Communication method and communication apparatus

Abstract

The present application provides a communication method and a communication apparatus. The method comprises: obtaining first information from a second apparatus, the first information being used for indicating N first probability distributions, the N first probability distributions being determined on the basis of N data features of first data, the first data being data collected by the second apparatus, and N being a positive integer; obtaining second data, the second data being at least one of the following: data generated by means of a simulation model, data generated by means of an algorithm, or data collected by a third apparatus; and on the basis of the N first probability distributions and N second probability distributions, processing the first data and / or the second data to obtain third data, the third data being used for training a first model, and the N second probability distributions being determined on the basis of N data features of the second data. The present application facilitates increasing the amount of training data without increasing the cost and / or difficulty of acquiring training data.

Description

Communication method and communication apparatus

[0001] This application claims priority to the Chinese Patent Application No. 202411383889.6, filed on September 30, 2024, and entitled "Communication method and communication apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, and more particularly, to a communication method and a communication apparatus. BACKGROUND

[0003] Currently, artificial intelligence (AI) is introduced into wireless communication networks and has been widely applied to many application scenarios of air interface technology, such as AI-based channel state information (CSI) prediction, AI-based beam management, AI-based CSI feedback, AI-based positioning, etc., and plays an increasingly important role.

[0004] In order to improve the accuracy of the AI model, as many training data as possible is needed to train the AI model. However, in some scenarios, it can not be possible to obtain enough training data for training the AI model. Or, in some scenarios, even if it is possible to obtain enough training data through the base station and / or user equipment (UE), it can not be possible to realize the acquisition of enough training data through the base station and / or UE for training the AI model due to cost problems. In summary, the existing way of collecting data for training the AI model has a large difficulty and / or cost. SUMMARY

[0005] The present application provides a communication method and a communication apparatus, which obtains the probability distribution of the training data collected by the second device through the generation model, and uses the probability distribution of the training data to fit more training data, thereby increasing the number of training data without increasing the cost and / or difficulty of obtaining the training data, thereby facilitating to improve the accuracy of training the model through the training data.

[0006] In a first aspect, a communication method is provided. The method comprises: obtaining first information from a second device, the first information being used to indicate N first probability distributions, the N first probability distributions being determined according to N data features of first data, the first data being data collected by the second device, N being a positive integer; obtaining second data, the second data being at least one of: data generated by a simulation model, data generated by an algorithm, or data collected by a third device; and processing the first data and / or the second data to obtain third data according to the N first probability distributions and N second probability distributions, the third data being used to train a first model, the N second probability distributions being determined according to N data features of the second data.

[0007] The method can be performed by a first device, which can be replaced by a device on a terminal device side, a device on a network device side, or a device on a core network element side.

[0008] The device on the terminal device side can include the terminal device itself, a communication module in the terminal device, or a circuit or chip responsible for communication functions in the terminal device (such as a modem chip, a baseband chip, or a system on chip (SoC) chip or a system in package (SIP) chip containing a modem core, etc.), or the device on the terminal device side can include an AI entity on the terminal device side. The AI entity on the terminal device side can be the terminal device itself, or an AI entity serving the terminal device, such as a server, for example, an over the top (OTT) server or a cloud server.

[0009] The device on the network device side can include the network device itself, a communication module in the network device, or a circuit or chip responsible for communication functions in the network device (such as a modem chip, a baseband chip, or a SoC chip or a SIP chip containing a modem core, etc.), or the device on the network device side can include an AI entity on the network device side. The AI entity on the network device side can be the network device itself, or an AI entity serving the network device, such as a radio access network (RAN) intelligent controller (RIC), an operation administration and maintenance (OAM), or a server, for example, an OTT server or a cloud server.

[0010] The device on the side of the core network element can include the core network element itself, a communication module in the core network element, or a circuit or chip (such as a modem chip, or a baseband chip, or a system on chip (SoC) chip or a SIP chip containing a modem core, etc.) responsible for communication functions in the core network element, or the device on the side of the core network element can include an AI entity on the side of the core network element. The AI entity on the side of the core network element can be the core network element itself, or an AI entity serving the core network element, such as a server, for example, an OTT server or a cloud server.

[0011] Based on the above technical solution, the first device can process the first data and / or the second data to obtain the third data according to the probability distribution of the first data and the probability distribution of the second data, so that the data used to train the first model is expanded from the first data to the first data and the third data, or the data used to train the first model is expanded from the second data to the second data and the third data, without increasing the cost and / or difficulty of the second device collecting data. In the case of increasing the data used to train the first model, it is beneficial to improve the performance of the first model trained.

[0012] For example, according to the N first probability distributions and the N second probability distributions, the first device determines N third probability distributions, and according to the N third probability distributions, the first device processes the first data and / or the second data to obtain the third data, wherein the N third probability distributions correspond to N data features respectively, and the data features of the third data include the N data features.

[0013] For example, the first device determines N third probability distributions according to the N first probability distributions and the N second probability distributions, and the N third probability distributions satisfy a first condition with the N first probability distributions, and then the first device processes the second data according to the N third probability distributions to obtain the third data.

[0014] The first condition can include one or more of the following: the similarity between the fourth probability distribution and the fifth probability distribution is greater than or equal to a first threshold value; or the difference between the fourth probability distribution and the fifth probability distribution is less than or equal to a second threshold value. The first threshold value and / or the second threshold value are predefined or preconfigured values.

[0015] The N first probability distributions include a fourth probability distribution, and the fourth probability distribution corresponds to a first data feature, and the first data feature is any one of the N data features. The N third probability distributions include a fifth probability distribution, and the fifth probability distribution corresponds to the first data feature.

[0016] It can be understood that the N third probability distributions and the N first probability distributions satisfying the first condition means that the third probability distributions and the first probability distributions corresponding to the same data features all satisfy the first condition.

[0017] For example, the first device determines N third probability distributions according to the N first probability distributions and the N second probability distributions, and the N third probability distributions and the N second probability distributions satisfy a second condition, and the first device processes the first data according to the N third probability distributions to obtain third data.

[0018] The second condition can include one or more of the following: a similarity between the sixth probability distribution and the fifth probability distribution is greater than or equal to a first threshold value; or a difference between the sixth probability distribution and the fifth probability distribution is less than or equal to a second threshold value. The first threshold value and / or the second threshold value are predefined or preconfigured values.

[0019] The N second probability distributions include a sixth probability distribution, and the sixth probability distribution corresponds to a first data feature. The first data feature is any one of the N data features. The N third probability distributions include a fifth probability distribution, and the fifth probability distribution corresponds to the first data feature.

[0020] It can be understood that the N third probability distributions and the N second probability distributions satisfying the second condition means that the third probability distributions and the second probability distributions corresponding to the same data features all satisfy the first condition.

[0021] In combination with the first aspect, in some implementations of the first aspect, the third data is input data for model training of the first model, and the N data features are related to input features of the first model; or the third data is a label for model training of the first model, and the N data features are related to output features of the first model.

[0022] In combination with the first aspect, in some implementations of the first aspect, the first data is obtained by the second device measuring at least one reference signal, and the N data features are related to one or more of the following: power, time delay, different streams of the at least one reference signal, different transmission antenna ports corresponding to the at least one reference signal, different reception antenna ports corresponding to the at least one reference signal, different frequency domain units of reference signal resources corresponding to the at least one reference signal, or different reference signals corresponding to different reference signal identifiers in the at least one reference signal.

[0023] For example, the first model is a model for positioning, and the first data can be a power delay profile (PDP) obtained by the second device measuring at least one reference signal, and the N data features of the first data can include power and time delay.

[0024] For another example, the first model is a model for compressing CSI and / or restoring compressed CSI, the first data can be channel state information (CSI) obtained by the second device by measuring at least one reference signal, and the N data features of the first data can be related to one or more of the following: different streams of the at least one reference signal, different transmission antenna ports corresponding to the at least one reference signal, different reception antenna ports corresponding to the at least one reference signal, different frequency domain units of reference signal resources corresponding to the at least one reference signal, or different reference signals in the at least one reference signal corresponding to different reference signal identifiers. The CSI can include one or more of the following: a channel response, a channel matrix, a channel feature matrix, a precoding matrix, a reference signal receiving power (RSRP), a signal to interference plus noise ratio (SINR), an identifier (ID) of an optimal beam, or an ID of top-K beams.

[0025] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: sending, to the second device, second information, the second information being used to indicate configuration parameters of the generated model, the configuration parameters of the generated model being used to determine the N first probability distributions.

[0026] Based on the above technical solutions, the first device can specify the configuration parameters of the generated model to the second device, so that the second device can generate and report the N first probability distributions based on the configuration parameters of the generated model specified by the first device. And based on the above technical solutions, the first device and the second device can align the configuration parameters of the generated model, thereby facilitating the first device to determine the N second probability distributions based on the N first probability distributions.

[0027] The second aspect provides a communication method, which includes: collecting first data; determining N first probability distributions based on N data features of the first data; N is a positive integer; and sending, to a first device, first information, the first information being used to indicate the N first probability distributions.

[0028] The method can be performed by the second device. The second device can be replaced by a device on a terminal equipment side or a device on a network equipment side.

[0029] The device on the terminal device side can include the terminal device itself, a communication module in the terminal device, or a circuit or chip (such as a modem chip, a baseband chip, or a system on chip (SoC) chip or a system in package (SIP) chip containing a modem core) responsible for a communication function in the terminal device, and the like.

[0030] The device on the network device side can include the network device itself, a communication module in the network device, or a circuit or chip (such as a modem chip, a baseband chip, or a SoC chip or a SIP chip containing a modem core) responsible for a communication function in the network device, and the like.

[0031] The beneficial effects of the second aspect can be referred to the description of the first aspect.

[0032] With reference to the second aspect, in some implementations of the second aspect, the first data is input data for model training of the first model, and / or the first data is used to determine input data for model training of the first model, and the N data features are related to input features of the first model; or the first data is a label for model training of the first model, and / or the first data is used to determine a label for model training of the first model, and the N data features are related to output features of the first model.

[0033] With reference to the second aspect, in some implementations of the second aspect, the collecting the first data includes: obtaining the first data by measuring at least one reference signal; and the N data features are related to one or more of the following: power, time delay, different streams of the at least one reference signal, different transmission antenna ports corresponding to the at least one reference signal, different reception antenna ports corresponding to the at least one reference signal, different frequency domain units of reference signal resources corresponding to the at least one reference signal, or different reference signals in the at least one reference signal corresponding to different reference signal identifiers.

[0034] With reference to the second aspect, in some implementations of the second aspect, the method further includes: receiving second information from the first device, the second information being used to indicate configuration parameters of the generated model, and the configuration parameters of the generated model being used to determine the N first probability distributions.

[0035] In a third aspect, a communication device is provided, which can be the first device, or a device or module for performing functions of the first device.

[0036] In a possible implementation, the communication apparatus can include a module or unit corresponding to each of the methods / operations / steps / actions described in the first aspect, which can be a hardware circuit, software, or a combination of hardware circuit and software.

[0037] In a design, the apparatus can include a processing module and a communication module. The communication module is configured to perform the sending actions and receiving actions performed by the first apparatus in the method described in the first aspect, and the processing module is configured to perform the processing-related actions performed by the first apparatus in the method described in the first aspect.

[0038] In a design, the apparatus can be a terminal device, or a device, module, circuit, or chip configured to be arranged in a terminal device, or a device capable of being used in combination with a terminal device, such as an OTT host or a cloud server.

[0039] In a design, the apparatus can be a network device, or a device, module, circuit, or chip configured to be arranged in a network device, or a device capable of being used in combination with a network device, such as an intelligent network element deployed with RIC.

[0040] In a design, the apparatus can be a core network element, or a device, module, circuit, or chip configured to be arranged in a core network element, or a device capable of being used in combination with a core network element, such as an intelligent network element deployed with RIC.

[0041] In a fourth aspect, a communication apparatus is provided. The communication apparatus can be the second apparatus, or a device or module for performing functions of the second apparatus.

[0042] In a possible implementation, the communication apparatus can include a module or unit corresponding to each of the methods / operations / steps / actions described in the second aspect, which can be a hardware circuit, software, or a combination of hardware circuit and software.

[0043] In a design, the apparatus can include a processing module and a communication module. The communication module is configured to perform the sending actions and receiving actions performed by the second apparatus in the method described in the second aspect, and the processing module is configured to perform the processing-related actions performed by the second apparatus in the method described in the second aspect.

