WO2023160656A1 - 一种通信方法及装置 - Google Patents

一种通信方法及装置 Download PDF

Info

Publication number
WO2023160656A1
WO2023160656A1 PCT/CN2023/078190 CN2023078190W WO2023160656A1 WO 2023160656 A1 WO2023160656 A1 WO 2023160656A1 CN 2023078190 W CN2023078190 W CN 2023078190W WO 2023160656 A1 WO2023160656 A1 WO 2023160656A1
Authority
WO
WIPO (PCT)
Prior art keywords
channel estimation
estimation information
terminal device
cell node
channel
Prior art date
Application number
PCT/CN2023/078190
Other languages
English (en)
French (fr)
Inventor
孙雅琪
吴艺群
孙琰
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2023160656A1 publication Critical patent/WO2023160656A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00—Baseband systems
    • H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00—Baseband systems
    • H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
    • H04L25/0202—Channel estimation
    • H04L25/0204—Channel estimation of multiple channels
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Definitions

  • the present disclosure relates to the field of communication technologies, and in particular, to a communication method and device.
  • a wireless communication network such as a mobile communication network
  • services supported by the network are becoming more and more diverse, and therefore requirements to be met are also becoming more and more diverse.
  • the network needs to be able to support ultra-high rates, ultra-low delays, and/or ultra-large connections, which make network planning, network configuration, and/or resource scheduling more and more complicated.
  • the functions of the network become more and more powerful, such as supporting higher and higher spectrum, supporting high-order multiple input multiple output (MIMO) technology, supporting beamforming, and/or supporting new technologies such as beam management, etc. technology, making network energy saving a hot research topic.
  • MIMO multiple input multiple output
  • beamforming supporting beamforming
  • new technologies such as beam management, etc. technology
  • the present disclosure provides a communication method and device in order to improve positioning performance.
  • the present disclosure provides a communication method, including:
  • M pieces of first channel estimation information where the m-th piece of first channel estimation information among the M pieces of first channel estimation information is the channel estimation information between the m-th cell node and the terminal device among the M cell nodes;
  • M is a positive integer greater than 1
  • m is a positive integer ranging from 1 to M;
  • M pieces of second channel estimation information are determined according to at least one piece of first channel estimation information among the M pieces of first channel estimation information,
  • the m-th second channel estimation information among the M pieces of second channel estimation information corresponds to the channel between the m-th cell node and the terminal device.
  • the second channel estimation information is derived based on the first channel estimation information measured by the terminal device or the cell node.
  • the second channel estimation information can be used to train a positioning-related model. This training method is more suitable for the actual scene environment and can improve the performance of the model, thereby improving the positioning accuracy.
  • the second channel estimation information is used to indicate at least one of the following: under the condition of line of sight (LOS), the distance between the mth cell node and the terminal device; under the condition of LOS , the signal transmission delay or signal transmission delay difference between the mth cell node and the terminal device; under the LOS condition, the signal departure angle (angle of departure, AoD) or signal angle of arrival (angle of arrival, AoA); under LOS conditions, the signal quality between the mth cell node and the terminal device; or, the mth cell node and the terminal device A type of an actual signal transmission path between devices, where the path type is LOS or a non-line of sight (NLOS).
  • LOS line of sight
  • NLOS non-line of sight
  • the second channel estimation information is used for model training; wherein, when performing the model training, the input of the model is based on the relationship between the mth cell node and the terminal device
  • the label corresponding to the input is determined according to the second channel estimation information corresponding to the channel between the mth cell node and the terminal device.
  • the label data that can be used for model training is derived, which helps to improve the performance of the model.
  • the method further includes: sending K pieces of second channel estimation information to the first device, where the K pieces of second channel estimation information are included in the M pieces of second channel estimation information, and K is a positive integer.
  • the method further includes: acquiring training request information from the first device, where the training request information is used to request the K pieces of second channel estimation information.
  • the training request information is used to indicate a parameter type indicated by the second channel estimation information.
  • specifying the parameter type indicated by the second channel estimation information can reduce the waste of transmission resources caused by additional information, and can reduce signaling overhead.
  • the acquiring M pieces of first channel estimation information includes: acquiring the m-th first channel estimation information from a first device; wherein, the first device is the m-th A cell node, or the first device is the terminal device.
  • the determining M pieces of second channel estimation information according to at least one piece of first channel estimation information in the M pieces of first channel estimation information includes: according to the M pieces of first channel estimation information According to at least one piece of first channel estimation information in the information, determine the first position of the terminal device; determine the M pieces of second channel estimation information according to the first position of the terminal device and the positions of the M cell nodes .
  • determining the first position of the terminal device according to at least one piece of first channel estimation information in the M pieces of first channel estimation information includes:
  • a first part of the plurality of second positions is located in the first area, a second part of the plurality of second positions is not located in the first area, and the number of the first part of positions is greater than the The number of the second partial positions; and determining the first position of the terminal device according to the first partial position in the plurality of second positions.
  • the N pieces of first channel estimation information and the locations of the N cell nodes determine the first location of the terminal device; wherein, the N pieces of first channel estimation information are in one-to-one correspondence with the N cell nodes, and the N pieces of The cell nodes are included in the M cell nodes, and N is a positive integer less than or equal to M.
  • a path between each cell node in the N cell nodes and the terminal device is a direct path.
  • first estimate the credible location of the terminal device namely the first location
  • second channel estimation information for training the model. help to improve the performance of the model.
  • the mth first channel estimation information is used to indicate one or more of the following parameters: the distance between the mth cell node and the terminal device; the distance between the mth cell node and the terminal device; The signal transmission delay or signal transmission delay difference between the m cell node and the terminal device; the signal departure angle or signal arrival angle corresponding to the m th cell node; the m th cell node and the Signal quality between terminal devices; the m-th first channel estimation information is used to indicate that the signal transmission path between the m-th cell node and the terminal device is a direct path or a non-direct path.
  • the M cell nodes belong to one access network device, or at least two of the M cell nodes belong to different access network devices.
  • the present disclosure provides a communication method, including:
  • the m-th first channel estimation information belongs to M first channel estimation information, M is a positive integer greater than 1, m is a positive integer ranging from 1 to M, and the The m-th first channel estimation information among the M pieces of first channel estimation information is the channel estimation information between the m-th cell node and the terminal device among the M cell nodes; wherein, the M first channel estimation information At least one piece of first channel estimation information among the M pieces of second channel estimation information is used to determine M pieces of second channel estimation information, and the m-th second channel estimation information in the M pieces of second channel estimation information corresponds to the m-th cell node and the terminal channels between devices;
  • Acquiring information for indicating a model wherein, when training the model, the input of the model is determined according to the channel information of the channel between the mth cell node and the terminal device, and the input corresponds to The label of is determined according to the second channel estimation information corresponding to the channel between the mth cell node and the terminal device.
  • the method further includes: sending channel information of the channel between the mth cell node and the terminal device.
  • the present disclosure provides a communication method, including:
  • the kth channel information in the K pieces of channel information is the channel information of the channel between the kth cell node and the terminal device among the K cell nodes; where K is a positive integer, k is a positive integer ranging from 1 to K;
  • the Kth second channel estimation information of the K pieces of second channel estimation information corresponds to the channel between the kth cell node and the terminal device
  • the Kth second channel estimation information corresponds to the channel between the kth cell node and the terminal device
  • the Kth The second channel estimation information is determined by at least one piece of first channel estimation information in the M pieces of first channel estimation information, wherein the m-th first channel estimation information in the M pieces of first channel estimation information is the first channel estimation information in the M cells.
  • Estimation information of channels between m cell nodes and the terminal device, the K cells are included in the M cells, M is a positive integer greater than 1, and m is a positive integer from 1 to M;
  • the method further includes: sending training request information, where the training request information is used to request the K pieces of second channel estimation information.
  • the training request information is used to indicate a parameter type indicated by the second channel estimation information.
  • the method further includes: sending first channel estimation information of the channel between the mth cell node and the terminal device.
  • the present disclosure provides a communication method, including:
  • the tth channel information is the tth cell node among the T cell nodes and Channel information of a channel between terminal devices; wherein, T is a positive integer greater than 1, and t is a positive integer ranging from 1 to T;
  • the t-th channel information and the model determine the t-th third channel estimation information, and the t-th third channel estimation information corresponds to the channel between the t-th cell node and the terminal device; wherein , the input of the model is determined according to the channel information of the channel between the tth cell node and the terminal device, and the output corresponding to the input includes the tth third channel estimation information;
  • the t-th third channel estimation information is used for positioning the terminal device.
  • the values of T and the above M may be the same or different, without limitation.
  • the tth third channel estimation information is used to indicate one or more of the following parameters: the LOS length distance between the tth cell node and the terminal device; the The signal transmission delay or channel transmission delay difference between the tth cell node and the terminal device conforming to LOS transmission; the signal departure angle or signal arrival angle corresponding to the tth cell node conforming to LOS transmission; the said The signal quality of LOS transmission between the tth cell node and the terminal device; the type of the actual signal transmission path between the tth cell node and the terminal device; or, the tth cell node A type of an actual signal transmission path with the terminal device, where the type is LOS or NLOS.
  • the input of the model is determined according to the channel information of the channel between the mth cell node and the terminal device among the M cell nodes, the The label corresponding to the input is determined according to the second channel estimation information corresponding to the channel between the mth cell node and the terminal device.
  • the second channel estimation information corresponding to the channel between the mth cell node and the terminal device is determined by at least one piece of first channel estimation information in the M pieces of first channel estimation information, and the M pieces of first channel estimation information
  • the m-th first channel estimation information in the piece of channel estimation information is estimation information of a channel between the m-th cell node and the terminal device among the M cell nodes.
  • the present disclosure provides a communication device.
  • the communication device may be a location management function (location management function, LMF) network element, hereinafter referred to as LMF; it may also be a device in the LMF, or it may be used in conjunction with the LMF installation.
  • LMF location management function
  • the communication device may include a one-to-one corresponding module for executing the method/operation/step/action described in the first aspect.
  • the module may be a hardware circuit, or software, or a combination of hardware circuit and software. accomplish.
  • the communication device may include a processing module and a communication module.
  • a communication module configured to acquire M pieces of first channel estimation information, where the m-th piece of first channel estimation information among the M pieces of first channel estimation information is between the m-th cell node among the M cell nodes and the terminal device Channel estimation information; wherein, M is a positive integer greater than 1, and m is a positive integer ranging from 1 to M;
  • a processing module configured to determine M pieces of second channel estimation information according to at least one piece of first channel estimation information in the M pieces of first channel estimation information, and the m-th second channel estimation information in the M pieces of second channel estimation information
  • the channel estimation information corresponds to the channel between the mth cell node and the terminal device.
  • the communication module is further configured to send K pieces of second channel estimation information to the first device, where the K pieces of second channel estimation information are included in the M pieces of second channel estimation information, and K is positive integer.
  • the communication module is further configured to acquire training request information from the first device, where the training request information is used to request the K pieces of second channel estimation information.
  • the training request information is used to indicate a parameter type indicated by the second channel estimation information.
  • the communication module is further configured to acquire the m-th first channel estimation information from the first device; wherein the first device is the m-th cell node, or the m-th A device is the terminal device.
  • the processing module is specifically configured to: determine the first location of the terminal device according to at least one piece of first channel estimation information in the M pieces of first channel estimation information; The first location of the terminal device and the locations of the M cell nodes determine the M pieces of second channel estimation information.
  • the present disclosure provides a communication device.
  • the communication device may be a terminal device or an mth cell node, or a device in a terminal device or an mth cell node, or it may be used in conjunction with a terminal device device, or a device that can be used in conjunction with the mth cell node.
