Communication method and communication apparatus

Abstract

Embodiments of the present application provide a communication method and a communication apparatus, which are applied to the technical field of wireless communications. The method comprises: an access network device configures the resource mapping location of a low-density reference signal for a terminal device, or the terminal device autonomously determines the resource mapping location of the low-density reference signal; the terminal device can obtain training data of an artificial intelligence model on the basis of the resource mapping location of the low-density reference signal; and upon the completion of training of the artificial intelligence model, on the basis of the resource mapping location of the low-density reference signal, the access network device can configure the reference signal for the terminal device and send the reference signal to the terminal device, so that the terminal device performs artificial intelligence demodulation on the basis of the received reference signal. By implementing the present application, reference signal overhead can be effectively reduced.

Description

Communication methods and communication devices

[0001] This application claims priority to Chinese Patent Application No. 202510127832.8, filed with the China National Intellectual Property Administration on January 27, 2025, entitled "Communication Method and Communication Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a communication method and a communication device. Background Technology

[0003] In communication systems, terminal equipment and access network equipment can use reference signals (RS) to measure and estimate the channel. For example, the RS can be a channel state information reference signal (CSI-RS) or a demodulation reference signal (DMRS). Taking the downlink channel as an example, a typical approach is as follows: the access network equipment first configures the resource mapping location of the RS for the terminal equipment; the access network equipment transmits signals at that RS resource mapping location; the terminal equipment receives signals at that RS resource mapping location; and estimates the downlink channel quality based on the received signals.

[0004] However, the density of resource mapping locations configured for RS is typically high, resulting in significant reference signal overhead. Summary of the Invention

[0005] This application provides a communication method and a communication device that can help reduce reference signal overhead.

[0006] In a first aspect, embodiments of this application provide a communication method that can be applied to a terminal device, a module in a terminal device, or a logical node, logical module, or software that can implement all or part of the functions of the terminal device.

[0007] The method includes: receiving first configuration information and second configuration information, wherein the first configuration information is used to configure the resource mapping position of a first reference signal RS, and the second configuration information is used to configure a first association relationship, wherein the first association relationship is the association relationship between the resource mapping positions of the first RS and the resource mapping positions of the second RS, and the first RS and the second RS are demodulated associated reference signals; and receiving the first RS according to the first configuration information.

[0008] By implementing the method described in the first aspect, the terminal device can receive a first RS according to first configuration information and determine the resource mapping position of a second RS according to a first association indicated by second configuration information, thereby determining channel state information at the resource mapping position of the second RS and / or the second RS. In this way, the terminal device can collect data based on the first RS and the second RS or the resource mapping position of the second RS, and learn that it can train an artificial intelligence (AI) model based on the collected data to approximate the demodulation performance when using the first RS, thereby reducing reference signal overhead.

[0009] For example, the terminal device can collect the received signal of the first RS and / or the channel state information at the resource mapping location of the first RS (hereinafter referred to as the first channel state information corresponding to the first RS or the first channel state information). It can also collect the received signal of the second RS and / or the channel state information at the resource mapping location of the second RS (hereinafter referred to as the second channel state information corresponding to the second RS or the second channel state information); or, based on the resource mapping location of the second RS but excluding the second RS, it can collect the second channel state information. The received signal of the first RS and / or the first channel state information, as well as the received signal of the second RS and / or the second channel state information, are used as training data for AI demodulation; wherein the resource mapping location density of the first RS is higher than that of the second RS. In this way, after the model corresponding to AI demodulation is trained, the model can be used for AI demodulation, i.e., demodulation is performed based on a low-density RS (such as the second RS) instead of directly based on the first RS, which can effectively reduce the reference signal overhead.

[0010] In one possible implementation, the resource mapping location of the first RS includes the resource mapping location of the second RS.

[0011] In this method, the resource mapping position of the first RS includes the resource mapping position of the second RS, and can also be understood as the resource mapping position of the second RS being a subset of the resource mapping positions of the first RS. Thus, the terminal device can determine the second RS from the received first RS based on the received resource mapping positions of the first and second RSs, without needing to repeatedly receive the second RS. This further helps to save reference signal overhead, and the method is compatible with the existing terminal devices' reference signal reception capabilities, exhibiting good compatibility.

[0012] In one possible implementation, the second configuration information includes one or more of the following: the sampling density and / or starting offset of the resource mapping position of the second RS relative to the resource mapping position of the first RS; or, the index of the resource mapping position of the second RS; or, the index of the pattern corresponding to the resource mapping position of the second RS, wherein the pattern is predefined or preconfigured.

[0013] In this approach, the first association can be flexibly configured using one or more of the following methods: sampling density and / or starting offset, or index of resource mapping location, or index of pattern.

[0014] In one possible implementation, the above pattern corresponds to the type of the first RS; or, the above pattern corresponds to the type of the first RS and the antenna port corresponding to the first RS; or, the above pattern corresponds to the type of the first RS and the number of additional RSs of the first RS; or, the above pattern corresponds to the type of the first RS, the antenna port corresponding to the first RS, and the number of additional RSs of the first RS.

[0015] In this method, the pattern can be flexibly defined or configured by one or more of the following: the type of the first RS, the antenna port corresponding to the first RS, or the number of additional RSs of the first RS.

[0016] In one possible implementation, the method further includes: receiving a second RS based on second configuration information.

[0017] In this method, the terminal device can also additionally receive a second RS based on the second configuration information. For example, the resource mapping position of the first RS may not include the resource mapping position of the second RS, or the second RS may be non-orthogonal to the first RS, or the resource mapping position of the second RS may completely overlap with the resource mapping position of the first RS (e.g., the second RS includes all of the first RS's resource mapping position and the remaining resource mapping positions, referred to as "complete overlap" in this application, where "remaining resource mapping positions" refers to positions other than the first RS's resource mapping position) or partially overlap (e.g., the second RS includes a portion of the first RS's resource mapping position and the remaining resource mapping positions, referred to as "partial overlap" in this application). In this case, the terminal device can collect data based on the received second RS and learn that it can train an AI model based on the collected data to approximate the demodulation performance when using the first RS, thereby reducing reference signal overhead.

[0018] In one possible implementation, the antenna port corresponding to the first RS and the antenna port corresponding to the second RS have a second association relationship, which is predefined or dynamically indicated.

[0019] In one possible implementation, the second configuration information mentioned above also includes the identifier of the first association relationship.

[0020] In one possible implementation, the first association relationship is the association relationship between the resource mapping positions of the first RS and the resource mapping positions of the second RS, including: the first association relationship is the association relationship between the resource mapping positions of N antenna ports of the first RS and the resource mapping positions of the second RS, where N is a positive integer and N is less than or equal to the number of antenna ports corresponding to the first RS.

[0021] In this approach, the terminal device can receive the first RS at the resource mapping positions of N antenna ports according to the first association relationship, instead of receiving the first RS at the resource mapping positions of all antenna ports corresponding to the first RS. This reduces the amount of data collected, thereby reducing the implementation complexity of the terminal device.

[0022] Secondly, embodiments of this application provide another communication method that can be applied to access network devices, modules in access network devices, or logical nodes, logical modules, or software that can implement all or part of the functions of access network devices.

[0023] The method includes: sending first configuration information and second configuration information, wherein the first configuration information is used to configure the resource mapping position of a first reference signal RS, and the second configuration information is used for a first association relationship, wherein the first association relationship is the association relationship between the resource mapping positions of the first RS and the resource mapping positions of the second RS, and the first RS and the second RS are demodulated associated reference signals; and sending the first RS.

[0024] In one possible implementation, the resource mapping location of the first RS includes the resource mapping location of the second RS.

[0025] In one possible implementation, the second configuration information includes one or more of the following: the sampling density and / or starting offset of the resource mapping position of the second RS relative to the resource mapping position of the first RS; or, the index of the resource mapping position of the second RS; or, the index of the pattern corresponding to the resource mapping position of the second RS, wherein the pattern is predefined or preconfigured.

[0026] In one possible implementation, the above pattern corresponds to the type of the first RS; or, the above pattern corresponds to the type of the first RS and the antenna port corresponding to the first RS; or, the above pattern corresponds to the type of the first RS and the number of additional RSs of the first RS; or, the above pattern corresponds to the type of the first RS, the antenna port corresponding to the first RS, and the number of additional RSs of the first RS.

[0027] In one possible implementation, the method further includes sending a second RS.

[0028] In one possible implementation, the antenna port corresponding to the first RS and the antenna port corresponding to the second RS have a second association relationship, which is predefined or dynamically indicated.

[0029] In one possible implementation, the second configuration information mentioned above also includes the identifier of the first association relationship.

[0030] In one possible implementation, the first association relationship is the association relationship between the resource mapping positions of the first RS and the resource mapping positions of the second RS, including: the first association relationship is the association relationship between the resource mapping positions of N antenna ports of the first RS and the resource mapping positions of the second RS, where N is a positive integer and N is less than or equal to the number of antenna ports corresponding to the first RS.

[0031] The beneficial effects in the second aspect can be found in the beneficial effects in the first aspect, and will not be repeated here.

[0032] Thirdly, embodiments of this application provide yet another communication method, which can be applied to a terminal device, a module in a terminal device, or a logical node, logical module, or software that can realize all or part of the functions of the terminal device.

[0033] The method includes: sending first indication information, which indicates the capability of AI demodulation based on a third reference signal RS, and / or the resource mapping position of the third RS; receiving third configuration information, which configures a fourth RS, wherein the number of resource mapping positions of the fourth RS is greater than or equal to the number of resource mapping positions of the third RS.

[0034] Implementing the method described in the third aspect, the terminal device can send first indication information indicating the capability for AI demodulation based on the third RS, and / or indicating the resource mapping location of the third RS, so that the access network device can send third configuration information based on the first indication information to configure the fourth RS terminal device to receive the fourth RS according to the third configuration information, thereby performing AI demodulation based on the fourth RS. Here, the fourth RS is a low-density reference signal, which is beneficial for reducing reference signal overhead. For example, the resource mapping location of the fourth RS includes at least the resource mapping location of the third RS; optionally, the resource mapping location of the fourth RS may also include other resource mapping locations.

[0035] In one possible implementation, the first indication information includes one or more of the following: a first association identifier, which is an identifier of the association between the resource mapping position of the first RS and the resource mapping position of the third RS, wherein the first RS is a demodulated associated reference signal; or, an index of the pattern corresponding to the resource mapping position of the third RS, wherein the pattern is predefined or preconfigured; or, the sampling density and / or starting offset of the resource mapping position of the third RS relative to the resource mapping position of the first RS; or, an index of the resource mapping position of the third RS.

[0036] In this approach, the first indication information can be flexibly configured using one or more of the following: the first associated identifier, the index of the pattern corresponding to the resource mapping location, the sampling density and / or the starting offset, or the index of the resource mapping location.

