Communication method, communication device, communication system, storage medium, and program product

Abstract

The present invention relates to a communication method, a communication device, a communication system, a storage medium, and a program product. The method comprises: receiving a first signal sent by a second device, wherein the first signal is transmitted on the basis of a superimposed signal generated by superimposing a baseband signal and a reference signal, and the baseband signal is a data signal obtained by modulating a transmission bitstream; and determining a second signal corresponding to the baseband signal. In the method of the present invention, during signal transmission, a first signal transmitted by a transmitting end is transmitted on the basis of a superimposed signal obtained by superimposing a baseband signal and a reference signal, thereby improving the utilization rate of transmission resources by data signals; and a receiving end can accurately obtain a second signal by means of reception or processing.

Description

Communication methods, communication equipment, communication systems, storage media and software products Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a communication method, communication device, communication system, storage medium, and program product. Background Technology

[0002] In wireless communication systems, the transmitting end can use a transmitter to send signals, and the receiving end can use a receiver to perform channel estimation, thereby recovering the transmitted signal and completing signal transmission. During signal transmission, the data and the reference signal used for channel estimation are independent or orthogonal to each other. The high resource overhead required by the reference signal may reduce the utilization rate of data transmission resources. Summary of the Invention

[0003] Based on the transmission relationship between data and reference signals, it is necessary to provide ways to improve the utilization of data transmission resources and ensure that the receiving end can receive accurately.

[0004] This disclosure provides a communication method, communication device, communication system, storage medium, and program product.

[0005] In a first aspect, embodiments of this disclosure provide a communication method, executed by a first device, the method comprising:

[0006] The device receives a first signal sent by a second device, wherein the first signal is a mixed signal generated by superimposing a baseband signal and a reference signal, and the baseband signal is a data signal after modulation of the transmitted bit stream.

[0007] Determine the second signal corresponding to the baseband signal.

[0008] Secondly, embodiments of this disclosure provide a communication method executed by a second device, the method comprising:

[0009] Based on the baseband signal and the reference signal, the superimposed aliasing signal is determined, wherein the baseband signal is the data signal after modulation of the transmitted bit stream;

[0010] Based on the aliasing signal, a first signal is sent to the first device, wherein the first signal is used by the first device to determine a second signal corresponding to the baseband signal.

[0011] Thirdly, embodiments of this disclosure provide a communication device, wherein the communication device is used to perform the method described in the first aspect or the second aspect.

[0012] Fourthly, embodiments of this disclosure provide a communication system, including a first device and a second device, wherein,

[0013] The first device is configured to implement the method as described in the first aspect;

[0014] The second device is configured to implement the method as described in the second aspect.

[0015] Fifthly, embodiments of this disclosure provide a storage medium storing instructions, wherein...

[0016] When the instructions are executed on the communication device, the communication device causes the communication device to perform the method as described in the first aspect or the second aspect.

[0017] In a sixth aspect, embodiments of this disclosure provide a program product, including at least one of a program and instructions, wherein when the program and instructions are executed by a communication device, they implement the method described in the first aspect or the second aspect.

[0018] In this embodiment of the present disclosure, the first signal transmitted by the transmitting end during signal transmission is based on the aliased signal obtained by superimposing the baseband signal and the reference signal, thereby improving the utilization rate of data signal transmission resources; the receiving end can accurately obtain the second signal based on reception or processing. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings required for the description of the embodiments are introduced below. The following drawings are only some embodiments of this disclosure and do not impose specific limitations on the protection scope of this disclosure.

[0020] Figure 1 is an exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure;

[0021] Figures 2A and 2B are exemplary interactive schematic diagrams of the method provided according to embodiments of the present disclosure;

[0022] Figure 2C is a constellation diagram of aliasing signals provided according to an embodiment of the present disclosure;

[0023] Figure 2D is a schematic diagram of a first model provided according to an embodiment of the present disclosure;

[0024] Figures 3A to 3C are exemplary interactive schematic diagrams of the method provided according to embodiments of the present disclosure;

[0025] Figure 4 is an exemplary interactive schematic diagram of the method provided according to an embodiment of the present disclosure;

[0026] Figure 5A is a schematic diagram of the structure of a first device according to an embodiment of the present disclosure;

[0027] Figure 5B is a schematic diagram of the structure of a second device according to an embodiment of the present disclosure;

[0028] Figure 6A is a schematic diagram of a communication device according to an embodiment of the present disclosure;

[0029] Figure 6B is a schematic diagram of a communication device according to an embodiment of the present disclosure. Detailed Implementation

[0030] This disclosure provides a communication method, communication device, communication system, storage medium, and program product.

[0031] In a first aspect, embodiments of this disclosure provide a communication method, executed by a first device, the method comprising:

[0032] The device receives a first signal sent by a second device, wherein the first signal is a mixed signal generated by superimposing a baseband signal and a reference signal, and the baseband signal is a data signal after modulation of the transmitted bit stream.

[0033] Determine the second signal corresponding to the baseband signal.

[0034] In the above embodiments, the first signal transmitted by the transmitting end in signal transmission is based on the aliased signal obtained by superimposing the baseband signal and the reference signal, thereby improving the utilization rate of data signal transmission resources; the receiving end can accurately obtain the second signal based on reception or processing.

[0035] In conjunction with the embodiments of the first aspect, in some embodiments, determining the second signal corresponding to the baseband signal includes:

[0036] Determine the second signal output by the first model.

[0037] In conjunction with the embodiments of the first aspect, in some embodiments, the input to the first model includes at least one of the following:

[0038] The resource grids corresponding to different receiving antennas after the first device receives the first signal;

[0039] The second device sends the resource grid corresponding to the reference signal in the first signal.

[0040] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0041] The first signal is de-orthogonal frequency division multiplexing (OFDM) modulation to obtain the resource grid corresponding to different receiving antennas.

[0042] In conjunction with the embodiments of the first aspect, in some embodiments, determining a second signal corresponding to the baseband signal includes:

[0043] The second signal output by the first model is determined based on the resource grid corresponding to different receiving antennas and the resource grid corresponding to the reference signal.

[0044] In conjunction with the embodiments of the first aspect, in some embodiments, the input of the first model further includes at least one of the following:

[0045] The first power allocation factor corresponding to the baseband signal in the aliased signal;

[0046] The second power allocation factor corresponding to the reference signal in the aliased signal.

[0047] In conjunction with the embodiments of the first aspect, in some embodiments, determining the second signal corresponding to the baseband signal includes:

[0048] The output of the first module in the first model is determined based on the resource grid corresponding to different receiving antennas and / or the resource grid corresponding to the reference signal.

[0049] The second signal output by the second module in the first model is determined based on one or more of the output of the first module, the resource grid corresponding to the reference signal, the first power allocation factor, and the second power allocation factor.

[0050] The first model includes a first module and a second module.

[0051] In conjunction with the embodiments of the first aspect, in some embodiments, the output of the first module is an aliased signal, and the second module includes a first layer and a second layer that do not have learning capabilities;

[0052] Based on the output of the first module, the symbol of the reference signal in the transmitted resource grid, the first power allocation factor, and the second power allocation factor, the second signal output by the second module in the first model is determined, including:

[0053] The output of the first layer is determined based on the aliasing signal output by the first module, the sign of the reference signal in the transmission resource grid, and the second power allocation factor.

[0054] The second signal of the second layer output is determined based on the output of the first layer and the first power allocation factor.

[0055] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0056] Receive indication information sent by the second device, the indication information indicating at least one of the following:

[0057] The resource grid corresponding to the reference signal;

[0058] First power allocation factor;

[0059] Second power allocation factor;

[0060] The time slot where the aliased signal is located.

[0061] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0062] The first model is trained on the dataset until it converges; the dataset includes the input dataset and the output label values.

[0063] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0064] The bit stream to be transmitted is determined based on the second signal.

[0065] In conjunction with the embodiments of the first aspect, in some embodiments, the Physical Downlink Control Channel (PDCCH), the Physical Downlink Shared Channel (PDSCH), and a reference signal are transmitted in the time slot where the aliased signal resides; or,

[0066] The Physical Uplink Control Channel (PUCCH), Physical Uplink Shared Channel (PUSCH), and reference signal are transmitted in the time slot where the aliasing signal is located.

[0067] The reference signal is the demodulation reference signal (DMRS), and the baseband signal carries PDSCH data or PUSCH data.

[0068] Secondly, embodiments of this disclosure provide a communication method executed by a second device, the method comprising:

[0069] Based on the baseband signal and the reference signal, the aliased signal generated by superposition is determined, wherein the baseband signal is the data signal after modulation of the transmitted bit stream;

[0070] Based on the aliasing signal, a first signal is sent to the first device, wherein the first signal is used by the first device to determine the second signal corresponding to the baseband signal.

[0071] In conjunction with embodiments of the second aspect, in some embodiments, the second signal is determined according to the first model.

[0072] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0073] Power normalization is performed on the baseband signal and the reference signal;

[0074] Power is allocated to the baseband signal and the reference signal based on the first power allocation factor and the second power allocation factor.

[0075] In conjunction with embodiments of the second aspect, in some embodiments, determining the superimposed aliased signal based on the baseband signal and the reference signal includes:

[0076] The data symbols in the baseband signal and the pilot symbols of the reference signal are superimposed and mapped onto the first resource element (RE) to determine the aliasing signal; wherein, the first RE includes REs other than the REs where the PDCCH or PUCCH is located in the resource grid.

[0077] In conjunction with embodiments of the second aspect, in some embodiments, the first power allocation factor or the second power allocation factor satisfies one of the following:

[0078] The second device is determined based on the second model, wherein the second model is used to determine the first power allocation factor and the second power allocation factor corresponding to each RE according to the channel information of different REs;

[0079] The second device is determined based on a third model, wherein the third model is used to determine the first power allocation factor and the second power allocation factor shared by different REs based on channel information;

[0080] Configured for network devices;

[0081] This is reported by the terminal.

[0082] In conjunction with the embodiments of the second aspect, in some embodiments, the input to the first model includes at least one of the following:

[0083] The resource grids corresponding to different receiving antennas after the first device receives the first signal;

[0084] The second device sends the resource grid corresponding to the reference signal in the first signal.

[0085] In conjunction with the embodiments of the second aspect, in some embodiments, the first model includes a first module.

[0086] In conjunction with the embodiments of the second aspect, in some embodiments, the input to the first model includes at least one of the following:

[0087] The first power allocation factor corresponding to the baseband signal in the aliased signal;

[0088] The second power allocation factor corresponding to the reference signal in the aliased signal.

[0089] In conjunction with the embodiments of the second aspect, in some embodiments, the first model includes a first module and a second module;

[0090] The first module outputs an aliased signal, and the second module includes a first layer and a second layer that do not have learning capabilities. The second layer determines the baseband signal.

[0091] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0092] Send an instruction message to the first device, the instruction message indicating at least one of the following:

[0093] The resource grid corresponding to the reference signal;

[0094] First power allocation factor;

[0095] Second power allocation factor;

[0096] The time slot where the aliased signal is located.