  • the communication device may include a one-to-one corresponding module for executing the method/operation/step/action described in the second aspect.
  • the module may be a hardware circuit, or software, or a combination of hardware circuit and software.
  • the communication device may include a processing module and a communication module.
  • a processing module configured to send the m-th first channel estimation information through the communication module, the m-th first channel estimation information belongs to M pieces of first channel estimation information, M is a positive integer greater than 1, and m is 1 A positive integer to M, the m-th first channel estimation information among the M pieces of first channel estimation information is the channel estimation information between the m-th cell node and the terminal device among the M cell nodes; wherein, the At least one piece of first channel estimation information among the M pieces of first channel estimation information is used to determine M pieces of second channel estimation information, and the m-th second channel estimation information among the M pieces of second channel estimation information corresponds to the first Channels between m cell nodes and the terminal equipment;
  • a communication module configured to obtain information indicating a model; wherein, when performing training of the model, the input of the model is determined according to channel information of a channel between the mth cell node and the terminal device , the label corresponding to the input is determined according to the second channel estimation information corresponding to the channel between the mth cell node and the terminal device.
  • the processing module is further configured to send the channel information of the channel between the mth cell node and the terminal device through the communication module.
  • the present disclosure provides a communication device, which may be a model training node, such as a terminal device, an mth cell node, or an artificial intelligence (AI) network element, or may be a model training node device, or a device that can be used in conjunction with the model training node.
  • the communication device may include a one-to-one corresponding module for executing the method/operation/step/action described in the third aspect, and the module may be a hardware circuit, or software, or a combination of hardware circuit and software accomplish.
  • the communication device may include a processing module and a communication module.
  • a processing module configured to determine K pieces of channel information, wherein the k-th channel information in the K pieces of channel information is the channel information of the channel between the k-th cell node and the terminal device among the K cell nodes; wherein, K is a positive integer, and k is a positive integer ranging from 1 to K;
  • a communication module configured to acquire K pieces of second channel estimation information, where the kth second channel estimation information among the K pieces of second channel estimation information corresponds to the channel between the kth cell node and the terminal device,
  • the K pieces of second channel estimation information are determined by at least one piece of first channel estimation information in the M pieces of first channel estimation information, where the m-th piece of first channel estimation information in the M pieces of first channel estimation information is Estimated information of the channel between the mth cell node in the M cells and the terminal device, the K cells are included in the M cells, M is a positive integer greater than 1, and m is taken from 1 to M positive integer;
  • the processing module is further configured to perform model training according to the K second channel estimation information; wherein, when performing the model training, the input of the model is based on the kth cell node and the terminal device The label corresponding to the input is determined according to the second channel estimation information corresponding to the channel between the kth cell node and the terminal device.
  • the communication module is further configured to send training request information, where the training request information is used to request the K pieces of second channel estimation information.
  • the training request information is used to indicate a parameter type indicated by the second channel estimation information.
  • the communication module is further configured to send first channel estimation information of a channel between the mth cell node and the terminal device.
  • the present disclosure provides a communication device, where the communication device may be a terminal device or a t-th cell node. It may also be a terminal device or a device in the tth cell node, or a device that can be matched with the terminal device or used with the tth cell node.
  • the communication device may include a one-to-one corresponding module for executing the method/operation/step/action described in the fourth aspect.
  • the module may be a hardware circuit, or software, or a combination of hardware circuit and software.
  • the communication device may include a processing module and a communication module.
  • a processing module configured to determine the t-th channel information, where the t-th channel information is the channel information of the channel between the t-th cell node and the terminal device among the T cell nodes; where T is greater than 1 A positive integer, m is a positive integer from 1 to T;
  • the processing module is further configured to determine the t-th third channel estimation information according to the t-th channel information and the model, and the t-th third channel estimation information corresponds to the t-th cell node and the terminal device The channel between; wherein, the input of the model is determined according to the channel information of the channel between the tth cell node and the terminal device, and the output corresponding to the input includes the tth third channel estimate information;
  • a communication module configured to send the t-th third channel estimation information, where the t-th third channel estimation information is used for positioning the terminal device.
  • the values of T and the above M may be the same or different, without limitation.
  • the communication module is further configured to obtain information indicating the model.
  • the present disclosure provides a communication device, where the communication device includes a processor, configured to implement the method described in the first aspect above.
  • the processor is coupled to the memory, and the memory is used to store instructions and data.
  • the communication device It can also include a memory; the communication device can also include a communication interface, which is used for the device to communicate with other devices.
  • the communication interface can be a transceiver, circuit, bus, module, pin or other type of communication interface.
  • the communication device includes:
  • a processor configured to use a communication interface to obtain M pieces of first channel estimation information, where the m-th piece of first channel estimation information among the M pieces of first channel estimation information is the connection between the m-th cell node and the terminal device among the M cell nodes
  • the present disclosure provides a communication device, where the communication device includes a processor, configured to implement the method described in any one of the second aspect to the fourth aspect.
  • the processor is coupled to the memory, and the memory is used to store instructions and data.
  • the communication device may also include a memory; the communication device may also include a communication interface, which is used for the device to communicate with other devices.
  • the communication interface may be a transceiver, a circuit, A bus, module, pin, or other type of communication interface.
  • the communication means includes:
  • a processor configured to use a communication interface to send the m-th first channel estimation information, where the m-th first channel estimation information belongs to M pieces of first channel estimation information, M is a positive integer greater than 1, and m is 1 A positive integer to M, the m-th first channel estimation information among the M pieces of first channel estimation information is the channel estimation information between the m-th cell node and the terminal device among the M cell nodes; wherein, the At least one piece of first channel estimation information among the M pieces of first channel estimation information is used to determine M pieces of second channel estimation information, and the m-th second channel estimation information among the M pieces of second channel estimation information corresponds to the first Channels between m cell nodes and the terminal equipment;
  • the communication interface uses the communication interface to obtain information for indicating the model; wherein, when performing the training of the model, the input of the model is determined according to the channel information of the channel between the mth cell node and the terminal device , the label corresponding to the input is determined according to the second channel estimation information corresponding to the channel between the mth cell node and the terminal device.
  • the communication means includes:
  • a processor configured to determine K pieces of channel information, wherein the k-th channel information among the K pieces of channel information is channel information of a channel between the k-th cell node and the terminal device among the K cell nodes; wherein, K is a positive integer, and k is a positive integer ranging from 1 to K;
  • the processor is further configured to use a communication interface to acquire K pieces of second channel estimation information, where the kth second channel estimation information among the K pieces of second channel estimation information corresponds to the relationship between the kth cell node and the terminal device channel between, the K pieces of second channel estimation information are determined by at least one piece of first channel estimation information among the M pieces of first channel estimation information, wherein the m-th piece of first channel estimation information among the M pieces of first channel estimation information
  • the channel estimation information is the channel estimation information between the mth cell node and the terminal device in the M cells, the K cells are included in the M cells, M is a positive integer greater than 1, and m is taken over A positive integer from 1 to M;
  • the processor is further configured to perform model training according to the K pieces of second channel estimation information; wherein, when performing the model training, the input of the model is based on the kth cell node and the terminal device The label corresponding to the input is determined according to the second channel estimation information corresponding to the channel between the kth cell node and the terminal device.
  • the communication means includes:
  • the t-th channel information is the channel information of the channel between the t-th cell node and the terminal device among the T cell nodes; where T is a positive integer greater than 1, and t is Take positive integers from 1 to T;
  • the t-th channel information and the model determine the t-th third channel estimation information, and the t-th third channel estimation information corresponds to the channel between the t-th cell node and the terminal device; wherein , the input of the model is determined according to the channel information of the channel between the tth cell node and the terminal device, and the output corresponding to the input includes the tth third channel estimation information;
  • the present disclosure provides a communication system, including the communication device as described in the fifth aspect or the ninth aspect; and as described in at least one of the sixth, seventh, and eighth aspects communication device;
  • it includes the communication device as described in the fifth aspect or the ninth aspect; and the communication device as described in the tenth aspect.
  • the present disclosure further provides a computer program, which, when the computer program is run on a computer, causes the computer to execute the method provided in any one of the first to fourth aspects above.
  • the present disclosure further provides a computer program product, including instructions, which, when run on a computer, cause the computer to execute the method provided in any one of the first to fourth aspects above.
  • the present disclosure also provides a computer-readable storage medium, where a computer program or instruction is stored in the computer-readable storage medium, and when the computer program or instruction is run on a computer, the computer Execute the method provided by any one of the first aspect to the fourth aspect above.
  • the present disclosure further provides a chip, the chip is used to read a computer program stored in a memory, and execute the method provided in any one of the first to fourth aspects above.
  • the present disclosure further provides a chip system, which includes a processor, configured to support a computer device to implement the method provided in any one of the above first to fourth aspects.
  • the chip system further includes a memory, and the memory is used to store necessary programs and data of the computer device.
  • the system-on-a-chip may consist of chips, or may include chips and other discrete devices.
  • FIG. 1A is one of the structural schematic diagrams of the communication system provided by the present disclosure.
  • FIG. 1B is one of the structural schematic diagrams of the communication system provided by the present disclosure.
  • FIG. 1C is one of the structural schematic diagrams of the communication system provided by the present disclosure.
  • Fig. 2 is a schematic diagram of the principle of a positioning method based on TDOA
  • FIG. 3 is a schematic diagram of a time-domain channel response
  • FIG. 4 is a schematic structural diagram of a signal transmission path
  • FIG. 5 is one of the structural schematic diagrams of the communication system provided by the present disclosure.
  • Figure 6A is a schematic diagram of a neuron structure
  • FIG. 6B is a schematic diagram of the layer relationship of the neural network
  • FIG. 7 is a schematic diagram of a model training framework provided by the present disclosure.
  • FIG. 8 is one of the schematic flowcharts of the communication method provided by the present disclosure.
  • Fig. 9 is a schematic diagram of position distribution
  • FIG. 10 is a schematic flowchart of a model-based positioning method provided by the present disclosure.
  • FIG. 11 is one of the schematic flowcharts of the communication method provided by the present disclosure.
  • FIG. 12 is one of the schematic flowcharts of the communication method provided by the present disclosure.
  • Fig. 13 is one of the structural schematic diagrams of the communication device provided by the present disclosure.
  • Fig. 14 is one of the structural schematic diagrams of the communication device provided by the present disclosure.
  • the present disclosure refers to at least one (item) as follows, indicating one (item) or more (items).
  • a plurality of (items) refers to two (items) or more than two (items).
  • "And/or" describes the association relationship of associated objects, indicating that there may be three types of relationships, for example, A and/or B may indicate: A exists alone, A and B exist simultaneously, and B exists independently.
  • the character "/" generally indicates that the contextual objects are an "or” relationship.
  • first, second, etc. may be used in the present disclosure to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another.
  • the communication system can be a third generation (3 th generation, 3G) communication system (such as a universal mobile telecommunications system (universal mobile telecommunications system, UMTS)), a fourth generation 4th generation (4G) communication systems (such as long term evolution (LTE) systems), 5th generation (5G) communication systems, worldwide interoperability for microwave access (WiMAX) ) or a wireless local area network (wireless local area network, WLAN) system, or a fusion system of multiple systems, or a future communication system, such as a sixth generation (6th generation, 6G) communication system, etc.
  • the 5G communication system may also be called a new radio (new radio, NR) system.
  • a network element in a communication system may send signals to another network element or receive signals from another network element.
  • the signal may include information, signaling, or data.
  • a network element may also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc., and the present disclosure takes a network element as an example for description.
  • the communication system may include at least one terminal device and at least one access network device, the access network device may send a downlink signal to the terminal device, and/or the terminal device may send an uplink signal to the access network device.
