Communication method and apparatus

Abstract

A communication method and apparatus are provided. The method includes: A terminal device (or an access network device) acquires channel features through inference by using a channel feature extraction model, and the channel features correspond to a channel between the terminal device and the access network device. The terminal device (or the access network device) sends the channel features to a location management function LMF. The LMF acquires positioning information of the terminal device through inference by using a positioning information acquisition model based on the channel features. The LMF may determine location information of the terminal device based on the positioning information. According to the method, an artificial intelligence model may be used to implement or assist in implementing positioning of the terminal device.

Description

[Technical field]

[0001] The present application relates to the field of communication technologies, and in particular to a positioning method and apparatus. [Background technology]

[0002] This application claims priority to Chinese Patent Application No. 202111367563.0, entitled "COMMUNICATION METHOD AND APPARATUS," filed with the China State Intellectual Property Office on November 18, 2021, the entire contents of which are incorporated herein by reference.

[0003] In a communication system, positioning technology can be used to obtain location information of a mobile terminal. For example, positioning technology may be applied in fields such as navigation and aviation, plotting and disaster relief, vehicle navigation, logistics information query, or traffic management. With the development of mobile communication, positioning technology based on wireless cellular networks has been widely applied. In wireless cellular networks, such as fourth generation (4G) or fifth generation (5G) mobile communication networks, positioning technology for mobile terminals has been widely investigated. How to improve the positioning efficiency of mobile terminals is a technical problem worthy of research. Summary of the Invention

[0004] The present application provides a communication method and apparatus, and in particular relates to a terminal device positioning method, in which a terminal device (or an access network device) and a location management function (LMF) use a channel feature extraction model and a positioning information acquisition model in a consistent manner, so that intelligent positioning of the terminal device can be implemented.

[0005] According to a first aspect, a communication method is provided, which may be implemented on a terminal device side, the method including: sending X channel features to an LMF, the X channel features corresponding to Y channels of the terminal device, the X channel features being obtained by using a channel feature extraction model, an input of the channel feature extraction model being determined based on the Y channel responses, the Y channel responses being in one-to-one correspondence with the Y channels, and X and Y being integers equal to or greater than 1.

[0006] Optionally, the Y channels are Y channels between the terminal device and the P access network devices. Optionally, there are E channels between each of the P access network devices and the terminal device, where E is an integer equal to or greater than 1. Optionally, when E is greater than 1, different channels in the E channels correspond to one or a combination of different cells, different transmit receive points (TRPs), different antenna panels, different antennas, different beams, or different frequency bands.

[0007] In this method, the channel characteristics sent to the LMF can be used to implement or assist in the implementation of the positioning of the terminal device. In this case, in this method, an artificial intelligence model may be used to solve the positioning problem of the terminal device, thereby improving the positioning efficiency. For example, compared with a traditional deterministic algorithm for calculating the location information of the terminal device, the artificial intelligence model is obtained through training by using actual channel data. In the above method, when artificial intelligence is used to implement or assist in the implementation of the positioning of the terminal device, the positioning is closer to the actual channel environment. Therefore, the positioning of the terminal device by using the model is more accurate.

[0008] In a possible implementation, X is less than or equal to Y and / or the total dimensionality of the X channel features is less than the total dimensionality of the Y channel responses.

[0009] According to this method, the signaling overhead between the LMF and the terminal device can be reduced.

[0010] In a possible implementation, the X channel features are used to determine an input of a positioning information acquisition model, the output of which includes positioning information of the terminal device.

[0011] According to this method, the LMF can acquire positioning information of the terminal device by using X channel features and a positioning information acquisition model, so that intelligent positioning of the terminal device can be implemented and positioning efficiency is improved.

[0012] In a possible implementation, the positioning information indicates location information of the terminal device.

[0013] In a possible implementation, the location information of the terminal device includes at least one of the following: longitude of the terminal device's location, latitude of the terminal device's location, altitude of the terminal device's location, offset of the terminal device's location relative to a reference location (e.g., a reference access network device location or a reference building location), etc.

[0014] According to this method, the location information of the terminal device is directly obtained through model inference, so that the positioning of the terminal device is simpler and more convenient.

[0015] In a possible implementation, the positioning information indicates at least one of the following for the Y channels: channel type, first path location, or relative azimuth angle of the terminal device.

[0016] Optionally, the channel type includes line of sight (LOS) or non-line of sight (NLOS).

[0017] Optionally, the first path location comprises a time domain location of the first path in the channel in one OFDM symbol.

[0018] Optionally, for each of the Y channels, a relative azimuth angle of the terminal device indicates a relative location between the terminal device and the access network device corresponding to the channel. Optionally, the relative azimuth angle includes at least one of the following: an angle of arrival (AoA) or an angle of departure (AOD) of a reference signal on the channel. Optionally, the reference signal is a reference signal on the channel and sent by the terminal device to the access network device.

[0019] The positioning information is used to determine location information of the terminal device. According to the present method, the LMF can obtain the positioning information of the terminal device by using a simpler and more convenient model to assist in implementing the positioning of the terminal device.

[0020] In a possible implementation, the method includes receiving information about a channel feature extraction model. Optionally, the information about the channel feature extraction model is received from an LMF or the information about the channel feature extraction model is received from an artificial intelligence (AI) function network element.

[0021] According to the method, online training of the channel feature extraction model can be implemented, so that the terminal device obtains a channel feature extraction model that better matches the current channel conditions, thereby improving the positioning accuracy.

[0022] In a possible implementation, the method includes determining a channel feature extraction model based on a first reference model, the first reference model including a first reference channel feature extraction model and a first reference positioning information acquisition model.

[0023] In a possible implementation, when the channel feature extraction model and the first reference positioning information acquisition model are used in a consistent manner, the value of the loss function is less than or equal to the first threshold value.

[0024] According to this method, the terminal device can obtain a channel feature extraction model through training by using a first reference model. In this way, the amount of training iterations can be reduced, and the channel feature extraction model obtained through training can better match the current channel state, so that fast, simple and convenient intelligent positioning can be implemented.

[0025] According to a second aspect, a communication method is provided, which may be implemented on an access network device side, comprising: sending E channel features to a location management function LMF, where E is an integer equal to or greater than 1, the E channel features correspond to E channels of a terminal device, each of the E channel features being obtained by using a channel feature extraction model, an input of the channel feature extraction model being determined based on a channel response, the channel response corresponding to a channel corresponding to the channel feature.

[0026] In a possible implementation, the dimension of the channel features is smaller than the dimension of the channel response.

[0027] In a possible implementation, the E channel features are used to determine an input of a positioning information acquisition model, the output of which includes positioning information of the terminal device.

[0028] For a description of the positioning information, please refer to the first aspect, and the details will not be described again in this specification.

[0029] In a possible implementation, the method includes receiving information about a channel feature extraction model. Optionally, the information about the channel feature extraction model is received from an LMF, or the information about the channel feature extraction model is received from an AI function network element.

[0030] In a possible implementation, the method includes determining a channel feature extraction model based on a first reference model, the first reference model including a first reference channel feature extraction model and a first reference positioning information acquisition model.

[0031] In a possible implementation, when the channel feature extraction model and the first reference positioning information acquisition model are used in a consistent manner, the value of the loss function is less than or equal to the first threshold value.

[0032] According to a third aspect, a communication method is provided, which can be implemented on an AI function network element side. The method includes: receiving X channel features, where the X channel features correspond to Y channels of a terminal device, and X and Y are positive integers equal to or greater than 1; and acquiring positioning information of the terminal device based on the X channel features and a positioning information acquisition model.

[0033] Optionally, the X channel characteristics are received from a terminal device. Optionally, the X channel characteristics are received from P access network devices. For further description of the channel characteristics, please refer to the first aspect or the second aspect. Details will not be described again in this specification.

[0034] For a description of the positioning information, please refer to the first aspect, and the details will not be described again in this specification.

[0035] In a possible implementation, X is less than or equal to Y and / or the total dimensionality of the X channel features is less than the total dimensionality of the Y channel responses.

[0036] In a possible implementation, the positioning information acquisition model is determined based on a first reference model, where the first reference model includes a first reference channel feature extraction model and a first reference positioning information acquisition model.

[0037] In a possible implementation, when the positioning information acquisition model and the first reference channel feature extraction model are used in a matched manner, the value of the loss function is less than or equal to the first threshold value.

[0038] According to a fourth aspect, a communication method is provided, which can be implemented on an AI function network element side. The method includes: receiving a training dataset, where each of the training data in the training dataset indicates Y channel responses and Y positioning information of Y channels of a terminal device, and the Y channel responses are in one-to-one correspondence with the Y positioning information; and obtaining a channel feature extraction model and a positioning information acquisition model through training based on the training dataset, where an input of the channel feature extraction model is determined based on at least one of the Y channel responses, and an input of the positioning information acquisition model is determined based on an output of the channel feature extraction model.

[0039] In a possible implementation, a loss function between an output of the positioning information acquisition model and the at least one positioning information corresponding to the at least one channel response is less than or equal to a threshold value.

[0040] In a possible implementation, the channel feature extraction model is sent to a terminal device, an access network device, or an LMF.

[0041] In a possible implementation, the positioning information acquisition model is sent to the LMF.

[0042] According to a fifth aspect, an apparatus is provided. The apparatus is configured to implement the method according to the first aspect. The apparatus may be a terminal device, or an apparatus disposed in a terminal device, or an apparatus capable of being used with a terminal device in a corresponding manner. In design, the apparatus includes units in one-to-one correspondence with and configured to implement the methods / operations / steps / acts described in the first aspect. The units may be implemented by hardware circuits, software, or hardware circuits in combination with software.

[0043] For example, the apparatus may include a processing unit and a communication unit, and the processing unit and the communication unit may implement corresponding functions in the first aspect. For example, as follows.

[0044] The communication unit is configured to send X channel features to the LMF, the X channel features corresponding to Y channels of the terminal device, the X channel features being obtained by using a channel feature extraction model, an input of the channel feature extraction model being determined based on the Y channel responses, the Y channel responses being in one-to-one correspondence with the Y channels, and X and Y being integers equal to or greater than 1. The X channel features are obtained by the processing unit by using the channel feature extraction model.

[0045] Please refer to the first aspect for the description of Y channels, X channel characteristics, etc. Details will not be described again.

[0046] In a possible implementation, the X channel features are used to determine an input of a positioning information acquisition model, the output of which includes positioning information of the terminal device.

[0047] For a description of the positioning information, please refer to the first aspect, and the details will not be described again in this specification.

[0048] In a possible implementation, the communication unit is configured to receive information about a channel feature extraction model. Optionally, the information about the channel feature extraction model is received from an LMF, or the information about the channel feature extraction model is received from an AI function network element.

[0049] In a possible implementation, the processing unit is configured to determine a channel feature extraction model based on a first reference model, the first reference model including a first reference channel feature extraction model and a first reference positioning information acquisition model.

[0050] For example, the apparatus includes a processor configured to implement the method described in the first aspect. The apparatus may further include a memory configured to store instructions and / or data. The memory is coupled to the processor. When executing the program instructions stored in the memory, the processor can implement the method described in the first aspect. The apparatus may further include a communication interface, which is used by the apparatus to communicate with another device. For example, the communication interface may be a transceiver, a circuit, a bus, a module, a pin, or another type of communication interface. In a possible design, the apparatus may include: a memory configured to store program instructions; A communication interface; and a processor configured to send X channel features to the LMF through a communication interface, the X channel features corresponding to Y channels of the terminal device, the X channel features being obtained by using a channel feature extraction model, inputs of the channel feature extraction model being determined based on the Y channel responses, the Y channel responses being in one-to-one correspondence with the Y channels, and X and Y being integers greater than or equal to 1.

[0051] Please refer to the first aspect for the description of Y channels, X channel characteristics, etc. Details will not be described again.

[0052] In a possible implementation, the processor receives information about the channel feature extraction model through the communication interface. Optionally, the information about the channel feature extraction model is received from the LMF, or the information about the channel feature extraction model is received from an AI function network element.

[0053] In a possible implementation, the processor is configured to determine a channel feature extraction model based on a first reference model, the first reference model including a first reference channel feature extraction model and a first reference positioning information acquisition model.

[0054] According to a sixth aspect, an apparatus is provided. The apparatus is configured to implement the method according to the second aspect. The apparatus may be an access network device, or an apparatus disposed in an access network device, or an apparatus capable of being used with an access network device in a corresponding manner. In design, the apparatus includes units in one-to-one correspondence with and configured to implement the methods / operations / steps / acts described in the second aspect. The units may be implemented by hardware circuits, software, or hardware circuits in combination with software.

[0055] For example, the apparatus may include a processing unit and a communication unit, and the processing unit and the communication unit may implement corresponding functions in the second aspect. For example, as follows.

[0056] The communication unit is configured to send E channel features to the location management function LMF, where E is an integer equal to or greater than 1, the E channel features correspond to E channels of the terminal device, and each of the E channel features is obtained by using a channel feature extraction model, and an input of the channel feature extraction model is determined based on a channel response, the channel response corresponds to a channel corresponding to the channel feature. The E channel features are obtained by the processing unit by using the channel feature extraction model.

[0057] For a description of the channel characteristics, please refer to the second aspect, and the details will not be described again.

[0058] In a possible implementation, the communication unit is configured to receive information about a channel feature extraction model. Optionally, the information about the channel feature extraction model is received from an LMF, or the information about the channel feature extraction model is received from an AI function network element.

[0059] In a possible implementation, the processing unit is configured to determine a channel feature extraction model based on a first reference model, the first reference model including a first reference channel feature extraction model and a first reference positioning information acquisition model.

[0060] For example, the apparatus includes a processor configured to implement the method described in the second aspect. The apparatus may further include a memory configured to store instructions and / or data. The memory is coupled to the processor. When executing the program instructions stored in the memory, the processor can implement the method described in the second aspect. The apparatus may further include a communication interface, the communication interface used by the apparatus to communicate with another device. For example, the communication interface may be a transceiver, a circuit, a bus, a module, a pin, another type of communication interface, etc. In a possible design, the apparatus may include: a memory configured to store program instructions; A communication interface; and a processor configured to send E channel features to the location management function LMF through the communication interface, where E is an integer greater than or equal to 1, the E channel features corresponding to the E channels of the terminal device, each of the E channel features being obtained by using a channel feature extraction model, an input of the channel feature extraction model being determined based on a channel response, the channel response corresponding to the channel corresponding to the channel feature.

[0061] For a description of the channel characteristics, please refer to the second aspect, and the details will not be described again.

[0062] In a possible implementation, the processor receives information about the channel feature extraction model through the communication interface. Optionally, the information about the channel feature extraction model is received from the LMF, or the information about the channel feature extraction model is received from an AI function network element.

[0063] In a possible implementation, the processor is configured to determine a channel feature extraction model based on a first reference model, the first reference model including a first reference channel feature extraction model and a first reference positioning information acquisition model.

[0064] According to a seventh aspect, an apparatus is provided for implementing the method according to the third aspect. The apparatus may be an LMF, or an apparatus disposed in an LMF, or an apparatus capable of being used with an LMF in a consistent manner. In design, the apparatus includes units in one-to-one correspondence with and configured to perform the methods / operations / steps / acts described in the third aspect. The units may be implemented by hardware circuits, software, or hardware circuits in combination with software.

[0065] For example, the apparatus may include a processing unit and a communication unit, and the processing unit and the communication unit may implement corresponding functions in the third aspect. For example, as follows.

[0066] The communication unit is configured to receive X channel characteristics, where the X channel characteristics correspond to Y channels of the terminal device, where X and Y are positive integers equal to or greater than one.

[0067] The communication unit is configured to acquire positioning information of the terminal device based on the X channel characteristics and the positioning information acquisition model.

[0068] For a description of channel characteristics, positioning information, etc., please refer to the third aspect. Details will not be described again.

[0069] In a possible implementation, the processing unit is configured to determine a positioning information acquisition model based on a first reference model, the first reference model including a first reference channel feature extraction model and a first reference positioning information acquisition model.

[0070] For example, the apparatus includes a processor configured to implement the method described in the third aspect. The apparatus may further include a memory configured to store instructions and / or data. The memory is coupled to the processor. When executing the program instructions stored in the memory, the processor can implement the method described in the third aspect. The apparatus may further include a communication interface, the communication interface used by the apparatus to communicate with another device. For example, the communication interface may be a transceiver, a circuit, a bus, a module, a pin, another type of communication interface, etc. In a possible design, the apparatus may include: a memory configured to store program instructions; A communication interface; and a processor configured to receive X channel characteristics through the communication interface, the X channel characteristics corresponding to Y channels of the terminal device, where X and Y are positive integers greater than or equal to 1.

[0071] The processor is configured to acquire positioning information of the terminal device based on the X channel characteristics and the positioning information acquisition model.

[0072] For descriptions of channel characteristics, positioning information, etc., please refer to the third aspect. Details will not be described again.

[0073] In a possible implementation, the processor is configured to determine a positioning information acquisition model based on a first reference model, the first reference model including a first reference channel feature extraction model and a first reference positioning information acquisition model.

[0074] According to an eighth aspect, an apparatus is provided for implementing the method according to the fourth aspect. The apparatus may be an AI function network element, or an apparatus disposed in an AI function network element, or an apparatus capable of being used with an AI function network element in a corresponding manner. In design, the apparatus includes a unit configured to perform the method / operation / step / act described in the fourth aspect and in one-to-one correspondence therewith. The unit may be implemented by a hardware circuit, software, or a hardware circuit in combination with software.

[0075] For example, the apparatus may include a processing unit and a communication unit, and the processing unit and the communication unit may implement corresponding functions in the fourth aspect. For example, as follows.

[0076] The communication unit is configured to receive a training data set, each of the training data in the training data set indicating Y channel responses and Y pieces of positioning information of Y channels of the terminal device, the Y channel responses being in one-to-one correspondence with the Y pieces of positioning information.

[0077] The processing unit is configured to obtain a channel feature extraction model and a positioning information acquisition model through training based on a training dataset, where an input of the channel feature extraction model is determined based on at least one of the Y channel responses, and an input of the positioning information acquisition model is determined based on an output of the channel feature extraction model.

[0078] In a possible implementation, the communication unit is configured to send the channel feature extraction model to a terminal device, an access network device, or an LMF.

[0079] In a possible implementation, the communication unit is configured to send a positioning information acquisition model to the LMF.

[0080] For example, the apparatus includes a processor configured to implement the method described in the fourth aspect. The apparatus may further include a memory configured to store instructions and / or data. The memory is coupled to the processor. When executing the program instructions stored in the memory, the processor can implement the method described in the fourth aspect. The apparatus may further include a communication interface, the communication interface used by the apparatus to communicate with another device. For example, the communication interface may be a transceiver, a circuit, a bus, a module, a pin, another type of communication interface, etc. In a possible design, the apparatus may include: a memory configured to store program instructions; A communication interface; and a processor configured to receive a training data set through the communication interface, each of the training data in the training data set indicating Y channel responses and Y pieces of positioning information for Y channels of the terminal device, the Y channel responses being in one-to-one correspondence with the Y pieces of positioning information.

[0081] The processor is configured to obtain a channel feature extraction model and a positioning information acquisition model through training based on a training dataset, an input of the channel feature extraction model being determined based on at least one of the Y channel responses, and an input of the positioning information acquisition model being determined based on an output of the channel feature extraction model.

[0082] In a possible implementation, the processor sends the channel feature extraction model to a terminal device, an access network device, or an LMF through a communication interface.

[0083] In a possible implementation, the processor sends the positioning information acquisition model to the LMF through a communication interface.

[0084] According to a ninth aspect, there is provided a communication system, comprising: A device according to the fifth aspect and a device according to the seventh aspect, A device according to a sixth aspect and a device according to a seventh aspect, A device according to a fifth aspect and a device according to an eighth aspect, A device according to a sixth aspect and a device according to an eighth aspect, A device according to the fifth aspect, a device according to the seventh aspect, and a device according to the eighth aspect; A device according to the sixth aspect, a device according to the seventh aspect, and a device according to the eighth aspect; or A device according to the fifth aspect, a device according to the sixth aspect, a device according to the seventh aspect, and a device according to the eighth aspect. Includes.