[0037] In one possible implementation, before sending the first indication information, the method further includes: receiving fourth configuration information, which is used to configure the resource mapping location of the first RS; and determining the resource mapping location of the third RS based on the fourth configuration information.

[0038] In this method, the terminal device can determine the resource mapping location of the third RS based on the resource mapping location of the first RS indicated by the fourth configuration information. Optionally, the resource mapping location of the third RS can be pre-determined by the access network device. For example, if the access network device configures an association between the resource mapping locations of the third RS and the resource mapping locations of the first RS, the terminal device can determine the resource mapping location of the third RS based on this association and the resource mapping location of the first RS. Alternatively, the terminal device can determine the resource mapping location of the third RS itself based on the resource mapping location of the first RS. For example, the terminal device can select a portion of the locations from the resource mapping locations of the first RS as the resource mapping locations of the third RS, and / or determine the remaining locations other than the resource mapping locations of the first RS as the resource mapping locations of the third RS. In this way, the terminal device can send first indication information based on the determined resource mapping location of the third RS to instruct the access network device to configure a reference signal with lower density, thereby reducing reference signal overhead.

[0039] Fourthly, embodiments of this application provide another communication method that can be applied to an access network device, a module in the access network device, or a logical node, logical module, or software that can implement all or part of the functions of the access network device.

[0040] The method includes: receiving first indication information, the first indication information being used to indicate the capability of AI demodulation based on a third reference signal RS, and / or the resource mapping position of the third RS; and sending third configuration information according to the first indication information, the third configuration information being used to configure a fourth RS, wherein the number of resource mapping positions of the fourth RS is greater than or equal to the number of resource mapping positions of the third RS.

[0041] In one possible implementation, the first indication information includes: a first association identifier, which is an identifier of the association between the resource mapping position of the first RS and the resource mapping position of the third RS, wherein the first RS is a demodulated associated reference signal; or, an index of the pattern corresponding to the resource mapping position of the third RS, wherein the pattern is predefined or preconfigured; or, the sampling density and / or starting offset of the resource mapping position of the third RS relative to the resource mapping position of the first RS; or, an index of the resource mapping position of the third RS.

[0042] In one possible implementation, before receiving the first indication information, the method further includes: sending fourth configuration information, which is used to configure the resource mapping location of the first RS.

[0043] The beneficial effects of the fourth aspect can be found in the beneficial effects of the third aspect, and will not be elaborated here.

[0044] Fifthly, embodiments of this application provide a communication device including functional modules for implementing the methods described in any one of the first to fourth aspects. The communication device may be a terminal device or an access network device, or a module (e.g., a processor, chip, or chip system) within the terminal device or access network device, or a logical node, logical module, or software capable of implementing all or part of the functions of the terminal device or access network device.

[0045] Sixthly, embodiments of this application provide a communication device, which includes a processor and an interface circuit. The interface circuit is used to receive signals from other communication devices and transmit them to the processor, or to send signals from the processor to other communication devices. The processor, through logic circuits or executable code instructions, implements the methods described in any one of the first to fourth aspects. The communication device may be a terminal device or an access network device, or a module (e.g., a processor, chip, or chip system) within a terminal device or access network device, or a logic node, logic module, or software capable of implementing all or part of the functions of a terminal device or access network device. Furthermore, the communication device may also include a memory, which can be used to store instructions executed by the processor, input data required for the processor to execute instructions, or data generated after the processor executes instructions.

[0046] In a seventh aspect, embodiments of this application provide a computer-readable storage medium storing computer instructions or programs that, when executed by a communication device, implement the method described in any one of the first to fourth aspects.

[0047] Eighthly, embodiments of this application provide a computer program product, which includes a computer program or program that, when executed by a communication device, implements the method described in any one of the first to fourth aspects. The communication device may be a terminal device or an access network device, or a module (e.g., a processor, chip, or chip system) within the terminal device or access network device, or a logical node, logical module, or software capable of implementing all or part of the functions of the terminal device or access network device.

[0048] Ninthly, embodiments of this application provide a communication system including a terminal device for performing the method as described in any one of the first aspects and an access network device for performing the method as described in any one of the second aspects.

[0049] The beneficial effects of aspects five through nine can be found in the beneficial effects of aspects one through four, and will not be repeated here. Attached Figure Description

[0050] Figure 1 is a schematic diagram of the architecture of a communication system 10 provided in an embodiment of this application;

[0051] Figure 2 is a schematic diagram of the resource mapping location of a demodulation reference signal provided in an embodiment of this application;

[0052] Figure 3 is a schematic diagram of artificial intelligence demodulation provided in an embodiment of this application;

[0053] Figure 4 is a flowchart illustrating the first communication method provided in an embodiment of this application;

[0054] Figure 5 is a schematic diagram of the index representation of the resource mapping position of a first reference signal provided in an embodiment of this application;

[0055] Figure 6 is a schematic diagram of configuring the resource mapping position of the second reference signal by sampling density and starting offset according to an embodiment of this application;

[0056] Figure 7 is a schematic diagram of another resource mapping position of the second reference signal configured by sampling density and starting offset according to an embodiment of this application;

[0057] Figure 8 is a schematic diagram of the pattern corresponding to the first type of low-density reference signal provided in the embodiments of this application;

[0058] Figure 9 is a schematic diagram of the pattern corresponding to the second type of low-density reference signal provided in the embodiments of this application;

[0059] Figure 10 is a schematic diagram of the pattern corresponding to the third type of low-density reference signal provided in the embodiments of this application;

[0060] Figure 11 is a schematic diagram of the pattern corresponding to the fourth type of low-density reference signal provided in the embodiments of this application;

[0061] Figure 12 is a schematic diagram of the pattern corresponding to the fifth type of low-density reference signal provided in the embodiments of this application;

[0062] Figure 13 is a schematic diagram of the pattern corresponding to the sixth type of low-density reference signal provided in the embodiments of this application;

[0063] Figure 14 is a flowchart illustrating the second communication method provided in an embodiment of this application;

[0064] Figure 15 is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0065] Figure 16 is a schematic diagram of another communication device provided in an embodiment of this application. Detailed Implementation

[0066] Figure 1 is a schematic diagram of the architecture of a communication system 10 provided in an embodiment of this application. As shown in Figure 1, the communication system 10 includes a radio access network (RAN) 100, wherein the RAN 100 includes at least one RAN node (110a and 110b in Figure 1, collectively referred to as 110), and may also include at least one terminal (120a-120j in Figure 1, collectively referred to as 120). The RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1). The terminal 120 is wirelessly connected to the RAN node 110. Terminals and RAN nodes can be interconnected via wired or wireless means. The communication system 10 may also include a core network 200. The RAN node 110 is connected to the core network 200 via wireless or wired means. The core network equipment in the core network 200 and the RAN node 110 in the RAN 100 may be independent and different physical devices, or they may be the same physical device integrating the logical functions of the core network equipment and the logical functions of the RAN node. Communication system 10 may also include Internet 300.

[0067] RAN100 can be an evolved universal terrestrial radio access (E-UTRA) system, a new radio (NR) system, a 6th generation (6G) radio access system, or a future radio access system as defined in the 3rd generation partnership project (3GPP), or it can be a WiFi system. RAN100 can also include two or more of the above-mentioned different radio access systems. RAN100 can also be an open RAN (O-RAN).

[0068] RAN nodes, also known as radio access network devices, RAN entities, or access nodes, are used to help terminals access communication systems wirelessly. In one application scenario, an RAN node can be a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next-generation NodeB (gNB) in a 5G mobile communication system, a next-generation base station in a 6G mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. RAN nodes can be macro base stations (as shown in Figure 1, 110a), micro base stations or indoor stations (as shown in Figure 1, 110b), relay nodes, or donor nodes.

[0069] In another application scenario, multiple RAN nodes can collaborate to help terminals achieve wireless access, with different RAN nodes implementing different functions of the base station. For example, a RAN node can be a central unit (CU), a distributed unit (DU), or a radio unit (RU). Here, the CU performs the functions of the base station's Radio Resource Control (RRC) and Packet Data Convergence Protocol (PDCP), and can also perform the functions of the Service Data Adaptation Protocol (SDAP). The DU performs the functions of the base station's Radio Link Control (RANC) and Medium Access Control (MAC) layers, and can also perform some or all of the physical layer functions. For specific descriptions of these protocol layers, refer to the relevant 3GPP technical specifications. The RU can be used to implement radio frequency signal transmission and reception. The CU and DU can be two independent RAN nodes or integrated into the same RAN node, such as within a baseband unit (BBU). The RU can be included in radio frequency equipment, such as in a remote radio unit (RRU) or an active antenna unit (AAU). The CU can be further divided into two types of RAN nodes: CU-control plane and CU-user plane.

[0070] In different systems, RAN nodes may have different names. For example, in an O-RAN system, a CU can be called an open CU (O-CU), a DU can be called an open DU (O-DU), and an RU can be called an open RU (O-RU). The RAN nodes in the embodiments of this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules. For example, a RAN node can be a server loaded with the corresponding software modules. The embodiments of this application do not limit the specific technology or device form used in the RAN nodes. For ease of description, a base station is used as an example of a RAN node in the following description.

[0071] A terminal is a device with wireless transceiver capabilities, capable of sending signals to or receiving signals from a base station. Terminals can also be called terminal equipment, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, airplanes, ships, robots, robotic arms, smart home devices, etc. The embodiments of this application do not limit the specific technology or device form used in the terminal.

[0072] Base stations and terminals can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can be deployed on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of the base stations and terminals.

[0073] The roles of base stations and terminals can be relative. For example, the helicopter or drone 120i in Figure 1 can be configured as a mobile base station. For terminals 120j that access the wireless access network 100 through 120i, terminal 120i is a base station; however, for base station 110a, 120i is a terminal, meaning that 110a and 120i communicate via a wireless air interface protocol. Of course, 110a and 120i can also communicate via a base station-to-base station interface protocol. In this case, relative to 110a, 120i is also a base station. Therefore, both base stations and terminals can be collectively referred to as communication devices. 110a and 110b in Figure 1 can be called communication devices with base station functions, and 120a-120j in Figure 1 can be called communication devices with terminal functions.

[0074] Communication between base stations and terminals, between base stations, and between terminals can be conducted using licensed spectrum, unlicensed spectrum, or both simultaneously. Communication can be conducted using spectrum below 6 GHz, spectrum above 6 GHz, or both simultaneously. The embodiments of this application do not limit the spectrum resources used for wireless communication.

[0075] In the embodiments of this application, the functions of the base station can be executed by modules (such as chips) within the base station, or by a control subsystem that includes base station functions. This control subsystem, including base station functions, can be a control center in the aforementioned application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. Similarly, the functions of the terminal can be executed by modules (such as chips or modems) within the terminal, or by a device that includes terminal functions.