  • the multiple terminal devices can also send signals to each other, that is, both the signal sending network element and the signal receiving network element can be terminal devices.
  • the communication system 100 includes an access network device 110 , an access network device 120 , an access network device 130 and a terminal device 140 .
  • the terminal device 140 may send an uplink signal to one or more access network devices among the access network device 110 , the access network device 120 and the access network device 130 .
  • One or more access network devices among the access network device 110 , the access network device 120 and the access network device 130 may send a downlink signal to the terminal device 140 .
  • the terminal equipment and access network equipment involved in FIG. 1A will be described in detail below.
  • the access network device may be a base station (base station, BS).
  • the access network device may also be called a network device, an access node (access node, AN), or a wireless access node (radio access node, RAN).
  • the base station may have various forms, such as a macro base station, a micro base station, a relay station, or an access point.
  • the access network device can be connected to a core network (such as an LTE core network or a 5G core network, etc.), and the access network device can provide wireless access services for terminal devices.
  • a core network such as an LTE core network or a 5G core network, etc.
  • Access network equipment includes, but is not limited to, at least one of the following: base stations in 5G, such as transmission and reception points (Transmission Reception Point, TRP) or next-generation node B (generation nodeB, gNB), open radio access network (open radio access network, O-RAN) in the access network equipment or modules included in the access network equipment, evolved node B (evolved node B, eNB), radio network controller (radio network controller, RNC), node B (node B , NB), base station controller (base station controller, BSC), base transceiver station (base transceiver station, BTS), home base station (for example, home evolved nodeB, or home node B, HNB), base band unit (base band unit, BBU), sending and receiving point (transmitting and receiving point, TRP), transmitting point (transmitting point, TP), and/or mobile switching center, etc.
  • base stations in 5G such as transmission and reception points (Transmission Reception Point, TRP) or next-generation node B
  • the access network device may also be a radio unit (radio unit, RU), a centralized unit (centralized unit, CU), a distributed unit (distributed unit, DU), a centralized unit control plane (CU control plane, CU-CP) node , or a centralized unit user plane (CU user plane, CU-UP) node.
  • the access network device may be a vehicle-mounted device, a wearable device, or an access network device in a future evolved public land mobile network (public land mobile network, PLMN).
  • PLMN public land mobile network
  • the communication device used to realize the function of the access network equipment may be the access network equipment, or the network equipment with some functions of the access network equipment, or a device capable of supporting the access network equipment to realize the function , such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module, the device can be installed in the access network equipment or matched with the access network equipment.
  • description is made by taking the communication device for realizing the function of the access network device as an example of the access network device.
  • the terminal equipment is also referred to as terminal, user equipment (user equipment, UE), mobile station (mobile station, MS), mobile terminal (mobile terminal, MT) and so on.
  • a terminal device may be a device that provides voice and/or data connectivity to a user.
  • Terminal equipment can communicate with one or more core networks through access network equipment.
  • Terminal equipment can be deployed on land, including indoors, outdoors, handheld, and/or vehicle; can also be deployed on water (such as ships, etc.); can also be deployed in the air (such as aircraft, balloons and satellites, etc.) .
  • End devices include handheld devices with wireless connectivity, other processing devices connected to wireless modems, or vehicle-mounted devices.
  • the terminal device may be a portable, pocket, hand-held, computer built-in or vehicle-mounted mobile device.
  • terminal equipment are: personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants, personal digital assistant (PDA), wireless network camera, mobile phone, tablet computer, notebook computer, palmtop computer, mobile internet device (mobile internet device, MID), wearable device such as smart watch, virtual reality (virtual reality) reality (VR) equipment, augmented reality (augmented reality, AR) equipment, wireless terminals in industrial control (industrial control), terminals in car networking systems, wireless terminals in self driving (self driving), smart grid (smart grid) wireless terminals in grid, wireless terminals in transportation safety, wireless terminals in smart city (smart city) such as smart fuel dispensers, terminal equipment on high-speed rail and wireless terminals in smart home (smart home), Such as smart speakers, smart coffee machines, smart printers, etc.
  • PCS personal communication service
  • SIP session initiation protocol
  • WLL wireless local loop
  • PDA personal digital assistant
  • wireless network camera mobile phone
  • tablet computer notebook computer
  • the communication device used to realize the function of the terminal device may be a terminal device, or a terminal device with some terminal functions, or a device capable of supporting the terminal device to realize this function, such as a chip system, which may be Installed in the terminal equipment or matched with the terminal equipment.
  • a system-on-a-chip may be composed of chips, and may also include chips and other discrete devices.
  • the number and types of devices in the communication system shown in FIG. 1A are only for illustration, and the present disclosure is not limited thereto.
  • the communication system may also include more terminal devices and more access networks.
  • the device may also include other network elements, for example, may include core network elements, and/or network elements for implementing artificial intelligence functions.
  • the method provided in the present disclosure involves positioning technology for terminal equipment.
  • a positioning server 150 is introduced into the communication system shown in FIG. 1A above, and the positioning server 150 is used for estimating the position of the terminal equipment.
  • the positioning server can detect the characteristic parameters between the terminal device and a fixed (that is, known location) access network device, and obtain the relative position between the terminal device and the access network device or angle information, so as to estimate the position of the terminal device.
  • some characteristic parameters include, for example, one or more of the following: signal quality, distance, signal transmission delay (or signal propagation time) or signal transmission delay difference, signal departure angle, or signal arrival angle, etc.;
  • the quality can be reflected by one or more indicators of signal-to-noise ratio, signal strength, signal field strength, signal energy, and signal receiving power.
  • the positioning server in FIG. 1B may be implemented by a location management function (location management function, LMF) network element.
  • LMF location management function
  • the communication system includes access network equipment, terminal equipment, and core network elements, such as access and mobility management function (access and mobility management function, AMF) network elements and Location management function (location management function, LMF) network element.
  • the access network devices may be base stations of the same standard, or base stations of different network standards.
  • Fig. 1C shows a 5G base station, such as gNB; and a 4G base station, such as ng-eNB, which can access the 5G core network.
  • the terminal device represented by UE in FIG.
  • the gNB can communicate through the NR-Uu interface, such as using the NR-Uu interface to transmit signaling related to positioning.
  • the terminal device and the ng-eNB communicate through the LTE-Uu interface, for example, the LTE-Uu interface is used to transmit positioning-related signaling.
  • the gNB and AMF communicate through the NG-C interface, and the ng-eNB and AMF communicate through the NG-C interface.
  • the NG-C interface can be used to transmit signaling related to positioning.
  • the AMF and the LMF communicate through the NL1 interface, for example, use the NL1 interface to transmit signaling related to positioning.
  • one of the terminal device or the access network device sends a reference signal; the other party measures the reference signal to obtain channel information, and according to the channel information, the characteristic parameters between the terminal device and the access network device can be determined, and the characteristic parameters can also be It is called the measurement quantity, and then reports the measurement quantity to the LMF.
  • a positioning reference signal positioning reference signal
  • PRS positioning reference signal
  • the terminal device can send a sounding reference signal (Sounding Reference Signal, SRS) to the access network device or to the access network device in the cell, and the access network device measures the SRS to obtain uplink channel information, and then accesses the The network device determines the measurement amount according to the uplink channel information, and reports the measurement amount to the LMF for positioning of the terminal device.
  • SRS Sounding Reference Signal
  • a positioning method based on a time difference of arrival which can utilize the synchronized positions of at least three access network devices to locate a terminal device.
  • the three access network devices are marked as eNB1, eNB2, and eNB3 respectively.
  • the distances between the three access network devices and the terminal devices are d1, d2, and d3 respectively, and the propagation times of the corresponding signals are respectively t1, t2, t3.
  • three access network devices respectively send PRSs to the terminal device, which are denoted as P1, P2, and P3 respectively.
  • the eNB1 can be set as a reference node, and the terminal device can measure the arrival time difference between P2 and P1, that is, t 2 -t 1 , also called a reference signal time difference (reference signal time difference, RSTD).
  • the terminal device can deduce d 2 -d 1 by using t 2 -t 1 , and obtain a curve so that each point on the curve satisfies that the distance difference between eNB2 and eNB1 is d 2 -d 1 ; similarly, the terminal device
  • the arrival time difference between P3 and P1 can be measured, that is, t 3 -t 1 , using t 3 -t 1 can infer d 3 -d 1 , and obtain another curve that satisfies every point on this curve to eNB3 and eNB1
  • the distance difference is d 3 -d 1 .
  • the terminal device can determine its own position by using the intersection point of the above two curves.
  • the terminal device may report at least one parameter among signal propagation time, time difference of arrival, distance or inferred distance difference between different access network devices and the terminal device to the LMF, and the LMF may determine the above two curves, and the two The intersection point of the two curves, thereby determining the position of the terminal device.
  • the correspondingly obtained time difference of arrival can be expressed as an interval range.
  • the interval corresponding to the schematic curve in Figure 2 is represented by a dotted line, and the position of the terminal device is obtained between the two curves The overlap between the intervals.
  • ( xi , y i ) represents the position coordinates of the eNBi, and the value of i is 1, 2 or 3; (x, y) represents the position coordinates of the terminal device to be obtained, and c represents the speed of light.
  • the TDOA-based positioning method described above performs positioning according to the PRS sent by the access network device to the terminal device.
  • This positioning method can also be called downlink-TODA (downlink-TODA, DL-TDOA) or observed time difference of arrival (observed time difference of arrival, OTDOA).
  • this positioning method can also be called uplink-TODA (uplink-TODA, UL-TDOA).
  • the signal here is a signal transmitted between the access network device and the terminal device, and both AoA and AoD are angles equivalent to the access network device. That is, in the scenario where the access network device sends PRS to the terminal device for positioning, at least two access network devices can send PRS to the terminal device, and the terminal device measures the PRS sent by different access network devices to determine the location of each access network device. The corresponding AoD, or determine the angle difference between the AoD corresponding to each access network device and the AoD reference value.
  • the AoD reference value may be an AoD corresponding to one of the at least two access network devices, or a preset AoD.
  • the terminal device reports the AoD or angle difference corresponding to at least two access network devices to the LMF, and the LMF can determine the position of the terminal device according to the AoD or angle difference corresponding to at least two access network devices.
  • the terminal device sends SRS to the access network device for positioning
  • the terminal device can send SRS to at least two access network devices, and different access network devices measure the SRS from the terminal device to determine the corresponding location of each access network device.
  • AoA or determine the angle difference between the AoA corresponding to each access network device and the AoA reference value.
  • the AoA reference value may be an AoA corresponding to one of the at least two access network devices, or a preset AoA.
  • Each access network device reports its corresponding AoA or angle difference to the LMF, and the LMF can determine the location of the terminal device according to the AoA or angle difference corresponding to at least two access network devices.
  • the LMF can exchange positioning configuration information with the terminal device or the access network device in advance to determine the terminal device to be located, the access network device participating in the positioning of the terminal device, and the configuration related to the positioning technology.
  • the configuration related to the positioning technology may indicate the positioning method used for positioning the terminal device, whether the measured reference signal is the PRS corresponding to the downlink positioning or the SRS corresponding to the uplink positioning, and/or the measurement amount used for positioning, etc.
  • the following takes the DL-TDOA method as an example to introduce the positioning process based on the LTE positioning protocol (LPP) that can be used in the 5G system.
  • LTP LTE positioning protocol
  • the LPP protocol specifies the process of exchanging information between the terminal device and the LMF, that is, the terminal device and the LMF can exchange information through LPP messages. It should be noted that, according to the connection between the terminal device-access network device-AMF-LMF, the LPP message can be transparently transmitted across the access network device and the AMF to realize the interaction between the terminal device and the LMF.