[0085] According to a tenth aspect, there is provided a computer readable storage medium comprising instructions which, when run on a computer, enable the computer to perform a method according to the first aspect, the second aspect, the third aspect or the fourth aspect.

[0086] According to an eleventh aspect, there is provided a computer program product comprising instructions which, when run on a computer, enable the computer to perform a method according to the first aspect, the second aspect, the third aspect or the fourth aspect.

[0087] According to a twelfth aspect, a chip system is provided. The chip system includes a processor and may further include a memory. The chip system is configured to implement a method according to the first aspect, the second aspect, the third aspect, or the fourth aspect. The chip system may include a chip, or may include a chip and another individual component. [Brief description of the drawings]

[0088] [Figure 1] FIG. 1 is a schematic diagram of the architecture of a communication system according to the present disclosure. [Diagram 2] FIG. 2 is a schematic diagram of layer relationships of a neural network according to the present disclosure. [Figure 3A] FIG. 1 is a schematic diagram of a network architecture according to the present disclosure. [Figure 3B] FIG. 1 is a schematic diagram of a network architecture according to the present disclosure. [Figure 3C] FIG. 1 is a schematic diagram of a network architecture according to the present disclosure. [Figure 3D] FIG. 1 is a schematic diagram of a network architecture according to the present disclosure. [Figure 3E] FIG. 1 is a schematic diagram of a network architecture according to the present disclosure. [Figure 4] 1 is a schematic flow chart of a positioning method according to the present disclosure. [Figure 5A] FIG. 1 is a schematic diagram of a system architecture according to the present disclosure. [Figure 5B] FIG. 1 is a schematic diagram of a system architecture according to the present disclosure. [Figure 6] 1 is a schematic flow chart of a positioning method according to the present disclosure. [Figure 7A] FIG. 2 is a schematic diagram of reference signal transmission between a UE and a base station according to the present disclosure. [Figure 7B] FIG. 2 is a schematic diagram of reference signal transmission between a UE and a base station according to the present disclosure. [Figure 8A] FIG. 1 is a schematic diagram of a model training structure according to the present disclosure. [Figure 8B] FIG. 1 is a schematic diagram of a model training structure according to the present disclosure. [Figure 8C] FIG. 1 is a schematic diagram of a model training structure according to the present disclosure. [Figure 9A] FIG. 2 is a schematic diagram of a model application structure according to the present disclosure. [Figure 9B] FIG. 2 is a schematic diagram of a model application structure according to the present disclosure. [Figure 9C] FIG. 2 is a schematic diagram of a model application structure according to the present disclosure. [Figure 10] FIG. 1 is an example diagram of estimating a location of a UE according to the present disclosure. [Figure 11] FIG. 2 is a schematic diagram of channel types according to the present disclosure. [Figure 12] 1 is a schematic flow chart of a positioning method according to the present disclosure. [Figure 13] 1 is a schematic flow chart of a positioning method according to the present disclosure. [Figure 14A] FIG. 1 is a schematic diagram of a model training structure according to the present disclosure. [Figure 14B] FIG. 1 is a schematic diagram of a model training structure according to the present disclosure. [Figure 15] 1 is a schematic flow chart of a positioning method according to the present disclosure. [Figure 16] FIG. 1 is a schematic diagram of the structure of an apparatus according to the present disclosure. [Figure 17] FIG. 1 is a schematic diagram of the structure of an apparatus according to the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0089] FIG. 1 is a schematic diagram of an architecture of a communication system 1000 to which the present disclosure can be applied. As shown in FIG. 1, the communication system includes a radio access network (RAN) 100 and a core network (CN) 200. Optionally, the communication system 1000 may further include an Internet 300. The radio access network 100 may include at least one access network device (or may be referred to as a RAN device, e.g., 110a and 110b in FIG. 1), and may further include at least one terminal (e.g., 120a to 120j in FIG. 1). The terminal is connected to the access network device in a wireless manner. The access network device is connected to the core network in a wireless or wired manner. The core network device and the access network device may be different physical devices independent of each other, or may be the same physical device incorporating the functions of the core network device and the access network device, or may be another possible case. For example, one physical device may incorporate the functionality of an access network device and part of the functionality of a core network device, and the other physical device implements the remaining part of the functionality of the core network device. The physical presence of the core network device and the access network device is not limited in this disclosure. A terminal may be connected to another terminal in a wired or wireless manner. An access network device may be connected to another access network device in a wired or wireless manner. Figure 1 is merely a schematic diagram and is not intended to limit the disclosure. For example, the communication system may further include another network device, for example, a wireless relay device, a wireless backhaul device, etc.

[0090] The access network device may be a base station, a NodeB, an evolved NodeB (eNodeB, or eNB), a transmission reception point (TRP), a next generation NodeB (gNB) in a 5th generation (5G) mobile communication system, an access network device in an open radio access network (O-RAN, or open RAN), a next generation base station in a 6th generation (6G) mobile communication system, a base station in a future mobile communication system, an access node in a wireless fidelity (Wi-Fi) system, etc. Alternatively, the access network device may be a module or unit that completes part of the function of the access network device, for example, a central unit (CU), a distributed unit (DU), a central unit control plane (CU-CP) module, or a central unit user plane (CU-UP) module. The access network device may be a macro base station (e.g., 110a in FIG. 1), a micro base station or an indoor base station (e.g., 110b in FIG. 1), or a relay node, a donor node, etc. The particular technology and the particular device form used by the access network device are not limited by this disclosure. The 5G system may also be referred to as a new radio (NR) system.

[0091] In the present disclosure, the apparatus configured to implement the function of the access network device may be an access network device, or may be an apparatus that can support the access network device in implementing the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The apparatus may be installed in the access network device, or may be used together with the access network device in a consistent manner. In the present disclosure, the chip system may include a chip, or may include a chip and another individual component. For ease of explanation, the following describes the provided technical solution by using an example in which the apparatus configured to implement the function of the access network device is an access network device, and the access network device is a base station.

[0092] (1) Protocol layer structure.

[0093] The communication between the access network device and the terminal conforms to a protocol layer structure. For example, the protocol layer structure may include a control plane protocol layer structure and a user plane protocol layer structure. For example, the control plane protocol layer structure may include a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, a media access control (MAC) layer, a physical (PHY) layer, etc. For example, the user plane protocol layer structure may include a PDCP layer, an RLC layer, a MAC layer, a physical layer, etc. In a possible implementation, there may further be a service data adaptation protocol (SDAP) layer on top of the PDCP layer.

[0094] Optionally, the protocol layer structure between the access network device and the terminal may further include an artificial intelligence (AI) layer used for transmitting data related to AI functions.

[0095] The protocol layer structure between the access network device and the terminal may be considered as an access stratum (AS) structure. Optionally, there may be a non-access stratum (NAS) layer on top of the AS, which is used by the access network device to forward information from the core network device to the terminal, or used by the access network device to forward information from the terminal to the core network device. In this case, it may be considered that there is a logical interface between the terminal and the core network device. Optionally, the access network device may forward information between the terminal and the core network device in a transparent transmission manner. For example, the NAS signaling / NAS message may be mapped to the RRC signaling or included in the RRC signaling as an element of the RRC signaling.

[0096] (2) Central unit (CU) and distributed unit (DU)

[0097] The access network device may include a CU and a DU. This design may be referred to as a CU-DU split. Multiple DUs may be controlled in a centralized manner by one CU. For example, the interface between the CU and the DU is referred to as an F1 interface. The control panel (CP) interface may be F1-C, and the user panel (UP) interface may be F1-U. The specific names of the interfaces are not limited in this disclosure. The CU and the DU may be obtained through a division based on a protocol layer of the wireless network. For example, the functions of the PDCP layer and the protocol layers above the PDCP layer (e.g., the RRC layer and the SDAP layer) are allocated to the CU, and the functions of the protocol layers below the PDCP layer (e.g., the RLC layer, the MAC layer, and the PHY layer) are allocated to the DU. In another example, the functions of the protocol layers above the PDCP layer are allocated to the CU, and the functions of the protocol layers below the PDCP layer are allocated to the DU. This is not limited.

[0098] The above allocation of processing functions of CU and DU based on protocol layer is only an example, and another allocation scheme may be used instead. For example, CU or DU may be obtained through division to have more functions of protocol layer. In another example, CU or DU is obtained through division to have a part of processing functions of protocol layer. For example, the functions of RLC layer and part of functions of protocol layer above RLC layer are allocated to CU, and the functions of RLC layer and the remaining part of functions of protocol layer below RLC layer are allocated to DU. In another example, the functions of CU or DU may be allocated based on service type or another system requirement, for example, based on delay. Functions that need processing time to meet delay requirements are allocated to DU, and functions that do not need processing time to meet delay requirements are allocated to CU.

[0099] Optionally, the CU may have one or more functions of a core network. For example, the CU may be disposed on the network side to facilitate centralized management. Optionally, a radio unit (RU) of the DU is disposed remotely, and the RU has radio frequency functions.

[0100] For example, the functions of the PHY layer may be allocated to the DU and the RU. For example, the DU may implement the upper layer functions of the PHY layer, and the RU may implement the lower layer functions of the PHY layer. When the PHY layer is used for transmission, the functions of the PHY layer may include at least one of the following functions: cyclic redundancy check (CRC) bit addition, channel coding, rate matching, scrambling, modulation, layer mapping, precoding, resource mapping, physical antenna mapping, or radio frequency transmission. When the PHY layer is used for reception, the functions of the PHY layer may include at least one of the following functions: CRC check, channel decoding, de-rate matching, descrambling, demodulation, de-layer mapping, channel detection, resource demapping, physical antenna demapping, or radio frequency reception. The upper layer functions of the PHY layer may include a part of the functions of the PHY layer, which part of the functions is closer to the MAC layer. The lower layer functions of the PHY layer may include another part of the functions of the PHY layer, which part of the functions is closer to the radio frequency functions, for example. For example, the upper layer functions of the PHY layer may include CRC bit addition, channel coding, rate matching, scrambling, modulation, and layer mapping, and the lower layer functions of the PHY layer may include precoding, resource mapping, physical antenna mapping, and radio frequency transmission. Alternatively, the upper layer functions of the PHY layer may include CRC bit addition, channel coding, rate matching, scrambling, modulation, layer mapping, and precoding, and the lower layer functions of the PHY layer may include resource mapping, physical antenna mapping, and radio frequency transmission. For example, the upper layer functions of the PHY layer may include CRC check, channel decoding, de-rate matching, decoding, demodulation, and de-layer mapping, and the lower layer functions of the PHY layer may include channel detection, resource demapping, physical antenna demapping, and radio frequency reception.Alternatively, the upper layer functions of the PHY layer may include CRC checking, channel decoding, de-rate matching, decoding, demodulation, de-layer mapping, and channel detection, and the lower layer functions of the PHY layer may include resource demapping, physical antenna demapping, and radio frequency reception.

[0101] Optionally, the function of the CU may be implemented by one entity or by different entities. For example, the function of the CU may be further allocated such that the control plane and the user plane are split and implemented by different entities. The split entities are a control plane CU entity (i.e., a CU-CP entity) and a user plane CU entity (i.e., a CU-UP entity), respectively. The CU-CP entity and the CU-UP entity may be combined with a DU to complete the function of an access network device together. In the present disclosure, an entity may be understood as a module or unit, and the existence form of an entity may be a hardware structure, a software module, or a hardware structure plus a software module. This is not limited.

[0102] Optionally, any one of the DU, CU, CU-CP, CU-UP, and RU may be a software module, a hardware structure, or a software module plus a hardware structure. This is not limited. Different entities may have the same form of existence or different forms of existence. For example, the DU, CU, CU-CP, and CU-UP are software modules, and the RU is a hardware structure. For the sake of brevity of description, other possible combinations are not enumerated herein. These modules and the methods implemented by these modules also fall within the scope of protection of the present disclosure. For example, when the method according to the present disclosure is implemented by an access network device, the method may be specifically implemented by a CU, a DU, or a near-real-time RIC described below.

[0103] The terminal may also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. The terminal may be widely used in various scenarios for communication. For example, the scenarios include, but are not limited to, at least one of the following: enhanced mobile broadband (eMBB), ultra-reliable low-latency communication (URLLC), massive machine-type communication (mMTC), device-to-device (D2D), vehicle-to-everything (V2X), machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, intelligent transportation, smart city, etc. A terminal may be a mobile phone, a tablet computer, a computer with wireless transceiver capabilities, a wearable device, a vehicle, an unmanned aerial vehicle, a helicopter, an airplane, a ship, a robot, a robotic arm, a smart home device, etc. The particular technology used by a terminal and the particular device form factor are not limited by this disclosure.

[0104] In the present disclosure, the device configured to implement the functions of the terminal may be a terminal, or may be a device that can support a terminal device in implementing the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The device may be installed in a terminal or used with a terminal in a consistent manner. For ease of explanation, the following describes the technical solution provided in the present disclosure by using an example in which the device configured to implement the functions of the terminal is a terminal, and optionally by using an example in which the terminal is a UE.

[0105] The base station and / or the terminal may be at a fixed location or may be mobile. The base station and / or the terminal may be deployed on the ground, indoors or outdoors, or may be handheld or vehicle-mounted, or may be deployed on water, or may be deployed on an airborne plane, balloon, or satellite. The environment / scenario for the base station and the terminal is not limited in this application. The base station and the terminal may be deployed in the same environment / scenario or different environments / scenarios. For example, the base station and the terminal are both deployed on the ground. Alternatively, the base station is deployed on the ground and the terminal is deployed on the water. Examples are not provided one by one.

[0106] The roles of a base station and a terminal may be relative. For example, the helicopter or unmanned aerial vehicle 120i in FIG. 1 may be configured as a mobile base station. For a terminal 120j that accesses the radio access network 100 by using 120i, the terminal 120i is a base station. For a base station 110a, 120i may be a terminal, in other words, 110a and 120i may communicate with each other according to a wireless air interface protocol. Alternatively, 110a and 120i communicate with each other according to an interface protocol between base stations. In this case, for 110a, 120i is also a base station. Therefore, the base station and the terminal may be collectively referred to as a communication apparatus (or communication device). 110a and 110b in FIG. 1 may be referred to as a communication apparatus having a base station function, and 120a to 120j in FIG. 1 may be referred to as a communication apparatus having a terminal function.

[0107] Communications may be performed between base stations and terminals, between base stations, or between terminals by using either licensed or unlicensed spectrum, or by using both licensed and unlicensed spectrum. Communications may be performed by using spectrum below 6 gigahertz (GHz) or above 6 GHz, or by using both spectrum below and above 6 GHz. Spectral resources used for wireless communications are not limited in this disclosure.

[0108] The core network 200 may include one or more core network elements. 5G is used as an example, and the core network may include at least one of the following network elements: an access and mobility management function (AMF) network element, a session management function (SMF) network element, a user plane function (UPF) network element, a policy control function (PCF) network element, a unified data management (UDM) network element, an application function (AF) network element, a location management function (LMF) network element, etc. These core network elements may be hardware structures, software modules, or hardware structures plus software modules. The implementations of different network elements may be the same or different. This is not limited. Different core network elements may be different physical devices (or may be referred to as core network devices), or multiple different core network elements may be integrated into one physical device, in other words, this physical device has the functions of multiple core network elements.

[0109] In the present disclosure, the apparatus configured to implement the functions of the core network device may be a core network device, or may be an apparatus that can support the core network device in implementing the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The apparatus may be installed in the core network device, or may be used together with the core network device in a consistent manner. In the present disclosure, an example in which the apparatus configured to implement the functions of the core network device is a core network device is used to describe the technical solution provided in the present disclosure.

[0110] In a communication system, a positioning technique for a mobile terminal may be implemented. The positioning technique is used to obtain location information of a mobile terminal. The positioning technique may be applied in fields such as navigation and aviation, plotting and disaster relief, vehicle navigation, logistics information query, or traffic management. With the development of mobile communication, the positioning technique based on wireless cellular networks has been widely applied. In wireless cellular networks, for example, in the fourth generation (4G) or 5G mobile communication networks, the positioning technique for a mobile terminal has been widely investigated. The 4G system includes a long term evolution (LTE) system.

[0111] In order to improve positioning efficiency and enable the system to intelligently implement or assist in the implementation of the positioning function, the present disclosure introduces artificial intelligence (AI) technology for the positioning function.

[0112] Artificial intelligence can enable machines with human intelligence. For example, a machine can simulate some intelligent human behavior by using computer software and hardware. To implement artificial intelligence, machine learning methods or other methods can be used. This is not limited. In machine learning methods, a machine obtains a model (or called rules) through learning or training by using training data, and performs inference or prediction using the model. The inference or prediction results can be used to solve practical problems. Machine learning methods include, but are not limited to, at least one of the following: neural network (NN), decision tree, random forest, linear model, Bayesian classifier, probabilistic graphical model, support vector machine (SVM), etc.

[0113] Neural networks are used as an example. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, which allows them to have the ability to learn any mapping. Therefore, neural networks can accurately perform abstract modeling for complex high-dimensional problems. The idea of ​​neural networks comes from the neuronal structure of brain tissue. Each neuron performs a weighted sum operation on the neuron's input values ​​and outputs the weighted sum result through an activation function. The input of a neuron is x=[x0,…,x n ], and the weights corresponding to the inputs are w=[w0,…,w n ] and the offset of the weighted sum is assumed to be b. The form of the activation function may vary. If the activation function of a neuron is y = f(z) = max(0,z), then the output of the neuron is

number

number

[0114] Neural networks generally include a multi-layer structure, and each of the layers may include one or more neurons. Increasing the depth and / or width of a neural network can improve the representation capability of the neural network and provide more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network indicates the amount of layers included in the neural network, and the amount of neurons included in each of the layers may be referred to as the layer width. FIG. 2 is an exemplary diagram of layer relationships of a neural network. In an implementation, a neural network includes an input layer and an output layer. After performing neuronal processing on the received input, the input layer of the neural network transfers the result to the output layer, and the output layer obtains the output result of the neural network. In another implementation, a neural network includes an input layer, a hidden layer, and an output layer. The input layer of the neural network performs neuronal processing on the received input and then transfers the result to an intermediate hidden layer. The hidden layer then transfers the calculation result to the output layer or an adjacent hidden layer. Finally, the output layer obtains the output result of the neural network. A neural network may include, but is not limited to, one or more hidden layers connected in series.

[0115] In the machine learning model training process, a loss function may be defined. The loss function describes the difference between the model's output value and an ideal target value. The specific form of the loss function is not limited in this disclosure. The model training process is a process of adjusting some or all of the model's parameters so that the value of the loss function is smaller than a threshold or meets a target requirement. For example, in the neural network training process, one or more of the following parameters may be adjusted, namely, the amount of layers of the neural network, the neural network width, the connection relationship between the layers, the weights of some or all of the neurons, the activation functions of some or all of the neurons, the offset in the activation function, etc., so that the difference between the neural network's output and the ideal target value is as small as possible or smaller than a threshold. The neural network may be considered as a model.

[0116] In this disclosure, a model may also be referred to as an AI model. An AI model may be considered as a particular way to implement an AI function. An AI model represents a mapping relationship or function model between the input and output of a model. An AI function may include at least one of the following: data collection, model training (or model learning), model information publication, model testing, model inference (or called model inference, inference, prediction, etc.), model monitoring or model checking, inference result publication, etc. An AI function may also be referred to as an AI (relational) operation.

[0117] In the present disclosure, an independent network element (e.g., referred to as an AI network element, AI node, or AI device) may be introduced into the communication system shown in FIG. 1 to implement some of the AI-related operations or functions or all of the AI-related operations or functions. The AI ​​network element may be directly connected to the base station or indirectly connected to the base station through a third-party network element. Optionally, the third-party network element may be a core network element, e.g., an AMF network element or a UPF network element. Alternatively, an AI entity may be disposed in another network element in the communication system to implement the AI-related operations or functions. The AI ​​entity may also be referred to as an AI module, an AI unit, or another name, and is mainly configured to implement some or all of the AI ​​functions. The specific name of the AI ​​entity is not limited in the present disclosure. Optionally, the other network element may be a base station, a core network element, an operation, administration, and maintenance (OAM) device, etc. In this case, the network element that performs the AI-related operations is a network element with built-in AI functions. Both AI network elements and AI entities implement AI-related functions. For ease of explanation, AI network elements and network elements with built-in AI functions are hereinafter collectively referred to as AI-capable network elements.