[0076] In this application, the base station sends downlink signals or downlink information to the terminal, with the downlink information carried on the downlink channel; the terminal sends uplink signals or uplink information to the base station, with the uplink information carried on the uplink channel. To communicate with the base station, the terminal needs to establish a radio connection on a cell controlled by the base station. The cell with which the terminal has established a radio connection is called the terminal's serving cell. When the terminal communicates with this serving cell, it is also susceptible to interference from signals from neighboring cells.

[0077] The following explanations of some terms used in the embodiments of this application are provided to facilitate understanding by those skilled in the art.

[0078] This section is for ease of understanding only and should not be regarded as a disclosure or specific limitation of the technical solution of this application.

[0079] I. Reference signal (RS)

[0080] A reference signal is a known signal provided by the transmitting equipment to the receiving equipment for channel estimation or channel sounding.

[0081] In the embodiments of this application, the reference signal can be used for measurement, channel estimation, or demodulation, such as for measuring one or more of the following: reference signal receiving quality (RSRQ), signal-noise ratio (SNR), signal-to-interference plus noise ratio (SINR), channel quality indicator (CQI), or precoding matrix indicator (PMI).

[0082] For example, the reference signal can be a channel state information reference signal (CSI-RS), a synchronizing signal / physical broadcast channel block (SSB), a sounding reference signal (SRS), or a demodulation reference signal (DMRS), or a reference signal that may appear in the future. Among them, CSI-RS, SSB, and DMRS can be used to measure, estimate, or demodulate the downlink channel, while SRS and DMRS can be used to measure, estimate, or demodulate the uplink channel.

[0083] Taking the DMRS used for downlink channel estimation as an example, the channel estimation results based on DMRS can be used for downlink data demodulation. Specifically: the access network device sends DMRS configuration information to the terminal device. The terminal device determines the resource mapping location of the DMRS based on the DMRS configuration information. The access network device sends the DMRS at that resource mapping location, and the terminal device receives the DMRS at that resource mapping location. Since the DMRS sent at that resource mapping location is known to the terminal device, the terminal device can perform downlink channel estimation and downlink data demodulation based on the known DMRS and the received DMRS.

[0084] Optionally, DMRS can be transmitted along with the data channel or control channel. That is, the resource mapping location of the DMRS is located on the resource block (RB) allocated by the data channel or control channel. In this case, the DMRS can be used to demodulate the data or control information carried in the data channel or control channel. For example, DMRS can be transmitted on the RB occupied by the physical downlink shared channel (PDSCH).

[0085] Optionally, the configuration information for DMRS includes, but is not limited to, the type of DMRS and / or the number of additional DMRS.

[0086] The DMRS is of type 1 or type 2, and the frequency domain density of the DMRS at each antenna port is different for Type 1 and Type 2. For Type 1, the resource mapping of the DMRS at each antenna port is a comb distribution. For example, the Type 1 DMRS in NR Release 15 is a Comb-2 distribution, meaning that the resource mapping positions of the DMRS (such as the resource elements (REs) of the DMRS) are distributed at frequency intervals in a certain symbol. The RE density of the DMRS at each antenna port on the symbol where the DMRS is located is 50%. For Type 2, the DMRS at each antenna port is generated based on orthogonal cover code (OCC). For example, in the case of frequency domain OCC, every two REs of the DMRS at each antenna port are connected together, with a spacing of 4 REs between them. The RE density of the DMRS at each antenna port on the symbol where the DMRS is located is 33.3%. It should be noted that the above examples are for single-symbol DMRS, applicable to DMRSs corresponding to ports 1000-1003 under Type 1 DMRS, or DMRSs corresponding to ports 1000-1005 under Type 2 DMRS. The above examples are only used to illustrate that resource mapping distributions can differ under different types of DMRS, and that the resource mapping location of the DMRS for each antenna port can be determined in a predefined manner. This application does not limit other DMRS types.

[0087] For example, taking an antenna port (such as port 1000) as an example, as shown in Figure 2, a small square represents a RE of a DMRS. The black square shown in Figure 2(a) represents the RE of the DMRS corresponding to the antenna port under Type 1, and the black square shown in Figure 2(c) represents the RE of the DMRS corresponding to the antenna port under Type 2.

[0088] Additional DMRS is a temporal-domain repeating extension of the aforementioned Type 1 DMRS or Type 2 DMRS. The number of additional DMRS can be configured as an integer greater than or equal to 0, suitable for high-speed mobile scenarios. This application does not limit the implementation method or number of additional DMRS.

[0089] For example, as shown in Figure 2(b), when the number of additional DMRS is configured to be 1, the RE of the DMRS is extended by one column based on the one in Figure 2(a). Similarly, as shown in Figure 2(d), when the number of additional DMRS is configured to be 1, the RE of the DMRS is extended by one column based on the one in Figure 2(c).

[0090] Optionally, the configuration information of the DMRS may also include one or more of the following: the mapping type of the physical data channel, the number of time units occupied by the physical data channel (e.g., time units are symbols), the number of time units of the front-end DMRS (e.g., time units are symbols), or the resource mapping location of the front-end DMRS, etc. This application does not limit this.

[0091] II. AI Demodulation

[0092] In this application, AI demodulation can also be referred to as AI channel estimation, as shown in Figure 3. It refers to the receiving device using AI technology and a received low-density reference signal to estimate the corresponding channel, aiming to approximate or achieve the same effect or performance as channel estimation using a high-density reference signal. The low-density reference signal has a lower density than the high-density reference signal. For example, based on the received low-density reference signal, or based on a reference signal corresponding to the received low-density reference signal (including both the low-density reference signal and additional reference signals), an AI model estimates a more accurate or refined channel state information that approximates the channel state information estimated using a high-density reference signal. Compared to non-AI demodulation, AI demodulation can demodulate using fewer reference signals, effectively reducing reference signal overhead. The reference signal overhead in this application can also be understood as the overhead of the reference signal on radio resources. Non-AI demodulation can be understood as a method that does not use AI technology in channel estimation or demodulation, thus requiring more reference signal overhead to improve channel estimation effect or performance.

[0093] In this application, a low-density reference signal can be understood as the reference signal received by the receiving device in AI demodulation, also known as a sparse reference signal, etc., and this application does not limit this definition. A high-density reference signal can be understood as the reference signal received by the receiving device in non-AI demodulation, also known as a non-sparse reference signal, etc., and this application does not limit this definition. Taking DMRS as an example, a high-density reference signal can be a DMRS already defined in the standard, such as a DMRS already supported in the current standard configured through the above content. A high-density reference signal can also be understood as a DMRS defined in the standard without using AI features (such as a DMRS used for terminal devices that do not have or have not configured / activated AI demodulation features). A low-density reference signal can refer to a DMRS with a lower density than the DMRS already defined in the standard. A low-density reference signal can also be understood as a DMRS defined in the standard using AI features (such as a DMRS used for terminal devices that have or have configured / activated AI demodulation features). Density can also be understood as the number of resource mapping locations of DMRS within a given time-frequency resource, such as the number of REs of DMRS in each RB. For example, high-density DMRS can be the DMRS corresponding to Type 1 in Figure 2 (such as the DMRS corresponding to antenna port 1000), that is, the number of REs of DMRS in an RB is 6. Sparse DMRS refers to DMRS in an RB with less than 6 REs.

[0094] Optionally, the AI ​​model used in AI demodulation can be a dual-end model or a single-end model. A dual-end model means that both the transmitting and receiving devices possess two parts of an AI model capable of performing AI demodulation. In other words, both the transmitting and receiving devices need to run their respective AI models simultaneously to achieve overall AI demodulation. Another possible implementation of a dual-end model is that the DMRS transmitted by the transmitting device is a DMRS determined based on AI training. This DMRS is jointly designed and optimized with the AI ​​demodulation function or AI model of the receiving device to improve overall demodulation performance. A single-end model means that the AI ​​model implementing the AI ​​demodulation function resides only in the transmitting or receiving device. This function does not require the transmitting and receiving devices to use a paired set of models.

[0095] For example, in the process of downlink channel estimation based on DMRS, the access network device is the transmitting device and the terminal device is the receiving device. In a single-ended model, the access network device can use the DMRS defined in the standard, such as DMRS generated based on the standard-defined formula, while the terminal device uses an AI model for channel estimation. In a dual-ended model, the access network device uses an AI-modified DMRS, and the terminal device uses an AI model adapted to that AI-modified DMRS for channel estimation. The AI-modified DMRS and the AI ​​model are obtained through joint training. In this case, the DMRS can be generated independently of the standard-defined formula, but rather by jointly training it with the AI ​​channel estimation model as trainable parameters. For example, after training, the AIDMRS can be determined using the trained parameters, or the AIDMRS generation model can be jointly trained with the AI ​​channel estimation model to generate the AIDMRS. Optionally, regardless of whether it is a single-ended or dual-ended model, the DMRS transmitted by the access network device can be high-density or low-density DMRS.

[0096] In this application, the AI ​​model can also be replaced with descriptions such as AI / machine learning (ML) functions, AI / ML features, or AI / ML configurations, and this application does not limit this.

[0097] The data distribution or source for AI inference and AI training must be consistent to ensure that AI inference performance does not degrade; otherwise, overfitting or underfitting may occur, affecting the use of AI functions. To ensure consistency between AI demodulation application (inference) and training, especially the consistency of data distribution or source in inference and training, embodiments of this application propose some communication methods and devices that can constrain the training phase of AI demodulation, particularly the data collection phase. The data collection phase refers to the phase of collecting training data, which is used to train the AI ​​model corresponding to the AI ​​demodulation. For example, the training data includes at least channel state information determined by a low-density reference signal and channel state information determined by a high-density reference signal. This training data can be used to train the AI ​​model based on the channel state information determined by the low-density reference signal to obtain an output result that approximates the channel state information determined by the high-density reference signal. The training data may also include low-density and high-density reference signals to determine their respective corresponding channel state information. After the AI ​​model is trained, the access network device configures and sends a reference signal to the terminal device using the AI ​​model based on the low-density reference signal. This enables the terminal device using the AI ​​model to perform AI demodulation based on the received reference signal. In this way, the performance of the AI ​​model is not degraded during inference by ensuring the consistency between inference and training, thereby effectively reducing the reference signal overhead.

[0098] The communication method and communication device proposed in the embodiments of this application will be further described below with reference to the accompanying drawings. It is understood that this application uses terminal devices and access network devices as examples to illustrate the execution of the interaction, but this application does not limit the execution subject of the interaction. For example, the method executed by the terminal device in this application can also be implemented by a communication / processing module in the terminal device or a circuit or chip in the terminal device responsible for communication / processing functions. The method executed by the access network device in this application can also be implemented by a module (e.g., circuit, chip, or chip system) in the access network device, or a logic node, logic module, or software that can implement all or part of the functions of the access network device.