  • the positioning configuration information includes positioning capabilities and positioning assistance information.
  • This process can be triggered by LMF or terminal equipment.
  • the LMF determines that the positioning assistance information needs to be provided to the terminal device, and sends an LPP Provide Assistance Data (LPP Provide Assistance Data) message to the terminal device.
  • LPP Provide Assistance Data LPP Provide Assistance Data
  • the terminal device first determines the required positioning assistance information, and sends an LPP request assistance data (LPP Request Assistance Data) message to the LMF, and the LPP request assistance data message can be used to indicate Positioning assistance information required by the terminal device.
  • the LMF sends an LPP provide assistance data message to the terminal device to provide the positioning assistance information required by the terminal device.
  • the positioning capability indicates at least one of the following contents of the terminal device: supported positioning methods, adopted protocols and procedures, configurable parameters and other information; positioning assistance information includes one or more of the following parameters: the physical cell where the terminal device is located Identification (identity, ID), global cell ID, ID of access network equipment, PRS configuration of access network equipment, synchronization signal/physical broadcast channel block (SSB) information of access network equipment, and PRS space Information such as direction information, geographic location coordinates of access network equipment, and time difference between access network equipment and reference nodes.
  • Identification identity, ID
  • ID global cell ID
  • ID of access network equipment ID of access network equipment
  • PRS configuration of access network equipment PRS configuration of access network equipment
  • SSB synchronization signal/physical broadcast channel block
  • PRS space Information such as direction information, geographic location coordinates of access network equipment, and time difference between access network equipment and reference nodes.
  • the terminal device and the LMF exchange positioning information that is, the measurement quantity (or location measurement result) determined by the terminal device measuring the PRS sent by each access network device is fed back to the LMF.
  • This process can be triggered by the terminal device or the LMF.
  • the LMF sends an LPP Request Location Information (LPP Request Location Information) message to the terminal device.
  • LPP Request Location Information is used to indicate the location measurement results required by the LMF, measurement configuration information, and/or Response time and other information requested.
  • the terminal device sends an LPP Provide Location Information (LPP Provide Location Information) message to the LMF before the required response time to feed back the measurement amount.
  • the terminal device When the terminal device triggers positioning information interaction, the terminal device sends an LPP providing positioning information message to the LMF to feed back the measurement amount.
  • the measurement quantity may include one or more items of information such as the arrival time stamp of the PRS, the propagation time of the PRS, the time difference of arrival corresponding to the PRS, or the received signal power of the PRS.
  • the measurement quantity may also include information for identifying the access network device, for example, including a physical cell ID, a global cell ID, and/or an access network device ID corresponding to each measurement quantity.
  • the access network equipment and Some positioning assistance information can also be exchanged between LMFs.
  • the LMF triggers the exchange of positioning assistance information between the access network device and the LMF.
  • the relevant process can refer to but not limited to the provisions of the NR positioning protocol A (NR positioning protocol A, NRPPa).
  • the access network device and the LMF are connected through the AMF.
  • the NRPPa protocol is transparent to the AMF, and the transparent transmission of the NRPPa data unit across the AMF allows the access network device to interact with the LMF.
  • the positioning assistance information of the access network device includes the physical cell ID, the global cell ID, the ID of the access network device, the PRS configuration of the access network device, the SSB information of the access network device, the spatial direction information of the PRS, or the One or more parameters such as the geographic location coordinates of the device.
  • the LMF sends a TRP Information Request (TRP Information Request) message to the access network device.
  • TRP Information Request is used to request the positioning assistance information of the access network device required by the LMF, and the access network device sends a TRP Information Response (TRP Information Response) message to the LMF.
  • the TRP Information Response message is used to indicate the location assistance information of the access network device required by the LMF, or the access network device sends a TRP Information Failure (TRP Information Failure) message to the LMF, and the TRP Information Failure message is used to indicate the cause of the failure.
  • TRP Information Failure TRP Information Failure
  • FIG. 3 illustrates the power
  • the signal power of the sampling points in the first period is weak, which corresponds to the noise signal; the signal power of the sampling points in the middle period is strong, corresponding to the multipath response of the actual signal. That is, in actual scenarios, it is necessary to judge the starting position of the actual signal in an environment with interference and noise, so as to obtain accurate signal propagation time or relative angle.
  • the head-path identification problem Determining the origin of the actual signal is also known as the head-path identification problem.
  • the measured reference signal is a signal propagated by a non-line of sight (NLOS)
  • NLOS non-line of sight
  • LOS line of sight
  • the NLOS between the access network device and the terminal device means that there is an obstacle between the access network device and the terminal device, so that the signal cannot be transmitted directly.
  • the LOS between the access network device and the terminal device means that the signal between the access network device and the terminal device is direct propagation.
  • the LOS (dotted line) between the eNB and UE is blocked by trees, and what actually arrives is the NLOS (solid line) reflected by the wall.
  • the distance of NLOS (d 2 +d 3 ) is greater than the distance of LOS (d 1 ). If the NLOS is mistaken for the LOS when locating the terminal equipment, large measurement errors may occur. It can be seen that the classification of LOS and NLOS is very important for the positioning of terminal equipment.
  • the present disclosure utilizes artificial intelligence (AI) technology to identify the first path, and derives a measurement quantity consistent with LOS propagation according to the obtained channel information, thereby reducing measurement errors and improving positioning accuracy.
  • AI artificial intelligence
  • the foregoing communication system may also include a network element implementing an AI function.
  • an AI function (such as an AI module or an AI entity) may be configured in an existing network element in a communication system to implement AI-related operations.
  • the existing network element may be an access network device (such as gNB), a terminal device, a core network device, or a network management device.
  • an independent network element may also be introduced into the communication system to perform AI-related operations.
  • the independent network element may be called an AI network element or an AI node, etc., and this disclosure does not limit the name.
  • the network element performing AI-related operations is a network element with a built-in AI function (such as an AI module or an AI entity).
  • AI-related operations may also be referred to as AI functions.
  • AI functions For the specific introduction of AI functions, please refer to the following.
  • the AI network element can establish a communication connection with the network elements included in the aforementioned communication system, such as terminal equipment, access network equipment, and core network elements.
  • the communication system includes terminal equipment, access network equipment, AMF network elements, and LMF network elements. establish a direct or indirect communication link between them.
  • the AI model is the specific realization of the AI function.
  • the AI model represents the mapping relationship between the input and output of the model. It can refer to a function model that maps an input of a certain dimension to an output of a certain dimension.
  • the AI model can be a neural network or other machine learning models, such as decision trees, support vector machines, etc.
  • the AI model may be referred to simply as a model.
  • the AI function may include at least one of the following: data collection (collecting training data and/or reasoning data), data preprocessing, model training (or model learning), model detection, model information publishing (configuring model information ), model inference, or release of inference results. Among them, reasoning can also be called prediction. Model checking can be used to check whether the trained model meets the requirements.
  • the AI model may be referred to simply as a model.
  • Machine learning is an important technical way to realize artificial intelligence. For example, machine learning can learn models or rules from raw data. Machine learning is divided into supervised learning, unsupervised learning, and reinforcement learning.
  • supervised learning uses machine learning algorithms to learn the mapping relationship between samples and sample labels, and uses machine learning models to express the learned mapping relationship.
  • the process of training a machine learning model is the process of learning this mapping relationship.
  • the sample is a received signal containing noise
  • the sample label is the real constellation point corresponding to the received signal.
  • Machine learning expects to learn the mapping relationship between samples and sample labels through training.
  • model parameters are optimized by calculating the error between the model's output (i.e., the predicted value) and the sample label.
  • the learned mapping relationship can be used to predict the sample label of the new sample.
  • the mapping relationship learned by supervised learning can include linear mapping and nonlinear mapping. According to the type of sample labels, machine learning tasks can be divided into classification tasks and regression tasks.
  • unsupervised learning uses algorithms to discover the internal patterns of the samples by itself.
  • algorithms such as autoencoder, confrontational generative network, etc.
  • the model learns the mapping relationship from sample to sample.
  • the relationship between the predicted value of the model and the sample itself is calculated. The error between them is used to optimize the model parameters and realize self-supervised learning.
  • Self-supervised learning can be used in signal compression and decompression recovery application scenarios.
  • Reinforcement learning is a class of algorithms that learn strategies to solve problems by interacting with the environment. Unlike supervised learning and unsupervised learning, reinforcement learning does not have clear sample labels. The algorithm needs to interact with the environment to obtain reward signals from environmental feedback, and then adjust decision-making actions to obtain greater reward signal values. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each terminal according to the total system throughput fed back by the wireless network, and expects to obtain a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and the optimal decision-making action. Training in reinforcement learning is achieved through iterative interactions with the environment.
  • a neural network is a specific implementation of AI or machine learning technology. According to the general approximation theorem, the neural network can theoretically approximate any continuous function, so that the neural network has the ability to learn any mapping.
  • Traditional communication systems need to rely on rich expert knowledge to design communication modules, while deep learning communication systems based on neural networks can automatically discover hidden pattern structures from a large number of data sets, establish mapping relationships between data, and achieve better results than traditional communication systems. The performance of the modeling method.
  • each neuron performs a weighted sum operation on its input values, and outputs the operation result through an activation function.
  • FIG. 6A it is a schematic diagram of a neuron structure.
  • the bias for performing weighted summation of the input values according to the weights is, for example, b.
  • the output of the neuron is:
  • the output of the neuron is:
  • b, w i , or xi may be various possible values such as decimals, integers (such as 0, positive integers or negative integers), or complex numbers.
  • the activation functions of different neurons in a neural network can be the same or different.
  • a neural network generally includes multiple layers, each layer may include one or more neurons. By increasing the depth and/or width of the neural network, the expressive ability or function fitting ability of the neural network can be improved, and more powerful information extraction and abstract modeling capabilities can be provided for complex systems.
  • the depth of the neural network may refer to the number of layers included in the neural network, and the number of neurons included in each layer may be referred to as the width of the layer.
  • a neural network includes an input layer and an output layer. The input layer of the neural network processes the received input information through neurons, and passes the processing result to the output layer, and the output layer obtains the output result of the neural network.
  • the neural network includes an input layer, a hidden layer, and an output layer.
  • a neural network processes the received input information through neurons, and passes the processing results to the middle hidden layer.
  • the processing results are calculated to obtain the calculation results, and the hidden layer transmits the calculation results to the output layer or the adjacent hidden layer, and finally the output layer obtains the output result of the neural network.
  • a neural network may include one hidden layer, or include multiple hidden layers connected in sequence, without limitation.
  • each neuron performs a weighted sum operation on its input values, and the weighted sum result generates an output through a function (for example, usually a nonlinear function, but not excluded as a linear function).
  • the weights of the neuron weighted summation operation and the nonlinear function in the neural network are called the parameters of the neural network.
  • the parameters of all neurons of a neural network constitute the parameters of this neural network.
  • the neural network involved in the present disclosure is, for example, a deep neural network (DNN).
  • DNN generally has multiple hidden layers, and in DNN, the model parameters of DNN include the weight corresponding to each neuron.
  • DNNs can use supervised learning or unsupervised learning strategies to optimize model parameters.
  • DNNs can include feedforward neural networks (FNN), convolutional neural networks (CNN) and recurrent neural networks (RNN).
  • FNN feedforward neural networks
  • CNN convolutional neural networks
  • RNN recurrent neural networks
  • FIG. 6B illustrate a neural network structure.
  • the characteristic of FNN is that neurons in adjacent layers are completely connected between pairs.
  • CNNs can be applied to process data with a grid-like structure.
  • the data with a similar grid structure may include time series data (discrete sampling on the time axis) and image data (two-dimensional discrete sampling) and the like.