[0097] In conjunction with the embodiments of the second aspect, in some embodiments, the physical downlink control channel (PDCCH), the physical downlink shared channel (PDSCH), and a reference signal are transmitted in the time slot where the aliasing signal resides; or,

[0098] The physical uplink control channel PUCCH, the physical downlink shared channel PUSCH, and reference signals are transmitted in the time slot where the aliasing signal is located.

[0099] The reference signal is the demodulation reference signal DM-RS, and the baseband signal carries PDSCH data or PUSCH data.

[0100] Thirdly, embodiments of this disclosure provide a communication device, wherein the communication device is used to perform the method described in the first aspect or the second aspect.

[0101] Fourthly, embodiments of this disclosure provide a communication system, including a first device and a second device, wherein,

[0102] The first device is configured to implement the method as described in the first aspect;

[0103] The second device is configured to implement the method as described in the second aspect.

[0104] Fifthly, embodiments of this disclosure provide a storage medium storing instructions, wherein...

[0105] When the instructions are executed on the communication device, the communication device causes the communication device to perform the method as described in the first aspect or the second aspect.

[0106] In a sixth aspect, embodiments of this disclosure provide a program product, including at least one of a program and instructions, wherein when the program and instructions are executed by a communication device, they implement the method described in the first aspect or the second aspect.

[0107] In a seventh aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the methods described in alternative implementations of the first and second aspects.

[0108] Eighthly, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the methods described according to optional implementations of the first and second aspects above.

[0109] It is understood that the aforementioned communication devices, communication systems, storage media, program products, computer programs, chips, or chip systems are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0110] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments. In all embodiments of this disclosure, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0111] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0112] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0113] In the embodiments disclosed herein, "multiple" refers to two or more.

[0114] In some embodiments, the terms “at least one of A or B, at least one of A and B”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0115] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of whether there is a branch B); in some embodiments, B (execute B regardless of whether there is a branch A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, both A and B are executed. The same applies when there are more branches such as A, B, C, etc.

[0116] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execute A regardless of whether a branch B exists); in some embodiments, B (execute B regardless of whether a branch A exists); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, and C.

[0117] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0118] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0119] In some embodiments, terms such as "time / frequency" and "time-frequency domain" refer to the time domain and / or frequency domain.

[0120] In some embodiments, terms such as “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “when…”, “if…”, etc. can be used interchangeably. These descriptions all refer to the device making a corresponding action under certain objective circumstances. They do not necessarily limit the time, nor do they require the device to make a judgment action when implementing it, nor do they mean that there must be other limitations.

[0121] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0122] In some embodiments, devices, etc., may be interpreted as physical or virtual, and their names are not limited to those described in the embodiments. Terms such as “device,” “equipment,” “circuit,” “network element,” “network function,” “network device,” “function,” “node,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” and “subject” are interchangeable.

[0123] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0124] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving cell," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0125] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0126] In some embodiments, access network devices, core network devices, or network devices can be replaced with terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced with communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, uplink link, downlink link, etc., can be replaced with sidelink link.

[0127] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0128] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0129] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0130] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0131] Figure 1 is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0132] As shown in Figure 1, the communication system 100 includes a first device 101 and a second device 102.

[0133] In this context, the first device 101 can be a receiving end or receiving device in communication, and the second device 102 can be a sending end or sending device in communication. For example, in uplink communication, the first device 101 is a network device, and the second device 102 is a terminal. As another example, in downlink communication, the first device 101 is a terminal, and the second device 102 is a network device. Yet another example is that the first device 101 is a terminal, and the second device 102 is another terminal.

[0134] In some embodiments, the terminal includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0135] In some embodiments, the network device may include at least one of an access network device and a core network device.

[0136] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The access network device may include at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system, but is not limited thereto.

[0137] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0138] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0139] In some embodiments, a core network device may be a single device comprising one or more network elements, or it may be multiple devices or a group of devices, each comprising all or part of one or more network elements. Network elements may be virtual or physical. The core network may include, for example, at least one of the following: Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC).

[0140] In some embodiments, core network equipment includes network elements with specific functions, such as Access Management Function (AMF) and Service Management Function (SMF).

[0141] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0142] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1 are illustrative. The communication system may include all or some of the main bodies in FIG1, or may include other main bodies outside of FIG1. ​​The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0143] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0144] In some implementations, the signal transmission process of a wireless communication system may include:

[0145] At the transmitting end: the transmitter encodes and modulates the source bit stream to obtain modulation symbols; it generates pilot symbols (or reference signals) for channel estimation at the receiving end, so that channel estimation can be completed at the receiving end; finally, the data symbols and pilot symbols are inserted into the resource grid to form an Orthogonal Frequency Division Multiplexing (OFDM) transmission signal; the OFDM signal reaches the receiving end through the channel.

[0146] At the receiving end: the receiver can use pilot symbols to perform channel estimation, and then perform subsequent data symbol detection, demodulation, decoding and other steps to obtain the final recovered bit stream.

[0147] In some implementations, due to the complexity and time-varying nature of the wireless channel environment, the receiver's estimation and recovery of the wireless channel directly affects the final data recovery performance. The transmitter allocates information data symbols and specific pilot symbols known to the receiver at different resource locations, such as demodulation reference signals (DMRS) and phase tracking reference signals (PTRS). During the channel estimation phase, the receiver can estimate the channel information at the resource location where the pilot symbols are placed based on the actual pilot symbols and the received pilot symbols; and recover the full channel information (e.g., using interpolation algorithms) based on the estimated channel information at the pilot locations for subsequent data recovery. Channel estimation methods, for example, utilize minimum mean-square error (MMSE).

[0148] In some implementations, data symbols and pilot symbols are placed at different resource locations. For example, in 5G NR, data symbols and pilot symbols are independent and orthogonal on time-frequency resources; that is, only one type of resource symbol, either a data symbol or a pilot symbol, can be placed at the same resource location. Given a fixed total transmission resource, pilot and data symbols compete for transmission resources. Increased resource overhead for pilots means less resource available for data transmission, resulting in relatively low data transmission resource utilization.

[0149] In some implementations, there is a lack of ways to improve the utilization of data transmission resources, and it is necessary to ensure that the receiving end can receive data accurately.

[0150] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2A, the present disclosure relates to a communication method, which includes:

[0151] In step S2101, the second device 102 determines whether to perform aliasing transmission in the first time slot.

[0152] In some embodiments, the second device 102 is a transmitting device, which may be a terminal in uplink communication or a network device in downlink communication.

[0153] Optionally, some embodiments of this disclosure are described using the second device 102 as a network device and the first device 101 as a terminal as an example. When the second device 102 is a terminal and the first device 101 is a network device, the description of this part of the embodiments can be referred to.

[0154] In some embodiments, the first time slot represents a specific time slot or sub-time slot, or any time slot or sub-time slot. For example, the second device 102 can determine whether each time slot is subject to aliasing transmission.

[0155] In some embodiments, aliasing transmission can refer to a signal transmission method in which the second device 102 superimposes the baseband signal and the reference signal to form an aliased signal, and then transmits the first signal to the first device 101. See the description of the embodiments below for details.

[0156] In some embodiments, the second device 102 determines the information transmitted on each time slot based on the protocol definition and / or the configuration of the network device, according to the resource grid corresponding to each time slot.

[0157] Optionally, for downlink transmission, when only PDCCH, PDSCH and DMRS are transmitted in a time slot, the second device 102 can determine that the time slot needs to be aliased.

[0158] Optionally, for uplink transmission, when only PUCCH, PUSCH and DMRS are transmitted in a time slot, the second device 102 can determine that the time slot needs to be aliased.

[0159] In some embodiments, the second device 102 can indicate to the first device 101 the time slot where aliasing transmission is required, or the time slot where the aliasing signal is located, by sending indication information. For example, in downlink communication, the network device indicates to the terminal the time slot where the aliasing signal is located.

[0160] In step S2102, the second device 102 determines the baseband signal based on the transmitted bit stream.

[0161] In some embodiments, the transmitted bit stream can be obtained by source bit stream through source coding and channel coding.

[0162] Optionally, the transmitted bit stream may include data or information that the sender needs to transmit.

[0163] Optionally, the bit stream to be transmitted may include the bit stream to be transmitted when the second device needs to transmit the first signal.

[0164] In some embodiments, the second device 102 can perform constellation modulation on the transmitted bit stream to determine the baseband signal.

[0165] Optionally, the second device 102 can map the transmitted bit stream to the corresponding resource grid (or transmission resource grid) based on the protocol definition or network device configuration to obtain the baseband signal.

[0166] Optionally, several bits in the transmitted bit stream can be mapped to a resource grid (RE).

[0167] Optionally, the horizontal axis in the resource grid represents symbols, and the vertical axis represents subcarriers. PDCCH or PUCCH and baseband signals can reside on the same resource grid, where the baseband signal represents PDSCH data or PUSCH data. The first two symbols in this resource grid can be mapped to PDCCH or PUCCH, and the remaining symbols can be mapped to baseband signals.

[0168] Optionally, in the resource grid corresponding to the aliased signal, the first two symbols are still PDCCH or PUCCH, and the other symbols can be aliased symbols of baseband signal and reference signal.

[0169] In some embodiments, the baseband signal is a modulated data signal of the transmitted bit stream. Alternatively, the baseband signal is a signal carrying data information.

[0170] Optionally, the constellation diagram corresponding to the baseband signal can be referenced as shown in Figure 2C. This baseband signal can be the constellation diagram obtained after the transmitted bit stream has been modulated by 16QAM.

[0171] In some embodiments, baseband signals, data signals, data symbols, modulation symbols, and data modulation symbols may indicate the same meaning and are interchangeable. Alternatively, in the resource grid corresponding to the baseband signal, the baseband signal may include data symbols, modulation symbols, or data modulation symbols, wherein each data symbol or modulation symbol corresponds to one RE in the resource grid.

[0172] Alternatively, the data symbol can correspond to PDSCH or PUSCH.

[0173] In step S2103, the second device 102 determines the aliasing signal based on the baseband signal and the reference signal.

[0174] In some embodiments, reference signals, pilots, pilot signals, pilot symbols, etc., can indicate the same meaning and are interchangeable. Alternatively, in the resource grid corresponding to the reference signal, the reference signal may include pilot symbols, wherein each pilot symbol corresponds to an RE in the resource grid.

[0175] In some embodiments, the aliasing signal may include aliasing symbols, each aliasing symbol corresponding to a RE in the resource grid.

[0176] In some embodiments, the constellation diagram of the reference signal may be shown in FIG2C.

[0177] In some embodiments, the second device 102 may select the resource grid of the corresponding reference signal after mapping the transmitted bit stream to a baseband signal, based on a protocol definition or network device configuration.

[0178] In some embodiments, as shown in the constellation diagram of FIG2C, the baseband signal and the reference signal can be superimposed to generate an aliased signal.

[0179] In some embodiments, the time slot containing the aliased signal transmits PDCCH, PDSCH, and DMRS, or transmits PUCCH, PUSCH, and DMRS.