[0099] As shown in Figure 4, Figure 4 illustrates a first communication method provided in an embodiment of this application. This communication method includes steps 401 to 402, wherein:

[0100] Step 401: The access network device sends the first configuration information and the second configuration information to the terminal device.

[0101] Accordingly, the terminal device receives the first configuration information and the second configuration information.

[0102] In one possible implementation, the first configuration information and the second configuration information may be carried in radio resource control (RRC). The first configuration information and the second configuration information may be sent simultaneously or sequentially, or they may be sent in the same configuration information; this application embodiment does not limit this.

[0103] The first configuration information is used to configure the resource mapping location of the first RS, where the first RS is a demodulation-associated reference signal, such as the first RS being a DMRS.

[0104] In one possible implementation, the first configuration information includes one or more of the following information, which are used to indicate the resource mapping location of the first RS: the type of the first RS, the number of supplementary RSs to the first RS, the mapping type of the physical data channel corresponding to the first RS, the number of time units occupied by the physical data channel corresponding to the first RS (e.g., time units are symbols), the number of time units of the preceding RS of the first RS (e.g., time units are symbols), or the resource mapping location of the preceding RS of the first RS, etc. This information can be referred to the configuration information of the DMRS described above, and will not be repeated here.

[0105] The second configuration information is used to configure the first association relationship, which is the association between the resource mapping positions of the first RS and the resource mapping positions of the second RS. The second RS is a demodulation-associated reference signal, such as a DMRS. In this way, the terminal device can determine the resource mapping position of the second RS based on the resource mapping position of the first RS and the first association relationship.

[0106] The channel state information determined by the resource mapping position of the first RS can be used as a label or ground truth during the training of the AI ​​model corresponding to AI demodulation. By determining the resource mapping position of the second RS, the AI ​​model can be trained to adapt to that position. For example, the received signal at the resource mapping position of the second RS (referred to as the received signal of the second RS) or the determined channel state information can be used as the training input information for the AI ​​model, thereby enabling the output of the trained AI model to approximate the channel state information determined based on the first RS. During the inference phase of the AI ​​model, based on RSs whose resource mapping positions include the resource mapping position of the second RS, the information required for the inference phase of the AI ​​model is obtained (e.g., the RS received at the resource mapping position of the second RS (i.e., the received signal of that RS), or the channel information determined based on that RS), thereby performing AI demodulation and reducing reference signal overhead.

[0107] In the embodiments of this application, for the sake of simplicity, unless otherwise specified, the description is based on the case of a single antenna port. For example, the first RS can be understood as the first RS under one antenna port, and the second RS can be understood as the second RS under one antenna port. If the first RS corresponds to multiple antenna ports, each antenna port can be processed using the same steps as under one antenna port.

[0108] In one possible approach, the density (or number) of resource mapping locations of the first RS is greater than or equal to the density (or number) of resource mapping locations of the second RS; that is, the first RS is a high-density RS or a non-sparse RS, and the second RS is a low-density RS or a sparse RS. In this approach, the second RS can be a reference signal associated with AI demodulation.

[0109] Optionally, the resource mapping location of the first RS includes resource mapping locations on one or more RBs used to carry the first RS. The resource mapping locations on different RBs used to carry the first RS may be the same or different. Similarly, the resource mapping location of the second RS includes resource mapping locations on one or more RBs used to carry the second RS. The resource mapping locations on different RBs used to carry the second RS may be the same or different. For ease of description, the following description uses a single RB as an example.

[0110] In the first example: the resource mapping location of the first RS includes the resource mapping location of the second RS, or the resource mapping location of the second RS includes a subset of the resource mapping location of the first RS, or the resource mapping location of the second RS is contained in the resource mapping location of the first RS.

[0111] In this example, the received signal from the second RS can be used for training the AI ​​model; for example, the received signal from the second RS, or channel state information determined based on the received signal from the second RS. Compared to the second RS having no received signal at its resource mapping location, acquiring more information can improve the accuracy and performance of the AI ​​model's training and inference.

[0112] In this example, the second configuration information includes one or more of the following:

[0113] (1) Index of the resource mapping location of the second RS.

[0114] In this embodiment of the application, the index of the resource mapping location of the second RS can be obtained from the index of the resource mapping location of the first RS.

[0115] The following describes how the index of the resource mapping location of the first RS is implemented:

[0116] In a first possible implementation, the index of the resource mapping location of the first RS includes a frequency domain index k and a time domain index l, as represented as (k, l). Optionally, a spatial domain index may also be included.

[0117] Optionally, the frequency domain index of the resource mapping position of the first RS can be the index of the frequency domain cell in which the resource mapping position of the first RS is located, such as the subcarrier index; the time domain index of the resource mapping position of the first RS can be the index of the time domain cell in which the resource mapping position of the first RS is located, such as the symbol index. For example, as shown in the first index representation in Figure 5, the resource mapping position corresponding to the first black square in the lower left corner can be represented as (0, 2), where 0 is the frequency domain index of the resource mapping position and 2 is the time domain index of the resource mapping position; the resource mapping position corresponding to the first black square in the upper right corner can be represented as (11, 9), where 11 is the frequency domain index of the resource mapping position and 9 is the time domain index of the resource mapping position.

[0118] Optionally, the resource mapping positions of the first RS are consecutively numbered in the frequency domain (e.g., 0, 1, 2...), and resource mapping positions other than the first RS are not included in the consecutive frequency domain numbering. The frequency domain index of the resource mapping positions of the first RS can be the frequency domain number obtained based on this method. Similarly, the resource mapping positions of the first RS are consecutively numbered in the time domain (e.g., 0, 1, 2...), and resource mapping positions other than the first RS are not included in the consecutive time domain numbering. The frequency domain index of the resource mapping positions of the first RS can be the time domain number obtained based on this method. For example, as shown in the second index representation method in Figure 5, the resource mapping position corresponding to the black square in the lower left corner can be represented as (0, 0), where 0 is the frequency domain index and 0 is the time domain index of the resource mapping position; the resource mapping position corresponding to the black square in the upper right corner can be represented as (5, 2), where 5 is the frequency domain index and 2 is the time domain index of the resource mapping position.

[0119] In the second possible implementation, the resource mapping positions of the first RS can be numbered according to a preset order (e.g., 0, 1, 2...), and the index of the resource mapping position of the first RS is the number p obtained based on this method. For example, the preset order can be from low to high in the frequency domain and then from small to large in the time domain, or from small to large in the time domain and then from low to high in the frequency domain. Optionally, the spatial domain can also be considered, but this application is not limited to this. Taking the preset order of from low to high in the frequency domain and then from small to large in the time domain as an example, as shown in the third index representation method in Figure 5, the resource mapping position corresponding to the black square in the lower left corner can be represented as 0, and the resource mapping position corresponding to the black square in the upper right corner can be represented as 17.

[0120] Based on the above, the access network device can determine a portion of the resource mapping locations from the resource mapping locations of the first RS as the resource mapping locations of the second RS, and carry the index of the resource mapping locations of the second RS in the second configuration information with reference to the index representation of the resource mapping locations of the first RS.

[0121] Optionally, the second configuration information may further include information determined based on the index of the resource mapping position of the second RS, such as a differential value. Optionally, corresponding to a first possible implementation of the resource mapping position of the first RS, the differential value may include a frequency domain index differential value and a time domain index differential value. For example, if the resource mapping positions of the second RS are the two positions with indices (0, 2) and (11, 9) shown in Figure 5, then the second configuration information may include (0, 2) and (11, 7), where 11 in (11, 7) represents the frequency domain index differential value corresponding to the position (11, 7), and 7 in (11, 7) represents the time domain index differential value corresponding to the position (11, 7). This can save signaling overhead on the second configuration information.

[0122] (2) Bitmap: The bitmap is used to indicate the resource mapping location of the second RS.

[0123] For example, the resource mapping positions of the first RS are numbered according to a preset order (e.g., 0, 1, ..., q). For example, the preset order can be from low to high in the frequency domain and from small to large in the time domain, or from small to large in the time domain and from low to high in the frequency domain. Optionally, the spatial domain can also be considered. A bit map of length q is defined according to the numbering. Different bits in the bit map correspond to different resource mapping positions of the first RS. If the bit value is the first value, then the resource mapping position corresponding to the bit is the resource mapping position of the second RS. If the bit value is the second value, then the resource mapping position corresponding to the bit is not the resource mapping position of the second RS. The first value and the second value are different, such as the first value being 1 and the second value being 0.

[0124] (3) The sampling density and / or starting offset of the resource mapping position of the second RS relative to the resource mapping position of the first RS.

[0125] The first possible implementation of the index corresponding to the resource mapping location of the first RS:

[0126] The sampling density includes the frequency domain sampling density (Freq Density) and / or the time domain sampling density (Time Density); the starting offset includes the frequency domain starting offset (Freq Offset) and / or the time domain starting offset (Time Offset). The starting offset is used to determine the starting resource mapping position for sampling. Thus, starting from the starting resource mapping position, the resource mapping positions of the first RS can be sampled according to the sampling density to obtain the sampled resource mapping position, which is also the resource mapping position of the second RS.

[0127] Optionally, Freq Density can be the difference between the frequency domain indices of the resource mapping locations of any two adjacent samples, or the difference minus A, where A can be a positive integer, such as 1, but is not limited to this. For ease of description, the following explanation uses this difference as an example.

[0128] Optionally, Time Density can be the difference between the time-domain indices of any two adjacent sampled resource mapping locations, or the difference minus A, where A can be a positive integer, such as 1, but is not limited to this. For ease of description, the following explanation uses this difference as an example for Time Density.

[0129] Optionally, the Freq Offset value is the difference between the frequency domain index of the starting resource mapping position and the preset resource mapping position, or the difference minus A. A can be a positive integer, such as 1, but is not limited to this. For ease of description, the following explanation uses this difference value as the Freq Offset value.

[0130] Optionally, the Time Offset value is the difference between the time domain index of the starting resource mapping position and the preset resource mapping position, or the difference minus A. A can be a positive integer, such as A being 1, but is not limited to this. For ease of description, the following content uses this difference value as an example.

[0131] For example, the preset resource mapping position can be the frequency mapping position with the lowest frequency and shortest time among the resource mapping positions of the first RS, or the frequency mapping position with the highest frequency and longest time among the resource mapping positions of the first RS, and is not limited to this. For example, as shown in Figure 6, assuming that the resource mapping position of the first RS is as shown on the left side of Figure 6, and the Freq Density value in the second configuration information is 5, the Time Density value is 2, the Freq Offset value is 0, and the Time Offset value is also 0, then the starting resource mapping position for sampling is the resource mapping position corresponding to the first black square in the lower left corner, and thus the resource mapping position of the second RS is as shown on the right side of Figure 6.