  • the convolutional layer of CNN does not use all the input information for convolution operation at one time, but sets one or more fixed-size windows, and uses each window to intercept part of the input information for convolution operation.
  • Such a design can greatly reduce the calculation amount of model parameters.
  • performing a convolution operation on any one of one or more fixed-size windows can be understood as performing multiplication and then addition operations on the coefficients of the window (such as weighting coefficients) and part of the input information intercepted by the window .
  • the output information corresponding to the window can be obtained.
  • the coefficients of different windows may be configured independently.
  • different windows can be configured with different coefficients, which can enable CNN to better extract the features of the input data.
  • the coefficients of the window may include convolution kernels.
  • the types of part of the input information intercepted by different windows can be different.
  • the people and objects in the same picture can be understood as different types of information, and one window can be intercepted in two fixed-size windows People in the picture, another window can intercept the objects in the picture.
  • RNN is a DNN network that utilizes feedback time series information.
  • Its input includes the current time The new input value at the moment and the part of the output value of the RNN at the previous moment, where the output value at the previous moment can be determined by the activation function and the input at the previous moment.
  • RNN is suitable for obtaining sequence features that are correlated in time, and is suitable for application scenarios such as speech recognition and channel coding and decoding.
  • a loss function can be defined.
  • the loss function describes the gap or difference between the output value of the neural network and the ideal target value, and the disclosure does not limit the specific form of the loss function.
  • the training process of the neural network is the process of adjusting the parameters of the neural network so that the value of the loss function is less than the threshold, or the value of the loss function meets the target requirements. Adjusting the parameters of the neural network, for example, adjusting at least one of the following parameters: the number of layers of the neural network, the width, the weight of the neurons, or the parameters in the activation function of the neurons.
  • the disclosure utilizes AI technology to train a model that can be deployed on the measurement reporting side.
  • the model is used to extract measurements from channel information.
  • the input type of the model may include channel information, and the output type may include information capable of characterizing measurement quantities.
  • the channel information corresponds to the channel between the terminal device and the access network device (or the cell node of the access network device), and the channel information may be channel response, channel characteristic matrix, channel delay distribution or channel characteristic vector, etc.
  • Fig. 7 it illustrates a model training framework.
  • the measurement quantity reporting side may be the access network device or a cell node of the access network device; in the downlink positioning scenario, the measurement quantity reporting side may be the terminal device.
  • the measurement quantity reporting side first sends the first channel estimation information to the LMF.
  • the first channel estimation information is used to indicate the measurement quantity determined by the measurement quantity reporting side through the measurement channel information.
  • the first channel estimation information can also be described as the first measurement information .
  • the LMF determines (or inversely derives) corresponding second channel estimation information according to the obtained first channel estimation information, and the second channel estimation information is used for model training.
  • the measurement reporting side may use an existing model to obtain the first channel estimation information from the channel information, and the second channel estimation information determined by the LMF is used to update and train the aforementioned existing model.
  • a communication method is illustrated, and the method mainly includes the following procedures.
  • one of the first device or the LMF initiates a model training request.
  • the model may be deployed in the first device, and is used for extracting channel estimation information for terminal device positioning from relevant channel information involved in positioning measurement.
  • the channel estimation information may represent the measurement quantities introduced above, which will be specifically described in S802 below.
  • the first device is a terminal device, or the first device is an mth cell node among M cell nodes.
  • the M cell nodes are the cell nodes that participate in the model training and locate the terminal equipment.
  • M is a positive integer greater than 1
  • m is a positive integer ranging from 1 to M.
  • the M cell nodes can be the same access network device, that is, the access network device can manage multiple cells, and can be called corresponding cell nodes in different cells; or, the M cell nodes can also be different access network devices.
  • the M cell nodes can also be described as M access network devices; or, at least two of the M cell nodes do not belong to the same access network device.
  • a cell node may also be described as a cell.
  • the access network device only manages one cell, for example, when the access network device is a micro station or a small station, the cell node of the access network device can also be understood as the access network device itself.
  • An optional manner may be that the first device sends training request information to the LMF, so as to trigger a training process of the model.
  • the cell node may send training request information to request training of a model applicable to the current scenario after building the basic model architecture.
  • the terminal device may initiate training when a large change occurs in its location, such as entering a shopping mall or arriving in a new city.
  • a terminal device or a cell node may also initiate training periodically to update the model on a regular basis.
  • terminal devices or cell nodes can also initiate training when computing resources are relatively idle.
  • the LMF sends training request information to the first device.
  • the LMF can initiate training according to actual needs. For example, the LMF initiates model update training when it judges that the model currently used by the first device is not effective, or the LMF can also initiate training periodically to implement regular update of the model.
  • the training request information described in the above optional manner may also be referred to as first request information or other names, which is not limited in the present disclosure.
  • FIG. 8 shows in S801 that the first device sends training request information to the LMF, so as to trigger the training process of the model.
  • the terminal device and the LMF can communicate according to the LPP protocol.
  • the access network device and the AMF involved in the transparent transmission between the terminal device and the LMF are omitted; the first When the device is a cell node, the access network device to which the cell node belongs and the LMF can communicate according to the NRPPa protocol.
  • Figure 8 omits the AMF involved in the transparent transmission between the cell node and the LMF.
  • the LMF acquires M pieces of first channel estimation information.
  • the m-th first channel estimation information among the M pieces of first channel estimation information is estimation information of a channel between the m-th cell node and the terminal device among the M cell nodes. Specifically, the m-th first channel estimation information among the M pieces of first channel estimation information is determined by the channel information of the channel between the m-th cell node and the terminal device among the M cell nodes.
  • the LMF may acquire the m-th first channel estimation information from the first device.
  • M cell nodes can send reference signals such as PRS to the terminal device; the terminal device measures the PRS sent by the mth cell node among the M cell nodes, and obtains the mth cell node and the terminal device The channel information between the channels; the terminal device determines the measurement quantity corresponding to the mth cell node according to the acquired channel information, and the terminal device sends the m first channel estimation information to the LMF, and the m first channel estimation information is used for Indicates the measurement quantity corresponding to the mth cell node.
  • the terminal device sends a reference signal such as SRS to the mth cell node among the M cell nodes; the mth cell node measures the PRS sent by the terminal device, and obtains the mth cell node and the terminal device The channel information of the channel between; the mth cell node determines the measurement quantity corresponding to the mth cell node according to the obtained channel information, the mth cell node sends the m first channel estimation information to the LMF, and the mth cell node The channel estimation information is used to indicate the measurement quantity corresponding to the mth cell node.
  • the LMF may configure the first device to periodically measure the reference signal during the training phase, and stop measuring until the first device receives an indication that the training is over.
  • the mth first channel estimation information may be specifically used to indicate one or more of the following parameters:
  • the mth first channel estimation information includes the distance between the mth cell node and the terminal device; or, the mth first channel estimation information includes the mth distance difference, and the mth distance difference Indicates the difference between the distance between the mth cell node and the terminal device relative to the reference distance; wherein, the reference distance can be preset, or the specified cell node among the M cell nodes and the terminal device the distance between.
  • the mth first channel estimation information includes the signal transmission delay between the mth cell node and the terminal device; or, the mth first channel estimation information includes the mth signal transmission delay difference (or called signal transmission time difference), the mth signal transmission time delay difference represents the difference between the signal transmission time delay between the mth cell node and the terminal equipment relative to the reference time delay; wherein, the reference time delay It may be preset, or it may be the signal transmission delay between a designated cell node among the M cell nodes and the terminal device.
  • the mth first channel estimation information includes the signal angle of arrival corresponding to the mth cell node, or the mth first channel estimation information includes the mth angle of arrival difference, and the mth The angle of arrival difference represents the difference between the angle of arrival of the signal between the mth cell node and the terminal device relative to the reference angle of arrival; wherein, the reference angle of arrival can be preset, or be the difference between the M cell nodes The angle of arrival of the signal corresponding to a cell node of .
  • the mth first channel estimation information includes the departure angle of the signal corresponding to the mth cell node, or the mth first channel estimation information includes the mth departure angle difference, and the mth The departure angle difference represents the difference between the signal departure angle between the mth cell node and the terminal device relative to the reference departure angle; wherein, the reference departure angle can be preset, or M cell nodes The signal departure angle corresponding to the specified cell node in .
  • a type of a signal transmission path between the mth cell node and the terminal device is a direct path or a non-direct path.
  • the first device may exchange positioning configuration information with the LMF before sending the m-th first channel estimation information to the LMF.
  • it may be implemented by referring to the foregoing manner of exchanging positioning configuration information between the terminal device and the LMF, which will not be described in detail in this disclosure.
  • the first device may measure channel information multiple times to determine the m-th first channel estimation information, and send the m-th first channel estimation information to the LMF multiple times.
  • the LMF acquires M pieces of first channel estimation information, including: the LMF acquires M pieces of first channel estimation information one or more times.
  • S803. Determine M pieces of second channel estimation information according to at least one piece of first channel estimation information in the M pieces of first channel estimation information.
  • the m-th second channel estimation information among the M pieces of second channel estimation information corresponds to the channel between the m-th cell node among the M cell nodes and the terminal device.
  • the parameters indicated by the mth second channel estimation information may be understood with reference to the parameters indicated by the first channel estimation information, for example, the mth second channel estimation information may indicate one or more of the following parameters: the mth The distance between the cell node and the terminal device; the signal transmission delay or signal transmission delay difference between the mth cell node and the terminal device; the departure angle of the signal corresponding to the mth cell node (AoD) or signal angle of arrival (AoA); the signal quality between the mth cell node and the terminal device; or, the actual signal transmission path between the mth cell node and the terminal device type.
  • the mth second channel estimation information may indicate one or more of the following parameters: the mth The distance between the cell node and the terminal device; the signal transmission delay or signal transmission delay difference between the mth cell node and the terminal device; the departure angle of the signal corresponding to the mth cell node (AoD) or signal angle of arrival (AoA); the signal quality between the mth cell no
  • the mth second channel estimation information except for the type of the actual signal transmission path, other parameters correspond to the path between the simulated mth cell node and the terminal device as LOS
  • the parameters calculated in the case of may be LOS or NLOS.
  • the parameter type indicated by the mth second channel estimation information and the parameter type indicated by the mth first channel estimation information may be the same, for example, the parameter indicated by the mth first channel estimation information includes as in S802
  • the parameters indicated by the mth second channel estimation information include labels corresponding to (1) to (3) described in S802.
  • the parameter type indicated by the mth second channel estimation information and the parameter type indicated by the mth first channel estimation information may also be different, for example, the parameter indicated by the mth first channel estimation information includes as in S802
  • the parameters indicated by the mth second channel estimation information include labels corresponding to (1)-(2) described in S802.
  • the parameter type indicated by the mth second channel estimation information may be based on actual It is determined by the training requirements of the actual model, which is not limited in the present disclosure.
  • the first device when sending the training request information to the LMF, may request related second channel estimation information through the training request information.
  • the first device may specify the parameter indicated by the second channel estimation information to the LMF through the training request information, for example, the first device may include the parameter type indicated by the second channel estimation information in the training request information.
  • the type of the parameter indicated by the second channel estimation information may also be understood as the type of the measured quantity represented by the output of the expected model of the first device.
  • the LMF may refer to the following method to determine the corresponding M pieces of second channel estimation information:
  • the LMF acquires M pieces of second channel estimation information according to the at least one first channel estimation information among the M pieces of first channel estimation information to determine the first location of the terminal equipment;
  • the LMF determines the first location of the terminal equipment according to the first location of the terminal equipment and the locations of the M cell nodes The M pieces of second channel estimation information.