[0180] In some embodiments, within the resource grid, the REs containing PDSCH and DMRS in a time slot are overlaid or aliased, or the REs containing PUSCH and DMRS in a time slot are overlaid or aliased. The REs containing PDCCH or PUCCH in a time slot are not overlaid or aliased.

[0181] For example, for downlink time slots on the base station side, if only PDCCH, PDSCH, and DM-RS signals exist in the resource grid, then the PDSCH and DM-RS signals are normalized and superimposed according to the power allocation factor in the following manner to form aliased symbols and allocated on REs other than PDCCH.

[0182] In some embodiments, step S2103 may include the following steps S2103-11 to S2103-12:

[0183] Step S2103-11: Perform power normalization processing on the baseband signal and the reference signal.

[0184] In this step, power normalization processing can be performed on the data symbols in the baseband signal and the pilot symbols in the reference signal, for example, power normalization processing can be performed on the PDSCH or PUSCH and DMRS symbols.

[0185] Step S2103-12: Perform power allocation on the baseband signal and the reference signal according to the first power allocation factor and the second power allocation factor.

[0186] In this step, power allocation and amplitude allocation can be interchanged.

[0187] In this step, the data symbols and pilot symbols are amplitude-allocated according to power based on the first power allocation factor β and the second power allocation factor α. For example, the PDSCH or PUSCH symbols are amplitude-allocated with the DMRS symbols according to power.

[0188] In this step, the first power allocation factor is the allocation factor corresponding to the data symbol, and the second power allocation factor is the allocation factor corresponding to the pilot symbol.

[0189] In some embodiments, after power allocation, the baseband signal and the reference signal can be superimposed or aliased.

[0190] In some embodiments, the data symbols in the baseband signal and the symbols of the reference signal are superimposed and mapped onto a first resource unit (RE) to determine the aliasing signal; wherein, the first RE includes REs other than the REs where the PDCCH or PUCCH is located in the resource grid corresponding to the baseband signal or the aliasing signal.

[0191] For example, aliased symbols, which are superimposed on data symbols and pilot symbols, are assigned to REs in the resource grid other than PDCCH.

[0192] In some embodiments, the first power allocation factor or the second power allocation factor can be determined in a variety of ways.

[0193] In one example, the first power allocation factor or the second power allocation factor is determined by the second device based on a second model, wherein the second model is used to determine the first power allocation factor and the second power allocation factor corresponding to each RE based on the channel information of different REs.

[0194] In this example, the second model is a neural network model, which performs power allocation on different REs. For example, the pilot symbols and data symbols are normalized in power, and then the neural network model is used to generate power allocation factors α and β on each RE according to the channel conditions of each RE. The power of the data symbols and pilot symbols is then allocated and superimposed on each RE.

[0195] In one example, the first power allocation factor or the second power allocation factor is determined by the second device based on a third model, wherein the third model is used to determine the first power allocation factor and the second power allocation factor shared by different REs based on channel information.

[0196] In this example, the third model can be a different neural network model than the second model, and power allocation for all REs can be performed according to the neural network model. For example, power normalization is performed on pilot symbols and data symbols, and then the neural network model is used to generate power allocation factors α and β shared by all REs based on the overall channel conditions, and power allocation for data symbols and pilot symbols is performed and superimposed on all REs.

[0197] In one example, either the first power allocation factor or the second power allocation factor is configured by the network device. In this example, power allocation can be performed according to a fixed configuration on the network side. Power normalization is performed on pilot and data symbols, and then power allocation is performed and superimposed on all data and pilot symbols on all REs according to the given power allocation factors α and β.

[0198] In this example, the network device can indicate the power allocation factor α and / or β to the terminal by sending indication information or configuration information.

[0199] In one example, either the first power allocation factor or the second power allocation factor is reported by the terminal. In this example, the terminal can report power allocation factors α and β to the network device, and the network side performs power allocation according to the information fed back by the user. Power normalization is performed on the pilot symbols and data symbols, and then the power allocation factors α and β fed back by the user are used to allocate and superimpose the power for the pilot and data modulation symbols on all REs.

[0200] In some embodiments, the baseband signal is superimposed with the reference signal to achieve non-orthogonal transmission of pilot and data, thereby sharing the time and frequency resources of both. While ensuring the bit error rate performance of data transmission, the amount of data transmitted is increased, effectively increasing the data throughput of the link.

[0201] In step S2104, the second device 102 sends a first signal to the first device 101 based on the aliasing signal.

[0202] In some embodiments, after the second device 102 obtains the aliasing signal, such as the aliasing signal shown in FIG2C, the second device 102 can perform subsequent processing based on the aliasing signal, such as performing digital precoding, analog precoding and OFDM modulation on the aliasing signal to obtain the first signal.

[0203] Optionally, the first signal can be an OFDM signal.

[0204] In some embodiments, after receiving the first signal, the second device 102 sends the first signal to the first device 101.

[0205] In some embodiments, the first device 101 receives a first signal.

[0206] Optionally, the second device 102 transmits a first signal via an antenna, which is then transmitted through a channel and received by the antenna of the first device 101. For example, the base station antenna transmits the first signal, which is then transmitted through a channel and received by the terminal antenna.

[0207] In step S2105, the first device 101 performs OFDM modulation on the first signal.

[0208] In some embodiments, after the first device 101 receives the first signal through an antenna, it can perform OFDM demodulation on the first signal to obtain resource grids corresponding to different receiving antennas. Each resource grid corresponding to a receiving antenna may include multiple REs. Each RE may correspond to one symbol, and each resource grid corresponding to a receiving antenna may include multiple symbols.

[0209] Optionally, the resource grid corresponding to different receiving antennas can be used to determine the second signal described below.

[0210] Optionally, the resource grid corresponding to different receiving antennas can be used as input to the first model described below.

[0211] For example, the information corresponding to all REs on the resource grid corresponding to different receiving antennas can be used as input to the first model described below. The information on each RE can be represented by the corresponding real and imaginary parts. In step S2106, the first device 101 determines the second signal corresponding to the baseband signal.

[0212] Optionally, in some embodiments, determining the second signal corresponding to the baseband signal includes:

[0213] The second signal corresponding to the baseband signal is determined based on at least one of the following:

[0214] The resource grid corresponding to different receiving antennas after the first device receives the first signal;

[0215] The second device sends the resource grid corresponding to the reference signal in the first signal.

[0216] In some embodiments, the first device 101 may determine the second signal corresponding to the baseband signal based on the first model.

[0217] Optionally, the first device 101 acquires the second signal determined by the first model.

[0218] Optionally, the second signal determined by the first model can be the second signal output by the first model.

[0219] Optionally, the second signal is the output of the first model, which may be the prediction result, output result, or inference result of the first model.

[0220] Optionally, the second signal corresponding to the baseband signal can represent the baseband signal predicted or inferred by the first model, or the baseband signal output by the model.

[0221] In some embodiments, the first model may also be referred to as the first function, which can predict and deduce the baseband signal corresponding to the first signal sent by the second device 102.

[0222] In some embodiments, the first model is a neural network model or an AI-based model.

[0223] In some embodiments, the second signal corresponding to the baseband signal output by the first model can be represented by X.

[0224] Optionally, the second signal output by the first model is the equalized baseband signal obtained after model inference.

[0225] Optionally, the input to the first model includes any one or any combination of the following (1)-(4):

[0226] (1) The resource grids corresponding to different receiving antennas after the first device receives the first signal;

[0227] (2) The second device sends the resource grid corresponding to the reference signal in the first signal;

[0228] (3) The first power allocation factor corresponding to the baseband signal in the aliased signal;

[0229] (4) The second power allocation factor corresponding to the reference signal in the aliased signal.

[0230] Optionally, the resource grids corresponding to different receiving antennas after the first device receives the first signal can be denoted as resource grids corresponding to different receiving antennas.

[0231] Optionally, the resource grid corresponding to different receiving antennas may include any of the following meanings: information corresponding to all REs in the resource grid corresponding to different receiving antennas (or the real and imaginary parts of all REs), the symbol of the resource grid corresponding to different receiving antennas, the symbol on the resource grid corresponding to the receiving antenna, etc.

[0232] Optionally, the resource grid corresponding to the reference signal may include any of the following meanings: information corresponding to all REs in the resource grid corresponding to the reference signal (or the real and imaginary parts of all REs), the symbol of the resource grid corresponding to the reference signal, the symbol of the reference signal on the transmitting resource grid, etc.

[0233] In some embodiments, the baseband signal can be determined through the following two implementations based on a first model with different model structures.

[0234] In the first embodiment, as shown in case 1 of FIG2D, the first model includes a module, denoted as the first module.

[0235] Optionally, the first module may include two parts: a convolutional module and a fully connected module. The model structure and parameter tuning can be seen in the model training process shown in Figure 2B.

[0236] In this embodiment, the input to the first model includes at least one of the following:

[0237] The resource grids corresponding to different receiving antennas after the first device receives the first signal are represented by Y.

[0238] The second device transmits the resource grid corresponding to the reference signal in the first signal, denoted by P.

[0239] In this embodiment, based on the first model, the first model can output a second signal X according to the inputs Y and P.

[0240] In the second embodiment, as shown in cases 2 to 3 of FIG2D, the first model includes multiple modules, such as a first module and a second module.

[0241] Optionally, the first module may include two parts: a convolutional module and a fully connected module. The second module may include a symbolic recovery module. The model structure and parameter tuning can be seen in the model training process shown in Figure 2B.

[0242] Optionally, the output of the first module in the first model is determined based on the resource grid corresponding to different receiving antennas and / or the resource grid corresponding to the reference signal.

[0243] For example, the output of the first module is determined based on the resource grid corresponding to different receiving antennas.

[0244] For example, the output of the first module is determined based on the resource grid corresponding to different receiving antennas and the resource grid corresponding to the reference signal.

[0245] Optionally, based on Y and P, the input of the first model in this embodiment may include at least one of the following:

[0246] The first power allocation factor β corresponding to the baseband signal in the aliased signal;

[0247] The second power allocation factor α corresponding to the reference signal in the aliased signal.

[0248] Optionally, the aliased signal is... express.

[0249] In one example of this embodiment, the inputs of the first model include: the input of the first module: the resource grid corresponding to different receiving antennas of the first device, i.e., Y; and the input of the second module: the resource grid (i.e., P) corresponding to the reference signal of the second device, a first power allocation factor β, and a second power allocation factor α. In this example, the first module obtains its output based on the input Y; and inputs at least one or more of the output of the first module, P, α, and β to the second module, thereby outputting a second signal X through the second module.

[0250] In another example of this embodiment, the inputs of the first model include: the inputs of the first module include: resource grids (i.e., Y) corresponding to different receiving antennas, and resource grids (i.e., P) corresponding to the reference signal of the second device; and the inputs of the second module include: P, a first power allocation factor β, and a second power allocation factor α. In this example, the first module obtains its output based on the inputs Y and P; and inputs at least one or more of the output of the first module, P, α, and β to the second module, through which the second module outputs a second signal X.