[0118] In the present disclosure, the OAM is configured for operation, management, and / or maintenance of the core network device (operation, administration, and maintenance system of the core network device) and / or for operation, management, and / or maintenance of the access network device (operation, administration, and maintenance system of the access network device). For example, the present disclosure includes a first OAM and a second OAM, where the first OAM is an operation, administration, and maintenance system of the core network device, and the second OAM is an operation, administration, and maintenance system of the access network device. Optionally, the first OAM and / or the second OAM includes an AI entity. In another example, the present disclosure includes a third OAM, where the third OAM is an operation, administration, and maintenance system of both the core network device and the access network device. Optionally, the third OAM includes an AI entity.

[0119] Optionally, an AI entity may be embedded in a terminal or a terminal chip to match and support the AI ​​function.

[0120] FIG. 3A is an exemplary diagram of an application framework of AI in a communication system. In FIG. 3A, a data source is used to store training data and inference data. A model training host performs training or update training based on training data provided by a data source to obtain an AI model, and deploys the AI ​​model on a model inference host. The AI ​​model represents a mapping relationship between the input and output of the model. Obtaining an AI model through learning by the model training host is equivalent to obtaining a mapping relationship between the input and output of the model through learning by the model training host by using training data. The model inference host uses the AI ​​model to perform inference based on inference data provided by a data source to obtain an inference result. The method can also be described as follows: The model inference host inputs inference data into the AI ​​model and obtains an output by using the AI ​​model, and the output is an inference result. The inference result may indicate a configuration parameter used (acted upon) by an execution object, and / or an operation performed by an execution object. The inference results may be uniformly planned by an actor entity and sent to one or more execution objects (e.g., a core network element, a base station, or a UE) for execution. Optionally, the model inference host may feed back the inference results of the model inference host to the model training host. This process may be referred to as model feedback. The fed back inference results are used by the model training host updating the AI ​​model and deploying the updated AI model on the model inference host. Optionally, the execution object may feed back the network parameters collected by the execution object to a data source. This process may be referred to as performance feedback. The fed back network parameters may be used as training data or inference data.

[0121] In the present disclosure, the application framework shown in FIG. 3A may be deployed in the network elements shown in FIG. 1. For example, the application framework of FIG. 3A may be deployed in at least one of the terminal device, the access network device, the core network device, or the independently deployed AI network element (not shown) of FIG. 1. For example, the AI ​​network element (which may be considered as a model training host) may perform analysis or training on training data provided by the terminal device and / or the access network device to obtain a model. At least one of the terminal device, the access network device, or the core network device (which may be considered as a model inference host) may perform inference by using the model and the inference data to obtain an output of the model. The inference data may be provided by the terminal device and / or the access network device. The input of the model includes the inference data, and the output of the model is an inference result corresponding to the model. At least one of the terminal device, the access network device, or the core network device (which may be considered as an execution object) may perform a corresponding operation based on the inference result. The model inference host and the execution object may be the same or different. This is not limited.

[0122] With reference to FIGS. 3B to 3E, the following describes, by using an example, a network architecture to which the method provided in the present disclosure can be applied.

[0123] As shown in FIG. 3B, in a first possible implementation, the access network device includes a near-real-time access network intelligent controller (RAN intelligent controller, RIC) configured to perform model training and inference. For example, the near-real-time RIC may be configured to train an AI model and use the AI ​​model for inference. For example, the near-real-time RIC may obtain information about the network side and / or the terminal side from at least one of the CU, DU, or RU. This information may be used as training data or inference data. Optionally, the near-real-time RIC may submit the inference result to at least one of the CU, DU, RU, or terminal device. Optionally, the CU and the DU may exchange the inference result. Optionally, the DU and the RU may exchange the inference result. For example, the near-real-time RIC submits the inference result to the DU, and the DU forwards the inference result to the RU.

[0124] As shown in FIG. 3B, in a second possible implementation, there is a non-real-time RIC outside the access network configured to perform model training and inference (optionally, the non-real-time RIC may be located in an OAM or core network device). For example, the non-real-time RIC is configured to train an AI model and use the model for inference. For example, the non-real-time RIC may obtain information about the network side and / or the terminal side from at least one of the CU, DU, or RU. This information may be used as training data or inference data. The inference result may be submitted to at least one of the CU, DU, RU, or terminal device. Optionally, the CU and DU may exchange the inference result. Optionally, the DU and RU may exchange the inference result. For example, the non-real-time RIC submits the inference result to the DU, and the DU forwards the inference result to the RU.

[0125] As shown in FIG. 3B, in a third possible implementation, the access network device includes a near-real-time RIC, and there is a non-real-time RIC outside the access network (optionally, the non-real-time RIC may be located in an OAM or core network device). As in the second possible implementation, the non-real-time RIC may be configured to perform model training and inference. Additionally / alternatively, as in the first possible implementation, the near-real-time RIC may be configured to perform model training and inference. Additionally / alternatively, the non-real-time RIC may perform model training, and the near-real-time RIC may obtain AI model information from the non-real-time RIC, obtain information about the network side and / or the terminal side from at least one of the CU, DU, or RU, and obtain an inference result by using this information and the AI ​​model information. Optionally, the near-real-time RIC may submit the inference result to at least one of the CU, DU, RU, or terminal device. Optionally, the CU and the DU may exchange the inference result. Optionally, the DU and the RU may exchange the inference result. For example, the near-real-time RIC submits the inference result to the DU, and the DU forwards the inference result to the RU. For example, the near real-time RIC is configured to train model A and use model A for inference. For example, the non-real-time RIC is configured to train model B and use model B for inference. For example, the non-real-time RIC is configured to train model C and send information about model C to the near real-time RIC, which uses model C for inference.

[0126] 3C is an exemplary diagram of a network architecture to which the method provided in the present disclosure can be applied. Compared with FIG. 3B, in FIG. 3C, the CU is split into a CU-CP and a CU-UP.

[0127] 3D is an example diagram of a network architecture to which the method provided in the present disclosure can be applied. As shown in FIG. 3D, optionally, the access network device includes one or more AI entities, and the function of the AI ​​entity is similar to that of the near-real-time RIC described above. Optionally, the OAM includes one or more AI entities, and the function of the AI ​​entity is similar to that of the non-real-time RIC described above. Optionally, the core network device includes one or more AI entities, and the function of the AI ​​entity is similar to that of the non-real-time RIC described above. When the OAM and the core network device each include an AI entity, the models obtained through training by the AI ​​entities of the OAM and the core network device are different and / or the models used for inference are different.

[0128] In the present disclosure, the model difference includes at least one of the following differences: structural parameters of the model (e.g., at least one of the amount of neural network layers, neural network width, connectivity between layers, neuron weights, activation functions of neurons, or offsets in activation functions), input parameters of the model (e.g., types of input parameters and / or dimensions of input parameters), or output parameters of the model (e.g., types of output parameters and / or dimensions of output parameters).

[0129] FIG. 3E is an exemplary diagram of a network architecture to which the method provided in the present disclosure can be applied. Compared with FIG. 3D, the access network device in FIG. 3E is split into a CU and a DU. Optionally, the CU may include an AI entity, and the function of the AI ​​entity is similar to that of the near-real-time RIC described above. Optionally, the DU may include an AI entity, and the function of the AI ​​entity is similar to that of the near-real-time RIC described above. When the CU and the DU include an AI entity respectively, the models trained by the AI ​​entities of the CU and the DU are different and / or the models used for inference are different. Optionally, the CU in FIG. 3E may be further split into a CU-CP and a CU-UP. Optionally, one or more AI models may be deployed in the CU-CP. Optionally, one or more AI models may be deployed in the CU-UP.

[0130] In Fig. 3D or Fig. 3E, the OAM of the access network device and the OAM of the core network device are deployed uniformly. Alternatively, as described above, in Fig. 3D or Fig. 3E, the OAM of the access network device and the OAM of the core network device may be deployed separately.

[0131] In the present disclosure, a model may obtain an output through inference, and the output includes one or more parameters. The learning or training processes of different models may be deployed on different devices or nodes, or on the same device or node. The inference processes of different models may be deployed on different devices or nodes, or on the same device or node.

[0132] In the present disclosure, a network element may perform some or all of the steps or operations related to the network element. These steps or operations are merely examples. Other operations or variations of various operations may also be performed in the present disclosure. In addition, steps may be performed in a different sequence than the sequence presented in the present disclosure, and not all operations in the present disclosure need to be performed.

[0133] In the examples of the present disclosure, unless otherwise stated or there is no logical contradiction, the terms and / or descriptions in different examples may be cross-referenced, and the technical features in different examples may be combined based on their internal logical relationships to form a new example.

[0134] In the present disclosure, at least one may be further described as one or more, and more may be two, three, four, or more. This is not limited. " / " may represent an "or" relationship between related objects. For example, A / B may represent A or B. "And / or" may be used to describe the existence of three relationships between related objects. For example, A and / or B may represent the following three cases: only A is present, both A and B are present, and only B is present, and A and B may be singular or plural. In the present disclosure, for ease of describing the technical solutions, terms such as "first", "second", "A", or "B" may be used to distinguish technical features with the same or similar functions. Terms such as "first", "second", "A", or "B" do not limit the quantity and execution sequence. In addition, terms such as "first", "second", "A", or "B" are not limited to be clearly different. Terms such as "example" or "for example" are used to denote an example, illustration, or explanation. Any design solution described as an "example" or "for example" should not be described as preferred or advantageous over another design solution. The use of terms such as "example" or "for example" is intended to present the concepts involved in a particular manner to make them easier to understand.

[0135] The network architecture and service scenarios described in this disclosure are intended to more clearly explain the technical solutions in this disclosure and do not constitute limitations on the technical solutions provided in this disclosure. Those skilled in the art may know that with the development of network architectures and the emergence of new service scenarios, the technical solutions provided in this disclosure are also applicable to similar technical problems.

[0136] FIG. 4 is a schematic flowchart of a positioning method according to the present disclosure. As shown in FIG. 4, in this method, the channel feature extraction model and the positioning information acquisition model used in a matched manner are used to implement the positioning of the UE or assist in implementing the positioning of the UE to acquire the location information of the UE. In this method, the channel feature extraction model is deployed on the RAN side, for example, in a base station or a UE, and is used to map channel information such as a channel response to a channel feature. The base station or the UE sends the channel feature to a core network. The positioning information acquisition model is deployed on the core network side, for example, in an LMF, and is used to map the channel feature to the positioning information of the UE. The positioning information can be used to determine the location information of the UE.

[0137] In this method, the AI ​​model can be used to intelligently locate the UE, thereby improving positioning efficiency. For example, compared with a traditional deterministic algorithm for calculating the location information of the UE, in the method according to the present disclosure, the model is obtained through channel information training, and the UE positioning information obtained based on the model is closer to the actual channel environment. Therefore, the positioning of the UE in which the model is used to implement or assist implementation is more accurate.

[0138] The channel feature extraction model is an AI model, and the name and / or model content (including, for example, model structure and model parameters) of the channel feature extraction model are not limited. For example, the channel feature extraction model may be referred to as a first model, a feature extraction model, or another name, and is used to map channel information, such as a channel response, to channel features.

[0139] The positioning information acquisition model is an AI model, and the name and / or model content (including, for example, model structure and model parameters) of the positioning information acquisition model is not limited. For example, the positioning information acquisition model may be called a second model, a positioning model, or another name, and is used to map channel characteristics to the positioning information of the UE.

[0140] In a possible implementation, the UE positioning information indicates the location information of the UE. For example, the location information of the UE includes at least one of the following: a longitude of the UE location, a latitude of the UE location, an altitude of the UE location, an offset of the UE location relative to a reference location (e.g., a reference base station location or a reference building location), etc. In this implementation, the positioning information acquisition model can be used to determine the location information of the UE.

[0141] In a possible implementation, the positioning information of the UE indicates at least one of the following: a type of a channel between the UE and the base station, a location of a first path of the channel between the UE and the base station, or a relative azimuth angle between the UE and the base station (e.g., an angle of arrival (AoA) and / or an angle of departure (AOD) of a signal transmitted between the UE and the base station). In this disclosure, the channel type includes line of sight (LOS) or non-line of sight (NLOS). The LMF may obtain at least one of the channel type, the first path location, or the relative azimuth angle of the UE, and determine the location information of the UE based on the obtained parameters. In this implementation, the positioning information acquisition model may assist the LMF in implementing a positioning function for the UE. In this disclosure, the relative azimuth angle represents a relative azimuth angle between the base station and the UE, for example, an azimuth angle of the UE to the base station, or an azimuth angle of the base station to the UE.

[0142] FIG. 5A is a schematic diagram of a system architecture of a positioning method according to the present disclosure. When the AMF decides to initiate a positioning service for the UE for a UE, or when the AMF receives a request related to a positioning service for the UE from another network element, for example, the UE or a gateway mobile location center (GMLC), the AMF sends a positioning service request to the LMF. The LMF obtains location information of the UE based on the positioning service request and sends the location information to the AMF. In a scenario where the AMF receives a request related to a positioning service for the UE from another network element, the AMF sends the location information of the UE to the other network element. The AMF and the LMF may be connected in a wired or wireless manner, and are usually connected in a wired manner. The positioning service request sent by the AMF to the LMF may include UE-related information. This information may be sent by a base station in the RAN to the AMF, or may be sent by the UE to the AMF. The RAN may include base stations based on one access technology or multiple access technologies. For example, FIG. 5A shows an LTE base station eNB and an NR base station gNB. The base station and the AMF may be connected in a wired or wireless manner, and are usually connected in a wired manner. Optionally, when the UE sends UE-related information to the AMF, or when the AMF sends the UE's location information to the UE, data transmission may be performed through a logical interface between the UE and the AMF.

[0143] In the present disclosure, data (or referred to as information) between a UE and a core network element, e.g., AMF or LMF, may be used as non-access stratum (NAS) data and forwarded through the air interface of the base station. For example, the base station may use data from the AMF as NAS data and forward the data through the air interface to the UE. The UE may send data sent to the AMF and used as NAS data through the air interface to the base station, which forwards the data to the AMF.

[0144] FIG. 5A illustrates a possible system framework according to an embodiment of the present application, and is not intended to limit the present application. For example, unlike the system framework illustrated in FIG. 5A, there is a logical interface between the UE and the LMF, and the UE may exchange data with the LMF through this logical interface without using the AMF. For example, the UE may send a positioning service request to the LMF, and the LMF may send the UE's location information to the UE. Similar to the above method for data exchange between the UE and the AMF, the data between the UE and the LMF may be used as NAS data and forwarded by the base station. In another example, unlike the system framework illustrated in FIG. 5A, there is an interface for data exchange between the base station and the LMF. In this case, the base station and the LMF may be connected in a wired or wireless manner, and are usually connected in a wired manner. In another example, unlike the communication system illustrated in FIG. 5A, the functions of the AMF and the functions of the LMF may be integrated into the same module, or the positioning functions of the AMF and the positioning functions of the LMF may be integrated into the same module. For example, as illustrated in FIG. 5B, the device in which the module is located may be called a positioning server. Examples are not provided one by one in this disclosure.

[0145] The present disclosure is described by using an example in which the LMF implements the positioning method. The present disclosure may also be applicable to another example in which another network element implements the positioning method. In this case, the LMF may be replaced with another network element. The network element configured to implement the positioning method may be referred to as an LMF or may have another name, for example, a first network element or another name. This is not limited. In the present disclosure, as described in FIG. 5A, the AMF may assist the LMF in implementing the positioning function of the UE. The AMF may have another name, for example, a second network element. This is not limited.

[0146] 6 is a flowchart of a first positioning method according to the present disclosure. The method includes the following operations.

[0147] Optionally, operation S601: UE sends training data to the AI ​​function network element. Optionally, operation S602: LMF sends training data to the AI ​​function network element. Optionally, operation S603: AI function network element performs model training by using the training data.

[0148] The AI ​​function network element may perform model training by using training data to obtain a channel feature extraction model and a positioning information acquisition model. The training data may be sent to the AI ​​function network element by the UE and / or the LMF.

[0149] In the present disclosure, when a UE exchanges information with an AI capability network element, for example, when the UE sends training data to the AI ​​capability network element or when the AI ​​capability network element sends information regarding a channel feature extraction model to the UE, the AI ​​capability network element communicates directly with the UE in a wired or wireless manner, or the AI ​​capability network element communicates with the UE through transmission by another network element (e.g., but not limited to, a core network element and / or a base station).

[0150] In the present disclosure, when an LMF exchanges information with an AI function network element, for example, when the LMF sends training data to the AI ​​function network element or when the AI ​​function network element sends model information to the LMF, the AI ​​function network element communicates directly with the LMF in a wired or wireless manner, or the AI ​​function network element communicates with the LMF through forwarding by another network element (e.g., but not limited to, a base station and / or an AMF or another core network element).

[0151] The operations S601, S602, and S603 are optional. For example, the channel feature extraction model and the positioning information acquisition model are agreed upon in a protocol after offline training. Alternatively, the channel feature extraction model and the positioning information acquisition model are downloaded from a third-party website. In this case, S601, S602, and S603 may be skipped.

[0152] Optionally, operations S601 and S603 are performed but operation S602 is not performed, or operations S602 and S603 are performed but operation S601 is not performed, or operations S601, S602, and S603 are all performed. In operation S601, the training data sent by the UE to the AI ​​function network element may be measured by the UE and / or sent by the base station to the UE by using signaling. In operation S602, the training data sent by the LMF to the AI ​​function network element may be sent by the UE and / or the base station to the LMF.

[0153] The training data acquired by the AI ​​function network element includes training data used to determine the input of the channel feature extraction model and a label corresponding to this input. The label corresponding to the input may be understood as the target output or ideal output of the positioning information acquisition model. For example, when the input of the channel feature extraction model is determined based on the training data A, the target output of the positioning information acquisition model is the label corresponding to the training data A.