[0044] In a design, the apparatus can be a terminal device, or a device, module, circuit, or chip configured to be arranged in a terminal device, or a device capable of being used in combination with a terminal device, such as an OTT host or a cloud server.

[0045] In an implementation, the apparatus is a communication device (e.g., a terminal device, a network device, or a core network element).

[0046] In a fifth aspect, a communication apparatus is provided. The apparatus includes at least one processor configured to execute computer program or instructions to perform the method in the first aspect and any possible implementation of the first aspect, or to perform the method in the second aspect and any possible implementation of the second aspect. Optionally, the apparatus further includes a memory configured to store the computer program or instructions. Optionally, the apparatus further includes a communication interface through which the processor reads the computer program or instructions.

[0047] In an implementation, the apparatus is a communication device (e.g., a terminal device, a network device, or a core network element).

[0048] In another implementation, the apparatus is a chip, chip system, or circuit for a communication device (e.g., a terminal device, a network device, or a core network element).

[0049] In a sixth aspect, a processor is provided. The processor is configured to perform the method in the first aspect, or to perform the method in the second aspect.

[0050] For the sending and obtaining / receiving operations of the processor, if no special description is provided, or if it does not contradict the actual role or inherent logic in the related description, it can be understood as the processor output and receive, input operations, or as the sending and receiving operations performed by the radio frequency circuit and the antenna, which are not limited in the present application.

[0051] Optionally, the apparatus further includes a memory configured to store programs. Correspondingly, the at least one processor is configured to execute the computer program or instructions in the memory.

[0052] Optionally, the apparatus further includes a communication interface. The communication interface is coupled with the processor, and can be used to input information to the processor, or output information in the processor.

[0053] In a seventh aspect, a computer readable storage medium is provided. The computer readable medium stores program codes for an apparatus to execute. The program codes include codes for performing the method in the first aspect and any possible implementation of the first aspect, or the program codes include codes for performing the method in the second aspect and any possible implementation of the second aspect.

[0054] In an eighth aspect, a computer program product including instructions, which, when executed on a computer, cause the computer to perform the method of the first aspect and any possible implementation of the first aspect, or cause the computer to perform the method of the second aspect and any possible implementation of the second aspect.

[0055] In a ninth aspect, a chip is provided, which includes a processing circuit and a communication interface. The processing circuit reads instructions on a memory through the communication interface, and executes the method provided by the first aspect and any possible implementation of the first aspect, or executes the method provided by the second aspect and any possible implementation of the second aspect.

[0056] Optionally, the processing circuit is one or more processors, or all or part of a circuit included in the one or more processors for control or processing.

[0057] Optionally, as an implementation form, the chip further includes a memory, and the memory stores a computer program or instructions. The processor is configured to execute the computer program or instructions on the memory. When the computer program or instructions are executed, the processor is configured to execute the method provided by the first aspect and any possible implementation of the first aspect, or execute the method provided by the second aspect and any possible implementation of the second aspect.

[0058] In a tenth aspect, a communication system is provided, which includes the first device and / or the second device. The first device is configured to implement the method provided by the first aspect and any possible implementation of the first aspect. The second device is configured to implement the method provided by the second aspect and any possible implementation of the second aspect.

[0059] It should be understood that the beneficial effects of the second aspect to the tenth aspect and any possible implementation thereof can refer to the first aspect and any possible implementation thereof. BRIEF DESCRIPTION OF DRAWINGS

[0060] FIG. 1 is a schematic diagram of a possible application framework in a communication system.

[0061] FIG. 2 is a schematic diagram of a possible application framework in a communication system.

[0062] FIG. 3 is a schematic diagram of a communication system suitable for the communication method according to the embodiments of the present application.

[0063] FIG. 4 is a schematic diagram of a communication system suitable for the communication method according to the embodiments of the present application.

[0064] FIG. 5 is a schematic diagram of a neuron structure.

[0065] FIG. 6 shows a schematic diagram of uplink positioning.

[0066] FIG. 7 shows a schematic diagram of an AI model based on auto-encoders (AE).

[0067] FIG. 8 shows a schematic flowchart of a communication method provided by an embodiment of the present application.

[0068] FIG. 9 shows a schematic flowchart of a communication method provided by an embodiment of the present application.

[0069] FIG. 10 shows a schematic diagram of probability distributions of pre-processed data and post-processed data provided by an embodiment of the present application.

[0070] FIG. 11 shows a schematic flowchart of a communication method provided by an embodiment of the present application.

[0071] FIG. 12 shows a schematic flowchart of a communication method provided by an embodiment of the present application.

[0072] FIG. 13 shows a schematic flowchart of a communication method provided by an embodiment of the present application.

[0073] FIG. 14 shows a schematic flowchart of a communication method provided by an embodiment of the present application.

[0074] FIG. 15 is a schematic diagram of a communication apparatus 2000 provided by an embodiment of the present application.

[0075] FIG. 16 is a schematic diagram of another communication apparatus 3000 provided by an embodiment of the present application. DETAILED DESCRIPTION

[0076] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0077] The technical solutions provided in the present application can be applied to various communication systems, for example, a 5th generation (5G) or new radio (NR) system, a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD) system, a wireless local area network (WLAN) system, a satellite communication system, a future communication system, or a fusion system of multiple systems, and the like. The technical solutions provided in the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and an internet of things (IoT) communication system or other communication systems.

[0078] A device in a communication system can send a signal to another device or receive a signal from another device. The signal can include information, signaling, or data, and the like. The device can also be replaced by an entity, a network entity, a communication device, a mobile device, a network element, a communication module, a node, a communication node, a communication apparatus, and the like. The device is taken as an example for description in the present disclosure. For example, the communication system can include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device.

[0079] In the embodiments of the present application, the terminal device can also be referred to as a user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user apparatus.

[0080] The terminal device can be a device providing voice / data, for example, a handheld device with wireless connection function, a vehicle-mounted device, etc. At present, some examples of terminals are: mobile phone, tablet computer, notebook computer, palm computer, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication function, computing device or other processing device connected to a wireless modem, wearable device, terminal device in a 5G network, or terminal device in a future evolved public land mobile network (PLMN), etc. The embodiments of the present application are not limited thereto.

[0081] By way of example and not limitation, in the embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing, and shoes. The wearable device is a portable device that is directly worn on the body or integrated into the user's clothes or accessories. The wearable device is not only a hardware device, but also a device that realizes powerful functions through software support and data interaction and cloud interaction. The general wearable smart device includes devices with full functions, large size, and the ability to realize complete or partial functions without relying on a smart phone, such as smart watches or smart glasses, and devices that focus on a certain application function and need to be used in cooperation with other devices, such as smart phones, such as various smart wristbands and smart jewelry for monitoring vital signs.

[0082] In the embodiments of the present application, the apparatus for implementing the function of the terminal device can be a terminal device, or can be an apparatus capable of supporting the terminal device to implement the function, for example, a chip system, which can be installed in the terminal device or used in matching with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or can include the chip and other discrete devices. In the embodiments of the present application, only the apparatus for implementing the function of the terminal device is taken as an example for description, and the scheme of the embodiments of the present application is not limited in this way.

[0083] The network device in the embodiments of the present application can include a device for communicating with a terminal device. For example, the network device can include an access network device or a radio access network device, such as a base station (BS). The radio access network device in the embodiments of the present application can refer to a radio access network (RAN) node (or device) that accesses a terminal device to a wireless network. The base station can broadly cover various names in the following or be replaced by the following names, such as: Node B (NodeB), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), primary station, secondary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. The base station can also refer to a communication module, modem, or chip used in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device that performs a base station function in D2D, V2X, M2M communication, a device that performs a base station function in a future communication system, etc. The base station can support networks of the same or different access technologies. Alternatively, the RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in the vehicle to everything (V2X) technology can be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form of the network device.

[0084] A base station can be fixed, or mobile. For example, a helicopter or unmanned aerial vehicle can be configured to function as a mobile base station, one or more cells can move according to the location of the mobile base station. In other examples, a helicopter or unmanned aerial vehicle can be configured to function as a device that communicates with another base station.

[0085] In some deployments, the network device mentioned in the embodiments of the present application can be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the network device can include a gNB-CU-CP, a gNB-CU-UP and a gNB-DU.

[0086] In some deployments, a plurality of RAN nodes cooperate to assist a terminal to implement wireless access, and different RAN nodes respectively implement part of the functions of a base station. For example, the RAN node can be a CU, a DU, a CU-CP, a CU-UP, or an RU, etc. The CU and the DU can be separately arranged, or can also be included in the same network element, for example, in a BBU. The RU can be included in a radio frequency device or a radio frequency unit, for example, included in an RRU, an AAU or an RRH.

[0087] The RAN node can support one or more types of fronthaul interfaces, different fronthaul interfaces respectively corresponding to DUs and RUs having different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more of baseband functions, and the RU is configured to implement one or more of radio frequency functions. If the fronthaul interface between the DU and the RU is another interface, which, relative to the CPRI, moves one or more of partial baseband functions of the downlink and / or uplink, such as, for the downlink, one or more of precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / add cyclic prefix (CP), from the DU to the RU for implementation, and for the uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / remove cyclic prefix (CP), from the DU to the RU for implementation. In a possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the splitting manner between the DU and the RU is different, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0088] Taking eCPRI Cat A as an example, for downlink transmission, with layer mapping as the cut, the DU is configured to implement layer mapping and one or more functions (i.e., one or more of encoding, rate matching, scrambling, modulation, layer mapping) before layer mapping, while other functions (e.g., one or more of RE mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / addition of cyclic prefix (CP)) after layer mapping are implemented in the RU. For uplink transmission, with de-RE mapping as the cut, the DU is configured to implement de-mapping and one or more functions (i.e., one or more of decoding, de-rate matching, de-scrambling, de-modulation, inverse discrete Fourier transform (IDFT), channel equalization, de-RE mapping) before de-mapping, while other functions (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) after de-mapping are implemented in the RU. It can be understood that the function description of the DU and the RU corresponding to various types of eCPRI can refer to the eCPRI protocol, which is not described here.

[0089] In a possible design, the processing unit in the BBU for implementing baseband functions is referred to as a base band high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is referred to as a base band low (BBL) unit.

[0090] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an open RAN (ORAN) system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. Any of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0091] In the embodiments of the present application, the apparatus for implementing the function of the network device can be a network device, or an apparatus capable of supporting the network device to implement the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The apparatus can be installed in the network device or used in combination with the network device. In the embodiments of the present application, only the apparatus for implementing the function of the network device is taken as an example for illustration, and the scheme of the embodiments of the present application is not limited in this way.

[0092] The network device and / or the terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on water; and can also be deployed on airplanes, balloons and satellites in the air. The scenarios in which the network device and the terminal device are located are not limited in the embodiments of the present application. In addition, the terminal device and the network device can be hardware devices, or software functions running on special hardware, software functions running on general hardware, such as virtualized functions instantiated on a platform (for example, a cloud platform), or entities including special or general hardware devices and software functions. The specific forms of the terminal device and the network device are not limited in the present application.

[0093] In a wireless communication network, for example, in a mobile communication network, the services supported by the network are increasingly diverse, and therefore the needs to be met are increasingly diverse. For example, the network needs to be able to support ultra-high rates, ultra-low latencies, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as the functions of the network become increasingly powerful, for example, supporting increasingly high frequency spectrums, supporting high-order multiple input multiple output (MIMO) technology, supporting beamforming, and / or supporting new technologies such as beam management, network energy saving has become a hot research topic. These new needs, new scenarios and new features bring unprecedented challenges to network planning, operation and efficient operation. In order to meet this challenge, artificial intelligence technology can be introduced into the wireless communication network, thereby realizing network intelligentization.

[0094] In order to support artificial intelligence (AI) technology in the wireless network, an AI node can also be introduced into the network.

[0095] Optionally, the AI node can be deployed in one or more of the following positions in the communication system: an access network device, a terminal device, or a core network device, etc., or the AI node can also be deployed separately, for example, deployed in a position other than any of the above devices, such as a host or a cloud server of an over the top (OTT) system. The AI node can communicate with other devices in the communication system, which can be one or more of the following: a wireless access network device, a terminal device, or a network element of a core network, etc.

[0096] It can be understood that the present application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, such as different AI nodes being responsible for different functions.