[0251] In this embodiment, when the first model includes a first module and a second module, the output of the second module is the second signal X, and the output of the first module is an intermediate output.

[0252] In this embodiment, the output of the first module is the predicted aliasing signal.

[0253] Alternatively, the baseband signal and the reference signal can be mixed or superimposed in the following ways:

[0254] Where Y represents the resource grid corresponding to different receiving antennas of the first device or the symbol on the resource grid corresponding to different receiving antennas, referring to the input of the first model in the following embodiment; P represents the resource grid corresponding to the reference signal of the second device or the symbol on the resource grid corresponding to the reference signal; α is the second power allocation factor; β is the first power allocation factor; and H represents the number of hidden layers set in the first model. This indicates an aliasing signal.

[0255] Alternatively, based on the aliased signal, the following method can be used to recover the baseband signal X:

[0256] Optionally, the second module includes a first layer and a second layer that do not have learning capabilities, where the first and second layers are lambda layers. "Not having learning capabilities" means that the parameters of the lambda layers do not change as the model is trained or learns.

[0257] For the first layer, i.e., the first Lambda layer, the aliased signal output by the first module can be... As input, subtract the pilot symbol after power factor α allocation corresponding to the pilot signal. Obtain the output of the first layer;

[0258] For the second layer, i.e. the second Lambda layer, the output of the first layer can be used as input. The output of the first layer is divided by the power factor β corresponding to the baseband signal to output the second signal, thus completing the recovery of the baseband signal.

[0259] Optionally, the second layer can output the real and imaginary parts of the baseband signal on each RE.

[0260] In some embodiments, the first model in this step is a model that has been trained and converged, and the training method of the model can be found in the embodiment of Figure 2B.

[0261] In some embodiments, during downlink communication, the first model can be deployed on the user side, and model inference is performed on the user side. For example, the first device 101 performing this step of model inference can be a terminal.

[0262] In some embodiments, during uplink communication, the first model can be deployed on the network side, and model inference is performed on the network side. For example, the first device 101 performing this step of model inference can be a network device.

[0263] In some embodiments, the receiver can use the trained model to perform model inference, perform signal equalization based on the model, and infer the baseband signal that can be reflected as a constellation diagram from the received signal, thereby optimizing the bit error rate performance of traditional demodulation schemes.

[0264] In step S2107, the first device 101 determines the bit stream to be transmitted based on the second signal.

[0265] In some embodiments, after the first device 101 outputs the equalized baseband signal, i.e., the second signal, based on the first model, the second signal can be demapped to restore the bit stream of the transmitting end.

[0266] Optionally, in this step, the transmitted bit stream is also the received bit stream. The received bit stream recovered by the first device 101 should be the same as the transmitted bit stream of the second device 102.

[0267] In some embodiments, the first device 101 may demap the second signal in a variety of ways.

[0268] Optionally, the first device 101 performs constellation demapping using non-AI techniques, such as maximum likelihood estimation.

[0269] Optionally, the first device 101 uses AI technology to perform constellation demapping, inputs the equalized baseband signal into the AI ​​model, and outputs the demapped bitstream through the model.

[0270] In some embodiments, after the first device 101 recovers the transmitted bit stream, it can perform subsequent processing on the transmitted bit stream based on the protocol definition, including but not limited to descrambling, dechannel coding, and decyclic redundancy check (CRC) coding.

[0271] In some embodiments, the above embodiments utilize a neural network model to jointly process channel estimation, equalization, and other modules at the receiving end. This can reduce the bit error rate in the demodulation process of non-orthogonal pilot and data superposition transmission. Simultaneously, the model input is flexible, enabling demodulation under multi-layer data transmission while maintaining performance, thus improving demodulation performance under multi-layer data transmission. The improved model performance compared to traditional demodulation schemes under aliased symbol transmission allows the transmitting end to process the transmitted bitstream with higher-order constellation modulation, thereby increasing the data throughput of the link while ensuring performance, meeting the service requirements of next-generation wireless networks.

[0272] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0273] In some embodiments, the terms "uplink", "uplink", and "physical uplink" can be used interchangeably, as can the terms "downlink", "downlink", and "physical downlink", as well as the terms "sidelink", "sidelink", "sidelink communication", "sidelink communication", "direct connection", "direct link", "direct communication", and "direct link communication".

[0274] In some embodiments, the terms “downlink control information (DCI),” “downlink (DL) assignment,” “DL DCI,” “uplink (UL) grant,” and “UL DCI” can be used interchangeably.

[0275] In some embodiments, terms such as "physical downlink shared channel (PDSCH)" and "DL data" can be used interchangeably, as can terms such as "physical uplink shared channel (PUSCH)" and "UL data".

[0276] In some embodiments, the terms “radio”, “wireless”, “radio access network (RAN)”, “access network (AN)”, and “RAN-based” can be used interchangeably.

[0277] In some embodiments, terms such as “moment,” “point in time,” “time,” and “time location” can be used interchangeably, as can terms such as “duration,” “segment,” “time window,” “window,” and “time.”

[0278] In some embodiments, "acquire," "get," "obtain," "receive," "transmit," "bidirectional transmission," and "send and / or receive" can be used interchangeably and can be interpreted as receiving from other entities, acquiring from protocols, acquiring from higher layers, obtaining through self-processing, or autonomous implementation. Protocols include, for example, at least one of the 3GPP protocol, Wi-Fi protocol, and audio and / or video protocols.

[0279] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transmit,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0280] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0281] In some embodiments, the determination or judgment can be made by a value represented by 1 bit (0 or 1), or by a true or false value (boolean), or by a comparison of numerical values ​​(e.g., a comparison with a predetermined value), but is not limited thereto.

[0282] In some embodiments, if an arrow in the interaction diagram representing the sending of information, signaling, etc. from one subject to another passes through other subjects, it can be interpreted as the information being forwarded from one subject to another via other subjects, or it can be interpreted as the information being sent from one subject to another without passing through other subjects.

[0283] The measurement method disclosed herein may include at least one of steps S2101 to S2107, wherein each step may be implemented as an independent embodiment, or two or more steps may be combined as an independent embodiment. For example, step S2106 may be implemented as an independent embodiment, steps S2104 and S2106 may be implemented as independent embodiments, and step S2103 may be implemented as an independent embodiment, but is not limited thereto.

[0284] In some embodiments, at least one of steps S2101 to S2105 and S2107 is optional. In different embodiments, one of these steps may be selected for execution, or one or more of these steps may be omitted or substituted in different embodiments.

[0285] In some embodiments, steps S2101, S2102, S2105, and S2107 are optional, and one of them may be performed in different embodiments, or one or more of these steps may be omitted or substituted in different embodiments.

[0286] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0287] In this embodiment, at the transmitting end, pilot signals and data can be transmitted in a non-orthogonal manner in the time and frequency domains, thereby breaking the resource competition between the two and sharing wireless transmission resources. At the receiving end, effective data reception is achieved from the mixed transmission of pilot signals and data based on a model, replacing the channel estimation and equalization process performed by the user side after receiving the base station signal. This ensures the equivalent effect of transmission resources for data reception and improves the overall system transmission gain.

[0288] Figure 2B is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2B, the present disclosure relates to a communication method, which includes:

[0289] In step S2201, the second device 102 determines whether to perform aliasing transmission in the first time slot.

[0290] In some embodiments, the implementation of step S2201 is described in the embodiment of step S2101 in FIG2A, and will not be repeated here.

[0291] In step S2202, the second device 102 determines the baseband signal based on the transmitted bit stream.

[0292] In some embodiments, the implementation of step S2202 is described in the embodiment of step S2102 in FIG2A, and will not be repeated here.

[0293] In some embodiments, during the model training phase, the second device 102 needs to retain the transmitted bitstream as part of the training dataset.

[0294] In step S2203, the second device 102 determines the aliasing signal based on the baseband signal and the reference signal.

[0295] In some embodiments, the implementation of step S2203 is described in the embodiment of step S2103 in FIG2A, and will not be repeated here.

[0296] In some embodiments, during the model training phase, the second device 102 needs to retain the reference signal as part of the training dataset.

[0297] In some embodiments, during the model training phase, the second device 102 needs to store the first power allocation factor and the second power allocation factor as part of the training dataset.

[0298] In step S2204, the second device 102 sends a first signal to the first device 101 based on the aliasing signal.

[0299] In some embodiments, the implementation of step S2204 is described in the embodiment of step S2104 in FIG2A, and will not be repeated here.

[0300] In step S2205, the first device 101 performs OFDM modulation demodulation on the first signal.

[0301] In some embodiments, the implementation of step S2204 is described in the embodiment of step S2104 in FIG2A, and will not be repeated here.

[0302] In some embodiments, during the model training phase, the first device 101 needs to retain the resource grids corresponding to different receiving antennas, such as the symbols on the resource grids of each receiving antenna, as part of the training dataset.

[0303] In step S2206, the first device 101 or the second device 102 trains the first model based on the training dataset.

[0304] In some embodiments, all or part of the datasets held by the first device 101 and the second device 102 are aggregated.

[0305] Optionally, at the transmitting end, one or more of the following can be retained: the transmitted bit stream of the second device 102, the reference signal (or the resource grid corresponding to the reference signal), the first power allocation factor, and the second power allocation factor.

[0306] Optionally, at the receiving end, the resource grids corresponding to different receiving antennas obtained by the first device 102 from the OFDM demodulation of the first signal are retained.

[0307] Optionally, some or all of the above datasets may be collected during the training phase of the first model, or they may be collected within a historical period set before training.

[0308] In some embodiments, the first model can be applied or used for inference after it has been trained.

[0309] In some embodiments, the first model can be trained continuously or in real time. For example, after the first model is trained, it can continue to update the trained first model based on the dataset within a set time period to optimize or update the model parameters of the first model.

[0310] Optionally, in this embodiment, the first device 101 and the second device 102 can aggregate the dataset within the set time period.

[0311] In some embodiments, the aforementioned dataset can be aggregated on the first device 101 side, such as when the second device 102 reports the retained dataset to the first device, and the first device trains the first model. Alternatively, the aforementioned dataset can be aggregated on the second device 102 side, such as when the first device reports the retained dataset to the second device, and the second device trains the first model.

[0312] Optionally, the datasets collected by the first device 101 and the datasets collected by the second device 102 are aggregated on the first device 101. The first device 101 trains a first model, and the trained first model can be deployed and used on the first device 101.

[0313] Optionally, the datasets collected by the first device 101 and the datasets collected by the second device 102 are aggregated on the first device 101. The first device 101 trains a first model, and the trained first model can be deployed and used on the second device 102.

[0314] Optionally, the datasets collected by the first device 101 and the datasets collected by the second device 102 are aggregated on the second device 102. The second device 102 trains the first model, and the trained first model can be deployed and used on the first device 101.

[0315] Optionally, the datasets collected by the first device 101 and the datasets collected by the second device 102 are aggregated on the second device 102. The second device 102 trains the first model, and the trained first model can be deployed and used on the second device 102.