[0154] Optionally, the training data used to determine the input of the channel feature extraction model includes at least one of the following: - The channel response between the UE and the base station. Optionally, the channel response between the UE and the base station is measured by the UE and then sent to the AI ​​function network element or LMF. For example, as shown in FIG. 7A, P (the case of three shown in FIG. 7A is used as an illustrative example, but is not limited to) base stations send Y downlink reference signals to the UE. The reference signal sent by the base station to the UE is a downlink reference signal, which may be referred to as a reference signal for short in this disclosure. The UE receives the Y reference signals. Y is an integer equal to or greater than 1, and is usually an integer greater than 1, for example, 3, 4, 5, or a larger number. P is an integer equal to or greater than 1 and less than or equal to Y (the case of Y equal to P in FIG. 7A is used as an illustrative example, but is not limited to). Optionally, in the present disclosure, when a UE receives a reference signal, the LMF or base station may configure at least one of the following of the reference signal for the UE: bandwidth, time domain resources, frequency domain resources, transmission count, antenna ports, spatial correlation, etc. In the present disclosure, one base station may manage one or more cells with different coverage. In one cell, the base station may operate in one or more frequency bands. The base station may send multiple reference signals to the UE in different cells, where one cell corresponds to one reference signal, and / or the base station may send multiple reference signals to the UE in different frequency bands of the same cell, where one frequency band corresponds to one reference signal. In this method, one reference signal may be considered to correspond to one channel. Optionally, different frequency bands may further be considered as different cells. For example, base station A sends reference signal 1 and reference signal 2 to the UE in cell 1 and cell 2, respectively. In this case, base station A may be considered to send reference signal 1 to the UE through channel 1 in cell 1 and send reference signal 2 to the UE through channel 2 in cell 2. The amount of reference signals sent to the UE by different base stations may be the same or different. This is not limited. Optionally, in one cell, the base station may send multiple reference signals to the UE by using multiple different beams, with one beam corresponding to one reference signal. In this disclosure, the downlink reference signal may be, but is not limited to, a downlink synchronization signal, a positioning reference signal (PRS), or another signal whose transmission sequence is known information. The known information may be agreed upon in a protocol or may be notified to the UE by the base station in advance by using signaling. For a y-th reference signal among the Y reference signals, the UE may estimate or calculate a channel response of a channel through which the reference signal passes based on the sending sequence of the reference signal known to the UE and the sequence of the reference signal received by the UE. The channel response corresponds to a channel between the UE and the base station sending the y-th reference signal. For example, if P is equal to Y and each of the base stations sends one reference signal to the UE, the channel response corresponds to a channel between the UE and the y-th base station among the Y base stations. The value of y ranges from 1 to Y. For example, the UE sends a total of Y channel responses to the AI ​​function network element or LMF. The Y channel responses are in one-to-one correspondence with the Y channels between the UE and the P base stations, and each of the channel responses uniquely corresponds to one of the channels. Each of the channel responses may be represented in the form of a multidimensional array. For example, if the amount of transmit antennas is Nt, the amount of receive antennas is Nr, there are K subcarriers in the frequency domain, and L orthogonal frequency division multiplexing (OFDM) symbols in the time domain, the array dimension of the channel response is Nt×Nr×K×L. Nt, Nr, K, and L are positive integers, and each of the elements indicates the channel response between the UE and the base station and on the index corresponding to the element. For example, Nt, Nr, K, and L correspond to the (j1)th transmit antenna, the (j2)th receive antenna, the (j3)th subcarrier, and the (j4)th OFDM symbol, respectively. For simplicity, noise is not considered. The response h between the UE and the base station satisfies the formula, i.e., Srs=Stx*h, where Srs represents the time-domain receive signal, Stx represents the time-domain transmit signal, * represents the convolution, and h represents the time-domain channel response. Alternatively, the response h between the UE and the base station satisfies the formula: Srs=Stx×h, where Srs represents the frequency domain received signal, Stx represents the frequency domain transmitted signal, × represents multiplication, and h represents the frequency domain channel response. Srs, Stx, and h can be real or complex.j1 is 1 or more and Nt or less, j2 is 1 or more and Nr or less, j3 is 1 or more and K or less, and j4 is 1 or more and L or less. For simplicity of explanation, the following uses an example in which one base station sends one reference signal to the UE for explanation. Optionally, the channel response between the UE and the base station is measured by the base station and then sent to the UE or LMF. For example, as shown in FIG. 7B, the UE sends uplink reference signals to P base stations (the case where three are shown in FIG. 7B is used as an example for illustration), respectively, totaling Y uplink reference signals. The reference signal sent by the UE to the base station is an uplink reference signal, which may be referred to as a reference signal for short in this disclosure. The P base stations receive the uplink reference signal, respectively. Y is an integer equal to or greater than 1, and is usually an integer greater than 1, for example, 3, 4, 5, or a larger number. P is an integer equal to or greater than 1 and less than or equal to Y (the case where Y is equal to P in FIG. 7B is used as an example for illustration, but is not limited thereto). Similar to the above description of the downlink reference signal, the UE may send multiple reference signals to one base station in different cells, one cell corresponding to one reference signal, and / or the UE may send multiple reference signals to one base station in different frequency bands of the same cell, one frequency band corresponding to one reference signal. In the method, one reference signal may be considered to correspond to one channel. Optionally, the different frequency bands may further be considered as different cells. For example, the UE sends reference signal 1 and reference signal 2 to base station A in cell 1 and cell 2, respectively. In this case, the UE may be considered to send reference signal 1 to base station A through channel 1 in cell 1, and send reference signal 2 to base station A through channel 2 in cell 2. Optionally, in one cell, the base station may receive multiple reference signals from the UE by using multiple different beams, one beam corresponding to one reference signal. The amount of reference signals sent by the UE to different base stations may be the same or different. This is not limited. In this disclosure, the uplink reference signal may be, but is not limited to, a random access preamble, a sounding reference signal (SRS), or another signal whose sending sequence is known.The known information may be agreed in a protocol or may be notified to the UE by the base station in advance by using signaling. After receiving the y-th uplink reference signal, the corresponding base station among the P base stations may estimate or calculate a channel response of the channel through which the reference signal passes based on the sending sequence of the reference signal known to the base station and the sequence of the reference signal received by the base station. The channel response is described as corresponding to the channel between the UE and the base station receiving the y-th uplink reference signal or corresponding to the channel through which the y-th uplink reference signal passes. The base station sends the channel response to the UE or the AI-functional network element. The value of y ranges from 1 to Y. The UE or the AI-functional network element receives a total of Y channel responses from the P base stations. For simplicity of explanation, the following uses an example in which the UE sends one reference signal to one base station for explanation. Optionally, in the present disclosure, when a base station receives a reference signal, the LMF may configure at least one of the following of the reference signal for the base station: bandwidth, time domain resources, frequency domain resources, transmission count, antenna ports, spatial correlation, etc. In this disclosure, both the uplink reference signal and the downlink reference signal may be referred to as the reference signal for short, but whether the reference signal is an uplink reference signal or a downlink reference signal may be determined based on the transmission body and / or the reception body. In this disclosure, the uplink reference signal and the downlink reference signal differ in at least one of the following: the transmission direction of the reference signal, the time domain resource, the frequency domain resource, or the sequence value. Optionally, in the training data, the "channel response between the UE and the base station" may be further exchanged with at least one of the following: the amplitude of the channel response, the phase of the channel response, the real part of the channel response, the imaginary part of the channel response, the phase difference of the channel response of different receiving or transmitting antennas, or the phase difference between multiple channel responses. The channel response and these variations of the channel response may be collectively referred to as channel information. Optionally, the channel information may further include a reference signal received power (RSRP), a reference signal time difference (RSTP), and a type of the environment in which the UE is located. - The RSRP of the channel between the UE and the base station. Optionally, the RSRP is measured by the UE and then sent to the AI-capable network element or LMF. For example, based on the above description of FIG. 7A, an example is used in which P is equal to Y and each of the base stations sends one reference signal to the UE. After estimating the channel response of the channel between the UE and the yth base station, the UE may obtain the RSRP of the channel based on the channel response. The value of y ranges from 1 to Y. For example, the UE sends a total of Y RSRPs to the AI-capable network element or LMF, and the Y RSRPs are in one-to-one correspondence with the Y channels between the UE and the Y base stations, and each of the RSRPs uniquely corresponds to one of the channels. The case in which P is not equal to Y is similar to the above description. Details will not be described again in this specification. Optionally, the information is measured by the base station and then sent to the UE or LMF. For example, based on the above description of FIG. 7B, an example is used in which P is equal to Y and the UE sends one reference signal to each of the base stations. After estimating the channel response of the channel between the UE and the yth base station, the yth base station may obtain the RSRP of the channel based on the channel response. The yth base station sends the RSRP to the LMF or UE. The value of y ranges from 1 to Y. The UE or AI function network element receives a total of Y RSRPs from the Y base stations. The case in which P is not equal to Y is similar to the above description. Details will not be described again in this specification. - RSTP on the channel between the UE and the base station. The information is measured by the UE and then sent to the AI-capable network element or LMF. For example, based on the above description of FIG. 7A, the UE may obtain the RSTD of different reference signals through estimation. For example, P is equal to Y, and each of the base stations sends one reference signal to the UE. The UE may measure the RSTD of the reference signal of the yth base station and the RSTD of the reference signal of the first base station to obtain a total of Y-1 RSTDs, and the UE sends the Y-1 RSTDs to the AI-capable network element or LMF. Alternatively, the UE may measure the RSTD of the reference signal of the yth base station and the RSTD of the reference signal of the (y-1)th base station to obtain a total of Y-1 RSTDs, and the UE sends the Y-1 RSTDs to the AI-capable network element or LMF. The specific RSTD reporting method is not limited in this disclosure. The value of y ranges from 2 to Y. The case where P is not equal to Y is similar to the above description. Details will not be described again in this specification. - The type of environment in which the UE is located. The type of environment in which the UE is located may be a factory environment, an office environment, a high-speed rail environment, a subway environment, a shopping mall environment, a residential area environment, or another possible environment. This is not limited. The information may be reported by the UE or the base station to the AI ​​function network element or the LMF. In the present disclosure, training data corresponding to different environments may be used to train models corresponding to different environments. Optionally, a target output (a label of the training data) of the positioning information acquisition model includes at least one of the following: - UE location information. The UE location information includes the longitude of the UE location, the latitude of the UE location, the altitude of the UE location, an offset of the UE location relative to a reference location (e.g., a reference base station location or a reference building location), and the like. Optionally, the UE is a beacon UE. The UE knows the location information of the UE, and the UE sends the location information to an AI-capable network element or an LMF. Alternatively, a base station knows the location information of the UE, and the base station sends the location information to the UE or the LMF. Alternatively, the LMF knows the location information of the UE, and the LMF sends the location information to an AI-capable network element. The base station is at least one of the P base stations. Optionally, the LMF obtains the location information of the UE by using a non-AI-based positioning method, and sends the location information to the AI-capable network element. For example, in this disclosure, the non-AI-based positioning method may be a downlink (DL)-time difference of arrival (TDOA) positioning method, an uplink (UL)-DOA positioning method, a UL-AoA positioning method, a DL-AOD positioning method, or another positioning method described in the 3rd generation partnership project (3GPP) 38.305 protocol. This is not limited. Optionally, in order to increase the accuracy, the LMF may obtain multiple estimated location information of the UE through multiple estimations, use a weighted average of the multiple estimated location information as the location information of the UE, and send the location information to the AI-capable network element. - The type of channel between the UE and the base station. For a given base station, the type of channel between the UE and the base station may be LOS or NLOS. Optionally, an example where P is equal to Y is used, and the UE is a beacon UE. The UE knows the channel type of the channel between the UE and the yth base station, and the UE sends the channel type to an AI-capable network element or LMF, and the UE sends a total of Y channel types. Alternatively, the yth base station knows the channel type of the channel between the UE and the yth base station, and the yth base station sends the channel type to the UE or LMF, and the total of Y base stations send the channel type to the UE or LMF, and the UE or LMF receives a total of Y channel types. Alternatively, the LMF knows the channel type of the channel between the UE and the yth base station, and the LMF sends the channel type to an AI-capable network element, and the LMF sends a total of Y channel types. The value of y ranges from 1 to Y. When P is not equal to Y, the method is similar. For example, for base station A, base station A performs transmission (transmission or reception) of reference signal 1 and reference signal 2 in cell 1 and cell 2, respectively, with the UE. In this case, for channel 1 corresponding to reference signal 1 and channel 2 corresponding to reference signal 2, the UE or base station A sends the channel type of channel 1 and the channel type of channel 2, respectively. In other words, a total of Y channel types are determined for the Y channels between the P base stations and the UE, and each of the channels corresponds to one reference signal. Similar cases will not be described again below. Optionally, an example where P is equal to Y is used. The LMF obtains the channel type of the channel between the UE and the yth base station by using a non-AI-based channel type determination method, and sends the channel type to the AI-capable network element. The LMF sends a total of Y channel types, where the value of y ranges from 1 to Y. Optionally, in order to increase the accuracy, the LMF may obtain the channel type of the channel between the UE and the yth base station through multiple estimations, and use the channel type that appears more frequently or with a higher probability as the channel type of the channel between the UE and the yth base station, and send the channel type to the AI-capable network element. For example, the LMF obtains the channel type of the channel between the UE and the yth base station through five estimations, and the channel types are LOS, NLOS, LOS, LOS, and LOS, respectively. Since LOS appears more frequently or with a higher probability, the LMF considers that the channel type between the UE and the yth base station is LOS. When P is not equal to Y, the method is similar. For example, for base station A, base station A performs transmission (send or receive) of reference signal 1 and reference signal 2 in cell 1 and cell 2 with the UE, respectively. In this case, for channel 1 corresponding to reference signal 1 and channel 2 corresponding to reference signal 2, the LMF determines the channel type of channel 1 and the channel type of channel 2, respectively. In other words, a total of Y channel types are determined for Y channels between P base stations and the UE, and each of the channels corresponds to one reference signal. Similar cases will not be described again below. Optionally, in the present disclosure, the non-AI based channel type determination method may be to determine whether the channel type is LOS or NLOS by using a Rician factor of the channel response. Usually, the Rician factor of the LOS signal is higher than that of the NLOS signal. For example, the Rician factor of the channel response may be compared with a threshold value. When the Rician factor is equal to or greater than the threshold value, the channel type is LOS, otherwise, the channel type is NLOS. For a channel response, the Rician factor of the channel response is

number

number

number

number

number

[0155] Optionally, in the present disclosure, when measuring training data, in order to improve measurement accuracy, the UE, the base station, and / or the LMF may repeatedly measure a single training data multiple times, and use the comprehensive value of the multiple repeated measurements, for example, the average value, the weighted sum, or another possible value, as the training data. This method can improve the reliability of the training data. Optionally, when measuring the training data, the UE, the base station, and / or the LMF may further mark the reliability and / or generation time of the training data for reference in the model training process. For example, training data that is close to the generation time and / or has high reliability during training may be used for model training.

[0156] Optionally, in the present disclosure, the AI ​​function network element obtains multiple training data corresponding to at least one UE. The multiple training data may be considered as one training data set. The AI ​​function network element performs model training by using the training data set to obtain a channel feature extraction model and a positioning information acquisition model. When one training data set corresponds to multiple UEs, two different training data in the training data set may correspond to two different UEs, correspond to measurement data of the same UE at two different geographic locations, correspond to measurement data of the same UE at two different moments, or correspond to measurement data of the same UE at two different frequency bands. When one training data set corresponds to one UE, two different training data in the training data set may correspond to measurement data of the same UE at two different geographic locations, correspond to measurement data of the same UE at two different moments, or correspond to measurement data of the same UE at two different frequency bands.

[0157] In the present disclosure, one training data set may correspond to one environment type. For example, the AI ​​function network element acquires multiple training data corresponding to at least one UE in the environment. The multiple training data may be considered as one training data set. The AI ​​function network element performs model training by using the training data set to acquire a channel feature extraction model and a positioning information acquisition model corresponding to the environment type. Similar to the above description, when one training data set corresponds to multiple UEs, two different training data in the training data set may correspond to two different UEs in the same environment type, or may correspond to measurement data of the same UE in the same environment type but at two different geographic locations, different moments, or different frequency bands. When one training data set corresponds to one UE, two different training data in the training data set correspond to measurement data of the same UE in the same environment type but at two different geographic locations, different moments, or different frequency bands. As described above, the environment type may be a factory environment, an office environment, a high-speed rail environment, a subway environment, a shopping mall environment, a residential area environment, or another possible environment. This is not limited. In this method, a model that better matches each of the environment types can be obtained by independently training the model for the environment type. Thus, during model application, the corresponding model can be matched and applied based on the environment of the UE.

[0158] In the present disclosure, the UE configured to perform model training and the UE configured to perform model inference may be the same (as shown in the figures of the present disclosure) or different. This is not limited. For example, the first UE performs operation S601, and the second UE performs operations S604, S606a, S606b, S607, and S608. The positioning information of the second UE is determined in operation S609. The first UE and the second UE may be the same or different. Regardless of whether the first UE and the second UE are the same, the base station configured to perform model training and the base station configured to perform model inference may be the same (as shown in the figures of the present disclosure) or different. This is not limited. For example, the model training process (e.g., operation S601) is related to a first group of P base stations, and the model application process (e.g., operation S607) is related to a second group of P base stations. The first group of P base stations and the second group of P base stations may be the same or different. When the first group of P base stations and the second group of P base stations are different, at least one base station in the first group of P base stations is not included in the second group of P base stations. Optionally, the first UE and the second UE are the same, and at least one same base station is present in the first group of P base stations and the second group of P base stations. The same base station communicates with the UE in the first cell when in the first group of P base stations, and communicates with the UE in the second cell when in the second group of P base stations. The first cell and the second cell may be the same or different.

[0159] After the training data set is collected, for the training data in the training data set, the AI ​​function network element may obtain a channel feature extraction model and a positioning information acquisition model through training by using the training data and the label corresponding to the training data. During the model training, the parameters of the model may be adjusted, and the purpose of the model training is as follows: when the input of the channel feature extraction model is determined based on the training data in the training data set, and the input of the positioning information acquisition model is obtained based on the output of the channel feature extraction model, the output of the positioning information acquisition model is as close as possible to the label of the training data. The training method of the AI ​​model is not described in detail or limited in this application. For example, mature methods in the industry for training neural networks, such as stochastic gradient descent (SGD) method, batch gradient descent (BGD) method, adaptive gradient algorithm (AdaGrad), momentum algorithm, and Newton's method, may be used to obtain neural network parameters that are as optimal as possible through iterative training. Model training methods obtained through industry research in the future are also applicable to the present disclosure, which is not limited thereto.

[0160] Optionally, the AI ​​function network element may further collect a new training data set, and perform model update training by using the new training data set to obtain an updated channel feature extraction model and an updated positioning information acquisition model. For example, the update training is periodic. The AI ​​function network element uses the data collected within the period as a training data set, and performs the update training by using the training data set. In another example, the update training is triggered by an event. For example, when the error of the measurement result of the positioning information acquisition model exceeds a threshold, the AI ​​function network element performs update training on the channel feature extraction model and the positioning information acquisition model based on the new training data set.

[0161] Figure 8A, Figure 8B, and Figure 8C are structural diagrams of training a channel feature extraction model and a positioning information acquisition model for positioning. The following describes how an AI function network element trains a channel feature extraction model and a positioning information acquisition model based on a training data set based on Figure 8A, Figure 8B, and Figure 8C.

[0162] For one training data A in the training set, a process of training the channel feature extraction model and the positioning information acquisition model by using the training data A may be referred to as a training process.

[0163] Optionally, as shown in FIG. 8A, the training data A may be a set of Y channel responses H1, H2, ..., H Y For each of the Y channel responses, or the yth channel response H y For, the AI ​​function network element is the input of the channel feature extraction model, Feature_model_In y The y value ranges from 1 to Y. The AI ​​feature network element determines the input Feature_model_In yand the channel feature extraction model and the output of the channel feature extraction model based on Feature_model_Out y where Feature_model_Out y is the channel feature S y The AI ​​function network element extracts a total of Y channel features S1, S2, ..., S based on the channel feature extraction model and the Y channel responses. Y In this method, the channel response H y For each, the channel feature extraction model extracts channel features S corresponding to the channel response. y is used to obtain

[0164] Optionally, a channel characteristic S y can be a real number, a vector, a matrix, or a multi-dimensional array (more than one dimension). This is not limited.

[0165] The AI ​​function network element determines the input of the positioning information acquisition model based on the output of the channel feature extraction model. For example, the AI ​​function network element determines the input of the positioning information acquisition model based on Y channel features. The AI ​​function network element outputs positioning information based on the input and the positioning information acquisition model. For example, the AI ​​function network element determines the input of the positioning information acquisition model based on Y channel features. Y Based on the positioning information acquisition model B inputs Position_model_In b The value of b ranges from 1 to B, where B is an integer equal to or greater than 1. The AI ​​function network element inputs B inputs to the positioning information acquisition model and obtains B outputs Position_model_Out b The value of b ranges from 1 to B. b The output corresponding to is Position_model_Out b It is.

[0166] Position_model_Out bindicates the location information of the UE or indicates at least one of the following for each of the Y channels: the channel type of the UE, the first path location, or the relative azimuth angle (e.g., the AOA and / or AOD of the reference signal communicated through the channel). In the model training algorithm, the channel feature extraction model and / or the positioning information acquisition model outputs Position_model_Out b is adaptively adjusted by comparing the output of the positioning information acquisition model with the label (target output) of the training data A. The channel feature extraction model and the positioning information acquisition model obtained in one training process may be used for the next iterative training. In the next iterative training, the channel feature extraction model and the positioning information acquisition model obtained through training based on the training data A are used as basic or initial models for update training. After multiple iterative training rounds, the difference between the output of the positioning information acquisition model and the target output is allowed to be as small as possible. For example, when the number of iterative training rounds N train can be defined, and N train The model obtained after N training iterations is used as the model obtained through training. train is a positive integer. In another example, a loss function may be defined. The loss function is used to represent the difference between the output of the positioning information acquisition model and the target output. After multiple iterations by using multiple training data in the training dataset, when the value of the loss function is as small as possible or smaller than (or equal to) a threshold, the model obtained through the iterative training is used as the model obtained through training.