[0097] It can also be understood that the AI node can be a separate device, can be integrated into the same device to implement different functions, or can be a network element in a hardware device, or a software function running on a dedicated hardware, or a virtualized function instantiated on a platform (e.g., a cloud platform), and the present application does not limit the specific form of the AI node.

[0098] The AI node can be an AI network element or an AI module.

[0099] FIG. 1 is a schematic diagram of a possible application framework in a communication system. As shown in FIG. 1, the network elements in the communication system are connected through interfaces (such as next generation (NG) interfaces, Xn interfaces), or air interfaces. One or more AI modules (only one is shown in FIG. 1 for clarity) are provided in one or more of the following network element nodes: a core network device, an access network node or device (RAN node or device), a terminal, or one or more devices in operation administration and maintenance (OAM). The access network node can be a separate RAN node, or can include multiple RAN nodes, for example, including a CU and a DU. The CU and / or DU can also be provided with one or more AI modules. Optionally, the CU can also be split into a CU-CP and a CU-UP. One or more AI models are provided in the CU-CP and / or the CU-UP.

[0100] The AI module is used to implement a corresponding AI function. The AI modules deployed in different network elements can be the same or different. The AI module can implement different functions according to different parameter configurations of the model of the AI module. The model of the AI module can be configured based on one or more of the following parameters: a structure parameter (for example, at least one of a number of neural network layers, a width of a neural network, a connection relationship between layers, a weight of a neuron, an activation function of a neuron, or a bias in the activation function), an input parameter (for example, a type of input parameter and / or a dimension of the input parameter), or an output parameter (for example, a type of output parameter and / or a dimension of the output parameter). The bias in the activation function can also be referred to as a bias of the neural network.

[0101] One AI module can have one or more models. One model can infer an output including one parameter or multiple parameters. The learning process, the training process, or the inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0102] FIG. 2 is a schematic diagram of a possible application framework in a communication system. As shown in FIG. 2, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI module shown in FIG. 1, which is used to implement AI-related functions. The RIC includes a near-real time RIC (near-RT RIC) and a non-real time RIC (Non-RT RIC). The non-real time RIC mainly processes non-real-time information, such as data that is not sensitive to latency, which can be on the order of seconds. The real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to latency, which is on the order of tens of milliseconds.

[0103] The near-real-time RIC is used for model training and inference. For example, for training an AI model, inference is performed using the AI model. The near-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data. Optionally, the near-real-time RIC can submit inference results to RAN nodes and / or terminals. Optionally, the inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, the near-real-time RIC submits the inference results to the DU, and the DU sends the inference results to the RU.

[0104] The non-real-time RIC is also used for model training and inference. For example, the non-real-time RIC is used for training an AI model, and inference is performed using the model. The non-real-time RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., a CU, a CU-CP, a CU-UP, a DU, and / or a RU) and / or a terminal. The information can be used as training data or inference data, and the inference result can be delivered to the RAN node and / or the terminal. Alternatively, the inference result can be exchanged between a CU and a DU, and / or between a DU and a RU, for example, the non-real-time RIC delivers the inference result to the DU, and the inference result is further delivered to the RU by the DU.

[0105] The near-real-time RIC and the non-real-time RIC can be respectively configured as a network element alone. Alternatively, the near-real-time RIC and the non-real-time RIC can be part of other devices, for example, the near-real-time RIC is configured in a RAN node (e.g., a CU, a DU), and the non-real-time RIC is configured in an OAM, a cloud server, a core network device, or other network devices.

[0106] FIG. 3 is a schematic diagram of a communication system suitable for the communication method according to the embodiments of the present application. As shown in FIG. 3, the communication system 100 can include at least one network device, for example, the network device 110 shown in FIG. 3, and the communication system 100 can also include at least one terminal device, for example, the terminal device 120 and the terminal device 130 shown in FIG. 3. The network device 110 and the terminal devices (e.g., the terminal device 120 and the terminal device 130) can communicate with each other through wireless links. The communication devices in the communication system, for example, the network device 110 and the terminal device 120, can communicate with each other through multi-antenna technology.

[0107] FIG. 4 is a schematic diagram of a communication system suitable for the communication method according to the embodiments of the present application. Compared with the communication system 100 shown in FIG. 3, the communication system 200 shown in FIG. 4 further includes an AI network element 140. The AI network element 140 is used to perform AI-related operations, for example, constructing a training data set or training an AI model.

[0108] In a possible implementation, the network device 110 can send data related to the training of the AI model to the AI network element 140, the AI network element 140 constructs a training data set and trains the AI model. For example, the data related to the training of the AI model can include data reported by the terminal device. The AI network element 140 can send the result of the AI model related operation to the network device 110 and forward it to the terminal device through the network device 110. For example, the result of the AI model related operation can include at least one of the following: a trained AI model, an evaluation result or a test result of the model, and the like. For example, part of the trained AI model can be deployed on the network device 110, and the other part can be deployed on the terminal device. Alternatively, the trained AI model can be deployed on the network device 110. Alternatively, the trained AI model can be deployed on the terminal device.

[0109] It should be understood that FIG. 4 is only used as an example to illustrate that the AI network element 140 is directly connected to the network device 110, and in other scenarios, the AI network element 140 can also be connected to the terminal device. Alternatively, the AI network element 140 can be connected to both the network device 110 and the terminal device. Alternatively, the AI network element 140 can also be connected to the network device 110 through a third-party network element. The connection relationship between the AI network element and other network elements is not limited in the embodiments of the present application.

[0110] The AI network element 140 can also be set as a module in the network device and / or the terminal device, for example, in the network device 110 or the terminal device 120 shown in FIG. 3.

[0111] It should be noted that FIG. 3 and FIG. 4 are only simplified schematic diagrams for understanding, for example, the communication system can also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in FIG. 3 and FIG. 4. In actual application, the communication system can include multiple network devices and multiple terminal devices. The number of network devices and terminal devices included in the communication system is not limited in the embodiments of the present application.

[0112] In order to facilitate understanding of the scheme of the embodiments of the present application, the terms that can be involved in the embodiments of the present application are explained as follows.

[0113] (1) Artificial intelligence: It is to make the machine have learning ability and can accumulate experience to solve the problems that can be solved by human experience, such as natural language understanding, image recognition and chess playing. Artificial intelligence can be understood as the intelligence shown by the machine made by human. Artificial intelligence usually refers to the technology of presenting human intelligence through computer program. The goal of artificial intelligence includes understanding intelligence by constructing symbolic reasoning or reasoning computer program.

[0114] (2) Machine Learning (ML): is a way of implementing artificial intelligence. Machine learning is a method that can give a machine the ability to learn and complete functions that cannot be completed by direct programming. In a practical sense, machine learning is a method of training a model by using data and then using the model for prediction. There are many methods of machine learning, such as neural networks (NN), decision trees, support vector machines, etc. Machine learning theory is mainly about designing and analyzing algorithms that allow computers to automatically learn. Machine learning algorithms are a class of algorithms that automatically analyze rules from data and use the rules to predict unknown data.

[0115] (3) Neural Network: Neural network is a specific embodiment of machine learning method. Neural network is a mathematical model that simulates the behavior characteristics of animal neural network for information processing. As shown in FIG. 5, neural network is a network that can be composed of three types of calculation layers, input layer, hidden layer and output layer. Each layer has one or more logical judgment units, which are called neurons. Common neural network structures include feedforward neural network (FNN), convolutional neural network (CNN) and recurrent neural network (RNN), etc., which are all based on neurons. Among them, each neuron can perform weighted summation operation on its input value, and the result of the weighted summation operation is output through a nonlinear function. The weights of the neurons in the neural network and the nonlinear function can be referred to as the parameters of the neural network, the connection relationship between the neurons in the neural network can be referred to as the structure of the neural network, and all the parameters of the neurons in the neural network constitute the parameters of the neural network.

[0116] (4) Deep Neural Network: Neural network with multiple hidden layers.

[0117] (5) Deep Learning: Machine learning using deep neural networks.

[0118] (6) AI Model: is an algorithm or computer program that can realize AI function. The AI model represents the mapping relationship between the input and output of the model, or in other words, the AI model is a function model that maps a certain dimension of input to a certain dimension of output. The parameters of the function model can be obtained by machine learning training. For example, f(x) = ax 2+b is a quadratic function model, which can be regarded as an AI model, and a and b are parameters of the AI model, and a and b can be obtained by machine learning training. Exemplarily, the AI model mentioned in the embodiments below is not limited to a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q learning model or other machine learning (ML) models.

[0119] The implementation of the AI model can be hardware circuit, software, or a combination of software and hardware, without limitation. Non-limiting examples of software include program code, programs, subprograms, instructions, instruction sets, codes, code segments, software modules, applications, or software applications, etc.

[0120] (7) AI positioning: Machine learning can be used to enhance positioning accuracy, taking a plurality of channel responses as inputs of an AI model to obtain a final UE position. The AI model can be deployed at a location management function (LMF) side, or the UE / base station can extract features of the channel responses by using the AI model, and then the LMF takes the extracted features as inputs of the AI model to obtain the UE position.

[0121] FIG. 6 shows a schematic diagram of uplink positioning.

[0122] As shown in (a) of FIG. 6, the AI model is deployed at the LMF side, and the base station can obtain channel responses based on sounding reference signals (SRS) from the UE, and send the channel responses to the LMF. Then the LMF takes the channel responses from a plurality of base stations as inputs of the AI model to obtain the position information of the UE. Assuming that the number of antennas at the base station side is 16 and the number of subcarriers is 4096, each base station needs to send 16*4096 complex numbers to the LMF.

[0123] As shown in (b) of FIG. 6, the AI model is deployed at the base station and LMF sides. The base station can obtain channel responses based on SRS from the UE, and take the channel responses as inputs of the AI model at the base station side to obtain features extracted from the channel responses as outputs of the AI model at the base station side. Then the base station sends the extracted features of the channel responses to the LMF, and the LMF takes the features of the channel responses as inputs of the AI model at the LMF side to obtain the position information of the UE. The dimension of the features of the channel responses is determined by the output dimension of the AI model at the base station side, for example, the AI model at the base station side can extract features with a dimension of 128*1 from channel responses with a dimension of 16*4096.

[0124] The downlink positioning manner is similar to the uplink positioning manner, except that in the downlink positioning, the base station sends a positioning reference signal (PRS) to the UE, and the UE obtains a channel response based on the PRS from the base station and sends the channel response to the LMF or sends features extracted from the channel response based on the UE-side AI model.

[0125] (8) AI-based channel state information (CSI) feedback (denoted as AI-CSI feedback):

[0126] In LTE and NR communication systems, the base station needs to obtain downlink CSI for deciding the configurations of the downlink data channel of the UE, such as resource, modulation and coding scheme (MCS), and precoding. In a TDD system, since the uplink and downlink channels are reciprocal, the base station can obtain the uplink CSI by measuring the uplink reference signal and then infer the more accurate downlink CSI, for example, using the uplink CSI as the downlink CSI. In an FDD system, the uplink and downlink reciprocity cannot be guaranteed, and the downlink CSI is obtained by the UE measuring the downlink reference signal, such as the channel state information reference signal (CSI-RS) or the synchronizing signal / physical broadcast channel block (SSB), and thus the UE needs to generate a CSI report according to the protocol predefinition or the base station configuration and feed back the CSI report to the base station to obtain the downlink CSI.

[0127] An auto-encoder (AE) model is composed of an encoder and a decoder, and the AE can generally refer to a network structure composed of two sub-models. The AE model can also be called a bilateral model or a double-end model or a collaborative model. The encoder and the decoder of the AE are usually trained together and can be used together. As shown in FIG. 7, the AI-CSI feedback can be implemented based on the AI model of the AE, for example, the UE-side performs compression and quantization of the CSI through the encoder, and the base station performs recovery of the CSI through the decoder. For the base station, the input of the AI model is the CSI fed back by the UE, and the output is the recovered CSI. In the process of training the AI model on the base station side, the CSI measured by the UE side can be used as the true value label of the recovered CSI.

[0128] (8) Training data set and inference data:

[0129] In the field of machine learning, ground truth generally refers to data that is considered accurate or true.

[0130] The training dataset is used for the training of the AI model, and the training dataset can include the input of the AI model or the input and target output of the AI model. The training dataset includes one or more training data, and the training data can include a training sample input into the AI model or a target output of the AI model. The target output can also be referred to as a label, a sample label, or a label sample. The label is the ground truth.