[0316] Optionally, one of the first device 101 and the second device 102 can be a terminal and the other a network device. For example, taking the above optional example, with the second device 102 as a network device, the second device 102 can collect the training dataset and train the first model. The first device 101 is the terminal at this time, and the first device 101 can report the collected training dataset to the second device 102.

[0317] In some embodiments, the above training dataset includes an input dataset and output label values.

[0318] Optionally, the input dataset includes the inputs of the first model during the training phase. For example, the input dataset may include at least one or more of the following combinations obtained during the training phase:

[0319] The resource grids corresponding to different receiving antennas after the first device receives the first signal;

[0320] The second device sends the resource grid corresponding to the reference signal in the first signal;

[0321] The first power allocation factor corresponding to the baseband signal in the aliased signal;

[0322] The second power allocation factor corresponding to the reference signal in the aliased signal.

[0323] Optionally, the output label value is used to verify the output of the first model during the training phase. For example, during the training phase, the output of the training phase is obtained based on the input of the first model. By calculating the loss value between the output of the training phase and the output label value, the model parameters of the first model are adjusted to improve the accuracy of the prediction of the first model.

[0324] Optionally, the output label value can be called the truth value.

[0325] Optionally, the output label value may include: the baseband signal actually transmitted by the transmitter, such as the second device 102, during the training phase, or the transmitted bit stream involved in the actual transmitted signal.

[0326] In some embodiments, before training the first model, the second device 102 may first determine the input and output of the first model, thereby determining the model structure of the first model.

[0327] Alternatively, referring to Figure 2D, the first model can have three types:

[0328] In the first example, as shown in case 1 of Figure 2D, the first model includes a first module. The inputs to the first model include: resource grids (Y) corresponding to different receiving antennas of the first device, and resource grids (P) corresponding to the reference signal; the output includes: a second signal X.

[0329] In this example, the baseband signal X corresponding to the transmitted bit stream is inferred from Y and P. The model structure or parameters of the training model can be determined based on the size of the resource grid (i.e., the number of subcarriers and symbols) and the specific training task characteristics and training requirements.

[0330] In the second example, as shown in case 2 of Figure 2D, the first model includes a first module and a second module. The inputs to the first module include: a symbol (Y) on the resource grid corresponding to the receiving antenna of the first device. The inputs to the second module include: a symbol (P) of the reference signal on the transmitting resource grid, a first power allocation factor β, and a second power allocation factor α. The output of the first model includes: a second signal X.

[0331] In the third example, as shown in case 3 of Figure 2D, the first model includes a first module and a second module. The inputs to the first module include: the resource grid (Y) corresponding to different receiving antennas of the first device, and the resource grid (P) corresponding to the reference signal of the second device. The inputs to the second module are: P, a first power allocation factor β, and a second power allocation factor α. The output of the first model includes the second signal X.

[0332] In the second and third examples, aliasing is obtained based on Y, with optional input P, ​​where Y and P are part of the input. After model inference, the aliased signal is obtained. Based on the non-learnable layer (such as the Lambda layer) added at the end of the first model, P, α, and β are used as inputs to the non-learnable layer to process the aliasing signal, thereby removing the influence of the reference signal and inferring the second signal X corresponding to the transmitted bit stream. The model structure or parameters of the training model can be determined according to the size of the resource grid (i.e., the number of subcarriers and symbols) and the specific training task characteristics and training requirements.

[0333] In Figure 2D This indicates an aliasing signal.

[0334] In some embodiments, the second device 102 uses a defined dataset and model structure to determine model parameters and a loss function.

[0335] In the first example above, the first module of the first model includes a convolutional module and a fully connected module (or a fully connected layer).

[0336] In this example, a convolutional module is formed by a convolutional layer, a batch normalization layer, and an activation function layer. The input size of the convolutional layer is equal to the number of user receiving antennas (L), the number of subcarriers (C) in the resource grid, the number of symbols (S) in the resource grid, and the real and imaginary parts of the symbols in each RE, all of which are of size 2. That is, the tensor size is (L, C, S, 2). The number of two-dimensional convolutional layers is set to S, corresponding to S convolutional modules, where the number of convolutional kernels in each two-dimensional convolutional layer is set to L. i The number of convolutional kernels needs to be set considering factors such as model size and generalization ability. For determining the composition of the S convolutional modules and the connection methods between them, the layer following each 2D convolutional layer is set as a batch normalization (BN) layer to address the vanishing gradient problem, normalize model weights, and improve the network's generalization ability. After the BN layer, a layer with ReLU activation function is added to process the output of the BN layer. Modules are connected using activation function layers to link the 2D convolutional layers. Multiple convolutional modules with different numbers of kernels can be connected in the model to enhance its learning ability on data.

[0337] In this example, in the fully connected module, the number of nodes in the input layer depends on the output size of the last convolutional module. The output matrix of the last convolutional module is flattened to transform it into one-dimensional data before being input into the fully connected layer. The number of nodes in the output layer depends on the size of the resource grid. Each RE corresponds to the real and imaginary parts of the baseband signal obtained from model inference on that RE. For example, the number of nodes in the output layer can be set to L*C*S*2. The number of hidden layers is set to H, and the number of nodes in each hidden layer is set to J. iThe number of hidden layers and nodes needs to take into account factors such as model size and model generalization ability.

[0338] Specifically, the process of determining the connection method between fully connected layers uses a fully connected approach, with the ReLU function as the activation function. Hidden layers are also fully connected, with the ReLU function used for activation. The connection between hidden layers and the output layer is also fully connected, with the ReLU function used for activation, thus outputting the real and imaginary parts of the baseband signal on each output node. By integrating the output results from each output node, the baseband signal corresponding to the transmitted bitstream can be deduced.

[0339] In this example, the loss function could be the mean squared error (MSE) loss function, etc.

[0340] In this example, the process of determining the hyperparameters of the network model can refer to setting the number of learning epochs to T. The setting of the number of learning epochs needs to weigh the impact on model training speed, training cost, and model training accuracy. An Adaptive Moment Estimation (Adam) optimizer is used, with the corresponding hyperparameters set to β1, β2, and ε; random weight initialization is chosen as the weight initialization method. Here, β1 represents the exponential decay rate of the first-moment estimation, β2 represents the exponential decay rate of the second-moment estimation, and ε represents a very small number to ensure numerical computation stability.

[0341] In the second example above, the first module of the first model includes a convolutional module and a fully connected module, and the second module includes a symbolic recovery module.

[0342] In this example, the descriptions of the convolutional and fully connected modules can be found in the previous example, and will not be repeated here.

[0343] In this example, the symbolic recovery module uses two non-learning lambda layers; that is, the parameters of the lambda layers do not change as the model learns. The input to the symbolic recovery module is the output of the fully connected module. Its number of nodes is exactly the same as the output nodes of the fully connected module. Assuming the fully connected module integrates the outputs of all nodes to a dimension of (L, C, S, 2), then the input and output dimensions of the symbolic recovery module are both (L, C, S, 2).

[0344] In this example, P, α, and β are used as inputs to a non-learnable layer. The aliasing of the reference signal and the baseband signal is as follows:

[0345] Therefore, for the aliasing symbols output by fully connected layers To recover the baseband signal X, the following steps are required:

[0346] In this example, the first Lambda layer takes the output of the fully connected layer as input and subtracts the pilot symbols after pilot power factor allocation. The second Lambda layer takes the output of the previous layer as input and divides the entire input by the data power allocation factor to recover the baseband signal. This outputs the real and imaginary parts of the baseband signal on each RE, allowing the inference of the baseband signal corresponding to the transmitted bitstream. By performing interference recovery of data symbols within the neural network model, a better performance gain is achieved.

[0347] In this example, the loss function could be the mean squared error (MSE) loss function, etc.

[0348] In this example, the process of determining the hyperparameters of the network model can refer to setting the number of learning epochs to T. The setting of the number of learning epochs needs to weigh the impact on model training speed, training cost, and model training accuracy. The Adam optimizer is used, and the corresponding hyperparameters are set to β1, β2, and ε; random weight initialization is selected as the weight initialization method.

[0349] In this example, a non-learnable module is added to the neural network model to perform the data symbol shift caused by the superimposed pilot within the model, and the output and label loss are forwarded to better enable the second module of the neural network model to learn.

[0350] In some embodiments, the various possible inputs described above are used as the input training dataset, and the baseband signal from the transmitter is used as the label value. The training loss value is calculated based on the baseband signal and label value output by the model. For example, the training loss value (loss) is calculated using MSE as the loss function.

[0351] Where I represents the amount of training data for the model, and yi represents the output result of the model after processing data i. This represents the label value of data i.

[0352] In some embodiments, the second device 102 updates the model parameters based on the training loss value, the model update method, and the selected hyperparameters, such as the stochastic gradient descent (SGD) algorithm, the Adam algorithm, etc., to update the parameters of the specific model layer.

[0353] Optionally, the SGD algorithm can be used to update the model parameters:

[0354] in, This represents the demodulation model parameters to be updated in round t. This represents the demodulation model parameters after the t-th round of updates. This represents the gradient of the training loss value calculated in round t. Let t represent the learning rate in round t.

[0355] In some embodiments, after the first model has been trained, for downlink communication, the first model can be deployed on the terminal. For uplink communication, the first model can be deployed on the network device side.

[0356] Optionally, for example, after the network device 102 trains the first model and the training of the first model converges, the network device 102 can send the model parameters of the first model to the terminal 101 to assist the terminal in deploying the model.

[0357] In some embodiments, the model can flexibly configure input and output according to the number of downlink transmission layers and the size of time-frequency resources at the transmitter, and ensure demodulation performance under multi-layer transmission based on training, adapting to the demodulation process of the transmitter superimposed with the receiver in real services with large inter-layer interference.

[0358] The measurement method involved in the embodiments of this disclosure may include at least one of steps S2201 to S2206, wherein each step may be implemented as an independent embodiment, or two or more steps may be combined as an independent embodiment. For example, step S2206 may be implemented as an independent embodiment, but is not limited thereto.

[0359] In some embodiments, step S2201 may be optionally performed, or one or more of these steps may be omitted or substituted in different embodiments.

[0360] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0361] Figure 3A is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3A, this embodiment of the present disclosure relates to a communication method, which includes:

[0362] In step S3101, the second device 102 sends a first signal to the first device 101.

[0363] In some embodiments, the implementation of step S3101 can be referred to the implementation of step S2104 in FIG2A, and will not be repeated here.

[0364] In step S3102, the first device 101 determines the baseband signal based on the first model and the first signal.

[0365] In some embodiments, the implementation of step S3102 can be referred to the implementation of step S2106 in FIG2A, and will not be repeated here.

[0366] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0367] Figure 3B is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3B, this embodiment of the present disclosure relates to a communication method, which includes:

[0368] In step S3201, the second device 102 determines the aliasing signal based on the baseband signal and the reference signal.