[0167] Optionally, as shown in FIG. 8B, the training data A may be a set of Y channel responses H1, H2, ..., H YThe AI ​​function network element determines an input of a channel feature extraction model based on the Y channel responses, and obtains an output of the channel feature extraction model based on the input and the channel feature extraction model, where the output indicates one channel feature S. Optionally, S may be a real number, a vector, a matrix, or a multi-dimensional array (greater than one dimension). This is not limited. It may be considered that the channel feature S corresponds to the Y channels between the UE and the P base stations. The AI ​​function network element determines an input of a positioning information acquisition model based on the channel feature S. The AI ​​function network element outputs positioning information of the UE based on the input and the positioning information acquisition model. For example, the AI ​​function network element may obtain an input Position_model_In of the positioning information acquisition model based on the channel feature S. The AI ​​function network element inputs Position_model_In to the positioning information acquisition model and outputs Position_model_Out.

[0168] Position_model_Out indicates the location information of the UE or indicates at least one of the following for each of the Y channels: the channel type of the UE, the first path location, or the relative azimuth angle (e.g., the AOA and / or AOD of the reference signal communicated through the channel). Similar to the above description of FIG. 8A, after multiple iterative trainings are completed by using multiple training data in the training dataset, a channel feature extraction model and a positioning information acquisition model can be obtained.

[0169] Optionally, as shown in FIG. 8C, the training data A may be a set of Y channel responses H1, H2, ..., H YThe AI ​​capability network element may determine a total of Q inputs of the channel feature extraction model based on the Y channel responses. Each of the inputs is determined by T channel responses among the Y channel responses, where Q and T are positive integers and Q×T=Y. For a qth input among the Q inputs, the AI ​​capability network element obtains an output of the channel feature extraction model based on the input and the channel feature extraction model, where the output is a channel feature S q where q ranges from 1 to Q. Optionally, the channel feature S q can be a real number, a vector, a matrix, or a multi-dimensional array (greater than one dimension). This is not limited. The AI ​​function network element extracts a total of Q channel features S1, S2, ..., S based on the channel feature extraction model and the Y channel responses. Q It may be assumed that the Q channel features correspond to the Y channels. In this method, for each T channel response, the channel feature extraction model obtains one channel feature S corresponding to the T channel responses. Q The AI ​​function network elements are S1, S2, ..., S Q The AI ​​network element determines the input of the positioning information acquisition model based on the input and the positioning information acquisition model. The AI ​​network element outputs the positioning information of the UE based on the input and the positioning information acquisition model. For example, the AI ​​network element may determine the input of the positioning information acquisition model based on the channel features S1, S2, ..., S Q Based on the positioning information acquisition model N inputs Position_model_In n The AI ​​function network element may obtain N inputs Position_model_In to the positioning information acquisition model, where the value of n ranges from 1 to N, and N is an integer equal to or greater than 1. n Input N outputs Position_model_Out n The value of n ranges from 1 to N. n The output corresponding to is Position_model_Out n It is.

[0170] Position_model_Out n indicates the location information of the UE, or indicates at least one of the following for each of the Y channels: a channel type of the UE, a first path location, or a relative azimuth angle (e.g., AOA and / or AOD of a reference signal communicated through the channel). Similar to the above description of FIG. 8A, after multiple iterative trainings are completed by using multiple training data in the training dataset, a channel feature extraction model and a positioning information acquisition model can be obtained.

[0171] Optionally, in the present disclosure, in the model training algorithm, the input dimension and / or output dimension of the model can be predefined or pre-determined. Thus, the channel feature extraction model obtained through training can meet the requirements for feedback overhead and positioning information accuracy. For example, a smaller output dimension of the channel feature extraction model indicates a lower feedback overhead. A larger output dimension of the channel feature extraction model indicates a higher positioning information accuracy.

[0172] In the present disclosure, determining an input of a channel feature extraction model based on a channel response includes, but is not limited to, using the channel response as an input of the channel feature extraction model, separating a real part of the channel response from an imaginary part and combining the separated real part matrix with a dimension of Z and the separated imaginary part matrix with a dimension of Z into a 2Z-dimensional matrix and using the 2Z-dimensional matrix as an input of the channel feature extraction model, or separating an amplitude of the channel response from a phase and combining a separated amplitude matrix with a dimension of Z and a separated phase matrix with a dimension of Z into a 2Z-dimensional matrix and using the 2Z-dimensional matrix as an input of the channel feature extraction model, combining the real part matrix, the imaginary part matrix, the amplitude matrix, and the phase matrix into a 4Z-dimensional matrix and using the 4Z-dimensional matrix as an input of the channel feature extraction model, or combining information about the channel response (at least one of the real part, the imaginary part, the amplitude, or the phase) and other feedback information (e.g., RSRP and / or RSTD) into an input of the channel feature extraction model.

[0173] In the present disclosure, determining an input of a positioning information acquisition model based on an output of a channel feature extraction model includes, but is not limited to, determining one input of the positioning information acquisition model based on one or more outputs of the channel feature extraction model. For example, one output of the channel feature extraction model may be used as one input of the positioning information acquisition model, or multiple outputs of the channel feature extraction model may be connected or combined to form one input of the positioning information acquisition model, or one or more outputs of the channel feature extraction model and other feedback information (e.g., RSRP and / or RSTD) may be combined into one input of the positioning information acquisition model. For example, S channel features may be denoted as S1, S2, ..., S Y One input of the positioning information acquisition model can be expressed as [S1, S 2, ...,S Y ] or [S 1, S2,...,S Y ] TFor example, the T channel features may include S, S2, ..., S T One input of the positioning information acquisition model can be expressed as [S1, S 2, ...,S T ] or [S 1, S2,...,S T ] T [ ] T represents a matrix transposition. Similar to determining the input of the channel feature extraction model based on the channel response, the input of the positioning information acquisition model can be further obtained by separating the real part of the channel feature from the imaginary part and / or separating the amplitude of the channel feature from the phase. The details will not be described again. A similar method can be further used to determine the input of the channel feature extraction model based on multiple channel responses. The details will not be described again.

[0174] Optionally, the present disclosure provides the above H y About H y H may be further divided into multiple subchannel responses, each of which corresponds to one antenna port, and the input of the channel feature extraction model is determined based on each of the subchannel responses. For example, H yThe dimension of is 512×4×16, where 512 represents the frequency domain dimension (e.g., corresponding to 512 subcarriers), 4 represents the time domain dimension (e.g., corresponding to 4 OFDM symbols), and 16 represents the spatial domain dimension (e.g., corresponding to 16 antenna ports), where 512, 4, and 16 are used only as examples and may be replaced with other integer values. The channel feature extraction model may be used to perform channel feature extraction for each channel response of the antenna ports. For example, the input of the channel feature extraction model is the channel response of one antenna port, and the dimension of the input is 512×4. Alternatively, one channel feature extraction model may be used for channel feature extraction for 16 antenna ports. For example, the input of the channel feature extraction model is the channel response of multiple antenna ports, and the dimension of the input is 512×4×16. Although different methods affect the input dimension of the channel feature extraction model, the methods of model training and model application are similar. Similarly, for the frequency domain and / or the time domain, the division may also be performed in a manner similar to that of the antenna ports. The division granularity of the frequency domain may be an integer amount of subcarriers, an integer amount of resource blocks (RB), an integer amount of resource block groups (RBG), or another possible case. The division granularity of the time domain may be an integer amount of OFDM symbols, an integer amount of slots, or another possible case.

[0175] Optionally, multiple pairs of models (channel feature extraction model + positioning information acquisition model) can be trained, and an appropriate model is selected and applied as necessary. The application of the AI ​​model can further take into account the compromise between complexity and performance. A neural network is used as an example, and more layers and neurons of the network indicate higher complexity and higher performance of the AI ​​model, but more computing resources need to be consumed. Fewer layers and neurons of the network indicate lower complexity and lower performance of the AI ​​model, but less computing resources need to be consumed. The AI ​​model can be selected by taking into account the actual application scenario. For example, for a UE with high computing power, such as a mobile phone, a tablet computer, or an in-vehicle terminal, a more complex AI model can be used. For a UE with low computing power, such as an Internet of Things terminal or an mMTC terminal, a slightly simpler AI model or an AI model with fewer parameters can be used. Correspondingly, an appropriate AI model can also be selected based on the computing power of the LMF.

[0176] Optionally, in the present disclosure, the input of the channel feature extraction model may further include the RSRP of the channel between the UE and the base station and / or the RSTP of the channel between the UE and the base station. Alternatively, optionally, in addition to the input of the positioning information acquisition model determined based on the output of the channel feature extraction model, the input of the positioning information acquisition model may further include the RSRP of the channel between the UE and the base station and / or the RSTP of the channel between the UE and the base station.

[0177] Optionally, operation S604: the UE sends the UE's capability information to the LMF.

[0178] The capability information of the UE indicates at least one of the following information of the UE: - Whether the UE supports AI-based positioning methods. For example, when the UE supports an AI-based positioning method, the LMF may determine the positioning information of the UE by using the AI-based positioning method. For example, to perform positioning, the UE uses the channel feature extraction model provided in this disclosure, and the LMF uses the positioning information acquisition model provided in this disclosure. When the UE does not support an AI-based positioning method, the LMF may determine the location information of the UE by using a non-AI-based positioning method. "Whether the UE supports an AI-based positioning method" may be replaced with the positioning method type supported by the UE. The type may be an AI-based positioning method or a non-AI-based positioning method. Optionally, in the present disclosure, the AI-based positioning method may be further described as a machine learning algorithm-based positioning method, an AI model-based positioning method, or another name, which is not limited thereto. - UE computing capability information. The computing capability information of the UE may indicate an amount of operations supported by the UE per unit time or may indicate a computing capability level of the UE. For example, multiple computing capability levels are agreed upon in a protocol or preconfigured by a network side (e.g., a base station, an AMF, or an LMF) for the UE, and each of the computing capability levels corresponds to an amount of operations supported by the UE per unit time. The UE may determine the computing capability level of the UE based on the amount of operations supported by the UE per unit time and the multiple computing capability levels. The network side (e.g., an LMF or an AI function network element described below) may configure an appropriate channel feature extraction model for the UE based on the computing capability information of the UE. According to this method, the UE can operate normally. For example, the computing resources used by the UE when the UE uses the channel feature extraction model to perform inference do not exceed the computing capability level of the UE or do not occupy too much of the computing capability of the UE. Occupying too much of the computing capability of the UE includes occupying more than 50% of the computing resources of the UE or another percentage of the computing resources of the UE. - Information about the models supported by the UE (AI models). The information indicates information about the AI ​​model supported by the UE. The information about the AI ​​model supported by the UE may indicate whether the UE supports a specific type of AI model, or may indicate whether the UE indicates a description manner of the AI ​​model, or may indicate the type of the AI ​​model supported by the UE. For example, the information indicates whether the UE supports at least one of the following types of AI models: fully connected neural network, convolutional neural network, recurrent neural network, neural network supporting attention mechanism, or different neural network types. According to the method, the network side may configure an appropriate model for the UE.

[0179] In the present disclosure, when a UE sends information to an LMF, for example, UE capability information, the following method may be used.

[0180] Optionally, when the UE sends information to the LMF, if there is a logical interface between the UE and the LMF, the information may be sent by the UE to the base station in the form of a NAS message and may be forwarded by the base station to a core network element A (e.g., an AMF or another network element) and then forwarded by the core network element A to the LMF, or the information may be sent by the UE to the base station in the form of a NAS message and then forwarded by the base station to the LMF.

[0181] Optionally, when the UE sends information to the LMF, if there is no logical interface between the UE and the LMF, the information may be sent by the UE to the base station in the form of a NAS message, may be forwarded by the base station to a core network element B (e.g., AMF or another network element), and then may be notified by the core network element B to the LMF, or the information may be sent by the UE to the base station in the form of a NAS message, may be forwarded by the base station to a core network element A, may be forwarded by the core network element A to a core network element B, and then may be notified by the core network element B to the LMF. There is a logical interface between the UE and the core network element B, and the logical interface is used to communicate the above information. There is no logical interface between the UE and the core network element A, or there is a logical interface between the UE and the core network element A, but the above information is not interpreted and cannot be communicated at the logical interface layer.

[0182] The core network element A may be one network element (one-hop forwarding) or may be multiple network elements (multi-hop forwarding).

[0183] In the present disclosure, when the LMF sends information to the UE, for example, information about a channel feature extraction model, as described below, the LMF may send information by using a path opposite to the above-mentioned method. For example, when the LMF sends information to the UE, if there is a logical interface between the UE and the LMF, the information may be sent by the LMF to the core network element A in the form of a NAS message, and may be forwarded by the core network element A to the base station, and then forwarded by the base station to the UE, or the information may be sent by the LMF to the base station in the form of a NAS message, and then forwarded by the base station to the UE. For the sake of brevity, the details will not be described again in this specification.

[0184] Optionally, the information sent by the UE to the LMF may be inquired (or requested) based on the LMF. For example, the LMF sends UE capability query information to the UE. After receiving the query information, the UE reports the UE capability information to the LMF.

[0185] Optionally, the UE may send the UE capability information to the LMF in advance. For example, when the UE accesses the network, the UE sends the UE capability information to the LMF in advance, or when the time domain resource (e.g., period and offset in the period) for reporting the capability information by the UE is agreed upon in the protocol or pre-configured by the LMF, the UE sends the UE capability information to the LMF on the time domain resource, or when the capability information changes or a network handover occurs, the UE sends the UE capability information to the LMF. The reason why the UE sends the UE capability information to the LMF is not limited in this application.

[0186] Operation S604 is optional. For example, if the UE's capabilities are agreed upon in a protocol, S604 does not need to be performed. For example, when there are multiple capability types of UEs in the system or the UE's capabilities can change autonomously, the UE may perform S604.

[0187] Optionally, operation S605 (not shown): a positioning information acquisition model is configured. Optionally, operation S606 (not shown): a channel feature extraction model is configured. S605 and S606 may be collectively referred to as model configuration. By performing operation S605 and operation S606, the AI ​​function network element may deploy the model acquired through training on the UE and the LMF.

[0188] Model configuration can be implemented by using model configuration method 1 or model configuration method 2 below.

[0189] Model configuration method 1:

[0190] Optionally, in operation S605a: the AI ​​function network element sends information about a positioning information acquisition model to the LMF. Optionally, in operation S606a: the AI ​​function network element sends information about a channel feature extraction model to the UE.

[0191] Operation S605a is optional. For example, the positioning information acquisition model may be agreed upon in a protocol after offline training, or the positioning information acquisition model may be downloaded from a third-party website. Therefore, S605a may be skipped.

[0192] Operation S606a is optional. For example, the channel feature extraction model may be agreed upon in a protocol after offline training, or the channel feature extraction model may be downloaded from a third-party website. Thus, S606a may be skipped.

[0193] In the above method, both operations S605a and S606a may be performed, or neither operation S605a nor operation S606a may be performed, or operation S605a may be performed but S606a is not performed, or operation S605a may not be performed but S606a is performed. This is not limited.

[0194] Model configuration method 2:

[0195] Optionally, in operation S605b, the AI ​​function network element sends information about the positioning information acquisition model and information about the channel feature extraction model to the LMF. In operation S606b, the LMF sends information about the channel feature extraction model to the UE.

[0196] In a possible implementation, the operation S605b and / or the operation S606b are optional. For example, the positioning information acquisition model and the channel feature extraction model are agreed upon in a protocol after offline training, or the positioning information acquisition model and the channel feature extraction model can be downloaded from a third-party website, or either the positioning information acquisition model or the channel feature extraction model is agreed upon in a protocol after offline training, and the other can be downloaded from a third-party website.

[0197] In the present disclosure, when model information is exchanged between different network elements (shown as network element C and network element D), for example, when information regarding a positioning information acquisition model or information regarding a channel feature extraction model is exchanged between an AI function network element and an LMF, or when information regarding a channel feature extraction model is exchanged between an AI function network element and a UE, or when information regarding a channel feature extraction model is exchanged between an LMF and a UE, or when information regarding a channel feature extraction model is exchanged between an LMF and a base station, as described below, or when information regarding a channel feature extraction model is exchanged between an AI function network element and a base station, as described below, an example is used in which network element C sends model information to network element D, and network element C may send at least one of the following information of the model to network element D: - The dimensions of the model's input parameters. - The type of the model's input parameters. For example, the types of input parameters include a channel response, an RSRP of the channel, an RSTP of the channel, and so on. - Gradient information of the model. For example, the information indicates gradient information of the currently sent model relative to a reference model or relative to a previously sent model. For example, the model information previously sent by network element C to network element D is information A, and network element D may obtain information B based on information A and the gradient information, which provides new model information of the model. In other words, the model may be updated or reconfigured by using the gradient information of the model. - The amount of layers in the model. - The connectivity between layers in the model. - The offset of the model's neurons. - The weights of the neurons in the model. - The index (or identifier) ​​of the model. - the validity period of the model. The model is available within the validity period. Otherwise, the model is unavailable.

[0198] Optionally, when the AI ​​function network element is an LMF or the AI ​​function network element and the LMF are located in the same device, the AI ​​function network element sending model information to the LMF may be implemented as follows: The LMF reads the model information.

[0199] Operation S607: The UE extracts a channel feature by using the channel feature extraction model. Operation S608: The UE sends the channel feature to the LMF. Operation S609: The LMF acquires positioning information of the UE by using the positioning information acquisition model.

[0200] For example, as shown in FIG. 7A, similar to the above description of model training, P base stations send Y downlink reference signals to the UE. The UE receives the Y reference signals. Y is an integer equal to or greater than 1, and is usually an integer greater than 1, for example, 3, 4, 5, or a larger number. For the yth reference signal among the Y reference signals, the UE may obtain a channel response of the channel through which the reference signal passes through through measurement. The channel response corresponds to the channel between the UE and the base station sending the reference signal. The value of y ranges from 1 to Y.

[0201] After acquiring the Y channel responses, the UE may determine an input of a channel feature extraction model based on the Y channel responses, and may acquire X channel features through inference by using the channel feature extraction model. The UE sends the X channel features to the LMF. The method may be described as follows: The UE sends X channel features to the LMF, where the X channel features correspond to Y channels of the UE, the X channel features are acquired by using a channel feature extraction model, and the input of the channel feature extraction model is determined based on the Y channel responses, the Y channel responses are in one-to-one correspondence with the Y channels, Y is a positive integer greater than or equal to 1, and X is an integer greater than or equal to 1.

[0202] The Y channels are Y channels between the UE and the P base stations. Optionally, there are E channels between each of the P base stations and the UE, where E is an integer equal to or greater than 1. Optionally, when E is greater than 1, different channels among the E channels correspond to different cells and / or frequency bands. For different base stations, the values ​​of E may be the same or different. This is not limited.

[0203] The LMF receives the X channel features, and determines positioning information of the UE by using the X channel features and the positioning information acquisition model. For example, the LMF determines an input of the positioning information acquisition model based on the X channel features, and acquires the positioning information of the UE through inference by using the positioning information acquisition model.

[0204] In this method, positioning is performed by using an AI model to implement intelligent positioning, so that the positioning performance is closer to the actual channel environment, thereby implementing more accurate positioning.

[0205] Optionally, X is a positive integer less than or equal to Y. Compared to reporting Y channel responses, when fewer than Y(X) channel characteristics are reported, the amount of reported information can be reduced and signaling overhead can be reduced.

[0206] Optionally, the total dimension of the X channel features is less than the total dimension of the Y channel responses. This method is a possible method for reducing the amount of reported information, and can reduce the signaling overhead between the UE and the LMF. For example, compared with sending a high-dimensional channel response to the LMF to determine the positioning information of the UE, in this method, sending a low-dimensional channel feature to the LMF to determine the positioning information of the UE can reduce the signaling overhead between the UE and the LMF. For example, the total dimension of the Y channel responses is 512×4×16, and the total dimension of the X channel features can be reduced to 16. For example, 16 real or complex numbers represent the channel features corresponding to the channel responses. This example is only used to explain the problem and is not intended to limit the present disclosure.