[0131] In the field of communication, the training dataset can include simulation data collected through a simulation platform, experimental data collected in an experimental scenario, or measured data collected in an actual communication network. Due to differences in geographical environment and channel conditions, such as differences in indoor, outdoor, mobile speed, frequency band, or antenna configuration, when collecting data, the collected data can be classified. For example, data with the same channel propagation environment and antenna configuration are classified into the same category.

[0132] Model training essentially learns some features from the training data. In the process of training an AI model (such as a neural network model), because the output of the AI model is expected to be as close as possible to the value that is truly intended to be predicted, the weight vector of each layer of the AI model can be updated according to the difference between the predicted value of the current network and the truly intended target value. (Of course, before the first update, there is usually an initialization process, that is, the parameters of each layer of the AI model are pre-configured). For example, if the predicted value of the network is too high, adjust the weight vector to make it predict lower, and keep adjusting until the AI model can predict the truly intended target value or a value very close to the truly intended target value. Therefore, it is necessary to define "how to compare the difference between the predicted value and the target value", which is the loss function or the objective function, which is an important equation for measuring the difference between the predicted value and the target value. Taking the loss function as an example, the higher the output value (loss) of the loss function, the greater the difference, and the training of the AI model becomes a process of minimizing the loss, so that the value of the loss function is less than a threshold, or the value of the loss function meets the target requirement. For example, the AI model is a neural network, and adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers of the neural network, the width, the weight of the neuron, or the parameters of the activation function of the neuron.

[0133] The training processes of different models can be deployed in different devices or nodes, or in the same device or node. The inference processes of different models can be deployed in different devices or nodes, or in the same device or node. For example, the model parameters of an AI model can include one or more of the following: structural parameters (such as the number of layers of the model, and / or weights, etc.) of the model, input parameters (such as input dimensions, the number of input ports) of the model, or output parameters (such as output dimensions, the number of output ports) of the model. It can be understood that the input dimensions can refer to the size of an input data, for example, when the input data is a sequence, the input dimensions corresponding to the sequence can indicate the length of the sequence. The number of input ports can refer to the number of input data. Similarly, the output dimensions can refer to the size of an output data, for example, when the output data is a sequence, the output dimensions corresponding to the sequence can indicate the length of the sequence. The number of output ports can refer to the number of output data.

[0134] The inference data can be input to the trained AI model for inference of the AI model. In the model inference process, the inference data is input to the AI model, and the corresponding output, i.e., the inference result, can be obtained.

[0135] (9) Generative model:

[0136] A generative model refers to a model capable of randomly generating observation data, especially under the condition of given certain hidden parameters. In machine learning (ML), a generative model can be used to directly model data (e.g., data sampling according to a probability density function of a certain variable) or to establish a conditional probability distribution between variables. The conditional probability distribution can be formed by the generative model according to Bayes' theorem. For example, the data generation method of a generative model includes the following steps:

[0137] a) obtaining a probability distribution model of the training sample data according to a specific generative learning method;

[0138] b) data sampling on the obtained probability distribution model to obtain newly generated data samples.

[0139] A generative model represents the distribution of data from a statistical perspective and can reflect the similarity of the same data.

[0140] For example, a generative model includes but is not limited to a Naive Bayes method, a Markov model, and a Gaussian mixture model (GMM), which are generally based on statistics and Bayes theory.

[0141] For another example, the generative model based on the deep learning idea includes but is not limited to variational autoencoder (VAE) and generative adversarial networks (GAN).

[0142] (9-1) Gaussian mixture model:

[0143] The GMM is a generative model, which can be regarded as a model composed of K single Gaussian models (also referred to as sub-steps), and K is an integer greater than or equal to 1. The K single Gaussian models are the hidden variables of the mixture model. Generally, a mixture model can use any probability distribution. Here, the Gaussian mixture model GMM is used because the Gaussian distribution has good mathematical properties and good computational performance.

[0144] For example, the definition of a single Gaussian model can be that when the sample data X is one-dimensional data, the probability density function satisfied by the Gaussian distribution is shown in formula (1).

[0145] Where μ is the mean of the data, and σ is the standard deviation of the data.

[0146] When the sample data X is multi-dimensional data, the probability density function satisfied by the Gaussian distribution is shown in the following formula (2).

[0147] Where μ is the mean of the data, Σ is the covariance of the data, and D is the dimension of the data.

[0148] The probability distribution of the Gaussian mixture model GMM satisfies the following formula (3).

[0149] Where, generally, a complete mixture Gaussian model includes a covariance matrix, a parameter mean vector, and a mixing weight, which can be represented as θ, that is, α k respectively represent the expectation (or mean), variance (or covariance), and probability (which can be referred to as weight) of the kth single Gaussian model in the mixture model.

[0150] (9-2) Variational autoencoder;

[0151] The VAE is a generative model, which is a structure composed of an encoder and a decoder, and is trained to minimize the reconstruction error between the output data after the encoder and the decoder and the initial input data. Optionally, in order to introduce certain regularization of the hidden space, the VAE can modify the encoding-decoding process, that is, the input data is encoded into a probability distribution in the hidden space instead of a single point in the hidden space, and the specific implementation manner includes the following steps:

[0152] a) encode the input as a distribution over the latent space;

[0153] b) sample a point in the latent space from the distribution;

[0154] c) decode the sampled point and compute the reconstruction error;

[0155] d) the reconstruction error is backpropagated through the network.

[0156] (9-3) Generative Adversarial Networks (GANs);

[0157] GAN is a typical unsupervised learning method that can automatically extract features and complete data generation. GAN is composed of two important parts: one is the generator (generate data through neural network), which is used to generate data as similar as possible to the original data to deceive the discriminator; the second is the discriminator (judge whether the data is real or machine generated through neural network), which is used to find out the “false data” generated by the generator.

[0158] The essence of GAN is actually to use the powerful nonlinear fitting ability of neural network to learn the nonlinear mapping from an arbitrary prior noise distribution to the real data distribution, so as to enable the generator to have the ability to generate realistic samples. Among them, the input of GAN is an arbitrary noise distribution, and the final data generation is completed through the supervision of the original training data.

[0159] (10) Expectation Maximization (EM) algorithm;

[0160] EM algorithm is an iterative optimization strategy that can solve the problem of parameter estimation under data missing. The basic idea is: first, estimate the value of the model parameter according to the given observation data; then estimate the value of the missing data according to the value of the model parameter, and then estimate the value of the model parameter according to the value of the missing data plus the given observation data, and iterate until the last convergence, and the iteration ends.

[0161] In order to improve the accuracy of AI model, as many training data as possible are needed to train the AI model. However, in some scenarios, it may not be possible to obtain enough training data for training AI model. Or, in some scenarios, even if it is possible to obtain enough training data through base station and / or user equipment (UE), it may also be impossible to obtain enough training data through base station and / or UE for training AI model due to cost problems.

[0162] Therefore, the application provides a communication method, a probability distribution of training data collected by a second device is obtained by generating a model, and more training data is fitted using the probability distribution of the training data, so that the quantity of the training data is increased without increasing the cost and / or difficulty of obtaining the training data, thereby facilitating to improve the accuracy of training the model by using the training data.

[0163] Before introducing the scheme of the application, the following points are explained.

[0164] (1) In the present application, "indication" can include direct indication, indirect indication, display indication, and implicit indication. When describing that certain indication information is used to indicate A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A.

[0165] In the present application, the information indicated by the indication information is referred to as to-be-indicated information. In the specific implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or the index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, a protocol), thereby reducing the indication overhead to a certain extent. In addition, the to-be-indicated information can be sent as a whole, or can be sent separately in multiple sub-information, and the sending period and / or sending time of these sub-information can be the same or different.

[0166] (2) In the present application, "sending" and "receiving" represent the direction of signal transmission. For example, "sending information to XX" can be understood as that the destination of the information is XX, which can include direct sending through the air interface, or indirect sending through the air interface by other units or modules. "Receiving information from YY" can be understood as that the source of the information is YY, which can include direct receiving from YY through the air interface, or indirect receiving from YY through the air interface from other units or modules. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface. In other words, sending and receiving can be carried out between devices, for example, between network devices and terminal devices, or can be carried out within a device, for example, between components, modules, chips, software modules or hardware modules in a device through a bus, wire or interface.

[0167] (3) In various embodiments of the present application, the terms and / or descriptions among different embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0168] (4) In the present application, "first", "second", and "#1", "#2", etc. are only convenient for description, used for distinguishing objects, and do not limit the scope of the embodiments of the present application. They are not used to describe the order or sequence of features. It should be understood that the objects thus described can be interchanged under appropriate circumstances, so as to be able to describe schemes other than the embodiments of the present application.

[0169] (5) In the present application, "predefined" can mean standard protocol predefined, or can also mean pre-agreed or pre-negotiated between devices.

[0170] (6) In the present application, the words such as "exemplarily", "such as" and the like are used to represent examples, illustrations or descriptions. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of the word "example" is intended to present the concept in a specific way. In the embodiments of the present application, "of", "corresponding" and "corresponding" can be used interchangeably at times, and it should be pointed out that when their differences are not emphasized, the meanings they express are consistent.

[0171] (7) "At least one" in the present application means one or more. "Multiple" means two or more. "And / or" describes the association between the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In the textual description of the present application, the character " / ", generally represents that the associated objects before and after are in an "or" relationship; in the formula of the present application, the character " / ", represents that the associated objects before and after are in a "division" relationship. "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.

[0172] (8) The arrows or blocks shown by dashed lines in the schematic diagram in the drawing part of the present application specification represent optional steps or optional modules.

[0173] The communication method provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments provided by the present application can be applied to the communication system shown in FIG. 3 or FIG. 4, without limitation.

[0174] The first device in the following embodiments is a device that uses or infers according to a generative model, and the first device is also used to train a first model, which is an AI model.

[0175] The second device in the following embodiments is a device that trains or fits a generative model.

[0176] The first device and the second device can be the same device or different devices, which are not limited in the present application.

[0177] The first device can be replaced by a device on the terminal device side, a device on the network device side, or a device on the LMF side.

[0178] The device on the terminal device side can include the terminal device itself, a communication module in the terminal device, or a circuit or chip responsible for communication functions in the terminal device (such as a modem chip, such as a baseband chip, or a SoC chip containing a modem core or a SIP chip, etc.), or an AI entity on the terminal device side. The AI entity on the terminal device side can be the terminal device itself, or an AI entity serving the terminal device, such as a server, such as an OTT server or a cloud server.

[0179] The device on the network device side can include the network device itself, a communication module in the network device, or a circuit or chip responsible for communication functions in the network device (such as a modem chip, such as a baseband chip, or a SoC chip containing a modem core or a SIP chip, etc.), or an AI entity on the network device side. The AI entity on the network device side can be the network device itself, or an AI entity serving the network device, such as a RIC, OAM, or a server, such as an OTT server or a cloud server.

[0180] The device on the LMF side can include the LMF itself, a communication module in the LMF, or a circuit or chip responsible for communication functions in the LMF (such as a modem chip, such as a baseband chip, or a SoC chip containing a modem core or a SIP chip, etc.), or an AI entity on the LMF side. The AI entity on the LMF side can be the LMF itself, or an AI entity serving the LMF, such as a server, such as an OTT server or a cloud server.

[0181] The second device or the third device can be replaced by a device on the terminal device side or a device on the network device side

[0182] FIG. 8 shows a schematic flowchart of a communication method according to an embodiment of the present application. As shown in FIG. 8, the method 800 can include the following steps.

[0183] S810, the first device obtains first information.

[0184] The first information is used for indicating N first probability distributions, the N first probability distributions being determined according to N data features of the first data, the first data being data collected by the second device. N is a positive integer.

[0185] It should be noted that the first data can further include other data features different from the N data features, which are not limited in the present application.

[0186] For example, the first device obtains the first information from the second device. The first device obtaining the first information includes the following modes.

[0187] Mode 1, the first device and the second device are the same device, and then the first device obtains the first information, including: the first device determines the first information according to the first data. The first device determining the first information according to the first data can be understood as that the first device determines N first probability distributions corresponding to N data features of the first data respectively.

[0188] Mode 2, the first device and the second device are different devices, and then the first device obtains the first information, including: the first device receives the first information from the second device. Correspondingly, the second device collects the first data, and after obtaining N first probability distributions corresponding to N data features of the first data respectively, the second device sends the first information to the first device.