[0132] It should be noted that if both Freq Offset and Time Offset are 0, the second configuration information may not include Freq Offset and Time Offset. The terminal device can sample based on a predefined or preconfigured starting resource mapping position, such as the position with the lowest frequency and shortest time in the resource mapping position of the first RS. Alternatively, if Freq Offset and / or Time Offset are predefined values, the second configuration information may not include Freq Offset and / or Time Offset. This can help save signaling overhead in the second configuration information.

[0133] A second possible implementation of the index corresponding to the resource mapping location of the first RS:

[0134] The sampling density and starting offset do not distinguish between the frequency domain and the time domain, and the starting offset is used to determine the starting resource mapping position for sampling. In this way, starting from the starting resource mapping position, the resource mapping positions of the first RS can be sampled according to the sampling order and sampling density to obtain the sampled resource mapping position, which is also the resource mapping position of the second RS.

[0135] Optionally, the second configuration information may also include the sampling order, or the sampling order may be predefined or preconfigured. For example, the sampling order may be an ascending order of the resource mapping location index of the first RS, or a descending order, etc., and is not limited to this.

[0136] Optionally, the sampling density can be the difference between the indices of the resource mapping positions of any two adjacent samples, or the difference minus A, where A can be a positive integer, such as 1, but is not limited to this. For ease of description, the following explanation uses this difference as the sampling density.

[0137] Optionally, the starting offset is the difference between the index of the initial resource mapping position and the index of the preset resource mapping position, or the difference minus A. A can be a positive integer, such as 1, but is not limited to this. For ease of description, the following explanation uses this difference as the starting offset.

[0138] For example, as shown in Figure 7, assuming the resource mapping position of the first RS is as shown on the left side of Figure 7, the sampling density in the second configuration information is 3, the starting offset is 0, and the sampling order is the order of the resource mapping position index of the first RS from small to large, then the starting resource mapping position of the sampling is the resource mapping position corresponding to the first black square in the lower left corner, and the resource mapping position of the second RS is as shown on the right side of Figure 7.

[0139] It should be noted that if the starting offset is 0, the second configuration information may not include the starting offset. The terminal device can sample based on a predefined or preconfigured starting resource mapping position, such as the position with the lowest frequency and shortest time among the resource mapping positions of the first RS. Alternatively, if the Freq Offset and / or Time Offset are predefined values, the second configuration information may not include the Freq Offset and / or Time Offset. This can help save on the signaling overhead of the second configuration information.

[0140] (4) The index of the pattern corresponding to the resource mapping location of the second RS, wherein the pattern is predefined or preconfigured.

[0141] The pattern corresponding to the resource mapping position of the second RS is one of at least one candidate pattern. The candidate pattern refers to the pattern corresponding to the resource mapping position of the low-density RS of the first RS. These candidate patterns can be predefined or preconfigured.

[0142] The following describes how to predefine or preconfigure candidate patterns:

[0143] In the first possible implementation, candidate patterns can be predefined or preconfigured based on the type of the first RS.

[0144] Taking DMRS as an example, as shown in Figure 2, the location distribution of REs in DMRS differs under different DMRS types, while the location distribution of REs in DMRS of the same DMRS type is similar. Therefore, different patterns can be defined for different DMRS types. In this way, candidate patterns can be predefined or pre-configured based on the type of the first RS, so that the pattern corresponding to the resource mapping position of the second RS corresponds to the type of the first RS. For ease of description, the following explanation uses DMRS as the first RS as an example.

[0145] As shown in Figure 8, assuming the first RS is of type Type 1, and the resource mapping positions of the first RS are the six black squares on the left side of Figure 8, which are arranged from bottom to top as the first to the sixth black squares, then we can pre-configure or pre-define pattern 1 under Type 1 to indicate that the first black square among these six black squares is the resource mapping position of the low-density RS, pattern 2 under Type 1 to indicate that the fourth black square among these six black squares is the resource mapping position of the low-density RS, pattern 3 under Type 1 to indicate that the fourth black square among these six black squares is the resource mapping position of the low-density RS, and pattern 3 under Type 1 to indicate that the fifth and sixth black squares among these six black squares are the resource mapping positions of the low-density RS. Assuming the first RS is of type Type2, the resource mapping positions of the first RS are the six black squares on the left side of Figure 8, and in order from bottom to top, they are the first to the sixth black squares. Pattern 1 under Type2 indicates that the first and second black squares among these six black squares are the resource mapping positions of low-density RSs. Pattern 2 under Type2 indicates that the third and fourth black squares among these six black squares are the resource mapping positions of low-density RSs. Pattern 3 under Type2 indicates that the fifth and sixth black squares among these six black squares are the resource mapping positions of low-density RSs.

[0146] Optionally, the number of antenna ports corresponding to the first RS can be multiple. Since the absolute positions of the resource mapping locations corresponding to different antenna ports can be the same or different, given that the type of the first RS is determined, they can all be understood as being offset based on the same resource mapping location distribution (for example, the DMRS of ports 1000 and 1002 of Type 1 are both Comb-2 structures in the frequency domain, but the frequency domain mapping locations are offset). Therefore, this method can pre-configure or pre-define candidate patterns to adapt to multiple different antenna ports.

[0147] For example, as shown in Figure 9, the first RS is of type Type 1, and the antenna ports corresponding to the first RS include port 0 and port 1. Therefore, the distribution of resource mapping positions corresponding to port 0 and port 1 shown on the left side of Figure 9 is the same as the distribution shown in Figure 2(a). As shown on the right side of Figure 9, pattern 1 indicates that the resource mapping position of the low-density RS is the first resource mapping position under port 0 and port 1; pattern 2 indicates that the resource mapping position of the low-density RS is the fourth resource mapping position under port 0 and port 1; and pattern 3 indicates that the resource mapping positions of the low-density RS are the fifth and sixth resource mapping positions under port 0 and port 1. In this implementation, considering that the resource mapping position distribution of DRMS ​​for different antenna ports has a similar distribution (the difference lies only in the possibility of overall position offset based on the same distribution), a pattern can be understood as applicable to all antenna ports.

[0148] Optionally, if there are multiple antenna ports corresponding to the first RS, then candidate patterns can be predefined or preconfigured based on the type of the first RS and the antenna ports corresponding to the first RS. Optionally, in this case, different candidate patterns can be predefined or preconfigured for different antenna ports (such as different distributions of resource mapping locations corresponding to candidate patterns, and / or different numbers of candidate patterns).

[0149] For example, as shown in Figure 10, the first RS is of type Type 1, and the antenna ports corresponding to the first RS include port 0 and port 1. Then, the distribution of resource mapping positions corresponding to port 0 and port 1 shown on the left side of Figure 9 is the same as the distribution shown in Figure 2(a). As shown on the right side of Figure 10, port 0 pattern 1 indicates that the resource mapping position of the low-density RS is the first resource mapping position under port 0, port 0 pattern 2 indicates that the resource mapping position of the low-density RS is the fourth resource mapping position under port 0, port 0 pattern 3 indicates that the resource mapping position of the low-density RS is the fifth and sixth resource mapping positions under port 0, port 1 pattern 1 indicates that the resource mapping position of the low-density RS is the first resource mapping position under port 1, and port 1 pattern 2 indicates that the resource mapping position of the low-density RS is the fourth resource mapping position under port 1.

[0150] In the second possible implementation, if the first configuration information also configures the number of additional RSs for the first RS, then candidate patterns can be predefined or preconfigured according to the type of the first RS and the number of additional RSs for the first RS.

[0151] For example, as shown in Figure 11, the first RS is of type Type 1, and the number of additional RSs for the first RS is configured to be 2. Then, the resource mapping position of the first RS is the eighteen black squares on the left side of Figure 11. Following the order from bottom to top and then from left to right, pattern 1 on the right side of Figure 11 indicates the resource mapping position of the first black square and the thirteenth black low-density RS among these eighteen black squares. Pattern 2 indicates the resource mapping position of the fourth black square among these six black squares as a low-density RS. Pattern 3 under Type 1 indicates the resource mapping position of the second black square among these eighteen black squares as a low-density RS. Pattern 3 also indicates the resource mapping positions of the sixth and seventh black squares among these eighteen black squares as low-density RSs.

[0152] Optionally, if there are multiple antenna ports corresponding to the first RS, then candidate patterns can be predefined or pre-configured by combining the type of the first RS, the antenna ports corresponding to the first RS, and the number of additional RSs for the first RS. Specific implementation details can be derived from the above, and will not be elaborated upon here.

[0153] In a third possible implementation, candidate patterns can be predefined or preconfigured based on the number of resource mapping locations of the first RS and the number of resource mapping locations of the low-density RS of the first RS.

[0154] For example, let X be the number of resource mapping locations of the first RS, and Y be the number of resource mapping locations of the low-density RSs of the first RS, where Y is less than or equal to X. Since all possible combinations of resource mapping locations of the low-density RSs total... This allows us to exhaustively enumerate all possible combinations and predefine or preconfigure the candidate patterns corresponding to each combination. Optionally, the indices of these candidate patterns can be...

[0155] For example, assuming the first RS is of type Type 1, and its resource mapping location is the six black squares on the left side of Figure 12, arranged from bottom to top as the first to sixth black squares, i.e., X is 6. Assuming Y is 1, then we can obtain 6 patterns, as shown on the right side of Figure 12: Pattern 1 under Type 1 indicates that the first black square among these six black squares is the resource mapping location of a low-density RS; Pattern 2 under Type 1 indicates that the second black square among these six black squares is the resource mapping location of a low-density RS; Pattern 3 under Type 1 indicates that the third black square among these six black squares is the resource mapping location of a low-density RS; Pattern 4 under Type 1 indicates that the fourth black square among these six black squares is the resource mapping location of a low-density RS; Pattern 5 under Type 1 indicates that the fifth black square among these six black squares is the resource mapping location of a low-density RS; and Pattern 6 under Type 1 indicates that the sixth black square among these six black squares is the resource mapping location of a low-density RS.

[0156] Optionally, the number X of resource mapping positions in the first RS can also include the number X1 of frequency domain resource mapping positions and the number X2 of time domain resource mapping positions; the number Y of resource mapping positions in the low-density RS of the first RS is the sum of the number of frequency domain resource mapping positions and the number of time domain resource mapping positions. Then, we can predefine the candidate patterns for all combinations according to methods such as frequency domain first then time domain, or time domain first then frequency domain, and select resource mapping positions to form combinations in ascending order of frequency / time domain, resulting in a total of [number missing] combinations. For example, if the frequency domain mapping position is {f1,f2,f3} (i.e., X1 = 3) and the time domain mapping position is {t1,t2} (i.e., X2 = 2), following the combination generation method of first frequency domain and then time domain, if Y = 2, then a total of 10 candidate patterns are predefined, namely, pattern1 is {f1,f2}, pattern2 is {f1,f3}, pattern3 is {f2,f3}, pattern4 is {f1,t1}, pattern5 is {f2,t1}, pattern6 is {f3,t1}, pattern7 is {f1,t2}, pattern8 is {f2,t2}, pattern9 is {f3,t2}, and pattern10 is {t1,t2}. Optionally, the generation of candidate patterns for combinations can also include the spatial domain. It should be understood that the above order of determining the candidate patterns for combinations is only an example and does not limit the specific order of candidate pattern generation.