[0369] In some embodiments, the implementation of step S3201 can be referred to the implementation of step S2103 in FIG2A, and will not be repeated here.

[0370] In step S3202, the second device 102 sends a first signal to the first device 101 based on the aliasing signal.

[0371] In some embodiments, the implementation of step S3202 can be referred to the implementation of step S2104 in FIG2A, and will not be repeated here.

[0372] In step S3203, the first device 101 determines the second signal corresponding to the baseband signal.

[0373] In some embodiments, the implementation of step S3203 can be referred to the implementation of step S2106 in FIG2A, and will not be repeated here.

[0374] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0375] Figure 3C is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3C, this embodiment of the present disclosure relates to a communication method, which includes:

[0376] In step S3301, the second device 102 sends an instruction message to the first device 101.

[0377] In some embodiments, the indication information indicates at least one of the following:

[0378] The resource grid corresponding to the reference signal;

[0379] First power allocation factor;

[0380] Second power allocation factor;

[0381] The time slot where the aliased signal is located.

[0382] In some embodiments, the second device 102 may be a network device, and the first device 102 may be a terminal. That is, the network device sends instruction information to the terminal.

[0383] In some embodiments, for network devices, the two power allocation factors during aliasing transmission can be dynamically adjusted based on terminal feedback, and the corresponding reference signal can be fed back to the terminal.

[0384] In some embodiments, a network device can provide feedback to the terminal on whether a certain time slot is an aliased transmission time slot in order to determine the signal processing scheme of the receiving end.

[0385] In some embodiments, for network devices, the instruction information may also indicate the model parameters of the first model, so that the terminal can deploy the trained model.

[0386] In step S3302, the second device 102 sends a first signal to the first device 101.

[0387] In some embodiments, the implementation of step S3302 can be referred to the implementation of step S2104 in FIG2A, and will not be repeated here.

[0388] In step S3303, the first device 101 determines the baseband signal based on the first model and the first signal.

[0389] In some embodiments, the implementation of step S3303 can be referred to the implementation of step S2106 in FIG2A, and will not be repeated here.

[0390] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0391] This disclosure provides a communication method, specifically a receiving method based on non-orthogonal pilot and data superposition transmission using a neural network. To facilitate understanding of the method described in this disclosure, some embodiments are listed below:

[0392] Example 1:

[0393] According to the protocol, the base station determines the transmission signal and maps the resource grid in each downlink transmission time slot configured by the base station. If the current time slot only contains PDCCH, PDSCH, and DM-RS signals, the RE containing the PDCCH is not processed. For the PDSCH and DM-RS symbols, they are normalized according to a given power factor and amplitude allocated according to power. Then, they are aliased and allocated to all REs in the resource grid except for the PDCCH. After completing the pilot and data overlay, the base station performs subsequent digital and analog precoding and OFDM modulation. After processing, the information is transmitted by the base station antenna, transmitted through the channel, and received by the user antenna.

[0394] After receiving information transmitted by the base station, the user antenna performs OFDM modulation demodulation to obtain the symbols on the resource grid of each receiving antenna.

[0395] Example 2:

[0396] Based on Example 1, symbols on the resource grids of all user receiving antennas, pilot symbols on the base station's transmitting resource grid, and the base station's transmitted bit stream are collected. A dataset is formed using these three data points, and a neural network model is trained. This model can use the symbols on the resource grids of the receiving antennas as input to infer the equalized baseband signal.

[0397] Example 3:

[0398] Based on Embodiments 1 and 2, the model is deployed on the user side after training. The base station can transmit aliased symbols according to the above-described aliasing scheme. After de-OFDM modulation of the received signal, the user side inputs the symbols on the resource grid of the receiving antenna into the model, and uses the pilot symbols on the resource grid transmitted by the base station to assist in inferring the equalized baseband signal. The baseband signal is then demapped to recover the transmitted bit stream.

[0399] Alternatively, the process in the above embodiments can be reversed, considering the uplink transmission time slots. For time slots containing only PUCCH, PUSCH, and DM-RS signals, the user side completes the non-orthogonal pilot and data superposition and transmission, while the base station side completes the signal reception process implemented using the above-described model.

[0400] Figure 4 is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 4, this embodiment of the present disclosure relates to a communication method, which includes:

[0401] In step S4101, the base station performs resource grid mapping according to the protocol and under the base station configuration, and completes symbol aliasing of PDSCH and DM-RS in a specific time slot, and then transmits it after subsequent processing.

[0402] Optionally, step S4101 includes the following steps:

[0403] Step S4101-1: The base station determines whether to perform aliasing transmission in the time slot.

[0404] In one embodiment, the base station determines that pilot and data modulation symbol aliasing transmission should be performed in the time slot if only PDCCH, PDSCH and DM-RS signals are transmitted on the resource grid in the time slot, based on the 5G NR standard and the base station configuration.

[0405] Step S4101-2: Power allocation and superposition of pilot and data modulation symbols.

[0406] In one embodiment, power allocation is performed according to a fixed configuration. The pilot and data modulation symbols are power normalized, and then the power of the pilots and data on all REs is allocated and superimposed according to given pilot power factors and data power factors.

[0407] In one embodiment, power allocation is performed based on user-feedback information. The pilot and data modulation symbols are power normalized, and then the pilot and data modulation symbols on all REs are allocated and superimposed using the user-feedback pilot power factor and data power factor.

[0408] In one embodiment, different power allocations are performed for different REs according to a neural network model. The power of the pilot and data modulation symbols is normalized, and then the neural network model is used to generate the power factors of the pilot and data modulation symbols on each RE according to the channel conditions of each RE. The power of the two is then allocated and superimposed on each RE.

[0409] In one embodiment, power allocation for all REs is performed according to a neural network model. Power normalization is applied to the pilot and data modulation symbols. Then, using the neural network model, based on the overall channel conditions, a shared pilot and data modulation symbol power factor is generated across all REs. The power of both is then allocated and superimposed across all REs.

[0410] In step S4101-3, the base station performs further processing on the processed resource grid and transmits it downlink.

[0411] In one embodiment, the base station performs subsequent processing on the resource grid generated after power allocation and superposition as described in step 102, including but not limited to digital precoding, analog precoding, and OFDM modulation. After processing, the data is sent downlink to the user.

[0412] Step S4102: The user-side UE receives the signal and constructs a dataset by combining it with the information transmitted by the base station. The signal reception neural network model on the user side is then trained.

[0413] Optionally, step S4102 may include the following steps:

[0414] In step S4102-1, the base station performs resource grid mapping and completes symbol aliasing of PDSCH and DM-RS in a specific time slot. After subsequent processing, the data is transmitted, and the transmitted bit stream and pilot symbols are retained to form part of the dataset.

[0415] In one embodiment, after the pilot and data modulation symbol power allocation is performed in step 102, the pilot symbols and the corresponding power allocation factors on the REs are saved, and the transmitted bit stream of the data modulation symbols before modulation is saved. The two together form part of the model training dataset.

[0416] Step S4102-2: The user side receives the signal, performs OFDM modulation demodulation, obtains the symbols on the resource grid of each antenna, and forms part of the dataset.

[0417] In one embodiment, the user side receives the signal processed and transmitted downlink by the base station, thereby obtaining the received symbols on the resource grid of each antenna on the user side, saving them to form part of the model training dataset, and providing model input for subsequent model training.

[0418] Step S4102-3: Summarize the datasets from the base station side and the user side, determine the input and output, and thus determine the model structure. Referring to Figure 2D, where Y represents the received symbol on the resource grid of the receiving antenna, P represents the pilot symbol on the resource grid, X represents the actual baseband signal of the transmitted bitstream after constellation modulation, and α and β represent the power allocation factors for the pilot and data, respectively. This represents the symbol on the resource grid after X and P are superimposed according to the data and pilot allocation factors.

[0419] In one embodiment, as shown in Figure 2D-Case 1, the neural network model consists of a single module. The red portion represents the first module of the neural network model.

[0420] In one embodiment, as shown in Figures 2DCase2 and 3, the neural network model consists of multiple modules. The red part represents the first module of the neural network model, and the blue part represents the second module of the neural network model.

[0421] In one embodiment, as shown in Figure 2D-Case 1, the model inputs include: the inputs to the first module of the neural network model: the received symbols and pilot symbols on the resource grid of the receiving antenna obtained by the user's OFDM modulation; the model outputs include: the modulation symbols at the transmitting end; and the model structure is designed based on these.

[0422] In one embodiment, as shown in Figure 2D-Case 2, the model inputs include: inputs to the first module of the neural network model: received symbols on the resource grid of the receiving antenna obtained by user de-OFDM modulation; inputs to the second module of the neural network model: pilot symbols on the resource grid, power allocation factors of pilot symbols, and power allocation factors of data symbols; the model outputs include: modulation symbols at the transmitting end; and the model structure is designed based on these.

[0423] In one embodiment, as shown in Figure 2D-Case 3, the model inputs include: inputs to the first module of the neural network model: received symbols and pilot symbols on the resource grid of the receiving antenna obtained by user de-OFDM modulation; inputs to the second module of the neural network model: pilot symbols on the resource grid, power allocation factors of pilot symbols, and power allocation factors of data symbols; the model outputs include: modulation symbols at the transmitting end; and the model structure is designed based on this.

[0424] Step S4102-4: Using the given dataset and model structure, determine the model parameters and loss function.

[0425] In one embodiment, as shown in Figure 2D-Case 1, a neural network model is trained to infer the baseband signal corresponding to the transmitted bitstream based on the received symbols on the resource grid of each antenna obtained by the user's OFDM decoding, as well as the pilot symbols on the resource grid. The model structure of the training model can be determined according to the size of the resource grid (i.e., the number of subcarriers and symbols) and the specific training task characteristics and training requirements.

[0426] In one embodiment, as shown in Figures 2D-Case 2 and 2D-Case 3, a neural network model is trained to process received symbols from the resource grid of each antenna obtained by the user in OFDM, and optionally, pilot symbols from the resource grid, both as part of the input. After model inference, aliased symbols are obtained, and a non-learnable layer (such as a Lambda layer) is added to the end of the model. The pilot symbols, data, and power factors of the pilot symbols from the resource grid are used as input to the non-learnable layer to process the aliased symbols output by the model, thereby removing the influence of aliased pilots and inferring the baseband signal corresponding to the transmitted bitstream. The model structure can be determined according to the size of the resource grid (i.e., the number of subcarriers and symbols) and the specific training task characteristics and training requirements.

[0427] In one embodiment, as shown in Figure 2D-Case 1, the model structure of the training model can be determined as follows.

[0428] The model consists of two parts: a convolutional module and a fully connected module. The convolutional module and the fully connected module together form the first module of the aforementioned neural network model.

[0429] The process of determining the number of layers and nodes in the model will first be explained using the convolution module.