[0189] Mode 3, the first device and the second device are different devices, and then the first device obtains the first information, including: the first device receives the first data from the second device; and the first device determines the first information according to the first data. Correspondingly, the second device collects the first data, and sends the first data to the second device.

[0190] Optionally, if the first device receives the first information from the second device, the method 800 further includes: the first device sends second information to the second device, the second information being used for indicating configuration parameters of a generation model, the configuration parameters of the generation model being used for determining the N first probability distributions.

[0191] For example, the generation model is GMM, and the second information can include one or more of the following: a maximum value of the number of single Gaussian models included in the GMM, a generation method of the GMM, a convergence threshold of the GMM, a maximum value of the number of iterations of the GMM, model parameters of the GMM, a maximum value of expected values of single Gaussian models included in the GMM, a maximum value of variances or covariances of single Gaussian models included in the GMM, or a maximum proportion of one or more single Gaussian models included in the GMM in the GMM. The model parameters of the GMM can include one or more of the following: expected values of each single Gaussian model included in the GMM, variances or covariances of each single Gaussian model, and proportions (or weights) of each single Gaussian model in the GMM.

[0192] Exemplarily, the generation model is a VAE, and the second information can include one or more of the following: a value of a model parameter of the VAE, a structure parameter of the VAE, or a type of neural network used by the VAE. The model parameter of the VAE can include one or more of the following: a weight of a neuron, an activation function of a neuron, or a bias in the activation function of a neuron. The structure parameter of the VAE can include one or more of the following: a number of neural network layers used by the VAE, a number of neurons included in the neural network used by the VAE, a parameter related to an input layer of the VAE (i.e., an input parameter), a parameter related to a hidden layer of the VAE, or a parameter related to an output layer of the VAE (i.e., an output parameter). The type of neural network used by the VAE can be a deep neural network (DNN) or another neural network.

[0193] It should be understood that the generation model can also be of other types, which are not limited in the present application.

[0194] The N first probability distributions are described as follows.

[0195] The N first probability distributions are determined according to the N data features of the first data, in other words, the N first probability distributions are respectively probability distributions corresponding to the N data features of the first data.

[0196] Optionally, any two data features in the N data features are different.

[0197] Exemplarily, the N data features correspond one-to-one to the N first probability distributions. Taking a data feature #1 in the N data features as an example, the first probability distribution corresponding to the data feature #1 of the first data can be understood as a probability distribution of data corresponding to the data feature #1 included in the first data.

[0198] Exemplarily, the N data features are related to input features of the first model, or the N data features are related to output features of the first model. For example, the first data is input data for training the first model, and / or the first data is used to determine input data for training the first model, then the N data features of the first data are related to the input features of the first model. For example, the first data is a label for training the first model, and / or the first data is used to determine a label for training the first model, then the N data features of the first data are related to the output features of the first model.

[0199] For example, the first data is obtained by the second device measuring at least one reference signal, and the N data features of the first data are related to one or more of the following: power, delay, different streams of the at least one reference signal, different transmission antenna ports corresponding to the at least one reference signal, different reception antenna ports corresponding to the at least one reference signal, different frequency domain units of reference signal resources corresponding to the at least one reference signal, or different reference signals in the at least one reference signal corresponding to different reference signal identifiers.

[0200] For example, the first model is a model for positioning, and the first data is a power delay profile (PDP) obtained by the second device measuring at least one reference signal, and the N data features of the first data can include power and delay.

[0201] For example, the first model is a model for compressing CSI and / or recovering compressed CSI, and the first data is CSI obtained by the second device measuring at least one reference signal, and the N data features of the first data can be related to one or more of the following: different streams of the at least one reference signal, different transmission antenna ports corresponding to the at least one reference signal, different reception antenna ports corresponding to the at least one reference signal, different frequency domain units of reference signal resources corresponding to the at least one reference signal, or different reference signals in the at least one reference signal corresponding to different reference signal identifiers. The CSI can include one or more of the following: channel response, channel matrix, channel feature matrix, precoding matrix, reference signal receiving power (RSRP), signal to interference plus noise ratio (SINR), identifier (ID) of an optimal beam, or identifier of top-K beams.

[0202] The at least one reference signal can comprise reference signals transmitted by the same device to the second device, or reference signals transmitted by different devices to the second device. The type of reference signal can be any one of: a sounding reference signal (SRS), a demodulation reference signal (DMRS), a phase tracking reference signal (PT-RS), a channel state information reference signal (CSI-RS), or a synchronization signal (SS), etc. The synchronization signal can comprise a primary synchronization signal (PSS) and a secondary synchronization signal (SSS).

[0203] The frequency domain unit can be one of: a subchannel, a subband, a physical resource block (PRB), a resource element (RE), a subcarrier, a carrier, a bandwidth part (BWP), etc.

[0204] For example, the N data features comprise a time delay and a power, and the value of N is 2. For another example, the N data features are related to one or more of: different streams of the at least one reference signal, different transmission antenna ports corresponding to the at least one reference signal, different reception antenna ports corresponding to the at least one reference signal, different frequency domain units of reference signal resources corresponding to the at least one reference signal, or different reference signals in the at least one reference signal corresponding to different reference signal identifiers, and the value of N is related to one or more of: a number Z of streams of the at least one reference signal, a number T of transmission antenna ports corresponding to the at least one reference signal, a number R of reception antenna ports corresponding to the at least one reference signal, a number P of frequency domain units included in the reference signal resources corresponding to the at least one reference signal, or a number S of reference signals in the at least one reference signal corresponding to different reference signal identifiers. Z, T, R, P and S are all positive integers.

[0205] For example, if N data features include different transmit antenna ports corresponding to at least one reference signal, then the value of N is equal to T, meaning that the N data features are equivalent to T transmit antenna ports corresponding to at least one reference signal. Correspondingly, the N first probability distributions include the probability distributions of the data in the first data corresponding to each of the T transmit antenna ports.

[0206] For another example, if N data features include different transmit antenna ports and receive antenna ports corresponding to at least one reference signal, then the value of N is equal to R×T, meaning that each data feature in the N data features is one antenna port combination among R×T antenna port combinations. Correspondingly, the N first probability distributions include the probability distributions of the data corresponding to each antenna port combination among the R×T antenna port combinations in the first data. Each antenna combination among the R×T antenna combinations includes one transmit antenna port from T transmit antenna ports and one receive antenna port from R receive antenna ports, and different antenna combinations among the R×T antenna combinations include different transmit antenna ports and / or receive antenna ports.

[0207] When N data features are related to one or more of the other items mentioned above, the method for determining the value of N can be referred to the examples above, and will not be described in detail here.

[0208] The first piece of information is described below.

[0209] The first piece of information is related to the generative models corresponding to the N first probability distributions.

[0210] For example, if the generative model corresponding to the N first probability distributions is a GMM, in other words, if all N first probability distributions are GMM probability distributions, then the first information may include one or more of the following: the value of at least one expected value corresponding to each of the N first probability distributions, the value of at least one variance or covariance corresponding to each first probability distribution, or the proportion of at least one single Gaussian model corresponding to each first probability distribution in the Gaussian mixture model.

[0211] In this context, the number of expected values, variances, or covariances corresponding to each of the N first probability distributions is the same as the number of single Gaussian models included in each first probability distribution. For example, if probability distribution #1 among the N first probability distributions includes k single Gaussian models, then the first information may include one or more of the following: the k expected values ​​corresponding to probability distribution #1. The value of , k variances or covariance The value of , or the proportion of k single Gaussian models in the Gaussian mixture model. The values ​​of , k expected values, k variances or covariances correspond one-to-one with k single Gaussian models.

[0212] More description about GMM can be referred to the above, which will not be repeated here for brevity.

[0213] For example, the N first probability distributions correspond to a VAE, in other words, each of the N first probability distributions is a VAE probability distribution, and the first information can include values of model parameters of the VAE corresponding to each of the N first probability distributions. The model parameters of the VAE can include one or more of the following: weights of neurons, or biases in activation functions of neurons (or biases of neural networks).

[0214] More description about VAE can be referred to the above, which will not be repeated here for brevity.

[0215] It should be noted that the above describes the first information by taking the GMM or the VAE as an example of the generation model corresponding to the N first probability distributions, and the present application does not limit the generation model corresponding to the N first probability distributions. It can be understood that if the generation model corresponding to the N first probability distributions is another generation model, for example, a GAN, the first information includes parameters related to the GAN.

[0216] Optionally, the method 800 further includes: the first device obtains the first data.

[0217] For example, the first device and the second device are the same device, and the first device obtaining the first data includes: the first device collecting the first data. For example, the first device obtains the first data by measuring at least one reference signal.

[0218] For example, the first device and the second device are different devices, and the first device obtaining the first data includes: the first device receiving the first data from the second device. Correspondingly, the second device sends the first data to the first device.

[0219] S820, the first device obtains the second data.

[0220] The second data is at least one of the following: data generated by a simulation model, data generated by an algorithm, or data collected by a third device. The third device and the second device are different devices.

[0221] For example, the parameters used to generate the second data by the simulation model or the algorithm are related to the way in which the second device collects the first data. For example, the first data is data obtained by the second device by measuring at least one reference signal, and the second data can be data generated by taking transmission parameters and / or reception parameters of the at least one reference signal as parameters of the simulation model or the algorithm.

[0222] For example, the second data is data collected by the third device, and the third device collects the second data in the same way as the second device collects the first data. For example, the first data is data obtained by the second device by measuring at least one reference signal, and the second data is data obtained by the third device by measuring at least one reference signal.

[0223] S830, the first device processes the first data and / or the second data to obtain third data according to the N first probability distributions and the N second probability distributions.

[0224] The N second probability distributions are determined according to N data characteristics of the second data.

[0225] For example, the N data characteristics of the first data are related to the input characteristics of the first model, and the N data characteristics of the second data are related to the input characteristics of the first model; the N data characteristics of the first data are related to the output characteristics of the first model, and the N data characteristics of the second data are related to the output characteristics of the first model. For example, the N data characteristics of the first data include time delay and power, and the N data characteristics of the second data include time delay or power. For another example, the N data characteristics of the first data include RXT antenna port combinations, and the N data characteristics of the second data include RXT antenna port combinations. The description of the antenna port combination can be referred to S810.

[0226] For example, the first device processes the first data and / or the second data according to the N first probability distributions and the N second probability distributions includes: the first device determines N third probability distributions according to the N first probability distributions and the N second probability distributions; the first device processes the first data and / or the second data according to the N third probability distributions to obtain third data.

[0227] The N third probability distributions correspond to N data characteristics of the third data respectively. The N data characteristics of the third data are the same as the N data characteristics of the first data. For example, the N data characteristics of the first data are related to the input characteristics of the first model, and the N data characteristics of the third data are related to the input characteristics of the first model; the N data characteristics of the first data are related to the output characteristics of the first model, and the N data characteristics of the third data are related to the output characteristics of the first model. For example, the N data characteristics of the first data include time delay and power, and the N data characteristics of the third data include time delay or power. For another example, the N data characteristics of the first data include RXT antenna port combinations, and the N data characteristics of the third data include RXT antenna port combinations. The description of the antenna port combination can be referred to S810.

[0228] The following describes a manner in which the first apparatus processes the first data and / or the second data according to the N third probability distributions to obtain third data.

[0229] In a possible implementation, the first apparatus processes the second data according to the N third probability distributions to obtain third data.

[0230] For example, the first apparatus processes the second data according to the N third probability distributions to obtain third data, when the N third probability distributions determined according to the N first probability distributions and the N second probability distributions satisfy a first condition.

[0231] The first condition can include one or more of the following: a similarity between a fourth probability distribution and a fifth probability distribution is greater than or equal to a first threshold value; or a difference between the fourth probability distribution and the fifth probability distribution is less than or equal to a second threshold value. The first threshold value and / or the second threshold value is a predefined or preconfigured value.

[0232] The N first probability distributions include the fourth probability distribution, and the fourth probability distribution corresponds to a first data feature. The first data feature is any one of the N data features. The N third probability distributions include the fifth probability distribution, and the fifth probability distribution corresponds to the first data feature.

[0233] It can be understood that the N third probability distributions and the N first probability distributions satisfying the first condition means that the third probability distribution and the first probability distribution corresponding to the same data feature both satisfy the first condition.

[0234] In a possible implementation, the first apparatus processes the first data according to the N third probability distributions to obtain third data.