[0207] Figure 9A, Figure 9B, and Figure 9C are structural diagrams of UE and LMF performing positioning by using a channel feature extraction model and a positioning information acquisition model. Figure 9A, Figure 9B, and Figure 9C are similar to Figure 8A, Figure 8B, and Figure 8C, respectively. Figure 8A, Figure 8B, and Figure 8C are used for model training, and Figure 9A, Figure 9B, and Figure 9C are used for model application or model inference. In Figure 8A, Figure 8B, and Figure 8C, and in Figure 9A, Figure 9B, and Figure 9C, the channel feature extraction model and the positioning information acquisition model operate in the same manner. The difference is that in Figures 8A, 8B, and 8C, model information of the channel feature extraction model and / or the positioning information acquisition model may be updated through training, and finally, the model information of the trained channel feature extraction model and / or the trained positioning information acquisition model is output, while in Figures 9A, 9B, and 9C, inference is performed by using the trained channel feature extraction model and / or the trained positioning information acquisition model, and in this process, the model information of the channel feature extraction model and / or the positioning information acquisition model does not change.

[0208] Optionally, as shown in FIG. 9A, Y channel responses H1, H2, ..., H Y After obtaining the y-th channel response H y For, the UE receives the input Feature_model_In of the channel feature extraction model. y The y value ranges from 1 to Y. The UE determines y Based on the channel feature extraction model and the inference, the output of the channel feature extraction model Feature_model_Out y Get Feature_model_Out y is the channel feature S y The UE extracts a total of Y channel features S1, S2, ..., S based on the channel feature extraction model and the Y channel responses. Y In this method, the channel response H yFor each, the channel feature extraction model extracts channel features S corresponding to the channel response. y Optionally, the channel features S y can be a real number, a vector, a matrix, or a multi-dimensional array (greater than one dimension). This is not limited. In practical processing, the UE may have (or store) one channel feature extraction model, and all of the Y channel features are obtained through inference by using the channel feature extraction model. This method can save storage resources of the UE. Alternatively, the UE may have (or store) multiple (e.g., Y) channel feature extraction models, and at least two of the Y channel features are obtained through inference by using the same channel feature extraction model. This method can improve the processing speed of the UE.

[0209] The method for how the UE determines the input of the channel feature extraction model based on the channel response is similar to the corresponding description in Figure 8A, and the details will not be described again here.

[0210] The UE receives Y channel features S1, S2, ..., S Y The LMF determines the input of the positioning information acquisition model based on the Y channel features. The LMF acquires the positioning information of the UE through inference based on the input and the positioning information acquisition model. For example, the LMF receives channel features S1, S2, ..., S Y Based on the positioning information acquisition model B inputs Position_model_In b The LMF can obtain B inputs Position_model_In b Input the following and generate a total of B outputs through inference: Position_model_Out b The value of b ranges from 1 to B, where B is an integer equal to or greater than 1. b The output corresponding to is Position_model_Out bWhen B is greater than 1, in the actual process, the LMF may have (or store) one positioning information acquisition model and may have multiple inputs Position_model_Out b are all obtained through inference by using the positioning information acquisition model. This method can save the storage resources of the LMF. Alternatively, the LMF may have (or store) multiple (e.g., B) positioning information acquisition models and may store multiple Position_model_Out b At least two of the Position_model_Out b is obtained through inference by using the same positioning information acquisition model. This method can improve the processing speed of LMF.

[0211] Optionally, the positioning information of the UE indicates location information of the UE.

[0212] Example A1:

[0213] B is equal to 1, Position_model_Out b indicates at least one of the longitude, latitude, and altitude of the UE.

[0214] Example B1:

[0215] B is equal to 1, Position_model_Out b indicates the offset of the UE relative to the reference location. Optionally, the input of the positioning information acquisition model may further include the reference location.

[0216] Optionally, in Examples A1 and B1, you can use the Position_model_In b may contain Y elements, where the yth element is S y where y values ​​range from 1 to Y. Alternatively, similar to the above description, b is Y S y The signal includes at least one of a real part, an imaginary part, an amplitude, and a response separated from the signal.

[0217] Optionally, the positioning information of the UE indicates at least one of the following for each of the Y channels: a channel type of the UE, a first path location, or a relative azimuth angle. The channel type, first path location, and / or the relative azimuth angle of the UE are used to determine location information of the UE.

[0218] Example C1:

[0219] B is 1 or more, and Position_model_Out b , b=1,...,B are the first path locations [First_Path1, First_Path2,..., First_Path Y ] is indicated.

[0220] For example, B is equal to 1, and Position_model_In b contains Y elements, where the yth element is S y where the y values ​​range from 1 to Y and b denotes the first path location of each of the Y channels.

[0221] In another example, B is greater than 1, e.g., B is equal to 2, and Position_model_In1 includes Y1 elements, where the (y1)th element is S y1 where y1 ranges from 1 to Y1, Position_model_Out1 indicates the first path location of each of the first channel through the (Y1)th channel, and Position_model_In2 includes Y2 elements, where the (y2)th element is S Y1+y2where y2 ranges from 1 to Y2, and Position_model_Out2 indicates the first path location from the (Y1+1)th channel to the (Y1+Y2)th channel, respectively. B being equal to 2 is used only as an example and is not intended to limit the present disclosure. b is determined by using the channel features of a group of channels, Position_model_Out b It can be understood that denotes the first path location of a group of channels.

[0222] Optionally, Position_model_Out b , b=1,...,B are the time domain locations of the first paths of each of the Y channels during the same time length (e.g., the length of one OFDM symbol). y where the value of y ranges from 1 to Y. After obtaining the first path locations of each of the channels, the LMF may obtain location information of the UE based on the first path locations of the at least three channels.

[0223] For example, FIG. 10 shows an example of estimating a location of a UE based on a first path location. In FIG. 10, base station 1 sends a reference signal P1 to the UE through channel 1, and the arrival time of P1 is t1, base station 2 sends a reference signal P2 to the UE through channel 2, and the arrival time of P2 is t2, and base station 3 sends a reference signal P3 to the UE through channel 3, and the arrival time of P3 is t3. t1, t2, and t3 are greater than 0. Through measurements, the UE may obtain the arrival time difference t1-t2 or t2-t1 between P1 and P2 (t1-t2 is used as an example in the figures and below), and may obtain the arrival time difference t1-t3 or t3-t1 between P1 and P3 (t1-t3 is used as an example in the figures and below). The UE may report the arrival time difference t1-t2 and t1-t3 to the LMF. The departure times of P1 and P2 are assumed to be P1_Tx_t and P2_Tx_t, respectively. P1_Tx_t and P2_Tx_t are greater than 0. In a possible implementation, P1_Tx_t and P2_Tx_t are the same as those agreed in the protocol. In another possible implementation, P1_Tx_t and P2_Tx_t can be flexibly configured. In this case, P1_Tx_t and P2_Tx_t can be the same or different. Base station 1 may send P1_Tx_t to the LMF, and base station 2 may send P2_Tx_t to the LMF. The departure times of P1 and P3 are assumed to be P1_Tx_t and P3_Tx_t, respectively. P3_Tx_t is greater than 0. In a possible implementation, P1_Tx_t and P3_Tx_t are the same as those agreed in the protocol. In another possible implementation, P1_Tx_t and P3_Tx_t can be flexibly configured. In this case, P1_Tx_t and P3_Tx_t can be the same or different. Base station 1 can send P1_Tx_t to the LMF, and base station 3 can send P3_Tx_t to the LMF.The LMF may determine that the arrival time difference between the first paths of P1 and P2 is (t1-P1_Tx_t+First_Path1)-(t2-P2_Tx_t+First_Path2), and the arrival time difference between the first paths of P1 and P3 is (t1-P1_Tx_t+First_Path1)-(t3-P3_Tx_t+First_Path3). When P1_Tx_t and P2_Tx_t are the same, (t1-P1_Tx_t+First_Path1)-(t2-P2_Tx_t+First_Path2) may be simplified as (t1+First_Path1)-(t2+First_Path2). When P1_Tx_t and P3_Tx_t are the same, (t1-P1_Tx_t+First_Path1)-(t3-P3_Tx_t+First_Path3) may be simplified as (t1+First_Path1)-(t3+First_Path3). The LMF may determine that the location of the UE that satisfies the arrival time difference is curve 1 based on the arrival time difference between the first paths of P1 and P3, and may determine that the location of the UE that satisfies the arrival time difference is curve 2 based on the arrival time difference between the first paths of P1 and P2. Thus, the LMF may consider the intersection of curve 1 and curve 2 to be the location of the UE, or in other words, the intersection of curve 1 and curve 2 may be considered to be the estimated location for the UE.

[0224] Optionally, Position_model_Out b First_Path with more than three B's, b=1,...,B y When the LMF indicates y , and estimate the location of the UE according to the above method. Alternatively, the LMF may estimate multiple locations for the UE and determine the average value of the multiple estimated locations as the location of the UE. Each of the estimated locations of the UE corresponds to one of the three First_Path y The signal is obtained through estimation based on three channels corresponding to

[0225] This disclosure does not limit the particular algorithm used by the LMF to determine the location of the UE based on the first route location, or in other words, how the LMF uses the output of the positioning information acquisition model to assist in implementing the positioning functionality of the UE.

[0226] Example D1:

[0227] B is 1 or more, and Position_model_Out b , b=1,...,B are the first path locations [First_Path1, First_Path2,..., First_Path Y ] and the channel type. As in example C1, B can be equal to 1 or greater than 1. b is determined by using the channel features of a group of channels, Position_model_Out b It can be understood that indicates the first path location and channel type of a group of channels.

[0228] As shown in FIG. 11, a base station sends a signal to a UE. The signal may arrive at the UE through multiple paths. However, because the LOS path between the base station and the UE is blocked by a tree, the UE cannot measure the signal on the LOS path. The first path measured by the UE is assumed to be on an NLOS path and is a signal reflected by a wall. If the location of the UE is estimated based on the arrival time of the signal on the NLOS path, the distance between the UE and the base station may be estimated to be d2+d3. However, the actual distance between the UE and the base station is d1 on the LOS path. Therefore, to improve the estimation accuracy of the location of the UE, when the first path between the UE and the base station is an LOS path, the location of the UE may be estimated based on the location of the first path.

[0229] In example D1, the LMF has a channel type of Position_model_Out b , b=1,...,B, the location of the UE may be determined by using a method similar to example C1 based on the first path location of the channel that is LOS indicated by b , b=1, ..., B indicates [First_Path1, First_Path2, ..., First_Path8], and Position_model_Out b , b=1,...,B indicates that channel 1, channel 2, channel 4, channel 5, channel 7, and channel 8 are LOS paths, and channel 3 and channel 6 are NLOS paths. In this case, the LMF may determine the location of the UE by using the method described in example C1 based on First_Path1, First_Path2, First_Path4, First_Path5, First_Path7, and First_Path8.

[0230] Example E1:

[0231] B is 1 or more, and Position_model_Out b , b=1,...,B denotes the channel type of each of the Y channels. As in example C1, B can be equal to 1 or greater than 1. b is determined by using the channel features of a group of channels, Position_model_Out b It can be understood that indicates the channel type of a group of channels.

[0232] Example E1 is similar to Example D1. Unlike Example D1, the first path location of each of the Y channels is b, b=1,...,B, and are obtained in another manner. The specific manner is not limited. For example, to simplify calculation, the first path locations of various channels are the same as those agreed upon in the protocol, or the first path locations are reported by the UE or the corresponding base station to the LMF. For example, the UE reports the first path locations of each of the Y channels, or each of the Y base stations corresponding to the Y channels reports the first path locations of the channels between the base station and the UE.

[0233] Example F1:

[0234] B is 1 or more, and Position_model_Out b , b=1,...,B are the relative azimuth angles [Direction1,Direction 2,..., Direction Y ] is indicated.

[0235] For example, B is equal to 1, and Position_model_In b contains Y elements, where the yth element is S y where the y values ​​range from 1 to Y and b denotes the azimuth angle of the UE corresponding to each of the Y channels.

[0236] In another example, B is greater than 1, e.g., B is equal to 2, and Position_model_In1 includes Y1 elements, where the (y1)th element is S y1 where y1 ranges from 1 to Y1, Position_model_Out1 indicates the relative azimuth angles of the UE corresponding to the first channel through the (Y1)th channel, respectively, and Position_model_In2 includes Y2 elements, where the (y2)th element is S Y1+y2where y2 ranges from 1 to Y2, and Position_model_Out2 indicates the relative azimuth angle of the UE corresponding to the (Y1+1)th channel to the (Y1+Y2)th channel, respectively. B being equal to 2 is used only as an example and is not intended to limit the present disclosure. b is determined by using the channel features of a group of channels, Position_model_Out b It can be understood that {overscore (E)} indicates the relative azimuth angle of the UE corresponding to the group of channels.

[0237] Optionally, Position_model_Out b , b=1,...,B are the relative azimuth angles of the UE corresponding to each of the Y channels. y where the value of y ranges from 1 to Y. After obtaining the relative azimuth angles of the UE corresponding to the channels, the LMF may obtain location information of the UE based on the relative azimuth angles of the UE corresponding to at least two of the channels.

[0238] For a channel, the relative azimuth angle of the UE corresponding to the channel may be AOA and / or AOD. For the method of how the LMF determines the location information of the UE by using AOA and AOD, please refer to the method described in the protocol of 3GPP 38.805, such as the DL (downlink)-AOD positioning method and the UL-AOA (uplink) positioning method described in the protocol. The present disclosure may further use another positioning method based on AOA and AOD. This is not limited.

[0239] Optionally, Position_model_Out b , b=1, ..., B is more than two directions y When indicating, LMF is yand may estimate the location of the UE according to the method above. Alternatively, the LMF may estimate multiple locations for the UE and determine an average value of the multiple estimated locations as the location of the UE.

[0240] This disclosure does not limit the particular algorithm used by the LMF to determine the location of the UE based on the UE's azimuth angle, or in other words, how the LMF uses the output of the positioning information acquisition model to assist in implementing the UE's positioning functionality.

[0241] Optionally, as shown in FIG. 9B, Y channel responses H1, H2, ..., H Y After obtaining Y channel responses, the UE determines one input Feature_model_In of the channel feature extraction model based on the Y channel responses, and obtains one output Feature_model_Out of the channel feature extraction model through inference based on the input and the channel feature extraction model. The output indicates a channel feature S. The UE may obtain a total of one channel feature S based on the channel feature extraction model and the Y channel responses. Optionally, S may be a real number, a vector, a matrix, or a multi-dimensional array (greater than one dimension). This is not limited. The UE sends the channel feature S to the LMF. In this method, the channel feature S may be considered to correspond to the Y channels.

[0242] The method for how the UE determines the input of the channel feature extraction model based on the channel response is similar to the corresponding description in Figure 8B, and the details will not be described again here.

[0243] The LMF determines an input of a positioning information acquisition model based on a channel feature S. The LMF acquires positioning information of the UE through inference based on the input and the positioning information acquisition model. For example, the LMF may acquire an input Feature_model_In of the positioning information acquisition model based on the channel feature S. The LMF acquires an output Feature_model_Out through inference based on the input and the positioning information acquisition model. The Feature_model_Out indicates the positioning information of the UE.

[0244] Optionally, the positioning information of the UE indicates the location information of the UE, or indicates the channel type and / or the first path location of each of the Y channels. The channel type and / or the first path location are used to determine the location information of the UE. The channel type and / or the first path location are used to assist the LMF to determine the location information of the UE. The description of Feature_model_Out is similar to those of FIG. 9A. The details are not described again. In FIG. 9A and FIG. 9B, the input and output of the channel feature extraction model are different, but their processing ideas are similar. In FIG. 9A, for the Y channels, the LMF side may perform processing by using one or more positioning information acquisition models. In FIG. 9B, for the Y channels, the LMF side may perform processing by using one positioning information acquisition model.

[0245] Optionally, as shown in FIG. 9C, Y channel responses H1, H2, ..., H Y After obtaining Y, the UE may determine a total of Q inputs of a channel feature extraction model based on the Y channel responses, where each of the inputs is determined by T channel responses among the Y channel responses, where Q and T are positive integers, and Q×T=Y. For a qth input among the Q inputs, the UE may obtain an output of the channel feature extraction model based on the input and the channel feature extraction model, where the output is a channel feature S q where q ranges from 1 to Q.

[0246] Optionally, a channel characteristic S q can be a real number, a vector, a matrix, or a multi-dimensional array (greater than one dimension). This is not limited. The UE extracts a total of Q channel features S1, S2, ..., S based on the channel feature extraction model and the Y channel responses. Q It may be assumed that the Q channel features correspond to the Y channels. In this method, for each T channel response, the channel feature extraction model obtains one channel feature S corresponding to the T channel responses. Q In the actual processing, the UE may store one channel feature extraction model, and each of the Q inputs is successively inferred based on the channel feature extraction model. Alternatively, the UE may store multiple (e.g., Q) channel feature extraction models, and at least two of the Q inputs are inferred based on different channel feature extraction models. This is not limited.

[0247] The UE transmits Q channel features S1, S2, ..., S Q LMF sends S1, S2, ..., S Q The LMF determines the input of the positioning information acquisition model based on the input and the positioning information acquisition model through inference to acquire the positioning information of the UE. For example, the LMF determines the input of the positioning information acquisition model based on the input and the positioning information acquisition model through inference based on the channel features S1, S2, ..., S Q Based on the positioning information acquisition model N inputs Position_model_In n where the value of n ranges from 1 to N, and N is an integer equal to or greater than 1. The LMF may provide N inputs Position_model_In n Input the following and generate N outputs through inference: Position_model_Out n The value of n ranges from 1 to N. n The output corresponding to is Position_model_Out n It is.

[0248] As in the description of Figure 9A, N=1 and Position_model_Out n indicates the location information of the UE. Alternatively, N is 1 or more, and Position_model_Out n , n=1,...,N indicates the channel type and / or the first path location of each of the Y channels. The channel type and / or the first path location are used to assist the LMF in determining the location information of the UE. Position_model_Out n The explanations of are similar to those of FIG. 9A. The details will not be described again. In FIG. 9A and FIG. 9C, the input and output of the channel feature extraction model are different, but their processing ideas are similar.

[0249] Figures 8A, 8B, 8C, 9A, 9B, and 9C are used to illustrate the architecture of the channel feature extraction model and the positioning information acquisition model and are not intended to limit the present disclosure.

[0250] 12 is a flowchart of a second positioning method according to the present disclosure. The method includes the following operations.

[0251] Optionally, operation S1201: the base station sends training data to the AI ​​function network element. Optionally, operation S1202: the LMF sends training data to the AI ​​function network element. Optionally, operation S1203: the AI ​​function network element performs model training by using the training data.

[0252] The AI ​​function network element may perform training through a model training process by using training data to obtain a channel feature extraction model and a positioning information acquisition model. The training data may be sent to the AI ​​function network element by the base station and / or the LMF.

[0253] In the present disclosure, when a base station exchanges information with an AI-capable network element, for example, when the base station sends training data to the AI-capable network element or when the AI-capable network element sends information regarding a channel feature extraction model to the base station, the AI-capable network element communicates directly with the base station in a wired or wireless manner, or the AI-capable network element communicates with the base station through forwarding by another network element (e.g., but not limited to, a core network element).

[0254] Operations S1201, S1202, and S1203 are optional. For example, the channel feature extraction model and the positioning information acquisition model are agreed upon in a protocol after offline training. Alternatively, the channel feature extraction model and the positioning information acquisition model are downloaded from a third-party website. In this case, S1201, S1202, and S1203 may be skipped.

[0255] Optionally, operations S1201 and S1203 are performed but S1202 is not performed, or operations S1202 and S1203 are performed but S1201 is not performed, or operations S1201, S1202, and S1203 are all performed. In operation S1202, the training data sent by the base station to the AI-functional network element may be measured by the base station and / or reported by the UE to the base station by using signaling. In operation S1202, the training data sent by the LMF to the AI-functional network element may be sent by the UE and / or the base station to the LMF.