  • the first location may be a credible location (or reliable location) of the terminal device preliminarily determined by the LMF in combination with the locations of M cell nodes and at least one first channel estimation information among the M pieces of first channel estimation information.
  • An optional implementation manner of determining the first position is introduced below.
  • the LMF may determine multiple second positions of the terminal device according to the M pieces of first channel estimation information and the positions of the M cell nodes. Wherein, a first part of the plurality of second positions is located in the first area, a second part of the plurality of second positions is not located in the first area, and the number of the first part of positions is greater than the The number of positions in the second part described. Furthermore, the LMF determines the first location of the terminal device according to the first part of locations in the plurality of second locations.
  • the parameters indicated by the m-th first channel estimation information among the M pieces of first channel estimation information include the signal transmission time between the m-th cell node and the terminal device delay.
  • Figure 9 shows a positioning scenario, assuming that M is 6, and the 6 cell nodes are denoted as C1, C2, C3, C4, C5 and C6 respectively. Wherein, the path between C6 and the terminal equipment is NLOS, and the paths between other cell nodes and the terminal equipment are LOS.
  • the LMF uses the positions of any three of the six cell nodes to estimate the position of the terminal device based on the M first channel estimation information, a total of 20 possible positions can be obtained, and these 20 positions are shown in Figure 9 Indicated by " ⁇ ". Since there is only one NLOS in the scenario shown in Figure 9, if the paths between the three cell nodes and the terminal equipment selected for estimating the position of the terminal are all LOS, that is, choose among C1, C2, C3, C4, and C5 3, the obtained 10 positions are relatively close, all located in the dotted box area in Figure 9 (corresponding to the aforementioned first area); and if the 3 cell nodes used to estimate the terminal position include C6, the obtained 10 positions Scattered outside the dashed box area. Therefore, the LMF may determine the first position of the terminal device according to the 10 positions within the dashed-line frame, for example, the 10 positions within the dashed-line frame may be averaged to obtain the first position.
  • the LMF may determine the first location of the terminal device according to the N pieces of first channel estimation information and the locations of the N cell nodes; wherein, the N pieces of first channel estimation information and The N cell nodes are in one-to-one correspondence, the N cell nodes are included in the M cell nodes, and N is a positive integer less than or equal to M.
  • a path between each cell node in the N cell nodes and the terminal device is a direct path.
  • the LMF may determine N cell nodes corresponding to direct paths among the M cell nodes according to the M pieces of first channel estimation information.
  • the parameter indicated by the mth first channel estimation information corresponding to the M first channel estimation information includes the signal transmission between the mth cell node and the terminal device delay.
  • LMF can arbitrarily select 3 cell nodes among the M cell nodes, and remember that the i-th small cell node among the 3 cell nodes
  • the location coordinates of the district nodes are ( xi , y , zi ) , where i is a positive integer from 1 to 3.
  • LMF uses the selected 3 cell nodes to calculate the location coordinates of the terminal equipment as (x, y, z).
  • LMF calculates the distance between the terminal device and the i-th cell node according to the position coordinates of the terminal device calculated above and the position coordinates of the i-th cell node as And the signal transmission delay between the terminal equipment and the i-th cell node can be calculated as
  • the m-th first channel estimation information includes the m-th signal transmission delay difference
  • the reference delay is the signal transmission delay between the specified cell node and the terminal device among the aforementioned M cell nodes.
  • the distance between the designated cell node and the terminal device is t 0
  • the time difference measurement corresponding to the i-th cell node among the aforementioned 3 cell nodes reported by the first device to the LMF is ⁇ i
  • ⁇ i
  • corresponding to the i-th cell node will be obtained.
  • ⁇ i is used to determine whether the path between the ith cell node and the terminal device is LOS or NLOS.
  • the LMF can determine whether the path between the i-th cell node and the terminal device is LOS or NLOS through the following formula:
  • th is the preset threshold. It can be understood that when ⁇ i ⁇ th, the value of los i is 1, indicating that the difference between ⁇ t i and ⁇ i is small, and the path between the i-th cell node and the terminal device is LOS; when ⁇ i >th, the value of los i is 0, indicating that the difference between ⁇ t i and ⁇ i is large, and the path between the i-th cell node and the terminal device is NLOS.
  • the LMF can select N cell nodes corresponding to the direct path from the M cell nodes by comparing the reported amount and the calculated amount.
  • the relationship between the cell node and the terminal device can be determined based on the above method of comparing the amount of reporting and calculation. The type of the signal transmission path will not be described in detail in this disclosure.
  • the LMF may directly According to the m th first channel estimation information, it is determined that the path type corresponding to the m th cell node is a direct path or a non-direct path, and then N cell nodes corresponding to the direct path are determined among the M cell nodes.
  • the LMF sends K pieces of second channel estimation information to the first device, where the first device is used for training the model.
  • the K pieces of second channel estimation information are included in the M pieces of second channel estimation information described in S803, it can be understood that the LMF sends part or all of the M pieces of second channel estimation information to the first device, K is a positive integer, and K is less than or equal to M.
  • the k-th second channel estimation information among the K second channel estimation information corresponds to the channel between the k-th cell node and the terminal device among the K cell nodes, the K cell nodes are included in the aforementioned M cell nodes, and k is taken over A positive integer from 1 to K.
  • the K pieces of second channel estimation information sent by the LMF to the first device only include the channel between the mth cell node and the terminal device
  • the corresponding second channel estimation information the mth cell node may train a corresponding model based on the second channel estimation information corresponding to the channel between the mth cell node and the terminal device.
  • k is synonymous with m.
  • the mth cell node A corresponding model may be trained based on part or all of the M pieces of second channel estimation information.
  • the LMF sends K
  • the second channel estimation information is part of the second channel estimation information in the M pieces of second channel estimation information, then the mth cell node can train the corresponding model.
  • the terminal device may train a corresponding model based on the M pieces of second channel estimation information.
  • the first device may decide to train the model according to part or all of the M second channel estimation information, or it may be described as the first device may decide to use part or all of the M cells
  • the second estimation information corresponding to the cell performs model training.
  • the first device sends the training request information to the LMF, it indicates that K pieces of second channel estimation information are requested.
  • the first device may include a value in the training request information is the instruction information of K.
  • the LMF may uniformly send K pieces of second channel estimation information corresponding to a set number of times when it acquires M pieces of first channel estimation information for a set number of times. estimated information.
  • the LMF may uniformly send K pieces of second channel estimation information of corresponding times at intervals of a set time according to the M pieces of first channel estimation information acquired one or more times within the set time.
  • the set times or the set time may be configured to the LMF by the first device, or may be pre-agreed, which is not limited in the present disclosure. In this manner, signaling overhead can be reduced.
  • the first device performs model training according to the K pieces of second channel estimation information.
  • the first device may use supervised learning for training.
  • the measured channel information is used as a sample, and the sample label is determined according to the acquired second channel estimation information, so as to obtain the training data set of the model.
  • the training-related loss function is not limited, for example, it may be determined by factors such as the structure type of the model, the training data set of the model, and/or the application scenario of the model. Examples of some model structure types are as follows: decision tree, random forest, support vector machine, or neural network, etc., where the neural network is, for example, CNN, RNN, or FNN.
  • the first device may acquire K pieces of channel information, where k-th channel information among the K pieces of channel information is channel information of a channel between the k-th cell node and the terminal device among the K cell nodes.
  • k-th channel information among the K pieces of channel information is channel information of a channel between the k-th cell node and the terminal device among the K cell nodes.
  • the input of the model is determined according to the channel information of the channel between the kth cell node and the terminal device, and the label corresponding to the input is determined according to the kth cell determined by the second channel estimation information corresponding to the channel between the node and the terminal device.
  • the channel information is a channel response
  • the input of the model may include the channel response of the channel between the kth cell node and the terminal device, the channel response after separation of the real and imaginary parts, or the amplitude and phase separation The subsequent channel response, etc.
  • the function of the model is related to the parameter type indicated by the second channel estimation information.
  • the input type of the trained model includes channel information, and the output type includes corresponding third channel estimation information, and the parameter type indicated by the third channel estimation information is the same as the parameter type indicated by the second channel estimation information;
  • the three channel estimation information are used to determine the second location of the terminal device.
  • a model-based positioning method is illustrated.
  • the trained model can be deployed on terminal devices or access network devices (cells of access network devices), and is used to determine the location of the terminal device according to the channel information involved in the positioning measurement. Positioned third channel estimation information.
  • the terminal device or the access network device may send the aforementioned third channel estimation information to the LMF, and the LMF calculates the second position of the terminal device according to the obtained third channel estimation information.
  • the first device can determine the distance between the tth cell node among the T cell nodes and the terminal device channel information
  • the first device can determine the tth third channel estimation information according to the channel information of the channel between the tth cell node and the terminal device by using the trained model.
  • T is a positive integer greater than 1
  • t is a positive integer ranging from 1 to T; optionally, the value of T and the above-mentioned M may be the same or different, without limitation.
  • the parameter indicated by the tth third channel estimation information includes: under the condition of LOS, the tth cell node The distance from the terminal device.
  • the distance may also be referred to as the LOS distance.
  • the parameter indicated by the tth third channel estimation information includes: the condition of the LOS Next, the signal transmission delay or the signal transmission delay difference between the tth cell node and the terminal device.
  • the signal transmission delay may also be referred to as a signal transmission delay conforming to LOS transmission
  • the signal transmission delay difference may also be referred to as a signal transmission delay difference conforming to LOS transmission.
  • the parameter indicated by the tth third channel estimation information includes the signal departure corresponding to the tth cell node corresponding to LOS transmission angle or signal arrival angle.
  • the parameter indicated by the tth third channel estimation information includes the actual signal transmission path between the tth cell node and the terminal device.
  • the type of signal transmission path includes the parameter indicated by the tth cell node and the terminal device.
  • the parameter type indicated by the second channel estimation information includes a signal transmission delay between the cell node and the terminal device, and a type of a signal transmission path between the cell node and the terminal device.
  • the first device can use the trained model to determine the t-th third channel estimation information according to the channel information of the channel between the t-th cell node and the terminal device, and the t-th third channel estimation channel information
  • the indicated parameters include the signal transmission delay between the tth cell node and the terminal device in compliance with LOS transmission, and the type of the actual signal transmission path between the tth cell node and the terminal device, for example, the actual signal transmission path The path is of type NLOS.
  • the channel estimation information is obtained according to the measurement of the terminal device or the cell node, the label used for model training is derived, and the label for model training is provided to the terminal device or the cell node, so that the terminal device or the cell node trains the model.
  • This training method is more suitable for the actual scene environment, and can improve the performance of the model, thereby improving the positioning accuracy.
  • the cell nodes participating in model training and the cell nodes participating in model reasoning may be the same or different.
  • the first group of cell nodes is used for model training, and the trained model is used for the second group of cell nodes.
  • the first group of cell nodes and the second group of cell nodes may be the same or different, without limitation.
  • terminal devices participating in model training and the terminal devices participating in model reasoning may be the same or different.
  • terminal A is used for model training
  • the trained model is used for terminal B.
  • Terminal A and terminal B may be the same or different without limitation.
  • a communication method is illustrated, and the method mainly includes the following procedures.
  • the first device or one of the LMF initiates a model training request.
  • This step can be implemented with reference to S801, which will not be repeated in this disclosure.
  • the LMF acquires M pieces of first channel estimation information.
  • This step can be implemented with reference to S802, which will not be repeated in this disclosure.
  • the LMF determines M pieces of second channel estimation information according to at least one piece of first channel estimation information in the M pieces of first channel estimation information.
  • This step can be implemented with reference to S803, which will not be repeated in this disclosure.