[0235] For example, the first apparatus processes the first data according to the N third probability distributions to obtain third data, when the N third probability distributions determined according to the N first probability distributions and the N second probability distributions satisfy a second condition.

[0236] The second condition can include one or more of the following: a similarity between a sixth probability distribution and the fifth probability distribution is greater than or equal to the first threshold value; or a difference between the sixth probability distribution and the fifth probability distribution is less than or equal to the second threshold value. The first threshold value and / or the second threshold value is a predefined or preconfigured value.

[0237] The N second probability distributions include the sixth probability distribution, and the sixth probability distribution corresponds to the first data feature. The first data feature is any one of the N data features. The N third probability distributions include the fifth probability distribution, and the fifth probability distribution corresponds to the first data feature.

[0238] It can be understood that the N third probability distributions satisfying the second condition with the N second probability distributions means that the third probability distribution and the second probability distribution corresponding to the same data feature both satisfy the first condition.

[0239] In a possible implementation, the first device processes the first data and the second data according to the N third probability distributions to obtain third data.

[0240] For example, the first device determines the N third probability distributions according to the N first probability distributions and the N second probability distributions, each of the N third probability distributions includes a probability distribution #X and a probability distribution #Y. The N probability distributions #X included in the N third probability distributions satisfy the first condition with the N first probability distributions, and the first device processes the second data according to the N probability distributions #X to obtain data #X included in the third data. The N probability distributions #Y included in the N third probability distributions satisfy the second condition with the N second probability distributions, and the first device processes the first data according to the N probability distributions #Y to obtain data #Y included in the third data.

[0241] After the first device obtains the third data, the first device can train the first model according to the third data, in other words, the third data is used to train the first model. The training can be original training (or initial training), retraining, model updating or model fine-tuning, etc.

[0242] For example, if the first device processes the second data to obtain the third data, and the first device obtains the first data, the first device can train the first model according to the first data and the third data.

[0243] For example, if the first device processes the first data to obtain the third data, the first device can train the first model according to the second data and the third data.

[0244] For example, if the first device processes the first data and the second data to obtain the third data, the first device can train the first model according to the first data and the data #X, or according to the second data and the data #Y.

[0245] In the embodiments of the present application, the first device can process the first data and / or the second data according to the probability distribution of the first data and the probability distribution of the second data to obtain the third data, so that the data used to train the first model is expanded from the first data to the first data and the third data, or the data used to train the first model is expanded from the second data to the second data and the third data, without increasing the cost and / or difficulty of the second device collecting data. In the case of increasing the data used to train the first model, it is beneficial to improve the performance of the first model trained.

[0246] The communication method provided by the present application is described below in combination with FIG. 9 to FIG. 12.

[0247] FIG. 9 shows a schematic flowchart of the communication method provided by the embodiment of the present application. As shown in FIG. 9, the method 900 can include the following steps. It should be noted that in the method shown in FIG. 9, the first model is used for positioning, the first device is a device on the side of a core network network element (for example, LMF), and the second device is a device on the side of an access network device.

[0248] S910, the core network network element sends second information.

[0249] Correspondingly, the access network device receives the second information.

[0250] The second information is used to indicate the configuration parameters of the generated model. More description of the second information can be referred to S810 above.

[0251] It should be noted that S910 is an optional step. For example, the configuration parameters of the generated model are predefined or preconfigured, and then the method 900 can not perform S910.

[0252] S920, the terminal device sends SRS.

[0253] Correspondingly, the access network device receives the SRS.

[0254] It should be noted that the method 900 is described by taking the terminal device sending SRS as an example. The terminal device can also send other types of reference signals, such as DMRS, to the access network device.

[0255] S930, the access network device obtains first data by measuring the SRS.

[0256] The first data is the time delay information and / or power information (denoted as time delay information#a and / or power information#a) of the SRS obtained by the access network device by measuring the SRS. For example, if the first data is the time delay information and the power information of the SRS, the first data can be referred to as the PDP of the SRS.

[0257] S940, the access network device obtains N first probability distributions.

[0258] For example, the N first probability distributions include: the probability distribution of the time delay information#a (denoted as probability distribution#a), and / or the probability distribution of the power information#a (denoted as probability distribution#b).

[0259] S950, the access network device sends first information.

[0260] Correspondingly, the core network network element receives the first information.

[0261] The first information is used to indicate the N first probability distributions.

[0262] For example, the N first probability distributions correspond to a GMM, and the first information includes one or more of the following: expected values of each single Gaussian model included in the probability distribution #a, variances or covariances of each single Gaussian model included in the probability distribution #a, proportions of each single Gaussian model included in the probability distribution #a in the GMM, expected values of each single Gaussian model included in the probability distribution #b, variances or covariances of each single Gaussian model included in the probability distribution #b, or proportions of each single Gaussian model included in the probability distribution #b in the GMM.

[0263] In S960, the core network element processes the first data and / or the second data according to the N first probability distributions and the N second probability distributions to obtain third data.

[0264] The second data is delay information and / or power information (denoted as delay information #b and / or power information #b) of the SRS generated by the core network element through the simulation model or the algorithm, or is delay information and / or power information (denoted as delay information #c and / or power information #c) of the SRS obtained by another access network device through measurement of the SRS from the terminal device.

[0265] For example, the N second probability distributions include a probability distribution (denoted as probability distribution #c) of the delay information #b (or the delay information #c), and / or a probability distribution (denoted as probability distribution #d) of the power information #b (or the power information #c).

[0266] It can be understood that the third data obtained by the core network element includes delay information and / or power information (denoted as delay information #d and / or power information #d) of the SRS.

[0267] More description of S960 can be referred to S830.

[0268] FIG. 10 shows a schematic diagram of the probability distribution #b, the probability distribution #d, and a probability distribution #f, which is a probability distribution of the power information #d obtained by processing the power information #a. As shown in FIG. 10, compared with the probability distribution #b, the probability distribution #f is closer to the probability distribution #d.

[0269] In S970, the core network element trains the first model according to the third data.

[0270] It should be noted that the access network device uses the trained first model for model inference, or the access network device uses a second model matched with the trained first model for model inference.

[0271] In the embodiments of the present application, the access network device can report the probability distribution of the measurement result (including the delay information and / or the power information) of the SRS to the core network element, and then the core network element can process the measurement result of the SRS measured by the access network device and / or the measurement result of the SRS obtained through simulation (or the measurement result of the SRS measured by other access network device) according to the information reported by the access network device, so that the processed data can be used for training the first model, thereby facilitating the expansion of the data amount used for training the first model without increasing the data collection cost and / or difficulty of the access network device. In the case of increasing the data used for training the first model, the performance of the first model trained is improved.

[0272] FIG. 11 shows a schematic flowchart of a communication method according to an embodiment of the present application. As shown in FIG. 11, the method 1100 can include the following steps. It should be noted that in the method shown in FIG. 11, the first model is used for positioning, the first device is a device on the side of the core network element (such as LMF), and the second device is a device on the side of the terminal device.

[0273] S1110, the core network element sends second information.

[0274] Correspondingly, the terminal device receives the second information.

[0275] The second information is used to indicate the configuration parameters of the generated model. For more description of the second information, please refer to S810 above.

[0276] It should be noted that S1110 is an optional step. For example, the configuration parameters of the generated model are predefined or preconfigured, and then the method 1100 can not perform S1110.

[0277] S1120, the access network device sends PRS.

[0278] Correspondingly, the terminal device receives the PRS.

[0279] It should be noted that the method 1100 is described by taking the access network device sending PRS as an example. The access network device can also send other types of reference signals to the terminal device, such as DMRS, CSI-RS, etc.

[0280] S1130, the terminal device obtains first data by measuring the PRS.

[0281] The first data is the delay information and / or power information (denoted as delay information#a1 and / or power information#a1) of the PRS obtained by the terminal device by measuring the PRS. For example, if the first data is the delay information and power information of the PRS, the first data can be referred to as the PDP of the PRS.

[0282] S1140, The terminal device obtains N first probability distributions.

[0283] For example, the N first probability distributions include: the probability distribution of time delay information #a1 (denoted as probability distribution #a1), and / or, the probability distribution of power information #a1 (denoted as probability distribution #b1).

[0284] S1150, the terminal device sends the first information.

[0285] Correspondingly, the core network elements receive the first information.

[0286] The first information is used to indicate N first probability distributions.

[0287] For example, if the generative model corresponding to the N first probability distributions is a Gaussian Mixture Model (GMM), then the first information includes one or more of the following: the expected value of each single Gaussian model included in probability distribution #a1, the variance or covariance of each single Gaussian model included in probability distribution #a1, the proportion of each single Gaussian model included in probability distribution #a1 in the Gaussian Mixture Model, the expected value of each single Gaussian model included in probability distribution #b1, the variance or covariance of each single Gaussian model included in probability distribution #b1, or the proportion of each single Gaussian model included in probability distribution #b1 in the Gaussian Mixture Model.

[0288] S1160, the core network element processes the first data and / or the second data according to N first probability distributions and N second probability distributions to obtain the third data.

[0289] The second data is the delay information and / or power information of the PRS generated by the core network element through a simulation model or algorithm (denoted as delay information #b1 and / or power information #b1), or the delay information and / or power information obtained by another terminal device by measuring the PRS from the access network device (denoted as delay information #c1 and / or power information #c1).

[0290] For example, the N second probability distributions include: the probability distribution of delay information #b1 (or delay information #c1) (denoted as probability distribution #c1), and / or, the probability distribution of power information #b1 (or power information #c1) (denoted as probability distribution #d1).

[0291] It is understood that the third data obtained by the core network elements includes the PRS delay information and / or power information (denoted as delay information #d1 and / or power information #d1).

[0292] For more details on S1160, please refer to the above text on S830.

[0293] S1170, the core network elements train the first model based on the third data.

[0294] It should be noted that the terminal device performs model inference using the first model trained, or the terminal device performs model inference using the second model matched with the first model trained.

[0295] In the embodiments of the present application, the terminal device can report the probability distribution of the measurement result (including the delay information and / or the power information) of the PRS to the core network element, and then the core network element can process the measurement result of the PRS measured by the terminal device and / or the measurement result of the PRS obtained through simulation (or the measurement result of the PRS measured by other terminal devices) according to the information reported by the terminal device, so that the processed data can be used for training the first model, thereby facilitating the expansion of the amount of data used for training the first model without increasing the data collection cost and / or difficulty of the terminal device. In the case of increasing the data used for training the first model, it is beneficial to improve the performance of the first model trained.

[0296] FIG. 12 shows a schematic flowchart of a communication method according to an embodiment of the present application. As shown in FIG. 12, the method 1200 can include the following steps. It should be noted that in the method shown in FIG. 12, the first model is used to compress CSI and / or recover compressed CSI, the first device is a device on the side of the access network equipment, and the second device is a device on the side of the terminal device.

[0297] S1210, the access network equipment sends second information.

[0298] Correspondingly, the terminal device receives the second information.

[0299] The second information is used to indicate the configuration parameters of the generated model. For more description of the second information, please refer to S810 above.

[0300] It should be noted that S1210 is an optional step. For example, the configuration parameters of the generated model are predefined or preconfigured, and then the method 1200 can not perform S1210.

[0301] S1220, the access network equipment sends CSI-RS.

[0302] Correspondingly, the terminal device receives the CSI-RS.

[0303] It should be noted that the method 1200 is described by taking the access network equipment sending the CSI-RS as an example. The access network equipment can also send other types of reference signals, such as DMRS, to the terminal device.

[0304] S1230, the terminal device obtains first data by measuring the CSI-RS.

[0305] The first data is CSI#1 of the CSI-RS obtained by the terminal device through measuring the CSI-RS. The CSI can include one or more of the following: channel response, channel matrix, channel eigenmatrix, precoding matrix, RSRP, SINR, ID of the optimal beam, or ID of the top-K beams.

[0306] In S1240, the terminal device obtains N first probability distributions.

[0307] For example, the N first probability distributions include: a probability distribution (denoted as probability distribution #a2) of the CSI corresponding to the receiving port #1 of the terminal device included in the CSI#1, and / or a probability distribution (denoted as probability distribution #b2) of the CSI corresponding to the receiving port #2 of the terminal device included in the CSI#1.

[0308] In S1250, the terminal device sends first information.

[0309] Correspondingly, the access network device receives the first information.