[0256] The training data acquired by the AI ​​function network element includes training data used to determine the input of the channel feature extraction model and the label corresponding to the input. The label corresponding to the input can be understood as the target output or ideal output of the positioning information acquisition model. For example, when the input of the channel feature extraction model is determined based on the training data A, the target output of the positioning information acquisition model is the label corresponding to the training data A.

[0257] Optionally, the training data used to determine the input of the channel feature extraction model includes at least one of the following: - The channel response between the UE and the base station. Optionally, the information is measured by the UE, then sent to the base station or LMF, and sent by the base station or LMF to the AI ​​function network element. For specific measurement methods, please refer to the corresponding description in Figure 6. Optionally, the information is measured by the base station and then sent to the LMF or the AI ​​function network element, and optionally sent by the LMF to the AI ​​function network element. For specific measurement methods, please refer to the corresponding description in Figure 6. - The RSRP of the channel between the UE and the base station. Optionally, the information is measured by the UE, then sent to the LMF or base station, and sent by the LMF or base station to the AI ​​function network element. For specific measurement methods, please refer to the corresponding description in Figure 6. Optionally, the information is measured by the base station and then sent to the LMF or the AI ​​function network element, and optionally sent by the LMF to the AI ​​function network element. For specific measurement methods, please refer to the corresponding description in Figure 6. - RSTP on the channel between the UE and the base station. The information is measured by the UE, then sent to the LMF or base station, and sent by the LMF or base station to the AI ​​function network element. For specific measurement methods, please refer to the corresponding description in Figure 6. - The type of environment in which the UE is located. For a description of the environment types, see the corresponding description in Figure 6. The information may be reported by the UE to the LMF or base station and sent by the LMF or base station to the AI ​​capability network element, or the information may be sent by the base station to the AI ​​capability network element or the LMF, and optionally sent by the LMF to the AI ​​capability network element. Optionally, in the training data, the target output of the positioning information acquisition model includes at least one of the following: - UE location information. For an explanation of the location information, please refer to the corresponding explanation in FIG. Optionally, the UE is a beacon UE. The UE knows the location information of the UE, and the UE reports the location information to the LMF or base station, and then the LMF or base station sends the location information to the AI-capable network element. Alternatively, the base station knows the location information of the UE, and the base station sends the location information to the AI-capable network element or the LMF, and then, optionally, the LMF sends the location information to the AI-capable network element. Alternatively, the LMF knows the location information of the UE, and the LMF sends the location information to the AI-capable network element. Optionally, the LMF obtains the location information of the UE by using a non-AI-based positioning method, and sends the location information to the AI-capable network element. For a description of the non-AI-based positioning method, please refer to the corresponding description of Figure 6. - The type of channel between the UE and the base station. Optionally, an example is used where P is equal to Y, and the UE is a beacon UE. The UE knows the channel type of the channel between the UE and the yth base station, the UE sends the channel type to the LMF or base station, the UE sends a total of Y channel types, and then the LMF or base station sends the Y channel types to the AI-capable network element. Alternatively, the yth base station knows the channel type of the channel between the UE and the yth base station, the yth base station sends the channel type to the AI-capable network element or LMF, the total of Y base stations send the channel type to the AI-capable network element or LMF, and then the AI-capable network element or LMF receives the total of Y channel types, and optionally the LMF sends the Y channel types to the AI-capable network element. Alternatively, the LMF knows the channel type of the channel between the UE and the yth base station, the LMF sends the channel type to the AI-capable network element, and the LMF sends a total of Y channel types. The value of y ranges from 1 to Y. Similar to the corresponding illustration in FIG. 6, when P is not equal to Y, the method is similar. Optionally, an example in which P is equal to Y is used. The LMF obtains the channel type of the channel between the UE and the yth base station by using a non-AI-based positioning method, and sends the channel type to the AI-capable network element. The LMF sends a total of Y channel types. The value of y ranges from 1 to Y. For a description of the non-AI-based positioning method, please refer to the corresponding description of FIG. 6. Similar to the corresponding description of FIG. 6, when P is not equal to Y, the method is similar. - The first path location of the channel between the UE and the base station. The method for determining the first path location of the channel between the UE and the base station and the method for reporting are the same as the above description of "Type of channel between the UE and the base station". The channel type is replaced with the first path location. The details are not described again in this specification.

[0258] Similarly to the corresponding description of Figure 6, the AI ​​function network element obtains a plurality of training data corresponding to at least one UE. The plurality of training data can be regarded as a training data set. Model training is implemented by using the training data set to obtain a channel feature extraction model and a positioning information acquisition model.

[0259] In the present disclosure, as with the corresponding description of FIG. 6, the UE configured to perform model training and the UE configured to perform model inference may be the same or different (as shown in the figures of the present disclosure). This is not limited. For example, the UE described in operation S1201, operation S1202, and operation S1203 is a first UE, and the UE described in operation S1207, S1208, and S1209 is a second UE. The first UE and the second UE may be the same or different. Regardless of whether the first UE and the second UE are the same, the base station configured to perform model training and the base station configured to perform model inference may be the same or different (as shown in the figures of the present disclosure). This is not limited. For example, the model training process (e.g., operation S1201) is related to a first group of P base stations, and the model application process (e.g., operation S1207) is related to a second group of P base stations. For the description of the first group of P base stations and the second group of P base stations, please refer to the corresponding description of FIG. 6. Details will not be described again in this specification. As with the corresponding description of FIG. 6, the AI ​​function network element may perform model training or model update training by using a training data set. In the method shown in FIG. 12, the process of the AI ​​function network element performing model training or model update training by using a training data set is the same as that shown in FIG. 8A. Details will not be described again in this specification.

[0260] Optionally, similar to the description of FIG. 6, multiple pairs of models (channel feature extraction model + positioning information acquisition model) can be trained, and an appropriate model is selected and applied as necessary. The AI ​​model can be selected by taking into account the actual application scenario. For example, for a base station with high computing power, such as a macro base station, a more complex AI model can be used. For a base station with low computing power, such as a small cell or micro base station, a slightly simpler AI model or an AI model with fewer parameters can be used. Correspondingly, an appropriate AI model may also be selected based on the computing power of the LMF.

[0261] Optionally, operation S1204: the base station sends capability information of the base station to the LMF.

[0262] The capability information of the base station indicates at least one of the following information of the base station: - Whether the base station supports AI-based positioning methods. For example, when the base station supports an AI-based positioning method, the LMF may determine the positioning information of the UE by using the AI-based positioning method. For example, to perform positioning, the base station uses the channel feature extraction model provided in this disclosure, and the LMF uses the positioning information acquisition model provided in this disclosure. When the base station does not support an AI-based positioning method, the LMF may determine the location information of the UE by using a non-AI-based positioning method. "Whether the base station supports an AI-based positioning method" may be replaced with the positioning method type supported by the base station. The type may be an AI-based positioning method or a non-AI-based positioning method. - Base station computing capability information. Similar to the computing capability information of the UE in the method shown in FIG. 6, the UE is replaced with a base station. - AI model supporting base station capability information. As with the AI ​​model that supports UE capability information in the method shown in FIG. 6, the UE is replaced with a base station.

[0263] In the present disclosure, when a base station sends information to an LMF, for example, the base station's capability information, the following method may be used.

[0264] Optionally, when the base station sends information to the LMF, if there is an interface between the base station and the LMF, the base station may send the information to the LMF. If there is no interface between the base station and the LMF, the LMF may send the information to a core network element E (e.g., an AMF or another network element), which then forwards the information to the LMF. The core network element E may be one network element (one-hop forwarding) or multiple network elements (multi-hop forwarding).

[0265] In the present disclosure, when the LMF sends information to the base station, for example, information regarding a channel feature extraction model, as described below, the LMF may send the information by using a path opposite to the above-mentioned method. For example, when the LMF sends information to the base station, if there is an interface between the base station and the LMF, the LMF sends the information to the base station. If there is no interface between the base station and the LMF, the LMF may send the information to a core network element E (e.g., an AMF or another network element), which then forwards the information to the base station.

[0266] Optionally, sending information by the base station to the LMF may be inquiring (or requesting) based on the LMF. For example, the LMF sends base station capability query information to the base station. After receiving the query information, the base station reports the base station capability information to the LMF. Alternatively, the base station may proactively send the base station capability information to the LMF. For example, during network deployment, the base station proactively sends the base station capability information to the LMF, or when the capability information changes, the base station sends the base station capability information to the LMF. This is not limited.

[0267] Operation S1204 is optional. For example, if the capabilities of the base station are agreed upon in a protocol, S1204 does not need to be performed. For example, when there are base stations of multiple capability types in the system or the capabilities of the base station can change autonomously, the base station may perform S1204.

[0268] Optionally, operation S1205 (not shown): a positioning information acquisition model is configured. Optionally, operation S1206 (not shown): a channel feature extraction model is configured. S1205 and S1206 may be collectively referred to as model configuration.

[0269] Model configuration can be implemented by using model configuration method 1 or model configuration method 2 below.

[0270] Model configuration method 1:

[0271] Optionally, in operation S1205a: the AI-capable network element sends information about a positioning information acquisition model to the LMF. Optionally, in operation S1206a: the AI-capable network element sends information about a channel feature extraction model to the base station.

[0272] Optionally, the AI ​​function network element and the base station are connected in a wired or wireless manner, or the AI ​​function network element and the base station communicate with each other through transmissions by another network element (e.g., but not limited to, a core network element).

[0273] For a description of the optionality of operation S1205a and operation S1206a, please refer to the corresponding description in Fig. 6. The details will not be described again here.

[0274] Model configuration method 2:

[0275] Optionally, Operation S1205b: The AI ​​function network element sends information about the positioning information acquisition model and information about the channel feature extraction model to the LMF. Operation S1206b: The LMF sends information about the channel feature extraction model to the base station.

[0276] For a description of the optionality of operation S1205b and operation S1206b, please refer to the corresponding description in Figure 6. The details will not be described again here.

[0277] Operation S1207: The base station extracts a channel feature by using the channel feature extraction model. Operation S1208: The base station sends the channel feature to the LMF. Operation S1209: The LMF determines the positioning information of the UE by using the positioning information acquisition model.

[0278] For example, as shown in FIG. 7B, an example is used in which P is equal to Y and the UE sends one reference signal to each of the base stations. The UE sends uplink reference signals to Y base stations (a case in which three are shown in FIG. 7B is used as an example for explanation). The Y base stations each receive the uplink reference signal. Y is an integer equal to or greater than 1, and is usually an integer greater than 1, for example, 3, 4, 5, or a larger number. After receiving the uplink reference signal, the yth base station among the Y base stations calculates a channel response H of the channel through which the reference signal passes based on the transmission sequence value of the reference signal known to the yth base station and the sequence value of the reference signal received by the base station. y The channel response H y corresponds to the channel between the UE and the yth base station. The value of y ranges from 1 to Y. The case where P is not equal to Y is similar to the above description. Details are not described again in this specification. When P is not equal to Y, the P base stations obtain a total of Y channel responses of the Y channels between the P base stations and the UE through estimation.

[0279] After obtaining the E channel responses corresponding to each of the base stations, each of the base stations may obtain E channel features based on the channel responses and the channel feature extraction model, where each of the channel features corresponds to one channel response. The base station sends the E channel features to the LMF. For each base station, the method may be described as follows: The base station sends E channel features to the LMF, where the E channel features correspond to E channels between the UE and the base station, each of the channel features is obtained by using the channel feature extraction model, and an input of the channel feature extraction model is determined based on the channel responses, where the channel responses correspond to the channels corresponding to the channel features. E is an integer equal to or greater than 1, and the values ​​of E corresponding to different base stations may be the same or different. A total of P base stations send y channel features to the LMF.

[0280] The LMF receives a total of Y channel features from the P base stations, and determines positioning information of the UE by using the Y channel features and the positioning information acquisition model. For example, the LMF determines an input of the positioning information acquisition model based on the Y channel features, and acquires the positioning information of the UE through inference by using the positioning information acquisition model.

[0281] In this method, positioning is performed by using an AI model to implement intelligent positioning, so that the positioning is closer to the actual channel environment, thereby implementing more accurate positioning.

[0282] Optionally, the dimension of the channel characteristics sent by the base station to the LMF is smaller than the dimension of the corresponding channel response. According to this method, the signaling overhead between the base station and the LMF can be reduced.

[0283] An example is used in which P is equal to Y. Figure 9A is a structural diagram in which a base station and an LMF perform positioning by using a channel feature extraction model and a positioning information acquisition model.

[0284] As shown in FIG. 9A, the yth base station (also called base station y) has a channel response H y Get H y Based on the channel feature extraction model input Feature_model_In y where the value of y ranges from 1 to Y. The base station y is y Based on the channel feature extraction model of the base station and the channel feature extraction model output Feature_model_Out y Get Feature_model_Out y is the channel feature S y The base station indicates the S y The LMF receives a total of Y channel characteristics from Y base stations. The Y channel characteristics are denoted as S1, S2, ..., S Y The LMF is expressed as Y The input of the positioning information acquisition model is obtained based on the LMF, and the positioning information of the UE is acquired through inference by using the positioning information acquisition model. Y The method of how to determine the positioning information and location information of the UE based on the above is similar to the corresponding description in Figure 6. The details will not be described again.

[0285] In the methods of FIG. 6 and FIG. 12, training data is collected, and the channel feature extraction model and the positioning information acquisition model are obtained through training by using the collected data. In the present disclosure, a reference data set and a reference model (including a reference channel feature extraction model and a reference positioning information acquisition model) may be further provided. The UE, the base station, and the LMF may perform inference by using the reference model to obtain the positioning information of the UE. Alternatively, the UE or the base station may perform update training on the reference channel feature extraction model by using an offline training or an online training method to obtain an updated channel feature extraction model, and / or the LMF may perform update training on the reference positioning information acquisition model by using an offline training or an online training method to obtain an updated positioning information acquisition model. The positioning information of the UE is obtained through inference by using the updated channel feature extraction model and the reference positioning information acquisition model, or by using the reference channel feature extraction model and the updated positioning information acquisition model, or by using the updated channel feature extraction model and the updated positioning information acquisition model.

[0286] 13 is a flowchart of a third positioning method according to the present disclosure. The method includes the following operations.

[0287] Action S1301: The UE and the LMF determine a first reference model.

[0288] The first reference model includes a first reference channel feature extraction model and a first reference positioning information acquisition model. The first reference model can be used by the UE and the LMF to determine the positioning information of the UE.

[0289] In the present disclosure, the first reference model may be determined by using any one of the following methods.

[0290] First Reference Model Determination Method 1:

[0291] The first reference model is agreed upon in the protocol. The first reference model may be considered to be agreed upon in the protocol after offline training. Optionally, the reference data set, the loss function, and the first threshold are agreed upon in the protocol.

[0292] For a detailed description of the reference dataset, the loss function, and the first threshold, see operation S1302 below.

[0293] First Reference Model Determination Method 2:

[0294] The AI ​​function network element obtains the first reference model through training by using the method described in operations S601, S602, and S603. The AI ​​function network element sends information about the first reference model to the UE and the LMF, or the AI ​​function network element sends information about the first reference model to the LMF, and the LMF sends information about the first reference model to the UE. Optionally, the AI ​​function network element further indicates at least one of the reference data set, the loss function, or the first threshold to the UE and the LMF. For example, the AI ​​function network element indicates the reference data set to the UE and the LMF, or the AI ​​function network element indicates the reference data set to the LMF, and the LMF indicates the first reference data set to the UE, and the loss function and the first threshold are agreed upon in the protocol. Other possible cases are not provided one by one.

[0295] First reference model determination method 3:

[0296] The UE determines a first reference model from the W reference models, where W is an integer equal to or greater than 1. The UE sends an index of the first reference model to the LMF, and the LMF determines the first reference model from the W reference models based on the index.

[0297] Optionally, the UE selects a first reference model from the W reference models based on the computing capability information of the UE. For a description of the computing capability information of the UE, please refer to the corresponding description of FIG. 6. For example, the W reference models have different structural complexities, and a more complex structure requires higher computing capability. The UE selects a first reference model from the W reference models based on the computing capability of the UE, which does not require higher computing capability than the computing capability of the UE.

[0298] Optionally, each of the reference models (denoted as reference model A) among the W reference models corresponds to a group of parameter configurations, the group of parameter configurations including at least one of a transmit antenna port amount corresponding to a channel response, a receive antenna port amount corresponding to a channel response, a bandwidth corresponding to the channel response, or an OFDM symbol amount corresponding to the channel response. The channel response is used to determine an input of a channel feature extraction model of reference model A. As shown in some examples of Tables 1 to 5, there is at least one different parameter configuration in two groups of parameter configurations corresponding to two different reference models. These examples do not constitute a limitation to the present disclosure. The UE selects an appropriate first reference model from the W reference models based on the UE's parameter configuration (e.g., transmit antenna port amount, receive antenna port amount, bandwidth capability, and / or maximum amount of processed time-domain OFDM symbols), or the UE selects an appropriate first reference model from the W reference models based on the UE's measurement configuration (e.g., measurement antenna port amount, measurement bandwidth, and / or measurement time-domain OFDM symbol amount). [Table 1] [Table 2] [Table 3] [Table 4] [Table 5]

[0299] Optionally, each of the reference models (denoted as reference model A) among the W reference models corresponds to a group of application scenarios, where the group of application scenarios includes at least one of the following scenarios: eMBB, URLLC, mMTC, D2D, V2X, MTC, IoT, virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, intelligent transportation, smart city, etc. As shown in Table 6, there is at least one different application scenario in the group of application scenarios corresponding to each of the reference models. The UE selects a first reference model from the W reference models based on the application scenario of the UE. [Table 6]

[0300] Optionally, each of the reference models (denoted as reference model A) among the W reference models corresponds to a group of application environments, where the group of application environments includes at least one of the following environments: factory environment, office environment, high-speed rail environment, subway environment, etc. As shown in Table 7, there is at least one different application environment in the group of application environments corresponding to each of the reference models. The UE selects a first reference model from the W reference models based on the environment in which the UE is located. [Table 7]

[0301] Optionally, the W reference models may be agreed upon in the protocol. Optionally, a reference dataset, a loss function, and a first threshold corresponding to each of the reference models are further agreed upon in the protocol. Optionally, the W reference models correspond to the same loss function and / or the same first threshold.

[0302] Optionally, the W reference models may be indicated by the AI ​​capability network element to the UE and the LMF. The indication method is similar to the corresponding description of the first reference model determination method 2. Optionally, the AI ​​capability network element further indicates at least one of a reference data set, a loss function, or a first threshold value corresponding to each of the reference models to the UE and the LMF. Optionally, the loss function and / or the first threshold value corresponding to each of the reference models are agreed upon in a protocol. Optionally, the W reference models correspond to the same loss function and / or the same first threshold value.

[0303] Optionally, in an operation S1302, the UE performs model updating training based on the first reference model and the first reference dataset to obtain an updated channel feature extraction model.

[0304] The first reference data set includes a plurality of training data and a label corresponding to each of the training data. For the description of the training data and the label, please refer to the corresponding description in FIG. 6. The UE obtains an updated channel feature extraction model through training by using the model training method described in operation S603. In operation S603, training data is collected from the UE and / or the LMF, and during the training process, parameters of both the channel feature extraction model and the positioning information acquisition model can be updated. In operation S1302, as shown in FIG. 14A, the training data is provided by a reference data set, and during the training process, parameters of the channel feature extraction model can be updated, where the initial model of the channel feature extraction model is the first reference channel feature extraction model, but the parameters of the positioning information acquisition model are not updated, in other words, the positioning information acquisition model is the first reference positioning information acquisition model. During the training process, iterative training is performed on the first reference channel feature extraction model by using the training data in the reference data set to obtain an updated channel feature extraction model. The purpose of the training is to determine the input of the updated channel feature extraction model by using training data in the reference dataset, and ensure that when the updated channel feature extraction model and the first reference positioning information acquisition model are used in a consistent manner, the loss function between the output of the first reference positioning information acquisition model and the label of the training data is smaller than a first threshold or less than or equal to a first threshold.