  • the LMF acquires channel information of channels between M cell nodes and the terminal device.
  • the LMF acquires channel information of the channel between the mth cell node and the terminal device from the first device.
  • the channel information of the channel between the mth cell node and the terminal device measured by the first device can be understood by referring to the content described in S802, which will not be repeated in this disclosure.
  • the LMF performs model training according to at least one second channel estimation information in the M pieces of second channel estimation information.
  • the LMF may train a corresponding model for the mth cell node according to the mth second channel estimation information; wherein, when performing the training of the model, the The input of the model is determined according to the channel information of the channel between the mth cell node and the terminal device, and the label corresponding to the input is determined according to the channel information corresponding to the mth cell node and the terminal device determined by the second channel estimation information.
  • the LMF can train the same model for K cell nodes according to the K second channel estimation information
  • K is a positive integer less than or equal to M
  • the K cell nodes are included in the aforementioned M cell nodes.
  • the K pieces of second channel estimation information are included in the M pieces of second channel estimation information.
  • the k-th second channel estimation information among the K pieces of second channel estimation information corresponds to the channel between the k-th cell node and the terminal device among the K cell nodes.
  • the input of the model is determined according to the channel information of the channel between the kth cell node and the terminal device, and the label corresponding to the input is determined according to the kth cell node
  • the second channel estimation information corresponding to the channel between the cell nodes and the terminal equipment is determined.
  • the LMF may train a model according to the M pieces of second channel estimation information.
  • the input of the model is determined according to the channel information of the channel between each of the M cell nodes and the terminal device, and the label corresponding to the input is determined according to the The second channel estimation information corresponding to the channel between each of the M cell nodes and the terminal device is determined.
  • the LMF sends information used to indicate the model to the first device.
  • the model corresponding to the mth cell may be specific to the cell, or shared by the cell and other cells, which is not limited.
  • the first device uses the trained model to extract third channel estimation information from the measured channel information, and the third estimation information is used to determine the second position of the terminal device. Specifically, it can be implemented with reference to the description in Solution 1, which will not be repeated in this disclosure.
  • LMF obtains channel estimation information based on terminal equipment or cell node measurements, derives labels for model training, and trains the model. This method is more suitable for the actual scene environment and can improve the performance of the model, and then LMF provides the trained model with Determining channel estimation information for positioning for terminal equipment or cell nodes can improve positioning accuracy.
  • a communication method is illustrated, and the method mainly includes the following procedures.
  • the LMF acquires training request information.
  • the first device performing model training may send the training request information to the LMF, or the measurement quantity reporting side may send the training request information to the LMF.
  • the measurement amount reporting side may be a terminal device, or a cell node of an access network device.
  • the measurement reporting side is represented by the second device.
  • FIG. 12 shows that the LMF acquires training request information from the second device.
  • the definition of the training request information can be understood with reference to the description in the corresponding solution in FIG. No further details will be given.
  • the positions of the M cell nodes are used to estimate the position of the terminal equipment.
  • the second device may be an mth cell node or a terminal device among the M cell nodes, and the LMF may acquire the mth first channel estimation information from the second device.
  • the definition of the M cell nodes and the first channel estimation information can be understood with reference to S801, which will not be repeated in this disclosure.
  • the LMF acquires M pieces of first channel estimation information.
  • This step can be implemented with reference to S802, which will not be repeated in this disclosure.
  • the LMF determines M pieces of second channel estimation information according to at least one piece of first channel estimation information in the M pieces of first channel estimation information.
  • This step can be implemented with reference to S803, which will not be repeated in this disclosure.
  • the LMF sends the M pieces of second channel estimation information to a first device, where the first device is used for training the model.
  • the first device may be an AI network element with a model training function in addition to M cell nodes and terminal devices, and the LMF sends the M pieces of second channel estimation information to the first device.
  • This step can be implemented with reference to S804, which will not be repeated in this disclosure.
  • the first device acquires channel information of channels between M cell nodes and the terminal device.
  • the first device may acquire channel information of a channel between the mth cell node and the terminal device from the second device.
  • the first device performs model training according to the M pieces of second channel estimation information.
  • this step may be implemented with reference to S1105, which will not be repeated in this disclosure.
  • the first device sends information used to indicate the model to the second device.
  • this step may be implemented with reference to S1106, which will not be repeated in this disclosure.
  • the second device uses the trained model to extract third channel estimation information from the measured channel information, and the third estimation information is used to determine the second position of the terminal device. Specifically, it can be implemented with reference to the description in Solution 1, which will not be repeated in this disclosure.
  • LMF obtains channel estimation information based on terminal equipment or cell node measurements, derives the label used for model training, and provides the label to a separate AI network element training model.
  • This method is more suitable for the actual scene environment and can improve the model.
  • the performance, and then the AI network element provides the trained model to the terminal device or cell node to determine the channel estimation information used for positioning, which can improve the positioning accuracy.
  • the present disclosure provides a communication device 1300 , where the communication device 1300 includes a processing module 1301 and a communication module 1302 .
  • the communication device 1300 may be an LMF, or it may be a communication device applied to or matched with an LMF, and capable of implementing a communication method performed on the LMF side; or, the communication device 1300 may be a first device, or a communication device applied to a second device A device or a communication device that is used in conjunction with the first device and can implement the communication method performed by the first device side; or, the communication device 1300 can be the second device, or it can be applied to the second device or matched with the second device A communication device capable of implementing the communication method performed by the second device side is used.
  • the communication module may also be referred to as a transceiver module, a transceiver, a transceiver, or a transceiver device and the like.
  • a processing module may also be called a processor, a processing board, a processing unit, or a processing device.
  • the communication module is used to perform the sending and receiving operations on the LMF side or the first device side in the above method.
  • the device used to implement the receiving function in the communication module can be regarded as a receiving unit, and the device used to implement the receiving function in the communication module can be regarded as a receiving unit.
  • a device with a sending function is regarded as a sending unit, that is, the communication module includes a receiving unit and a sending unit.
  • the processing module 1301 can be used to realize the processing function of the LMF in the example shown in FIG. 8, FIG. 11 or FIG.
  • the transceiving function of the LMF in the example can also be understood with reference to possible designs in the fifth aspect and the ninth aspect in the summary of the invention.
  • the processing module 1301 can be used to realize the processing function of the first device or the second device in the example shown in FIG. 8 , FIG. 11 , or FIG. 12
  • the communication module 1302 can be used In order to realize the transceiving function of the first device or the second device in the example shown in FIG. 8 , FIG. 11 , or FIG. 12 .
  • the first device represents the terminal device or the cell node
  • the first device represents the AI network element
  • the second device represents the terminal device or the cell node.
  • the communication device can also be understood with reference to the sixth aspect in the summary of the invention and possible designs in the sixth aspect, or can also be understood with reference to the seventh aspect in the summary of the invention and possible designs in the seventh aspect, or can also be understood with reference to the invention
  • the eighth aspect in the content and possible designs in the eighth aspect understand the communication device.
  • the aforementioned communication module and/or processing module may be realized by a virtual module, for example, the processing module may be realized by a software function unit or a virtual device, and the communication module may be realized by a software function or a virtual device.
  • the processing module or the communication module may also be implemented by a physical device, for example, if the device is implemented by a chip/chip circuit, the communication module may be an input and output circuit and/or a communication interface, and perform an input operation (corresponding to the aforementioned receiving operation), Output operation (corresponding to the aforementioned sending operation); the processing module is an integrated processor or a microprocessor or an integrated circuit.
  • each functional module in each example of this disclosure can be integrated in a processor. It can also exist separately physically, or two or more modules can be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules.
  • the present disclosure also provides a communication device 1400 .
  • the communication device 1400 may be a chip or a chip system.
  • the system-on-a-chip may be constituted by chips, and may also include chips and other discrete devices.
  • the communication device 1400 may be used to implement the function of any network element in the communication system described in the preceding examples.
  • the communication device 1400 may include at least one processor 1410, and the processor 1410 is coupled to a memory.
  • the memory may be located within the device, the memory may be integrated with the processor, or the memory may be located outside the device.
  • the communication device 1400 may further include at least one memory 1420 .
  • the memory 1420 stores necessary computer programs, computer programs or instructions and/or data for implementing any of the above examples; the processor 1410 may execute the computer programs stored in the memory 1420 to complete the methods in any of the above examples.
  • the communication device 1400 may further include a communication interface 1430, and the communication device 1400 may perform information exchange with other devices through the communication interface 1430.
  • the communication interface 1430 may be a transceiver, a circuit, a bus, a module, a pin or other types of communication interfaces.
  • the communication interface 1430 in the device 1400 can also be an input and output circuit, which can input information (or call it receiving information) and output information (or call it sending information)
  • the processor is an integrated processor or microprocessor or integrated circuit or A logic circuit in which a processor determines output information based on input information.
  • the coupling in the present disclosure is an indirect coupling or communication connection between devices, units or modules, which may be in electrical, mechanical or other forms, and is used for information exchange between devices, units or modules.
  • the processor 1410 may cooperate with the memory 1420 and the communication interface 1430 .
  • the specific connection medium among the processor 1410, the memory 1420, and the communication interface 1430 is not limited in the present disclosure.
  • the bus 1440 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus or the like.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 14 , but it does not mean that there is only one bus or one type of bus.
  • a processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the present invention.
  • a general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed in conjunction with the present disclosure may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.
  • the memory may be a non-volatile memory, such as a hard disk (hard disk drive, HDD) or a solid-state drive (solid-state drive, SSD), etc., or a volatile memory (volatile memory), such as random memory Access memory (random-access memory, RAM).
  • a memory is, but is not limited to, any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
  • the memory in the present disclosure may also be a circuit or any other device capable of implementing a storage function for storing program instructions and/or data.
  • the communication apparatus 1400 can be applied to the first device, and the specific communication apparatus 1400 can be the first device, or can support the first device, and implement the first device in any of the above-mentioned examples. function of the device.
  • the memory 1420 stores computer programs (or instructions) and/or data for realizing the functions of the first device in any of the above examples.
  • the processor 1410 may execute the computer program stored in the memory 1420 to complete the method performed by the first device in any of the foregoing examples.
  • the communication interface in the communication apparatus 1400 can be used to interact with the LMF, send information to the LMF or receive information from the LMF.
  • the communication device 1400 can be applied to the second device, and the specific communication device 1400 can be the second device, or can support the second device, and implement the second device in any of the above-mentioned examples. function of the device.
  • the memory 1420 stores computer programs (or instructions) and/or data for realizing the functions of the first device in any of the above examples.
  • the processor 1410 may execute the computer program stored in the memory 1420 to complete the method performed by the second device in any of the foregoing examples.
  • the communication interface in the communication apparatus 1400 can be used to interact with the LMF, send information to the LMF or receive information from the LMF.
  • the communication device 1400 may be applied to LMF, and the specific communication device 1400 may be an LMF, or may be a device capable of supporting LMF and realizing the function of LMF in any of the above-mentioned examples.
  • the memory 1420 stores computer programs (or instructions) and/or data implementing the functions of the LMF in any of the above examples.
  • the processor 1410 may execute the computer program stored in the memory 1420 to complete the method performed by the LMF in any of the foregoing examples.
  • the communication interface in the communication apparatus 1400 can be used to interact with the first device or the second device, for example, send information to the first device or the second device, or receive information from the first device or the second device.
  • the communication apparatus 1400 provided in this example can be applied to the first device to complete the above method performed by the first device, Either it is applied to the second device to complete the method executed by the second device, or it is applied to the LMF to complete the method executed by the LMF. Therefore, the technical effect that it can obtain can refer to the above method examples, and will not be repeated here.
  • the present disclosure provides a communication system, including a terminal device, at least one cell node, and an LMF.