[0310] The first information is used to indicate the N first probability distributions.

[0311] For example, the N first probability distributions correspond to a GMM, and the first information includes one or more of the following: an expectation value of each single Gaussian model included in the probability distribution #a2, a variance or covariance of each single Gaussian model included in the probability distribution #a2, a proportion of each single Gaussian model included in the probability distribution #a2 in the GMM, an expectation value of each single Gaussian model included in the probability distribution #b2, a variance or covariance of each single Gaussian model included in the probability distribution #b2, or a proportion of each single Gaussian model included in the probability distribution #b2 in the GMM.

[0312] In S1260, the access network device processes the first data and / or the second data to obtain third data according to the N first probability distributions and the N second probability distributions.

[0313] The second data is CSI (denoted as CSI#2) generated by the access network device through a simulation model or an algorithm, or is CSI (denoted as CSI#3) obtained by another terminal device through measuring the CSI-RS from the access network device.

[0314] For example, the N second probability distributions include: a probability distribution (denoted as probability distribution #c2) of the CSI corresponding to the receiving port #1 of the terminal device included in the CSI#2 (or CSI#3), and / or a probability distribution (denoted as probability distribution #d2) of the CSI corresponding to the receiving port #2 of the terminal device included in the CSI#2 (or CSI#3).

[0315] It can be understood that the third data obtained by the access network device is CSI (denoted as CSI#4).

[0316] More description of S1260 can be referred to S830 above.

[0317] S1270, the access network device trains the first model according to the third data.

[0318] It should be noted that the terminal device uses the trained first model for model inference, or the terminal device uses the second model matched with the trained first model for model inference.

[0319] In the embodiments of the present application, the terminal device can report the probability distribution of the CSI corresponding to each data feature (such as the receiving port) included in the CSI to the access network device, and then the access network device can process the CSI measured by the terminal device and / or the CSI obtained by simulation (or the CSI measured by other terminal devices) according to the information reported by the terminal device, so that the processed data can be used for training the first model, thereby facilitating the expansion of the data amount used for training the first model without increasing the data collection cost and / or difficulty of the terminal device. In the case of increasing the data used for training the first model, it is beneficial to improve the performance of the trained first model.

[0320] As described above, the first device can be replaced by at least one of the device (such as the terminal device, the access network device or the core network element) or the AI entity on the device side. If the first device is replaced by the device and the AI entity on the device side, the following steps in the above embodiments can be performed by the AI entity of the device: processing the first data and / or the second data to obtain the third data according to the probability distribution of the first data and the probability distribution of the second data.

[0321] Taking the first device as the core network element (such as LMF) for example, the AI entity on the side of the core network element can be an intelligent network element (such as RIC, OAM, host of OTT system or cloud server, etc.), then S830 in method 800 shown in FIG. 8, S960 and / or S970 in method 900 shown in FIG. 9 or S1160 and / or S1170 in method 1100 shown in FIG. 11 can be executed by the intelligent network element.

[0322] For example, FIG. 13 shows a schematic flowchart of the method provided by the present application from the perspective of the interaction of the intelligent network element, the core network element, the terminal device and the access network device. The intelligent network element is an AI entity on the side of the core network element.

[0323] As shown in FIG. 13, the method 1300 can include the following steps.

[0324] S1310, the core network element sends the second information.

[0325] Correspondingly, the access network device receives the second information.

[0326] S1310 can refer to S910 in the above method 900.

[0327] S1320, the terminal device sends the SRS.

[0328] Correspondingly, the access network device receives the SRS.

[0329] S1320 can refer to S920 in the above method 900.

[0330] S1330, the access network device obtains the first data by measuring the SRS.

[0331] S1330 can refer to S930 in the above method 900.

[0332] S1340, the access network device obtains N first probability distributions.

[0333] S1340 can refer to S940 in the above method 900.

[0334] S1350, the access network device sends the first information.

[0335] Correspondingly, the core network element receives the first information.

[0336] S1350 can refer to S950 in the above method 900.

[0337] S1360, the core network element sends the first information.

[0338] Correspondingly, the intelligent network element receives the first information.

[0339] It should be noted that S1350 and S1360 can be combined into one step, that is, the access network device can directly send the first information to the intelligent network element without forwarding through the core network element. Correspondingly, the intelligent network element directly receives the first information from the access network device.

[0340] S1370, the intelligent network element processes the first data and / or the second data to obtain third data according to the N first probability distributions and the N second probability distributions.

[0341] S1370 can refer to 960 in the above method 900.

[0342] S1380, the core network element trains the first model according to the third data.

[0343] S1380 can refer to S970 in the above method 900.

[0344] For example, the flow of the intelligent network element, the core network element, the access network device and the terminal device interacting to perform the method shown in FIG. 10 can refer to the flow shown in FIG. 13.

[0345] For example, taking the first device as the access network device, the AI entity on the access network device side can be an intelligent network element (such as RIC, OAM, host of OTT system or cloud server, etc.), then S830 in method 800 shown in FIG. 8, S960 and / or S970 in method 900 shown in FIG. 9, S1160 and / or S1170 in method 1100 shown in FIG. 11 or S1360 and / or S1370 of method 1300 shown in FIG. 13 can be performed by the intelligent network element.

[0346] For example, FIG. 14 shows a schematic flowchart of the method provided by the present application from the perspective of the interaction of the intelligent network element, the terminal device and the access network device. The intelligent network element is the AI entity on the access network device side.

[0347] As shown in FIG. 14, the method 1400 can include the following steps.

[0348] S1410, the access network device sends the second information.

[0349] Correspondingly, the terminal device receives the second information.

[0350] S1410 can refer to S1210 in the above method 1200.

[0351] S1420, the access network device sends the CSI-RS.

[0352] Correspondingly, the terminal device receives the CSI-RS.

[0353] S1420 can refer to S1220 in the above method 1200.

[0354] S1430, the terminal device obtains the first data through the CSI-RS.

[0355] S1430 can refer to S1230 in the above method 1200.

[0356] S1440, the terminal device obtains N first probability distributions.

[0357] S1440 can refer to S1240 in the above method 1200.

[0358] S1450, the terminal device sends the first information.

[0359] Correspondingly, the access network device receives the first information.

[0360] S1450 can refer to S1250 in the above method 1200.

[0361] S1460, the access network device sends the first information.

[0362] Correspondingly, the intelligent network element receives the first information.

[0363] It should be noted that S1450 and S1460 can be combined into one step, that is, the terminal device can directly send the first information to the intelligent network element without forwarding through the access network device. Correspondingly, the intelligent network element directly receives the first information from the terminal device.

[0364] S1470, the intelligent network element processes the first data and / or the second data according to the probability distribution of the first data and the probability distribution of the second data to obtain third data.

[0365] S1470 can refer to S1260 in the above method 1200.

[0366] S1480, the access network device trains the first model according to the third data.

[0367] S1480 can refer to S1270 in the above method 1200.

[0368] Taking the first device as a terminal device for example, the AI entity on the terminal device side can be an OTT server (or a cloud server, etc.), then S830 in the method 800 shown in FIG. 8, S960 and / or S970 in the method 900 shown in FIG. 9, S1160 and / or S1170 in the method 1100 shown in FIG. 11 or S1260 and / or S1270 in the method 1200 shown in FIG. 12 can be executed by the OTT server.

[0369] It should be understood that the size of the serial number of each process described above does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0370] It should also be understood that in each embodiment of the present application, the terms and / or descriptions of different embodiments are consistent and can be mutually referred to if there is no special description and no logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0371] It can be understood that the methods and operations realized by the devices (such as the first device, the second device, and the third device) in each of the above method embodiments can also be realized by components (such as chips or circuits) of the devices.

[0372] The communication method provided by the embodiments of the present application is described in detail above in combination with FIG. 8 to FIG. 14. The above communication method is mainly introduced from the perspective of interaction between devices. It can be understood that the first device, the second device and the third device comprise corresponding hardware structures and / or software modules for performing various functions in order to achieve the above functions.

[0373] It can be understood that, in order to achieve the functions in the above embodiments, the first device, the second device and the third device comprise corresponding hardware structures and / or software modules for performing various functions. Those skilled in the art should easily realize that, in combination with the units and method steps of each example described in the embodiments disclosed in the present application, the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is realized in the form of hardware or computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0374] FIG. 15 and FIG. 16 are schematic block diagrams of communication devices provided by the embodiments of the present application. These communication devices can be used to realize the functions of the first device, the second device or the third device in the above method embodiments, and thus can also realize the beneficial effects possessed by the above method embodiments.

[0375] FIG. 15 is a schematic block diagram of a communication device 2000 provided by the embodiments of the present application. As shown in FIG. 15, the communication device 2000 comprises a transceiver unit (or a communication unit) 2020, and optionally, the communication device 2000 further comprises a processing unit 2010. The communication device 2000 is used to realize the functions of the first device or the second device in the method embodiments shown in FIG. 8, FIG. 9, FIG. 11, FIG. 12, FIG. 13 or FIG. 14.

[0376] When the communication device 2000 is used to realize the functions of the first device in the method embodiments shown in FIG. 8, FIG. 9, FIG. 11, FIG. 12, FIG. 13 or FIG. 14, the transceiver unit 2020 and / or the processing unit 2010 are used to obtain first information from a second device, the second information being used to indicate N first probability distributions, the N first probability distributions being determined according to N data features of first data, the first data being data collected by the second device; the processing unit 2010 is used to obtain second data, the second data being at least one of the following: data generated by a simulation model, data generated by an algorithm, and data collected by a third device; the processing unit 2010 is further used to process the first data and / or the second data to obtain third data according to the N first probability distributions and N second probability distributions, the third data being used to train a first model, the N second probability distributions being determined according to N data features of the second data.

[0377] Optionally, the processing unit 2010 is specifically configured to: determine N third probability distributions according to the N first probability distributions and the N second probability distributions; and process the first data and / or the second data to obtain third data according to the N third probability distributions. The N third probability distributions correspond to the N data features respectively, and the data features of the third data include the N data features.

[0378] Optionally, the processing unit 2010 is configured to process the second data to obtain third data according to the N first probability distributions and the N second probability distributions, and the N first probability distributions and the N third probability distributions satisfy a first condition. The first condition includes at least one of the following: a similarity between a fourth probability distribution and a fifth probability distribution is greater than or equal to a first threshold, or a difference between the fourth probability distribution and the fifth probability distribution is less than or equal to a second threshold. The fourth probability distribution corresponds to a first data feature, the first data feature is any one of the N data features, the N first probability distributions include the fourth probability distribution, the N third probability distributions include the fifth probability distribution, and the fifth probability distribution corresponds to the first data feature.

[0379] Optionally, the processing unit 2010 is configured to process the first data to obtain third data according to the N first probability distributions and the N second probability distributions, and the N second probability distributions and the N third probability distributions satisfy a second condition. The second condition includes at least one of the following: a similarity between a sixth probability distribution and the fifth probability distribution is greater than or equal to the first threshold, or a difference between the sixth probability distribution and the fifth probability distribution is less than or equal to the second threshold. The sixth probability distribution corresponds to the first data feature, the first data feature is any one of the N data features, the N second probability distributions include the sixth probability distribution, the N third probability distributions include the fifth probability distribution, and the fifth probability distribution corresponds to the first data feature.

[0380] Optionally, the third data is input data for model training of a first model, and the N data features are related to input features of the first model; or the third data is a label for model training of the first model, and the N data features are related to output features of the first model.

[0381] Optionally, the first data is obtained by a second device through measurement of at least one reference signal, and the N data features are related to one or more of the following: power, time delay, different streams of the at least one reference signal, different transmission antenna ports corresponding to the at least one reference signal, different reception antenna ports corresponding to the at least one reference signal, different frequency domain units of reference signal resources corresponding to the at least one reference signal, or different reference signals corresponding to different reference signal identifiers in the at least one reference signal.

[0382] Optionally, the transceiver 2020 is further configured to send, to the second device, second information, the second information being used to indicate configuration parameters of a generation model, the configuration parameters of the generation model being used to determine the N first probability distributions.

[0383] When the communication device 2000 is configured to implement the function of the second device in the method embodiments shown in FIG. 8, FIG. 9, FIG. 11, FIG. 12, FIG. 13 or FIG. 14, the processing unit 2010 is configured to collect first data; the processing unit 2010 is further configured to determine N first probability distributions according to N data features of the first data; and the transceiver 2020 is configured to send first information, the first information being used to indicate the N first probability distributions.