[0157] It should be noted that the first to third possible implementation methods mentioned above can be implemented individually or in combination, and this application does not limit this.

[0158] In the second example: the resource mapping location of the second RS includes all other locations except the resource mapping location of the first RS.

[0159] In one possible implementation, the first RS is an orthogonal RS, meaning that the sequences corresponding to each antenna port of the first RS are orthogonal to each other. The second RS includes non-orthogonal RS and / orthogonal RS. Non-orthogonal RS means that the sequences corresponding to each antenna port of the second RS are not orthogonal.

[0160] In this example, the received signal from the second RS can be used for training the AI ​​model; for example, the received signal from the second RS, or channel state information determined based on the received signal from the second RS. Compared to the second RS having no received signal at its resource mapping location, acquiring more information can improve the accuracy and performance of the AI ​​model's training and inference.

[0161] Since the first RS is an orthogonal RS, the channel state information determined by the first RS will be more accurate than when the first RS is non-orthogonal. Therefore, the channel state information determined in this case is more suitable as a label or ground truth when training an AI model.

[0162] Optionally, for non-orthogonal RS, the access network device can generate non-orthogonal RS according to the formula defined in the standard, or it can generate non-orthogonal RS through AI training. The resource mapping location of the non-orthogonal RS is determined by the standard definition, configuration, or AI training.

[0163] In this example, the second configuration information includes one or more of the following:

[0164] (1) Index of the resource mapping location of the second RS.

[0165] Specifically, after determining the resource mapping location of the second RS, the access network device can obtain the index of the resource mapping location of the second RS by referring to any possible implementation of the resource mapping location of the first RS.

[0166] (2) Bitmap: The bitmap is used to indicate the resource mapping location of the second RS.

[0167] For example, the resource mapping positions of the entire RB are numbered according to a preset order (e.g., 0, 1, ..., q). For example, the preset order can be from low to high in the frequency domain and from small to large in the time domain, or from small to large in the time domain and from low to high in the frequency domain. Optionally, the spatial domain can also be considered. A bit map of length q is defined according to the numbering. Different bits in the bit map correspond to different resource mapping positions of the entire RB. If the bit value is the first value, then the resource mapping position corresponding to the bit is the resource mapping position of the second RS. If the bit value is the second value, then the resource mapping position corresponding to the bit is not the resource mapping position of the second RS. The first value and the second value are different, such as the first value being 1 and the second value being 0.

[0168] (3) The index of the pattern corresponding to the resource mapping location of the second RS, wherein the pattern is predefined or preconfigured.

[0169] Specifically, the resource mapping location of the second RS generated by the access network device can correspond to a pattern, and the terminal device can be made aware of the pattern and its index through a predefined or preconfigured method, so that the terminal device can determine the resource mapping location of the second RS based on the index of the pattern.

[0170] In one possible implementation, the antenna port corresponding to the first RS and the antenna port corresponding to the second RS have a second association relationship, which is predefined or dynamically indicated.

[0171] Optionally, the second correlation indicates that the channel state information determined by the RS on the antenna port corresponding to the second RS is the same as or similar to the channel state information determined by the RS on the antenna port corresponding to the first RS. In other words, during AI model training, the training label or ground truth value corresponding to the channel state information determined by the RS on the antenna port corresponding to the second RS is the channel state information determined by the RS on the antenna port corresponding to the first RS. During AI model inference, by using the channel state information determined by the RS on the antenna port corresponding to the second RS and the AI ​​model, a channel state information close to that determined by the RS on the antenna port corresponding to the first RS can be obtained. This eliminates the need to transmit the first RS and achieves better channel estimation accuracy, reducing reference signal overhead.

[0172] Optionally, if the second association is predefined, then the second association may or may not be indicated when the access network device subsequently indicates the antenna port of the first RS to the terminal. Alternatively, if the second association is dynamically indicated, then the second association may be indicated when the access network device subsequently indicates the antenna port of the first RS to the terminal.

[0173] For example, the second association can be indicated by an identifier indicating the second association and / or an identifier of the antenna port of the second RS corresponding to the second association, but this application is not limited to this.

[0174] For example, as shown in Figure 13, the first RS is an orthogonal RS, and its resource mapping position is shown on the left side of Figure 13. The second RS includes non-orthogonal RSs, and their resource mapping positions are shown on the right side of Figure 13. The association between non-orthogonal port0 and orthogonal port0 or orthogonal port1 can be predefined or dynamically indicated. It should be noted that the resource mapping position of the second RS and the second configuration information can be implemented according to the first or second example above, or a combination of the first and second examples above. For example, the resource mapping position of the second RS includes all or part of the resource mapping position of the first RS, as well as the remaining resource mapping positions, which are positions other than the resource mapping positions of the first RS. Therefore, the first example can be used to indicate part or all of the resource mapping positions of the first RS in the resource mapping position of the second RS, and the second example can be used to indicate the remaining resource mapping positions. This will not be elaborated here.

[0175] Optionally, based on the first and / or second examples above, the second configuration information may also include an identifier of the first association.

[0176] Optionally, based on the first and / or second examples above, the second configuration information may also indicate the resource mapping locations of the N antenna ports of the first RS and the resource mapping locations of the second RS, with the first association being the association between them.

[0177] Where N is a positive integer, and N is less than or equal to the number of antenna ports corresponding to the first RS. The terminal device receives the first RS at the resource mapping positions of N antenna ports in ascending order of antenna port identifiers, or in other predefined or preconfigured order. When N is less than the number of antenna ports corresponding to the first RS, the amount of data received by the terminal device can be reduced, thereby reducing the data collection requirements of the terminal device and reducing the implementation complexity of the terminal device. For example, the resource mapping positions of the first RS are shown on the left side of Figure 13. Then the antenna ports corresponding to the first RS include orthogonal port0 and orthogonal port1. If N is 2, the terminal device can receive the first RS at the resource mapping positions corresponding to orthogonal port0 and orthogonal port1 in sequence. If N is 1, the terminal device can receive the first RS at the resource mapping positions corresponding to orthogonal port0 or orthogonal port1 in sequence.

[0178] In the third example: the resource mapping location of the second RS includes any resource mapping location on the RB where the first RS is located.

[0179] In this example, the channel state information determined at the resource mapping location of the second RS can be used to train the AI ​​model. Compared to having a received signal at the resource mapping location of the second RS, it is not necessary to receive a signal at the resource mapping location of the second RS, which reduces the data collection requirements and thus reduces the implementation complexity of the terminal device.

[0180] In this example, the second configuration information includes one or more of the following, which can be referred to the first and / or second examples above for implementation, and will not be elaborated here:

[0181] (1) Index of the resource mapping location of the second RS.

[0182] (2) The resource mapping position of the second RS relative to the sampling density and / or starting offset of the RB where the first RS is located.

[0183] (3) Bitmap: The bitmap is used to indicate the resource mapping location of the second RS.

[0184] (4) The index of the pattern corresponding to the resource mapping location of the second RS, wherein the pattern is predefined or preconfigured.

[0185] Step 402: The access network device sends the first reference signal RS to the terminal device.

[0186] Corresponding to the first or third example in step 401, the terminal device receives the first RS accordingly.

[0187] Specifically: The terminal device can first determine the resource mapping location of the first RS according to the first configuration information in step 401, and then receive the first RS in step 402 at the resource mapping location of the first RS.

[0188] Optionally, the terminal device may further determine the resource mapping location of the second RS based on the resource mapping location of the first RS in step 401 and the second configuration information, and determine the received second RS from the received first RS based on the resource mapping location of the second RS.

[0189] Optionally, the terminal device may also determine the resource mapping location of the second RS based on the resource mapping location of the first RS in step 401 and the second configuration information, and determine the channel state information at the resource mapping location of the second RS (hereinafter referred to as the second channel state information or second channel state information corresponding to the second RS) based on the channel state information determined in the first RS (such as the channel state information of the RB where the first RS is located).

[0190] Corresponding to the second example in step 402, the access network device also sends a second RS to the terminal device; accordingly, the terminal device receives the first RS and the second RS.

[0191] Further, optionally, the terminal device may obtain the received signal of the first RS and / or the channel state information at the resource mapping location of the first RS (hereinafter referred to as the first channel state information corresponding to the first RS or the first channel state information), as well as the received signal of the second RS and / or the second channel state information. The received signal of the first RS is used to determine the first channel state information, and the received signal of the second RS is used to determine the second channel state information.

[0192] Optionally, the terminal device may also estimate the channel state information of the RB where the resource mapping location of the first RS is located based on the received signal of the first RS and / or the first channel state information to obtain the third channel state information.

[0193] Optionally, the terminal device may also estimate the channel state information of the RB where the resource mapping location of the second RS is located based on the received signal of the second RS and / or the second channel state information to obtain the fourth channel state information.

[0194] Optionally, if the terminal device is configured with an AI model corresponding to AI demodulation and has the ability to train locally, the terminal device can train the AI ​​model based on the first channel state information and the second channel state information, or based on the third channel state information and the fourth channel state information, or based on the third channel state information and the second channel state information, or based on the first channel state information and the second RS received signal, or based on the third channel state information and the second RS received signal, so that the trained AI model can be demodulated based on low-density RS.

[0195] Optionally, the terminal device can send multiple of the following information to the training device of the AI ​​model: the received signal of the first RS, the first channel state information, the received signal of the second RS, the second channel state information, the third channel state information, or the fourth channel state information. The training device can then train the AI ​​model based on this information, enabling the trained AI model to perform AI demodulation based on low-density RS (the training information can refer to the training information required in local training scenarios). Optionally, the terminal device can also send an identifier of the first association relationship to the training device. Optionally, the terminal device can also send a cell identifier, etc.

[0196] Based on the embodiment described in Figure 4, the access network device can configure the resource mapping position of the first RS to the terminal device through first configuration information; and configure the resource mapping position of the second RS to the terminal device through second configuration information. The terminal device can determine the resource mapping position of the first RS and receive the first RS according to the first configuration information, determine the resource mapping position of the second RS and determine the second RS according to the second configuration information, or determine the resource mapping position of the second RS and determine the channel state information at the resource mapping position of the second RS according to the second configuration information. In this way, the terminal device can collect data according to the resource mapping positions of the first RS and the second RS / second RS, and know that it can train an AI model based on the collected data to perform AI demodulation based on low-density RS, instead of demodulation based on the first RS, which can effectively save reference signal overhead. At the same time, it can also enable subsequent access network devices to know what type of low-density RS to send to the terminal device that has completed the training, thereby ensuring the consistency between training and inference.