[0430] A convolutional module consists of a convolutional layer, a batch normalization (BN) layer, and an activation function layer. Naturally, the input size of the convolutional layer is equal to the number of user receiving antennas (L), the number of subcarriers (C) in the resource grid, the number of symbols (S) in the resource grid, and the real and imaginary parts of the symbols in each RE, all of which are of size 2. That is, the tensor size is (L, C, S, 2). The number of two-dimensional convolutional layers is set to S, corresponding to S convolutional modules, where the number of convolutional kernels in each two-dimensional convolutional layer is set to L. i The number of convolutional kernels should be set according to factors such as model size and model generalization ability.

[0431] The process of determining the composition of the S convolutional modules and the connection methods between them involves setting the next layer after each 2D convolutional layer as a batch normalization (BN) layer to address the vanishing gradient problem, normalize model weights, and improve the network's generalization ability. After the BN layer, a layer with ReLU activation is added to process the output of the BN layer. Modules are connected using activation function layers to link the 2D convolutional layers. Multiple convolutional modules with different numbers of kernels can be connected in the model to enhance its learning ability on data.

[0432] Next, the process of determining the number of layers and nodes in the model will be explained, specifically the fully connected layer.

[0433] The number of nodes in the input layer depends on the output size of the last convolutional module. The output matrix of the last convolutional module is flattened to transform it into one-dimensional data before being input into the fully connected layer. The number of nodes in the output layer is set to Y', and its size depends on the size of the resource grid. Each RE corresponds to the real and imaginary parts of the baseband signal obtained from model inference on that RE. For example, the size of Y' can be set to L*C*S*2. The number of hidden layers is set to H, and the number of nodes in each hidden layer is set to J. i The number of hidden layers and nodes needs to take into account factors such as model size and model generalization ability.

[0434] The process of determining the connection method between fully connected layers uses a fully connected approach, with the ReLU function as the activation function. Hidden layers are also fully connected, with the ReLU function used for activation. The connection between hidden layers and the output layer is also fully connected, with the ReLU function used for activation, thus outputting the real and imaginary parts of the baseband signal on each output node. By integrating the output results from each output node, the baseband signal corresponding to the transmitted bitstream can be deduced.

[0435] The process of determining the loss function can include using the mean squared error (MSE) loss function, etc.

[0436] For determining the hyperparameters of the network model, the number of learning epochs can be set to T. The choice of learning epochs needs to consider the impact on model training speed, training cost, and model training accuracy. The Adam optimizer is used, and the corresponding hyperparameters are set to β1, β2, and ε; random weight initialization is chosen as the weight initialization method.

[0437] In one embodiment, as shown in Figures 2D-Case2 and 2D-Case3, the model structure of the training model can be determined as follows.

[0438] The model consists of three parts: a convolutional module, a fully connected module, and a symbolic recovery module. The convolutional module and the fully connected module form the first module of the neural network model, while the symbolic recovery module forms the second module.

[0439] The process for determining the number of layers and nodes in the model is the same as in the above embodiments.

[0440] The process for determining the number of layers and nodes in the model is the same as in the above embodiments.

[0441] The process of determining the number of layers and nodes in the model is explained in the symbolic recovery module.

[0442] Here's an explanation: The model's output and labels can be the baseband signal recovered from the transmitted bitstream. In the embodiment that only includes the first module, the fully connected module serves as the model output, so its output is the baseband signal X recovered from the transmitted bitstream. However, this embodiment includes both the first and second modules, and the fully connected module's output is the model's intermediate output; the fully connected module outputs aliasing symbols. The model output is completed through the symbol recovery module. Therefore, the output of the symbol recovery module is the baseband signal X recovered from the transmitted bit stream.

[0443] The symbolic recovery module uses two non-learning lambda layers; that is, the parameters of the lambda layers do not change as the model learns. The input to the symbolic recovery module is the output of the fully connected module. Its number of nodes is exactly the same as the output nodes of the fully connected module. Assuming the fully connected module integrates the outputs of all nodes to a dimension of (L, C, S, 2), then the input and output dimensions of the symbolic recovery module are both (L, C, S, 2).

[0444] Pilot symbols, data, and the power factor of pilot symbols on the resource grid are used as inputs to the non-learnable layer. This is because the aliasing of pilots and data follows the following formula:

[0445] Therefore, for the aliasing symbols output by fully connected layers To recover the baseband signal X, the following steps are required:

[0446] Therefore, the first Lambda layer takes the output of the fully connected layer as input and subtracts the pilot symbols after pilot power factor allocation; the second Lambda layer takes the output of the previous layer as input and divides the entire input by the data power allocation factor to complete the recovery of the baseband signal. This outputs the real and imaginary parts of the baseband signal on each RE, allowing the deduction of the baseband signal corresponding to the transmitted bitstream.

[0447] The process of determining the loss function can include using the mean squared error (MSE) loss function, etc.

[0448] For determining the hyperparameters of the network model, the number of learning epochs can be set to T. The choice of learning epochs needs to consider the impact on model training speed, training cost, and model training accuracy. The Adam optimizer is used, and the corresponding hyperparameters are set to β1, β2, and ε; random weight initialization is chosen as the weight initialization method.

[0449] Step S4102-5: Train the model.

[0450] In one embodiment, as shown in Figure 2D-Case 1, the received symbols and pilots on the resource grid of the user's receiving antenna are taken from the dataset as input to the model; the output of the model is the inferred baseband signal X of all REs on the resource grid.

[0451] In one embodiment, as shown in Figure 2D-Case 2, the received symbols on the resource grid of the user's receiving antenna are taken as input to the model from the dataset; the pilots and power factors of the data, and the pilots on the resource grid are taken as another input; the output of the model is the baseband signal X of all REs on the resource grid inferred.

[0452] In one embodiment, as shown in Figure 2D-Case 3, the received symbols on the resource grid of the user's receiving antenna and the pilots on the resource grid are taken as inputs to the model from the dataset; the pilots and the power factor of the data, and the pilots on the resource grid are taken as another input; the output of the model is the baseband signal X of all REs on the resource grid inferred.

[0453] In one embodiment, the training loss value is calculated based on the model's output and label information, for example, using the mean squared error (MSE) function.

[0454] Where I represents the amount of training data for the model, and y i This represents the output result of the model after data i is processed. This represents the label value of data i.

[0455] In one embodiment, the base station updates the model parameters based on the training loss value, the model update method, and the selected hyperparameters, such as stochastic gradient descent (SGD) or the Adam algorithm, to update the parameters of specific model layers. For example, the SGD algorithm is used to update the model parameters.

[0456] in, This represents the demodulation model parameters to be updated in round t. This represents the demodulation model parameters after the t-th round of updates. This represents the gradient of the training loss value calculated in round t. Let t represent the learning rate in round t.

[0457] Step S4102-6: After completing the model training, deploy the model on the user side for subsequent invocation.

[0458] In one embodiment, for the downlink superimposed signal transmitted by the base station, the model is deployed on the user side to complete the reception.

[0459] In one embodiment, for user uplink transmission of superimposed signals, the model is deployed at the base station to complete the reception. In this embodiment, the aforementioned PDCCH, PDSCH, and DM-RS signals are replaced with PUCCH, PUSCH, and DM-RS signals.

[0460] In step S4103, after receiving the signal, the user performs OFDM decoding to obtain the symbols on the resource grid of each antenna. The received symbols are then input into the model, and the model infers the equalized baseband signal.

[0461] Optionally, step S4103 may include the following steps:

[0462] Step S4103-1: The user receives the signal sent by the base station and performs OFDM demodulation on the user side to obtain the symbols on the resource grid of each receiving antenna.

[0463] In one embodiment, the user side receives the signal that has been superimposed and downlinked by the base station, and performs OFDM modulation on it to obtain the received symbols on the resource grid of each antenna on the user side.

[0464] In step S4103-2, the user inputs the symbols on the resource grid of each receiving antenna into the demodulation model, and uses pilot symbols as an aid to infer the equalized baseband signal from the model.

[0465] In one embodiment, taking Figure 2D-Case 1 as an example, the model is deployed on the user side, and model inference is completed on the user side. The user inputs the received symbols and pilots on the resource grid of the receiving antenna into the model, and uses the trained model to equalize the non-orthogonal pilot and data superimposed transmission signals to recover the equalized baseband signal.

[0466] In one embodiment, taking Figure 2D-Case2 as an example, the model is deployed on the user side, and model inference is completed on the user side. The user uses the received symbols on the resource grid of the receiving antenna as the input to the model; the power factors of the pilots and data, and the pilots on the resource grid are used as another input; the trained model is used to equalize the non-orthogonal pilot and data superimposed transmission signals to recover the equalized baseband signal.

[0467] In one embodiment, taking Figure 2D-Case 3 as an example, the model is deployed on the user side, and model inference is completed on the user side. The user uses the received symbols on the resource grid of the receiving antenna and the pilots on the resource grid as inputs to the model; the power factors of the pilots and data, and the pilots on the resource grid are used as another input; the trained model is used to equalize the non-orthogonal pilot and data superimposed transmission signals to recover the equalized baseband signal.

[0468] In step S4104, the user demaps the equalized baseband signal to restore the bit stream from the transmitting end.

[0469] Optionally, step S4104 may include the following steps:

[0470] Step S4104-1: The user demaps the obtained baseband signal to obtain the received bit stream.

[0471] In one embodiment, the user uses non-AI techniques for constellation demapping, such as maximum likelihood estimation.

[0472] In one embodiment, the user uses AI technology to perform constellation demapping, inputting the equalized baseband signal into the AI ​​model and outputting the demapped bitstream through the model.

[0473] Step S4104-2: The user performs subsequent processing on the received bit stream according to the NR standard, including but not limited to descrambling, dechannel coding, and deCRC coding.

[0474] In some embodiments, a neural network model is used to process the received signal, replacing the channel estimation and equalization process performed by the user side after receiving the base station signal. After the equalized baseband signal is inferred using the model, subsequent processing can be performed based on the protocol definition, thereby recovering the transmitted data block at the receiving end.

[0475] In some embodiments, a neural network model trained using AI technology optimizes the bit error rate performance of the receiver in pilot and data modulation symbol overlay transmission using traditional NR schemes. The AI-trained neural network model replaces the channel estimation and equalization steps at the receiver in traditional NR schemes, reducing the complexity of signal processing for the receiver. The model can flexibly configure input and output according to the number of downlink transmission layers and the available time-frequency resources at the transmitter, ensuring demodulation performance under multi-layer transmission and adapting to the transmitter-overlay transmission and receiver demodulation process in real-world services with significant inter-layer interference.

[0476] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0477] This disclosure also proposes an apparatus (also referred to as a communication device, etc.) for implementing any of the above methods. For example, an apparatus is proposed that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Furthermore, another apparatus is proposed that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0478] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0479] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0480] Figure 5A is a schematic diagram of a first device according to an embodiment of this disclosure. The first device 5100 is used to perform any of the above methods. In some embodiments, as shown in Figure 5A, the first device 5100 may include at least one of a transceiver module 5101, a processing module 5102, etc. In some embodiments, the transceiver module 5101 is used to receive a first signal sent by a second device, wherein the first signal is sent based on an aliased signal generated by superimposing a baseband signal and a reference signal, and the baseband signal is a data signal after modulation of the transmitted bit stream; the processing module 5102 is used to determine a second signal corresponding to the baseband signal.