[0384] Optionally, the first data is used to determine input data for model training of a first model, and the N data features are related to input features of the first model; or the first data is used to determine labels for model training of the first model, and the N data features are related to output features of the first model.

[0385] Optionally, the processing unit 2010 is configured to obtain the first data by measuring at least one reference signal. The N data features are related to one or more of the following: power, time delay, different streams of the at least one reference signal, different transmission antenna ports corresponding to the at least one reference signal, different reception antenna ports corresponding to the at least one reference signal, different frequency domain units of reference signal resources corresponding to the at least one reference signal, or different reference signals in the at least one reference signal corresponding to different reference signal identifiers.

[0386] Optionally, the transceiver 2020 is further configured to receive second information from the first device, the second information being used to indicate configuration parameters of a generation model, the configuration parameters of the generation model being used to determine the N first probability distributions.

[0387] For more detailed description of the processing unit 2010 and the transceiver 2020, please refer to the related description in the method embodiments shown in FIG. 8, FIG. 9, FIG. 11, FIG. 12, FIG. 13 or FIG. 14.

[0388] The device 2000 in each of the above schemes has a function of implementing the corresponding steps performed by the first device in the above methods, or the device 2000 in each of the above schemes has a function of implementing the corresponding steps performed by the second device in the above methods. The functions can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions; for example, the transceiver can be replaced by a transceiver (for example, the transmitting unit in the transceiver can be replaced by a transmitter, and the receiving unit in the transceiver can be replaced by a receiver), and other units such as the processing unit can be replaced by a processor, which respectively performs the transceiving operations and related processing operations in each method embodiment.

[0389] In addition, the transceiver unit can also be a transceiver circuit (e.g., which can include a receiving circuit and a transmitting circuit), and the processing unit can be a processing circuit. The processing circuit can be one or more processors, or all or part of circuitry in the one or more processors for control or processing functions. In embodiments of the present application, the apparatus in FIG. 15 can be the first apparatus or the second apparatus in the foregoing embodiments, or can be a chip or a chip system, such as a system on chip (SoC). The transceiver unit can be an input / output circuit, a communication interface; and the processing unit can be a processor or a microprocessor integrated on the chip or an integrated circuit. This is not limited herein.

[0390] FIG. 16 is a schematic block diagram of a communication apparatus 3000 according to an embodiment of the present application. The apparatus 3000 includes a processing circuit. The apparatus can also include a communication circuit. The processing circuit and the communication circuit communicate with each other through an internal connection path. The processing circuit is configured to execute instructions to control the communication circuit to transmit and / or receive signals.

[0391] Taking the processing circuit including one or more processors and the communication circuit being a transceiver as an example, as shown in FIG. 16, the communication apparatus 3000 includes a processor 3010 and a transceiver 3020. The processor 3010 and the transceiver 3020 are coupled with each other. It can be understood that the transceiver 3020 can be a transceiver or an input / output interface. Optionally, the communication apparatus 3000 can also include a memory 3030 configured to store instructions executed by the processor 3010 or store input data required by the processor 3010 to execute instructions or store data generated after the processor 3010 executes instructions. Sometimes, the transceiver 3020 can also be understood as part of the processor 3010. In this case, the communication apparatus 3000 includes the processor 3010.

[0392] In a possible implementation, the apparatus 3000 is configured to implement the procedures and steps corresponding to the first apparatus in the method embodiments described above. In another possible implementation, the apparatus 3000 is configured to implement the procedures and steps corresponding to the second apparatus in the method embodiments described above.

[0393] It can be understood that the apparatus 3000 can be the first apparatus or the second apparatus in the embodiments described above, or can be a chip or a chip system. Correspondingly, the communication circuit can be an interface circuit of the chip, or an input / output circuit, which is not limited herein. Specifically, the apparatus 3000 can be configured to perform the procedures and steps corresponding to the first apparatus or the second apparatus in the method embodiments described above.

[0394] When the communication apparatus 3000 is used to implement the method shown in FIG. 8, FIG. 9, FIG. 11, FIG. 12, FIG. 13 or FIG. 14, the processor 3010 is configured to implement the functions of the processing unit 2010 described above, and the transceiver 3020 is configured to implement the functions of the transceiving unit 2020 described above.

[0395] When the communication apparatus is a chip or an OTT device applied to the first device, the chip or the OTT device of the first device implements the functions of the first device in the method embodiments described above, for example, implements the processing functions of the first device. The chip or the OTT device of the first device receives information from the second device or the third device, which can be understood as that the information is first received by other modules (such as a radio frequency module or an antenna) in the first device and then transmitted to the chip or the OTT device of the first device by the modules. The chip or the OTT device of the first device transmits information to the second device or the third device, which can be understood as that the information is first transmitted by the chip or the OTT device of the first device to other modules (such as a radio frequency module or an antenna) in the first device and then transmitted to the second device or the third device by the modules.

[0396] When the communication apparatus is a chip or an OTT device applied to the second device, the chip or the OTT device of the second device implements the functions of the second device in the method embodiments described above, for example, implements the processing functions of the second device. The chip or the OTT device of the second device receives information from the first device or the third device, which can be understood as that the information is first received by other modules (such as a radio frequency module or an antenna) in the second device and then transmitted to the chip or the OTT device of the second device by the modules. The chip or the OTT device of the second device transmits information to the first device or the third device, which can be understood as that the information is first transmitted by the chip or the OTT device of the second device to other modules (such as a radio frequency module or an antenna) in the second device and then transmitted to the first device or the third device by the modules.

[0397] The embodiments of the present application also provide a computer readable storage medium, having stored thereon computer instructions for implementing the method performed by the first device or the second device in the method embodiments described above.

[0398] For example, the computer program is executed by a computer, so that the computer can implement the method performed by the first device or the second device in the method embodiments described above.

[0399] The embodiments of the present application also provide a computer program product, comprising instructions, which, when executed by a computer, implement the method performed by the first device or the second device in the method embodiments described above.

[0400] The embodiments of the present application also provide a communication system, comprising the first device or the second device described above.

[0401] The explanations and beneficial effects of the related content in any of the above-provided devices can refer to the corresponding method embodiments provided above, and will not be repeated here.

[0402] It can be understood that, in order to realize the functions in the above embodiments, the first device or the second device comprises a hardware structure and / or a software module corresponding to each function. Those skilled in the art should easily realize that, in combination with the units and method steps of each example described in the embodiments disclosed in the present application, the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is realized in the form of hardware or computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0403] It can be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), image processors, artificial intelligence processors, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor can be a microprocessor, or any conventional processor.

[0404] The method steps in the embodiments of the present application can be realized in hardware, or in software instructions executable by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, a register, a hard disk, a mobile hard disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, so that the processor can read information from the storage medium, and can write information to the storage medium. The storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in the first device or the second device. The processor and the storage medium can also exist as discrete components in the first device or the second device.

[0405] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer programs or instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments are performed. The computer can be a general purpose computer, a special purpose computer, a computer network, a network device, a user equipment or other programmable apparatus. The computer programs or instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer programs or instructions can be transferred from one website site, computer, server or data center to another website site, computer, server or data center through wired or wireless manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like integrated with one or more available media. The available media can be a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape; or an optical medium, such as a digital video disc; or a semiconductor medium, such as a solid state disk. The computer readable storage medium can be a volatile or non-volatile storage medium, or can include both volatile and non-volatile storage media.

[0406] In each of the above embodiments, the terms and / or descriptions of different embodiments are consistent and can be referred to each other if there is no special description and logical conflict. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0407] Those skilled in the art can clearly understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0408] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0409] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. The division of the units is merely logical function division. There can be other division manners in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0410] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0411] In addition, each functional unit in the various embodiments of the present application can be integrated into a processing unit, or each unit can be a physically independent unit, or two or more units can be integrated into a unit.

[0412] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0413] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: The method comprises: obtaining first information from a second device, the first information being used to indicate N first probability distributions, the N first probability distributions being determined according to N data features of first data, the first data being data collected by the second device, N being a positive integer; obtaining second data, the second data being at least one of: data generated by a simulation model, data generated by an algorithm, or data collected by a third device; processing the first data and / or the second data according to the N first probability distributions and N second probability distributions to obtain third data, the third data being used to train a first model, the N second probability distributions being determined according to the N data features of the second data.

2. The method of claim 1, wherein, The processing the first data and / or the second data according to the N first probability distributions and N second probability distributions to obtain third data comprises: determining N third probability distributions according to the N first probability distributions and the N second probability distributions; processing the first data and / or the second data according to the N third probability distributions to obtain the third data, wherein the N third probability distributions respectively correspond to the N data features, and data features of the third data include the N data features.

3. The method of claim 2, wherein, The processing the second data according to the N first probability distributions and the N second probability distributions to obtain the third data, wherein the N first probability distributions and the N third probability distributions satisfy a first condition, the first condition comprising at least one of: a similarity between a fourth probability distribution and a fifth probability distribution is greater than or equal to a first threshold value, the fourth probability distribution corresponding to a first data feature, the first data feature being any one of the N data features, the N first probability distributions including the fourth probability distribution, the N third probability distributions including the fifth probability distribution, the fifth probability distribution corresponding to the first data feature; a difference between the fourth probability distribution and the fifth probability distribution is less than or equal to a second threshold value.

4. The method according to claim 2 or 3, characterized in that, The processing the first data according to the N first probability distributions and the N second probability distributions to obtain the third data, wherein the N second probability distributions and the N third probability distributions satisfy a second condition, the second condition comprising at least one of: a similarity between a sixth probability distribution and a fifth probability distribution is greater than or equal to a first threshold value, the sixth probability distribution corresponding to a first data feature, the first data feature being any one of the N data features, the N second probability distributions including the sixth probability distribution, the N third probability distributions including the fifth probability distribution, the fifth probability distribution corresponding to the first data feature; a difference between the sixth probability distribution and the fifth probability distribution is less than or equal to a second threshold value.

5. The method according to any one of claims 1 to 4, characterized in that, the third data is input data for model training of the first model, the N data features are related to input features of the first model. Alternatively, the third data is a label for model training of the first model, and the N data features are related to output features of the first model.

6. The method according to any one of claims 1 to 5, characterized in that, The first data is obtained by the second device measuring at least one reference signal, and the N data features are related to one or more of the following: power, time delay, different streams of the at least one reference signal, different transmission antenna ports corresponding to the at least one reference signal, different reception antenna ports corresponding to the at least one reference signal, different frequency domain units of reference signal resources corresponding to the at least one reference signal, or different reference signals in the at least one reference signal corresponding to different reference signal identifiers.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: sending second information to the second device, the second information being used to indicate configuration parameters of a generation model, the configuration parameters of the generation model being used to determine the N first probability distributions.

8. A communication method characterized by comprising: comprising: collecting first data; determining N first probability distributions according to N data features of the first data; N is a positive integer; sending first information to a first device, the first information being used to indicate the N first probability distributions.

9. The method of claim 8, wherein, The first data is used to determine input data for model training of a first model, and the N data features are related to input features of the first model; or the first data is used to determine a label for model training of the first model, and the N data features are related to output features of the first model.

10. The method according to claim 8 or 9, characterized in that, collecting first data, comprising: obtaining the first data by measuring at least one reference signal; The N data features are related to one or more of the following: power, time delay, different streams of the at least one reference signal, different transmission antenna ports corresponding to the at least one reference signal, different reception antenna ports corresponding to the at least one reference signal, different frequency domain units of reference signal resources corresponding to the at least one reference signal, or different reference signals in the at least one reference signal corresponding to different reference signal identifiers.

11. The method according to any one of claims 8 to 10, characterized in that, The method further includes: receiving second information from the first device, the second information being used to indicate configuration parameters of a generation model, the configuration parameters of the generation model being used to determine the N first probability distributions.

12. A communications device, characterized by comprising a module or unit for performing the method of any one of claims 1 to 7.

13. A communications device, characterized by comprising a module or unit for performing the method of any one of claims 8 to 11.

14. A computer-readable storage medium, characterized in that, The computer readable storage medium is contained in a communication device, and the computer readable storage medium stores computer instructions which, when executed, cause the method of any one of claims 1 to 11 to be implemented.

15. A computer program product, the computer program product being embodied in a communication device, characterized in that The computer program product, when executed, causes the method of any one of claims 1 to 11 to be implemented.

Images