[0197] As shown in Figure 14, Figure 14 illustrates a second communication method provided in an embodiment of this application. This communication method includes steps 1401 to 1402, wherein:

[0198] Step 1401: The terminal device sends the first instruction information to the access network device.

[0199] The first indication information is used to indicate the capability of AI demodulation based on the third RS, and / or the resource mapping location of the third RS.

[0200] Step 1402: The access network device sends third configuration information to the terminal device.

[0201] This application embodiment does not limit the execution order of steps 1401 and 1402; that is, step 1401 can be executed first and then step 1402, or step 1402 can be executed first and then step 1401. The following description uses the example of executing step 1401 first and then step 1402 as an example:

[0202] The third configuration information is used to configure the fourth RS, where the number of resource mapping locations of the fourth RS is greater than or equal to the number of resource mapping locations of the third RS. For example, the resource mapping locations of the fourth RS may include the resource mapping locations of the third RS, or may include the resource mapping locations of the third RS as well as the remaining resource mapping locations.

[0203] In this embodiment, the terminal device can train the AI ​​model corresponding to AI demodulation based on the resource mapping location of the third RS and the resource mapping location of the first RS, and execute steps 1401 and 1402 after the AI ​​model training is completed, so that the access network device can configure the fourth RS to the terminal device according to the first instruction information, and the terminal device can perform AI demodulation based on the fourth RS and the trained AI model, thereby ensuring the consistency of training and inference.

[0204] In one possible approach, the density (or number) of resource mapping locations of the first RS is greater than or equal to the density (or number) of resource mapping locations of the third RS, i.e., the first RS is a high-density RS or a non-sparse RS, and the third RS is a low-density RS or a sparse RS.

[0205] In the first example: the resource mapping location of the third RS is determined by the terminal device itself. The specific implementation is as follows:

[0206] In a first possible implementation, the terminal device receives fourth configuration information, which is used to configure the resource mapping location of the first RS; the terminal device determines the resource mapping location of the third RS based on the fourth configuration information.

[0207] Optionally, the terminal device may randomly select a resource mapping position from the resource mapping positions of the first RS, and determine the resource mapping position of the third RS based on the selected resource mapping position. Optionally, the resource mapping position of the third RS is the selected resource mapping position; or, the terminal device may pre-determine the resource mapping position, and the resource mapping position of the third RS is obtained by matching the selected resource mapping position with the pre-determined resource mapping position (e.g., taking the intersection or union). Corresponding to this optional method, the first indication information in step 1401 may include the index of the resource mapping position of the third RS, and the specific implementation of the index of the resource mapping position of the second RS described above can be referred to, and will not be repeated here.

[0208] Optionally, the terminal device can sample from the resource mapping position of the first RS and determine the resource mapping position of the third RS based on the sampled resource mapping position. For example, the terminal device independently determines the sampling density and / or starting offset of the sampled resource mapping position relative to the resource mapping position of the first RS. The sampling density and / or starting offset can be implemented with reference to the corresponding content in Figure 4. Optionally, the resource mapping position of the third RS is the sampled resource mapping position; or, the terminal device pre-determines the resource mapping position, and the resource mapping position of the third RS is obtained by matching the sampled resource mapping position with the pre-determined resource mapping position (e.g., taking the intersection or union). Corresponding to this optional method, the first indication information in step 1401 may include the sampling density and / or starting offset, and / or the resource mapping position of the third RS.

[0209] Optionally, the terminal device knows at least one candidate pattern, which refers to the pattern corresponding to the resource mapping position of the low-density RS of the first RS. These candidate patterns can be predefined or pre-configured. Then, the terminal device can determine one candidate pattern from the at least one candidate pattern and determine the resource mapping position of the third RS based on the determined candidate pattern. The predefinition or pre-configuration method of the candidate pattern can be implemented with reference to the corresponding content in Figure 4, and will not be elaborated here. Optionally, the resource mapping position of the third RS is the resource mapping position corresponding to the candidate pattern; or, the terminal device pre-determines the resource mapping position, and the resource mapping position of the third RS is obtained by matching the resource mapping position corresponding to the candidate pattern with the pre-determined resource mapping position (such as taking the intersection or union). Corresponding to this optional method, the first indication information in step 1401 may include the index of the pattern corresponding to the third RS, and / or the resource mapping position of the third RS. Optionally, the access network device sends the first RS after sending the fourth configuration information; the terminal device receives the first RS according to the fourth configuration information and obtains the first channel state information corresponding to the first RS; the terminal device determines the resource mapping location of the third RS based on the first channel state information. For example, the terminal device can process the first channel state information according to a pre-configured or predefined algorithm to estimate the channel state information of the RB where the resource mapping location of the first RS is located, and then the terminal device can determine the resource mapping location of the third RS from this RB. Optionally, the resource mapping location of the third RS may include a subset of the resource mapping locations of the first RS, and / or other resource mapping locations besides the resource mapping location of the first RS. Corresponding to this optional method, the first indication information in step 1401 may include the resource mapping location of the third RS.

[0210] In the second possible implementation, the terminal device determines the desired resource mapping location of the third RS and determines the resource mapping location of the third RS based on the resource mapping location of the first RS.

[0211] Corresponding to this approach, the first indication information in step 1401 may include sampling density and / or starting offset, and / or, the resource mapping location of the third RS, and / or, the index of the pattern corresponding to the third RS, etc., which are not limited in this application. Specific implementation methods can refer to the various optional methods in the first possible implementation described above.

[0212] Corresponding to the first or second possible implementation described above, the terminal device can determine its own model running capability or model training capability, and determine the resource mapping position of the third RS based on the model running capability or model training capability. For example, if the terminal device has poor model running capability (e.g., fewer computing resources to support model inference, power consumption constraints that do not support running complex models, etc., this application does not limit this), then the terminal device can determine the resource mapping position of the third RS with higher density; if the terminal device has good model running capability (e.g., more computing resources to support model inference, power consumption level that supports running complex models, etc., this application does not limit this), then the terminal device can determine the resource mapping position of the third RS with lower density.

[0213] Furthermore, after step 1402, the access network device can send a fourth RS to the terminal device; the terminal device receives the fourth RS according to the third configuration information and performs AI demodulation based on the received fourth RS. The fourth RS can be a low-density RS, thus effectively saving reference signal overhead.

[0214] In the second example: the resource mapping location of the third RS is configured by the access network device.

[0215] This optional method can be seen in the embodiment corresponding to Figure 4, which describes how the access network device configures the resource mapping location of the second RS, and will not be elaborated here.

[0216] The first indication information in step 1401 may include one or more of the following: a first association identifier, an index of the pattern corresponding to the resource mapping position of the third RS, a sampling density and / or starting offset of the resource mapping position of the third RS relative to the resource mapping position of the first RS, or an index of the resource mapping position of the third RS. The first association identifier identifies the association between the resource mapping positions of the first RS and the third RS. This first association identifier is pre-configured and pre-defined, and can be specifically implemented as shown in the first association identifier in the embodiment of Figure 4, which will not be elaborated here. In this case, the terminal device can determine the resource mapping positions of the first RS and the third RS independently based on the first association identifier, without requiring the access network device to configure the resource mapping position of the first RS, thus reducing the signaling overhead of configuration information.

[0217] It should be noted that the access network device can configure the resource mapping position of the first RS and the resource mapping position of the third RS to the terminal device according to the embodiment corresponding to FIG4. Then, the terminal device collects the training data of the AI ​​model corresponding to the AI ​​demodulation and trains the AI ​​model according to the resource mapping position of the first RS and the resource mapping position of the third RS. Then, the terminal device executes steps 1401 and 1402.

[0218] Alternatively, the access network device can configure the resource mapping positions of the first RS and the third RS to the terminal device with data collection capabilities, referring to the embodiment corresponding to Figure 4. Then, the terminal device with data collection capabilities collects training data of the AI ​​model corresponding to the AI ​​demodulation based on the resource mapping positions of the first RS and the third RS, and sends the training data and the indication information of the resource mapping positions of the third RS to a device with model running capabilities or model training capabilities (hereinafter referred to as the training device). After the training device completes the training of the AI ​​model, it executes steps 1401 and 1402. The data collection capability can refer to the example with good model running capabilities described above, which will not be repeated here. Optionally, the terminal device may have one or more of the following capabilities by default: data collection capability, model running (inference) capability, and model training capability.

[0219] Based on the embodiment described in Figure 14, the terminal device can send a first indication information to the access network device, indicating that it has the ability to perform AI demodulation based on the third RS (i.e., to obtain a trained AI model based on the third RS), and / or indicating the resource mapping location of the third RS, so that the access network device can send third configuration information to configure the fourth RS based on the first indication information. The terminal device receives the fourth RS according to the third configuration information, and then performs AI demodulation based on the fourth RS. This can effectively reduce reference signal and signaling overhead.

[0220] Optionally, before step 401 or step 1401 above, the terminal device may indicate its capability information to the access network device. This capability information indicates that it possesses one or more of the following capabilities: data collection capability, model running (inference) capability, and model training capability. This can facilitate triggering the access network device to send the aforementioned first configuration information, second configuration information, or third configuration information to the appropriate terminal device.

[0221] For example, when initially accessing the access network device, the terminal device sends capability information to the access network device. After accessing the access network device, the terminal device sends request information to the access network device. This request information requests the access network device to configure the terminal device to perform data collection, model running, and / or model training. Optionally, the request information may also indicate that the terminal device has data collection capabilities, model running capabilities, and / or model training capabilities. For example, the request information may be carried in UE assistance information (UAI).

[0222] It is understood that, in order to achieve the functions in the above embodiments, the access network device and the terminal device include hardware structures and / or software modules corresponding to perform each function. Those skilled in the art should readily recognize that, based on the units and method steps of the various examples described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0223] Figures 15 and 16 are schematic diagrams of possible communication devices provided in embodiments of this application. These communication devices can be used to implement the functions of access network devices or terminal devices in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments. In the embodiments of this application, the communication device can be one of the terminals 120a-120j shown in Figure 1, or it can be RAN node 110a or 110b shown in Figure 1, or it can be a module (such as a chip) applied to terminal devices or access network devices.

[0224] As shown in Figure 15, the communication device 1500 includes a processing unit 1510 and a transceiver unit 1520. The communication device 1500 is used to implement the functions of the terminal device or access network device in the method embodiments shown in Figure 4 or Figure 14 above.