[0305] Optionally, in operation S1303: the LMF performs model update training based on the first reference model and the first reference dataset to obtain an updated positioning information acquisition model.

[0306] The first reference data set includes a plurality of training data and a label corresponding to each of the training data. For the description of the training data and the label, please refer to the corresponding description in FIG. 6. The LMF obtains an updated positioning information acquisition model through training by using the model training method described in operation S603. In operation S603, training data is collected from the UE and / or the LMF, and during the training process, parameters of both the channel feature extraction model and the positioning information acquisition model can be updated. In operation S1303, as shown in FIG. 14B, the training data is provided by a reference data set, and during the training process, parameters of the channel feature extraction model are not updated, in other words, the channel feature extraction model is a first reference channel feature extraction model, but the positioning information acquisition model can be updated, where the initial model of the positioning information acquisition model is the first reference positioning information acquisition model. During the training process, iterative training is performed on the first reference positioning information acquisition model by using the training data in the reference data set to obtain an updated positioning information acquisition model. The purpose of the training is to determine the input of the first reference channel feature extraction model by using training data in the reference dataset, and ensure that when the first reference channel feature extraction model and the updated positioning information acquisition model are used in a consistent manner, the loss function between the output of the updated positioning information acquisition model and the label of the training data is smaller than a first threshold or less than or equal to a first threshold.

[0307] Optionally, when there are W reference models, the LMF may first determine a first reference model, and then train a channel feature extraction model based on the first reference model. Alternatively, the LMF may obtain a corresponding channel feature extraction model in advance through training based on each of the reference models in the W reference models. When the first reference model is determined, a channel feature extraction model trained based on the first reference model may be obtained.

[0308] Operation S1304: The UE extracts channel features by using the channel feature extraction model. Operation S1305: The UE sends the channel features to the LMF.

[0309] In this operation, if S1302 is not performed, the channel feature extraction model is the first reference channel feature extraction model, or if S1302 is performed, the channel feature extraction model is the updated channel feature extraction model.

[0310] Optionally, when there are W reference models, the UE may first determine a first reference model, and then train a channel feature extraction model based on the first reference model. Alternatively, the UE may obtain a corresponding channel feature extraction model in advance through training based on each of the reference models in the W reference models. When the first reference model is determined, a channel feature extraction model trained based on the first reference model may be obtained.

[0311] The specific implementation of S1304 and S1305 is similar to the corresponding description in Figure 6. The details will not be described again in this specification.

[0312] Action S1306: The LMF determines the positioning information of the UE by using the positioning information acquisition model.

[0313] In this operation, when S1303 is not performed, the positioning information acquisition model is the first reference positioning information acquisition model, or when S1303 is performed, the positioning information acquisition model is the updated positioning information acquisition model. The specific implementation of S1306 is the same as the corresponding description in Fig. 6. The details are not described again in this specification.

[0314] 15 is a flowchart of a fourth positioning method according to the present disclosure. The method includes the following operations.

[0315] Action S1501: The base station and the LMF determine a first reference model.

[0316] The first reference model includes a first reference channel feature extraction model and a first reference positioning information acquisition model, and is used by the base station and the LMF to determine the positioning information of the UE.

[0317] The base station and the LMF may determine the first reference model by using any one of the following methods.

[0318] First Reference Model Determination Method 1: Same as the corresponding explanation in FIG.

[0319] First reference model determination method 2: Similar to the corresponding description in FIG. 13, the UE is replaced with the base station.

[0320] First Reference Model Determination Method 3:

[0321] The base station determines a first reference model from the W reference models, where W is an integer greater than 1. The base station sends an index of the first reference model to the LMF, and the LMF determines the first reference model from the W reference models based on the index.

[0322] Optionally, the base station selects a first reference model from the W reference models based on the computing capability information of the base station. For a description of the computing capability information of the base station, please refer to the corresponding description of FIG. 12. For example, the W reference models have different structural complexities, and a more complex structure requires higher computing capability. The base station selects a first reference model from the W reference models based on the computing capability of the base station, which does not require higher computing capability than the computing capability of the base station.

[0323] Optionally, each of the reference models (denoted as reference model A) among the W reference models corresponds to a group of parameter configurations, the group of parameter configurations including at least one of a transmit antenna port amount corresponding to a channel response, a receive antenna port amount corresponding to a channel response, a bandwidth corresponding to a channel response, or an OFDM symbol amount corresponding to a channel response. The channel response is used to determine an input of a channel feature extraction model of reference model A. As shown in some examples of Tables 1 to 5, there is at least one different parameter configuration in the group of parameter configurations corresponding to each of the reference models. The base station selects a suitable first reference model from the W reference models based on the base station's parameter configuration (e.g., a transmit antenna port amount, a receive antenna port amount, a bandwidth capability, and / or a maximum amount of processed time-domain OFDM symbols), or the base station selects a suitable first reference model from the W reference models based on the base station's measurement information (e.g., a measured antenna port amount, a measured bandwidth, and / or an amount of measured time-domain OFDM symbols).

[0324] Optionally, each of the reference models (denoted as reference model A) among the W reference models corresponds to a group of application scenarios of the UE. For a description of the application scenarios, please refer to the corresponding description in FIG. 13. As shown in Table 6, there is at least one different application scenario in the group of application scenarios corresponding to each of the reference models. The base station selects a first reference model from the W reference models based on the application scenario of the UE. Optionally, the application scenario of the UE learned by the base station is determined, for example, based on the service type of the UE, or reported by the UE to the base station. This is not limited.

[0325] Optionally, each of the reference models (denoted as reference model A) among the W reference models corresponds to a group of application environments. For a description of the application scenario, please refer to the corresponding description of FIG. 13. As shown in Table 7, there is at least one different application environment among the group of application environments corresponding to each of the reference models. The base station selects a first reference model from the W reference models based on the environment in which the UE is located. Optionally, the environment in which the UE is located, which is learned by the base station, is obtained through estimation based on measurement information corresponding to the UE, for example, or is reported by the UE to the base station. This is not limited.

[0326] Optionally, the W reference models may be agreed upon in the protocol. Optionally, a reference dataset, a loss function, and a first threshold corresponding to each of the reference models are further agreed upon in the protocol. Optionally, the W reference models correspond to the same loss function and / or the same first threshold.

[0327] Optionally, the W reference models may be indicated by the AI-capable network element to the base station and the LMF. The indication method is similar to the corresponding description of the first reference model determination method 2. Optionally, the AI-capable network element further indicates at least one of a reference data set, a loss function, or a first threshold value corresponding to each of the reference models to the base station and the LMF. Optionally, the loss function and / or the first threshold value corresponding to each of the reference models are agreed upon in a protocol. Optionally, the W reference models correspond to the same loss function and / or the same first threshold value.

[0328] Optionally, Operation S1502: The base station performs model updating training based on the first reference model and the first reference dataset to obtain an updated channel feature extraction model.

[0329] The first reference data set includes a plurality of training data and a label corresponding to each of the training data. For the description of the training data and the label, please refer to the corresponding description of FIG. 12. As shown in FIG. 14A, the base station obtains an updated channel feature extraction model through training by using the model training method described in operation S1203. The difference between operation S1502 and S1203 is similar to the difference between operation S1302 and S603. The details are not described again in this specification.

[0330] Optionally, in operation S1503, the LMF performs model updating training based on the first reference model and the first reference dataset to obtain an updated channel feature extraction model.

[0331] The first reference data set includes a plurality of training data and a label corresponding to each of the training data. For the description of the training data and the label, please refer to the corresponding description of FIG. 12. As shown in FIG. 14B, the LMF obtains an updated channel feature extraction model through training by using the model training method described in operation S1203. The difference between operation S1503 and S1203 is similar to the difference between operation S1303 and S603. The details are not described again in this specification.

[0332] Operation S1504: The base station extracts a channel feature by using the channel feature extraction model. Operation S1505: The base station sends the channel feature to the LMF.

[0333] In this operation, if S1502 is not performed, the channel feature extraction model is the first reference channel feature extraction model, or if S1502 is performed, the channel feature extraction model is the updated channel feature extraction model.

[0334] The specific implementation of S1304 and S1305 is similar to the corresponding description in Figure 12. The details will not be described again in this specification.

[0335] Action S1506: The LMF determines the positioning information of the UE by using the positioning information acquisition model.

[0336] In this operation, when S1503 is not performed, the positioning information acquisition model is the first reference positioning information acquisition model, or when S1503 is performed, the positioning information acquisition model is the updated positioning information acquisition model. The specific implementation of S1506 is the same as the corresponding description in Fig. 12. The details are not described again in this specification.

[0337] It can be understood that in order to implement the functions in the above method, the base station, the UE, the LMF, and the AI ​​function network element include corresponding hardware structures and / or software modules for implementing the functions. Those skilled in the art will easily recognize that the present application can be implemented by hardware or a combination of hardware and computer software with reference to the units and method steps in the examples described in the present application. Whether the functions are performed by hardware or by hardware driven by computer software depends on the specific application scenario and the design constraints of the technical solution.

[0338] 16 and 17 are schematic diagrams of possible communication device structures according to the present disclosure. These communication devices can be configured to implement the functions of the base station, UE, LMF, and AI function network element in the above method, and thus can also implement the beneficial effects of the above method.

[0339] As shown in Figure 16, the communication device 900 includes a processing unit 910 and a transceiver unit 920. The communication device 900 is configured to implement the method shown in Figure 6, Figure 12, Figure 13, or Figure 15.

[0340] When the communication device 900 is configured to implement the functionality of the UE in the method shown in FIG. 6 or FIG. 13, the transceiver unit 920 is configured to send X channel features to the LMF, and the processing unit 910 is configured to obtain the X channel features based on the Y channel responses and the channel feature extraction model, where X and Y are integers equal to or greater than 1. The X channel features correspond to the Y channels between the UE and the P base stations, and the Y channel responses are in one-to-one correspondence with the Y channels.

[0341] 12 or 15, the transceiver unit 920 is configured to send E channel features to the LMF, where E is an integer equal to or greater than 1, and the processing unit 910 is configured to obtain channel features corresponding to the channel responses based on each of the E channel responses and the channel feature extraction model. The E channel features correspond to the E channels between the UE and the base station.

[0342] When the communication apparatus 900 is configured to implement the functionality of the LMF in the method shown in FIG. 6 , FIG. 12 , FIG. 13 , or FIG. 15 , the transceiver unit 920 is configured to receive X channel features, where the X channel features correspond to Y channels between the UE and the P base stations, where X and Y are integers greater than or equal to 1, and the processing unit 910 is configured to acquire positioning information of the UE based on the X channel features and the positioning information acquisition model.

[0343] When the communication device 900 is configured to implement the functionality of the AI ​​function network element in the method shown in FIG. 6, FIG. 12, FIG. 13, or FIG. 15, the transceiver unit 920 is configured to receive training data, and the processing unit 910 is configured to obtain a channel feature extraction model and a positioning information acquisition model through training based on the training data.

[0344] For a more detailed description of the processing unit 910 and the transceiver unit 920, please refer to the relevant description in the method shown in Figure 6, Figure 12, Figure 13, or Figure 15 to directly obtain the description. The details will not be described again in this specification.

[0345] As shown in Fig. 17, the communication device 1000 includes a processor 1010 and an interface circuit 1020. The processor 1010 and the interface circuit 1020 are coupled to each other. It may be understood that the interface circuit 1020 may be a transceiver, a pin, or an input / output interface. Optionally, the communication device 1000 may further include a memory 1030 configured to store at least one of instructions executed by the processor 1010, input data required by the processor 1010 to execute the instructions, or data generated after the processor 1010 executes the instructions.

[0346] When the communications device 1000 is configured to implement the aforementioned method, the processor 1010 is configured to implement the functions of the processing unit 910 described above, and the interface circuit 1020 is configured to implement the functions of the transceiver unit 920 described above.

[0347] When the communication device is a chip used in a UE, the UE chip implements the functions of the UE in the aforementioned method. The UE chip receives information from another module (e.g., a radio frequency module or an antenna) in the UE, where the information is sent to the UE by a base station, an LMF, an AI-functional network element, etc. Alternatively, the UE chip sends information to another module (e.g., a radio frequency module or an antenna) in the UE, where the information is sent by the UE to a base station, an LMF, an AI-functional network element, etc.

[0348] When the communication device is a module used in a base station, the base station module implements the functions of the base station in the aforementioned method. The base station module receives information from another module (e.g., a radio frequency module or an antenna) in the base station, where the information is sent by the UE, the LMF, or the AI-functional network element to the base station. Alternatively, the base station module sends information to another module (e.g., a radio frequency module or an antenna) in the base station, where the information is sent by the base station to the UE, the LMF, the AI-functional network element, etc. The base station module in this specification may be a baseband chip in the base station, or may be a quasi-real-time RIC, CU, DU, or another module. The quasi-real-time RIC, CU, and DU in this specification may be the quasi-real-time RIC, CU, and DU in the O-RAN architecture.

[0349] When the communication device is used in the LMF module, the LMF module implements the functionality of the LMF in the above-mentioned method. The LMF module receives information from another module in the LMF (e.g., a radio frequency module or an antenna), where the information is sent by the UE, the base station, or an AI-capable network element to the base station. Alternatively, the LMF module sends information to another module in the LMF (e.g., a radio frequency module or an antenna), where the information is sent by the LMF to the UE, the base station, the AI-capable network element, etc.

[0350] In this application, a processor may be a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or another programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component that may implement or perform the methods, steps, and logic block diagrams in this disclosure. A general purpose processor may be a microprocessor, any conventional processor, etc. The steps of the methods in this disclosure may be performed directly by a hardware processor, or may be performed by a combination of hardware and software modules in a processor.

[0351] In this application, the memory may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), or a volatile memory, such as a random access memory (RAM). The memory is any other medium that can carry or store the expected program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. Alternatively, the memory in this application may be a circuit or any other device that can implement a storage function and is configured to store program instructions and / or data.

[0352] The method in this application may be fully or partially implemented by software, hardware, firmware, or any combination thereof. When software is used to implement the method, the method may be fully or partially implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the process or function in this application is fully or partially performed. The computer may be a general-purpose computer, a special-purpose computer, a computer network, an access network device, a terminal device, a core network device, an AI function network element, or another programmable device. The computer program or instructions may be stored in a computer-readable storage medium or transmitted from a computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless manner. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device that integrates one or more available media, such as a server or a data center. The available medium may be a magnetic medium, such as a floppy disk, a hard disk drive, or a magnetic tape, or an optical medium, such as a digital video disk, or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile storage media.

[0353] The above description is merely a specific implementation of the present invention, and is not intended to limit the protection scope of the present invention. Any modifications or replacements that are easily conceived by those skilled in the art within the technical scope disclosed in the present invention shall fall within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. 1. A communication method comprising: sending X channel characteristics to a Location Management Function LMF; 1. A communication method, comprising: the X channel features corresponding to Y channels of a terminal device; the X channel features being obtained by using a channel feature extraction model, an input of the channel feature extraction model being determined based on Y channel responses, the Y channel responses being in one-to-one correspondence with the Y channels, and X and Y being integers equal to or greater than 1.

2. The method of claim 1 , wherein X is less than or equal to Y and / or the total dimensionality of the X channel features is less than the total dimensionality of the Y channel responses.

3. The method of claim 1 or 2, wherein the X channel features are used to determine an input of a positioning information acquisition model, the output of which comprises positioning information of the terminal device.

4. the positioning information indicating location information of the terminal device; or The positioning information indicates at least one of the following for the Y channels: a channel type, a first path location, or a relative azimuth angle of the terminal device. The method according to claim 3.

5. 1. A communication method comprising: sending E channel features to a Location Management Function LMF, where E is an integer greater than or equal to 1; 1. A method for communications, comprising: the E channel features corresponding to E channels between a terminal device and an access network device; and each of the E channel features being obtained by using a channel feature extraction model, an input of the channel feature extraction model being determined based on a channel response, the channel response corresponding to a channel corresponding to the channel features.

6. The method of claim 5 , wherein the dimension of the channel characteristics is smaller than the dimension of the channel response.

7. The method according to claim 5 or 6, wherein the E channel features are used to determine an input of a positioning information acquisition model, the output of which comprises positioning information of the terminal device.

8. the positioning information indicating location information of the terminal device; or The positioning information indicates at least one of the following for the E channels: a channel type, a first path location, or a relative azimuth angle of the terminal device. The method according to claim 7.

9. The method of claim 4 or 8, wherein at least one of the channel type, the first path location, or the relative azimuth angle of the terminal device is used to determine the location information of the terminal device.

10. The method comprises: receiving information regarding the channel feature extraction model; The method of any one of claims 1 to 9, further comprising:

11. The method comprises: The method further includes determining the channel feature extraction model based on a first reference model, the first reference model including a first reference channel feature extraction model and a first reference positioning information acquisition model.

11. The method according to any one of claims 1 to 10.

12. The method of claim 11 , wherein when the channel feature extraction model and the first reference positioning information acquisition model are used in a consistent manner, a value of the loss function is less than or equal to a first threshold value.

13. 1. A communication method comprising: receiving X channel characteristics, the X channel characteristics corresponding to Y channels of a terminal device, where X and Y are positive integers greater than or equal to 1; acquiring positioning information of the terminal device based on the X channel characteristics and a positioning information acquisition model; A communication method comprising:

14. The method of claim 13 , wherein X is less than or equal to Y and / or the total dimensionality of the X channel features is less than the total dimensionality of the Y channel responses.

15. the positioning information indicating location information of the terminal device; or The positioning information indicates at least one of the following for the Y channels: a channel type, a first path location, or a relative azimuth angle of the terminal device.

15. The method according to claim 13 or 14.

16. determining the location information of the terminal device based on at least one of the channel type, the first path location, or the relative azimuth angle of the terminal device; 16. The method of claim 15 further comprising:

17. The method comprises: receiving information regarding the positioning information acquisition model; 17. The method of any one of claims 13 to 16, further comprising:

18. The method comprises: The method further includes determining the positioning information acquisition model based on a first reference model, the first reference model including a first reference channel feature extraction model and a first reference positioning information acquisition model.

17. The method according to any one of claims 13 to 16.

19. 20. The method of claim 18, wherein when the positioning information acquisition model and the first reference channel feature extraction model are used in a consistent manner, a value of the loss function is less than or equal to a first threshold.

20. The method comprises: sending information about a channel feature extraction model, the output of the channel feature extraction model including the channel features; 20. The method of any one of claims 13 to 19.

21. 1. A communication method comprising: receiving a training data set, each of the training data in the training data set indicating Y channel responses and Y pieces of positioning information of Y channels of a terminal device, the Y channel responses being in one-to-one correspondence with the Y pieces of positioning information; obtaining a channel feature extraction model and a positioning information acquisition model through training based on the training data set, an input of the channel feature extraction model being determined based on at least one of the Y channel responses, and an input of the positioning information acquisition model being determined based on an output of the channel feature extraction model; A communication method comprising:

22. A communication device configured to implement a method according to any one of claims 1 to 12.

23. A communications device comprising a processor and a memory, the processor coupled to the memory, the processor configured to implement a method according to any one of claims 1 to 12.

24. A communication device configured to implement a method according to any one of claims 13 to 20.

25. A communications device comprising a processor and a memory, the processor coupled to the memory, the processor configured to implement a method according to any one of claims 13 to 20.

26. A communications device configured to implement the method of claim 21.

27. A communication device according to claim 22 or 23 and a communication device according to claim 24 or 25, A communication device according to claim 22 or 23 and a communication device according to claim 26, Comprising a communication device according to claim 24 or 25 and a communication device according to claim 26, or The communication device according to claim 22 or 23, the communication device according to claim 24 or 25, and the communication device according to claim 26, Communication systems.

28. A computer readable storage medium having instructions stored thereon that, when run on a computer, enable the computer to perform a method according to any one of claims 1 to 12, or any one of claims 13 to 20, or the method according to claim 21.

29. A computer program product comprising instructions, which when run on a computer, enable the computer to carry out the method according to any one of claims 1 to 12, or the method according to any one of claims 13 to 20, or the method according to claim 21.

Images