage medium, It is characterized in that The non-transitory readable storage medium stores a computer program, and the computer program is used to cause a processor to execute the method of claim 12.

Images