[0481] Optionally, the transceiver module 5101 is used to perform at least one of the communication steps such as sending and / or receiving performed by the first device in any of the above methods, which will not be described in detail here. Optionally, the processing module 5102 is used to perform at least one of the other steps performed by the first device in any of the above methods, which will not be described in detail here.

[0482] Figure 5B is a schematic diagram of the structure of the second device proposed in an embodiment of this disclosure. The second device 5200 is used to perform any of the above methods. In some embodiments, as shown in Figure 5B, the second device 5200 may include at least one of a transceiver module 5201, a processing module 5202, etc. In some embodiments, the processing module 5202 is used to determine an aliased signal generated by superposition based on a baseband signal and a reference signal, wherein the baseband signal is a data signal after modulation of the transmitted bit stream; the transceiver module 5201 is used to send a first signal to the first device based on the aliased signal, wherein the first signal is used by the first device to determine a second signal corresponding to the baseband signal.

[0483] Optionally, the transceiver module 5201 is used to perform at least one of the communication steps such as sending and / or receiving performed by the core network device 103 in any of the above methods, which will not be described in detail here. Optionally, the processing module 5202 is used to perform at least one of the other steps performed by the core network device 103 in any of the above methods, which will not be described in detail here.

[0484] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0485] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module.

[0486] In some embodiments, the processing module can be replaced by the processor, and the transceiver module can be replaced by the transceiver.

[0487] Figure 6A is a schematic diagram of the structure of the communication device 6100 proposed in an embodiment of this disclosure. The communication device 6100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0488] As shown in Figure 6A, the communication device 6100 is used to execute any of the above methods. In some embodiments, the communication device 6100 includes one or more processors 6101. The processor 6101 may be a general-purpose processor or a special-purpose processor, such as a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 6100 is used to execute any of the above methods. Optionally, one or more processors 6101 are used to invoke instructions to cause the communication device 6100 to execute any of the above methods.

[0489] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps such as sending and / or receiving in the above-described method, and the processor 6101 performs at least one of the other steps. In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., can be used interchangeably; the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0490] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data and / or instructions. Optionally, one or more processors 6101 are used to invoke instructions stored in the memory 6103 to cause the communication device 6100 to perform any of the above methods. Optionally, all or part of the memory 6103 may also be located outside the communication device 6100. In optional embodiments, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuit 6104 is connected to the memory 6103 and can be used to receive data and / or instructions from the memory 6103 or other devices, and can be used to send data and / or instructions to the memory 6103 or other devices. For example, the interface circuit 6104 can read data and / or instructions stored in the memory 6103 and can be used to send data and / or instructions to the memory 6103 or other devices. For example, the interface circuit 6104 can read data and / or instructions stored in the memory 6103 and send the data and / or instructions to the processor 6101.

[0491] The communication device 6100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6A. The communication device may be a standalone device or may be part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data, programs and / or instructions; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (6) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (7) others, etc.

[0492] Figure 6B is a schematic diagram of the structure of chip 6200 according to an embodiment of this disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to the schematic diagram of chip 6200 shown in Figure 6B, but it is not limited thereto.

[0493] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.

[0494] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data and / or instructions. Optionally, all or part of the memories 6203 may be located outside of chip 6200. Optionally, interface circuit 6202 is connected to memory 6203, and interface circuit 6202 can be used to receive data and / or instructions from memory 6203 or other devices, and interface circuit 6202 can be used to send data and / or instructions to memory 6203 or other devices. For example, interface circuit 6202 can read data and / or instructions stored in memory 6203 and send the data and / or instructions to processor 6201.

[0495] In some embodiments, the interface circuit 6202 performs at least one of the communication steps, such as sending and / or receiving, in the above-described method. For example, the interface circuit 6202 performing the communication steps, such as sending and / or receiving, in the above-described method means that the interface circuit 6202 performs data and / or instruction interaction between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of the other steps.

[0496] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0497] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 6100, cause the communication device 6100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0498] This disclosure also proposes a program product, including a program and / or instructions, which, when executed by the communication device 6100, cause the communication device 6100 to perform any of the above methods. Optionally, the program product is a computer program product. Optionally, the program product is stored on the storage medium.

[0499] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods. Industrial applicability

[0500] In signal transmission, the first signal transmitted by the transmitting end is based on the aliased signal obtained by superimposing the baseband signal and the reference signal, thereby improving the utilization rate of data signal transmission resources; the receiving end can accurately obtain the second signal based on reception or processing.

Claims

1. A method of communication performed by a first device, the method comprising: receiving a first signal transmitted by a second device, wherein the first signal is transmitted according to an aliasing signal generated by superimposing a baseband signal and a reference signal, the baseband signal being a data signal after a bit stream is modulated; determining a second signal corresponding to the baseband signal.

2. The method of claim 1, wherein, The determining the second signal corresponding to the baseband signal comprises: determining the second signal output by a first model.

3. The method of claim 2, wherein, The input of the first model comprises at least one of: a resource grid corresponding to different receiving antennas of the first device after the first device receives the first signal; a resource grid corresponding to a reference signal in the first signal transmitted by the second device.

4. The method of any one of claims 1-3, wherein, The method further comprises: performing de-orthogonal frequency division multiplexing (OFDM) modulation on the first signal to obtain a resource grid corresponding to different receiving antennas of the first device.

5. The method of any one of claims 1-4, wherein, The determining the second signal corresponding to the baseband signal comprises: determining the second output by the first model according to the resource grid corresponding to the different receiving antennas of the first device and the resource grid corresponding to the reference signal.

6. The method of claim 2 or 3 or 5, wherein, The input of the first model comprises at least one of: a first power allocation factor corresponding to the baseband signal in the aliasing signal; a second power allocation factor corresponding to the reference signal in the aliasing signal.

7. The method of claim 6, wherein, The determining the second signal corresponding to the baseband signal comprises: determining an output of a first module in the first model according to the resource grid corresponding to the different receiving antennas and / or the resource grid corresponding to the reference signal; determining the second signal output by a second module in the first model according to one or more of the output of the first module, the resource grid corresponding to the reference signal, the first power allocation factor and the second power allocation factor; wherein the first model comprises the first module and the second module. 8.The method of claim 7, wherein the output of the first module is the aliasing signal, and the second module comprises a first layer and a second layer without learning ability; the determining the second signal output by the second module in the first model according to the output of the first module, the resource grid corresponding to the reference signal, the first power distribution factor and the second power distribution factor comprises: determining an output of the first layer according to the aliasing signal output by the first module, the resource grid corresponding to the reference signal and the second power distribution factor; determining the second signal output by the second layer according to the output of the first layer and the first power distribution factor.

9. The method of any one of claims 1 to 8, wherein, The method further comprises: receiving indication information transmitted by the second device, the indication information indicating at least one of: the resource grid corresponding to the reference signal; the first power distribution factor; the second power distribution factor; a time slot in which the aliasing signal is located.

10. The method of any one of claims 1 to 9, wherein, The method further comprises: training the first model according to a data set until the first model converges, wherein the data set comprises an input data set and an output label value.

11. The method of any one of claims 1 to 10, wherein, The method further comprises: determining the bit stream according to the second signal.

12. The method of any one of claims 1-11, wherein, the time slot in which the aliasing signal is located transmits a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), and a reference signal; or the time slot in which the aliasing signal is located transmits a physical uplink control channel (PUCCH), a physical uplink shared channel (PUSCH), and a reference signal; wherein the reference signal is a demodulation reference signal (DM-RS), and the baseband signal carries the PDSCH data or the PUSCH data.

13. A communication method performed by a second device, the method comprising: determining, according to a baseband signal and a reference signal, an aliasing signal generated by superposition, wherein the baseband signal is a data signal after modulation of a transmission bit stream; transmitting, according to the aliasing signal, a first signal to a first device, wherein the first signal is used by the first device to determine a second signal corresponding to the baseband signal.

14. The method of claim 13, wherein, The second signal is determined according to a first model.

15. The method of claim 13 or 14, wherein, The method further comprises: power normalizing the baseband signal and the reference signal; power allocating the baseband signal and the reference signal according to a first power allocation factor and a second power allocation factor.

16. The method of any one of claims 13 to 15, wherein, The determining, according to a baseband signal and a reference signal, an aliasing signal generated by superposition comprises: superimposing data symbols in the baseband signal and pilot symbols of the reference signal, and mapping the superimposed symbols on a first resource element (RE) to determine the aliasing signal, wherein the first RE includes REs other than REs occupied by a PDCCH or a PUCCH in a resource grid.

17. The method of claim 15, wherein, The first power allocation factor or the second power allocation factor satisfies one of the following: determined for the second device based on a second model, wherein the second model is used to determine the first power allocation factor and the second power allocation factor corresponding to each RE according to channel information of different REs; determined for the second device based on a third model, wherein the third model is used to determine the first power allocation factor and the second power allocation factor common to different REs according to channel information; configured for the second device by a network device; reported by a terminal.

18. The method of any one of claims 14 to 17, wherein, The input of the first model includes at least one of the following: a resource grid corresponding to different receiving antennas after the first device receives the first signal; a resource grid corresponding to a reference signal in the first signal transmitted by the second device.

19. The method of any one of claims 14 to 18, wherein, The input of the first model includes at least one of the following: a first power allocation factor corresponding to the baseband signal in the aliasing signal; a second power allocation factor corresponding to the reference signal in the aliasing signal.

20. The method of claim 19, wherein, the first model includes the first module and the second module; wherein an output of the first module is the aliasing signal, and the second module includes a first layer and a second layer without learning ability, and the second layer determines the second signal.

21. The method of any one of claims 18 to 20, wherein, The method further comprises: transmitting, to the first device, indication information indicating at least one of the following: a resource grid corresponding to the reference signal; a first power allocation factor; a second power allocation factor; a time slot in which the aliasing signal is located.

22. The method of any of claims 13 to 21, wherein, a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), and a reference signal are transmitted in a time slot in which the aliasing signal is located; or a physical uplink control channel (PUCCH), a physical uplink shared channel (PUSCH), and a reference signal are transmitted in a time slot in which the aliasing signal is located. wherein the reference signal is a demodulation reference signal (DM-RS), and the baseband signal carries the PDSCH data or the PUSCH data.

23. A communications device, comprising: The communication device is configured to perform the method of any of claims 1 to 12, or any of claims 13 to 22.

24. A communication system including a first device and a second device, wherein, the first device is configured to implement the method of any of claims 1 to 12; the second device is configured to implement the method of any of claims 13 to 22.

25. A storage medium having stored thereon instructions, wherein, the instructions, when executed on a communication device, cause the communication device to perform the method of any of claims 1 to 12, or any of claims 13 to 22.

26. A program product comprising at least one of a program, instructions, wherein, at least one of the program, the instructions, when executed on a communication device, implement the method of any of claims 1 to 12, or any of claims 13 to 22.

Images