[0225] When the communication device 1500 is used to implement the functions of the terminal device in the method embodiment shown in FIG. 4: the transceiver unit 1520 is used to receive first configuration information and second configuration information, and to receive a first RS according to the first configuration information; the processing unit 1510 is used to process the first configuration information and the second configuration information. When the communication device 1500 is used to implement the functions of the terminal device in the method embodiment shown in FIG. 14: the transceiver unit 1520 is used to send first indication information and receive third configuration information; the processing unit 1510 is used to generate the first indication information and process the third configuration information.

[0226] When the communication device 1500 is used to implement the function of the access network device in the method embodiment shown in FIG. 4: the transceiver unit 1520 is used to send first configuration information, second configuration information, and a first RS; the processing unit 1510 is used to generate the first configuration information and the second configuration information. When the communication device 1500 is used to implement the function of the access network device in the method embodiment shown in FIG. 14: the transceiver unit 1520 is used to receive the first configuration information and send the first instruction information according to the first instruction information and send the third configuration information; the processing unit 1510 is used to process the first instruction information.

[0227] For a more detailed description of the above-mentioned processing unit 1510 and transceiver unit 1520, please refer to the relevant description in the method embodiment shown in Figure 4 or Figure 14.

[0228] As shown in Figure 16, the communication device 1600 includes a processor 1610 and an interface circuit 1620. The processor 1610 and the interface circuit 1620 are coupled to each other. It is understood that the interface circuit 1620 can be a transceiver or an input / output interface. Optionally, the communication device 1600 may also include a memory 1630 for storing instructions executed by the processor 1610, or storing input data required by the processor 1610 to execute instructions, or storing data generated after the processor 1610 executes instructions. Sometimes, the interface circuit 1620 can also be understood as part of the processor 1610, in which case the communication device 1600 includes the processor 1610.

[0229] When the communication device 1600 is used to implement the method shown in FIG4 or FIG14, the processor 1610 is used to implement the function of the processing unit 1510, and the interface circuit 1620 is used to implement the function of the transceiver unit 1520.

[0230] When the aforementioned communication device is a chip applied to a terminal device, the chip implements the functions of the terminal device in the above method embodiments. The chip receives information from the access network device, which can be understood as the information being first received by other modules (such as radio frequency modules or antennas) in the terminal device, and then sent to the chip by these modules. The chip sends information to the access network device, which can be understood as the information being first sent to other modules (such as radio frequency modules or antennas) in the terminal device, and then sent to the access network device by these modules.

[0231] When the aforementioned communication device is a chip applied to an access network device, the chip implements the functions of the access network device in the above method embodiments. The chip receives information from the terminal device, which can be understood as the information being first received by other modules (such as radio frequency modules or antennas) in the access network device, and then sent to the chip by these modules. The chip sends information to the terminal device, which can be understood as the information being sent down to other modules (such as radio frequency modules or antennas) in the access network device, and then sent to the terminal device by these modules.

[0232] In this application, entity A sends information to entity B, either directly or indirectly through other entities. Similarly, entity B receives information from entity A, either directly or indirectly through other entities. Entities A and B can be RAN nodes or terminals, or modules within RAN nodes or terminals. Information transmission and reception can be between RAN nodes and terminals, such as between a base station and a terminal; between two RAN nodes, such as between a CU and a DU; or between different modules within a single device, such as between a terminal device chip and other modules of the terminal device, or between an access network device chip and other modules of the access network device.

[0233] It is understood that the processor in the embodiments of this application can be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, field-programmable gate arrays, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0234] The method steps in the embodiments of this application can be implemented in hardware or in software instructions executable by a processor. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, optical discs, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. The storage medium can also be a component of the processor. The processor and the storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the ASIC can reside in a base station or terminal. The processor and the storage medium can also exist as discrete components in the base station or terminal.

[0235] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, an access network device, a terminal device, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer program or instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0236] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0237] Depending on whether the specification uses "optional": In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates an "or" relationship between the preceding and following related objects; in the formulas of this application, the character " / " indicates a "division" relationship between the preceding and following related objects. "Including at least one of A, B, and C" can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B, and C.

[0238] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers described above does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

Claims

1. A communication method, characterized in that, The method includes: Receive first configuration information and second configuration information. The first configuration information is used to configure the resource mapping position of the first reference signal RS. The second configuration information is used to configure a first association relationship. The first association relationship is the association relationship between the resource mapping positions of the first RS and the resource mapping positions of the second RS. The first RS and the second RS are demodulated associated reference signals. The first RS is received based on the first configuration information.

2. The method according to claim 1, characterized in that, The resource mapping location of the first RS includes the resource mapping location of the second RS.

3. The method according to claim 1 or 2, characterized in that, The second configuration information includes one or more of the following: The sampling density and / or starting offset of the resource mapping position of the second RS relative to the resource mapping position of the first RS; Alternatively, the index of the resource mapping location of the second RS; Alternatively, the index of the pattern corresponding to the resource mapping location of the second RS, wherein the pattern is predefined or preconfigured.

4. The method according to claim 3, characterized in that, The pattern corresponds to the type of the first RS; Alternatively, the pattern corresponds to the type of the first RS and the antenna port corresponding to the first RS; Alternatively, the pattern corresponds to the type of the first RS and the number of additional RSs to the first RS; Alternatively, the pattern corresponds to the type of the first RS, the antenna port corresponding to the first RS, and the number of additional RSs to the first RS.

5. The method according to claim 1, characterized in that, The method further includes: The second RS is received according to the second configuration information.

6. The method according to claim 5, characterized in that, The antenna port corresponding to the first RS and the antenna port corresponding to the second RS have a second association relationship, which is predefined or dynamically indicated.

7. The method according to any one of claims 1-6, characterized in that, The second configuration information also includes the identifier of the first association relationship.

8. The method according to any one of claims 1-7, characterized in that, The first association relationship is the association relationship between the resource mapping positions of the first RS and the resource mapping positions of the second RS, including: The first association relationship is the association relationship between the resource mapping positions of the N antenna ports of the first RS and the resource mapping positions of the second RS, where N is a positive integer and N is less than or equal to the number of antenna ports corresponding to the first RS.

9. A communication method, characterized in that, The method includes: Send first configuration information and second configuration information. The first configuration information is used to configure the resource mapping position of the first reference signal RS. The second configuration information is used for the first association relationship. The first association relationship is the association relationship between the resource mapping positions of the first RS and the resource mapping positions of the second RS. The first RS and the second RS are demodulated associated reference signals. Send the first RS.

10. The method according to claim 9, characterized in that, The resource mapping location of the first RS includes the resource mapping location of the second RS.

11. The method according to claim 9 or 10, characterized in that, The second configuration information includes one or more of the following: The sampling density and / or starting offset of the resource mapping position of the second RS relative to the resource mapping position of the first RS; Alternatively, the index of the resource mapping location of the second RS; Alternatively, the index of the pattern corresponding to the resource mapping location of the second RS, wherein the pattern is predefined or preconfigured.

12. The method according to claim 11, characterized in that, The pattern corresponds to the type of the first RS; Alternatively, the pattern corresponds to the type of the first RS and the antenna port corresponding to the first RS; Alternatively, the pattern corresponds to the type of the first RS and the number of additional RSs to the first RS; Alternatively, the pattern corresponds to the type of the first RS, the antenna port corresponding to the first RS, and the number of additional RSs to the first RS.

13. The method according to claim 9, characterized in that, The method further includes: Send the second RS.

14. The method according to claim 13, characterized in that, The antenna port corresponding to the first RS and the antenna port corresponding to the second RS have a second association relationship, which is predefined or dynamically indicated.

15. The method according to any one of claims 9-14, characterized in that, The second configuration information also includes the identifier of the first association relationship.

16. The method according to any one of claims 9-15, characterized in that, The first association relationship is the association relationship between the resource mapping positions of the first RS and the resource mapping positions of the second RS, including: The first association relationship is the association relationship between the resource mapping positions of the N antenna ports of the first RS and the resource mapping positions of the second RS, where N is a positive integer and N is less than or equal to the number of antenna ports corresponding to the first RS.

17. A communication method, characterized in that, The method includes: Send a first indication message, which is used to indicate the capability of AI demodulation based on a third reference signal RS, and / or the resource mapping location of the third RS; Receive third configuration information, which is used to configure a fourth RS, wherein the number of resource mapping locations of the fourth RS is greater than or equal to the number of resource mapping locations of the third RS.

18. The method according to claim 17, characterized in that, The first indication information includes one or more of the following: The first association identifier is an identifier of the association relationship between the resource mapping position of the first RS and the resource mapping position of the third RS, and the first RS is a demodulation associated reference signal; Alternatively, the index of the pattern corresponding to the resource mapping location of the third RS, wherein the pattern is predefined or preconfigured; Alternatively, the sampling density and / or starting offset of the resource mapping position of the third RS relative to the resource mapping position of the first RS; Alternatively, the index of the resource mapping location of the third RS.

19. The method according to claim 17 or 18, characterized in that, Before sending the first indication information, the method further includes: Receive fourth configuration information, which is used to configure the resource mapping location of the first RS; The resource mapping location of the third RS is determined based on the fourth configuration information.

20. A communication method, characterized in that, The method includes: Receive first indication information, the first indication information being used to indicate the capability of performing artificial intelligence (AI) demodulation based on a third reference signal RS, and / or the resource mapping location of the third RS; The third configuration information is sent according to the first instruction information. The third configuration information is used to configure the fourth RS. The number of resource mapping locations of the fourth RS is greater than or equal to the number of resource mapping locations of the third RS.

21. The method according to claim 20, characterized in that, The first indication information includes one or more of the following: The first association identifier is an identifier of the association relationship between the resource mapping position of the first RS and the resource mapping position of the third RS, and the first RS is a demodulation associated reference signal; Alternatively, the index of the pattern corresponding to the resource mapping location of the third RS, wherein the pattern is predefined or preconfigured; Alternatively, the sampling density and / or starting offset of the resource mapping position of the third RS relative to the resource mapping position of the first RS; Alternatively, the index of the resource mapping location of the third RS.

22. The method according to claim 20 or 21, characterized in that, Before receiving the first indication information, the method further includes: Send fourth configuration information, which is used to configure the resource mapping location of the first RS.

23. A communication device, characterized in that, include: One or more functional modules for performing the method as described in any one of claims 1-22.

24. A communication device, characterized in that, The device includes a processor and an interface circuit, wherein the interface circuit is used to receive signals from other communication devices and transmit them to the processor or to send signals from the processor to other communication devices, and the processor is used to implement the method as described in any one of claims 1-22 through logic circuits or executing code instructions.

25. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions, which, when executed by a communication device, implement the method as described in any one of claims 1-22.

26. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by the communication device, they implement the method as described in claims 1-22.

Images