  • AI network elements are also included.
  • the terminal device, at least one cell node, AI network element and LMF can implement the communication method provided in the examples shown in FIG. 8 , FIG. 11 , or FIG. 12 .
  • the first device represents a terminal device or a cell node
  • the second device represents a terminal device or a cell node.
  • the technical solution provided by the present disclosure may be fully or partially realized by software, hardware, firmware or any combination thereof.
  • software When implemented using software, it may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions.
  • the computer program instructions When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present disclosure are produced in whole or in part.
  • the computer may be a general computer, a dedicated computer, a computer network, an LMF, a terminal device, a cell node, an AI network element or other programmable devices.
  • the computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server or data center Transmission to another website site, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media.
  • the available medium may be a magnetic medium (for example, a floppy disk, a hard disk, or a magnetic tape), an optical medium (for example, a digital video disc (digital video disc, DVD)), or a semiconductor medium.
  • the examples can refer to each other, for example, the methods and/or terms between the method examples can refer to each other, for example, the functions and/or terms between the apparatus examples can refer to each other , for example, functions and/or terms between the apparatus example and the method example may refer to each other.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Power Engineering (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本公开提供一种通信方法及装置，能够提升定位性能。该方法包括：获取M个第一信道估计信息，M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，M为大于1的正整数，m为取遍1至M的正整数；根据M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息，M个第二信道估计信息中的第m个第二信道估计信息对应第m个小区节点与终端设备之间的信道。

Description

一种通信方法及装置
相关申请的交叉引用
本申请要求在2022年02月28日提交中华人民共和国知识产权局、申请号为202210191893.7、申请名称为“一种通信方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及通信技术领域，尤其涉及一种通信方法及装置。
背景技术
在无线通信网络中，例如在移动通信网络中，网络支持的业务越来越多样，因此需要满足的需求也越来越多样。例如，网络需要能够支持超高速率、超低时延、和/或超大连接，该特点使得网络规划、网络配置、和/或资源调度越来越复杂。此外，由于网络的功能越来越强大，例如支持的频谱越来越高、支持高阶多入多出(multiple input multiple output，MIMO)技术、支持波束赋形、和/或支持波束管理等新技术，使得网络节能成为了热门研究课题。这些新需求、新场景和新特性给网络规划、运维和高效运营带来了前所未有的挑战。为了迎接该挑战，可以将人工智能技术引入无线通信网络中，从而实现网络智能化。基于此，如何在网络中有效地实现人工智能是一个值得研究的问题。
发明内容
本公开提供一种通信方法及装置，以期提升定位性能。
第一方面，本公开提供一种通信方法，包括：
获取M个第一信道估计信息，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，M为大于1的正整数，m为取遍1至M的正整数；根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息，所述M个第二信道估计信息中的第m个第二信道估计信息对应所述第m个小区节点与所述终端设备之间的信道。
在上述设计中，基于终端设备或小区节点测量的第一信道估计信息，推导出第二信道估计信息。第二信道估计信息可用于训练定位相关的模型，这样的训练方式更适合实际场景环境，能够提升模型的性能，从而提升定位精度。可选的，第二信道估计信息用于指示以下至少一项：在直射路径(line of sight，LOS)条件下，所述第m个小区节点与所述终端设备之间的距离；在LOS条件下，所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；在LOS条件下，所述第m个小区节点对应的信号出发角度(angle of departure,AoD)或信号到达角度(angle of arrival，AoA)；在LOS条件下，所述第m个小区节点与所述终端设备之间的信号质量；或，所述第m个小区节点与所述终端设备之间的实际信号传输路径的类型，该路径类型为LOS或者非直射路径(non-line of sight，NLOS)。
在一种可能的设计中，所述第二信道估计信息用于模型的训练；其中，在进行所述模型的训练时，所述模型的输入是根据所述第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。基于测量的第一信道估计信息，推导可用作模型训练的标签数据，有助于提升模型的性能。
在一种可能的设计中，还包括：向第一设备发送K个第二信道估计信息，所述K个第二信道估计信息包含于所述M个第二信道估计信息，K为正整数。通过这样的设计，可以实现针对不同小区节点训练对应的模型，使得模型的训练及应用更为灵活。
在一种可能的设计中，还包括：从所述第一设备获取训练请求信息，所述训练请求信息用于请求所述K个第二信道估计信息。
在一种可能的设计中，所述训练请求信息用于指示所述第二信道估计信息指示的参数类型。通过这样的设计，指定第二信道估计信息指示的参数类型，降低由于额外的信息所造成的传输资源浪费，能够降低信令开销。
在一种可能的设计中，所述获取M个第一信道估计信息，包括：从第一设备获取所述第m个第一信道估计信息；其中，所述第一设备为所述第m个小区节点，或者所述第一设备为所述终端设备。
在一种可能的设计中，所述根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息，包括：根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定所述终端设备的第一位置；根据所述终端设备的第一位置和所述M个小区节点的位置，确定所述M个第二信道估计信息。
可选的，根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定所述终端设备的第一位置，包括：
根据所述M个第一信道估计信息和所述M个小区节点的位置，确定所述终端设备的多个第二位置。其中，所述多个第二位置中的第一部分位置位于第一区域，所述多个第二位置中的第二部分位置不位于所述第一区域，且所述第一部分位置的数量大于所述第二部分位置的数量；以及根据所述多个第二位置中的第一部分位置，确定所述终端设备的第一位置。或者，
根据N个第一信道估计信息和所述N个小区节点的位置，确定所述终端设备的第一位置；其中，N个第一信道估计信息与N个小区节点一一对应，所述N个小区节点包含于所述M个小区节点，N为小于或者等于M的正整数。所述N个小区节点中每个小区节点与所述终端设备之间的路径为直射路径。
通过这样的设计，基于第一信道估计信息，首先估算终端设备的可信位置(即第一位置)，再利用该可信位置，反推出可信的第二信道估计信息用于训练模型，有助于提升模型的性能。
在一种可能的设计中，所述第m个第一信道估计信息用于指示以下中的一个或多个参数：所述第m个小区节点与所述终端设备之间的距离；所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；所述第m个小区节点对应的信号出发角度或信号到达角度；所述第m个小区节点与所述终端设备之间的信号质量；所述第m个第一信道估计信息用于指示所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径或者非直射路径。
在一种可能的设计中，所述M个小区节点属于一个接入网设备，或者所述M个小区节点中至少两个小区节点所属的接入网设备不同。
第二方面，本公开提供一种通信方法，包括：
发送第m个第一信道估计信息，所述第m个第一信道估计信息属于M个第一信道估计信息，M为大于1的正整数，m为取遍1至M的正整数，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，所述M个第一信道估计信息中的至少一个第一信道估计信息用于确定M个第二信道估计信息，所述M个第二信道估计信息中第m个第二信道估计信息对应所述第m个小区节点与所述终端设备之间的信道；
获取用于指示模型的信息；其中，在进行所述模型的训练时，所述模型的输入是根据所述第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
在一种可能的设计中，还包括：发送所述第m个小区节点与终端设备之间的信道的信道信息。
关于第一信道估计信息指示的参数以及M个小区节点的定位可参照第一方面的描述，本公开对此不再进行赘述。
第三方面，本公开提供一种通信方法，包括：
确定K个信道信息，其中，所述K个信道信息中的第k个信道信息是K个小区节点中第k个小区节点与终端设备之间的信道的信道信息；其中，K为正整数，k为取遍1至K的正整数；
获取K个第二信道估计信息，所述K个第二信道估计信息中第k个第二信道估计信息对应所述第k个小区节点与所述终端设备之间的信道，所述K个第二信道估计信息由M个第一信道估计信息中的至少一个第一信道估计信息确定，其中，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区中第m个小区节点与所述终端设备之间的信道的估计信息，所述K个小区包含于所述M个小区，M为大于1的正整数，m取遍1至M的正整数；
根据所述K个第二信道估计信息，进行模型的训练；其中，在进行所述模型的训练时，所述模型的输入是根据所述第k个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第k个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
在一种可能的设计中，还包括：发送训练请求信息，所述训练请求信息用于请求所述K个第二信道估计信息。
在一种可能的设计中，所述训练请求信息用于指示所述第二信道估计信息指示的参数类型。
在一种可能的设计中，还包括：发送所述第m个小区节点与所述终端设备之间的信道的第一信道估计信息。
关于第一信道估计信息指示的参数以及M个小区节点的定位可参照第一方面的描述，本公开对此不再进行赘述。
第四方面，本公开提供一种通信方法，包括：
确定第t个信道信息，其中，所述第t个信道信息是T个小区节点中第t个小区节点与 终端设备之间的信道的信道信息；其中，T为大于1的正整数，t为取遍1至T的正整数；
根据所述第t个信道信息和模型，确定第t个第三信道估计信息，所述第t个第三信道估计信息对应所述第t个小区节点与所述终端设备之间的信道；其中，所述模型的输入是根据所述第t个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的输出包括所述第t个第三信道估计信息；
发送所述第t个第三信道估计信息，所述第t个第三信道估计信息用于对所述终端设备进行定位。可选地，T和上述M的取值可以相同，也可以不同，不予限制。
在一种可能的设计中，所述第t个第三信道估计信息用于指示如下的一个或多个参数：所述第t个小区节点与所述终端设备之间的LOS长度距离；所述第t个小区节点与所述终端设备之间符合LOS传输的信号传输时延或信道传输时延差；所述第t个小区节点对应的符合LOS传输的信号出发角度或信号到达角度；所述第t个小区节点与所述终端设备之间符合LOS传输的信号质量；所述第t个小区节点与所述终端设备之间的实际信号传输路径的类型；或，所述第t个小区节点与所述终端设备之间的实际信号传输路径的类型，其中，所述类型为LOS或NLOS。
通过这样的设计，可以实现利用模型得到符合LOS传输的测量量，和/或者利用模型识别终端设备与小区节点之间的信号传输路径。应用于定位场景，能够提升定位精度。
在一种可选的设计中，在进行所述模型的训练时，所述模型的输入是根据M个小区节点中第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
其中，所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息是由M个第一信道估计信息中的至少一个第一信道估计信息确定的，所述M个第一信道估计信息中第m个第一信道估计信息是所述M个小区节点中第m个小区节点与终端设备之间的信道的估计信息。
第五方面，本公开提供一种通信装置，该通信装置可以是位置管理服务功能(location management function，LMF)网元，如下简称LMF；也可以是LMF中的装置，或者是能够和LMF匹配使用的装置。一种设计中，该通信装置可以包括执行第一方面中所描述的方法/操作/步骤/动作所一一对应的模块，该模块可以是硬件电路，也可是软件，也可以是硬件电路结合软件实现。一种设计中，该通信装置可以包括处理模块和通信模块。
一种示例：
通信模块，用于获取M个第一信道估计信息，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，M为大于1的正整数，m为取遍1至M的正整数；
处理模块，用于根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息，所述M个第二信道估计信息中的第m个第二信道估计信息对应所述第m个小区节点与所述终端设备之间的信道。
关于第二信道估计信息的定义可参照第一方面的描述，本公开对此不再进行赘述。
在一种可能的设计中，通信模块，还用于向第一设备发送K个第二信道估计信息，所述K个第二信道估计信息包含于所述M个第二信道估计信息，K为正整数。
在一种可能的设计中，通信模块，还用于从所述第一设备获取训练请求信息，所述训练请求信息用于请求所述K个第二信道估计信息。
在一种可能的设计中，所述训练请求信息用于指示所述第二信道估计信息指示的参数类型。
在一种可能的设计中，通信模块，还用于从第一设备获取所述第m个第一信道估计信息；其中，所述第一设备为所述第m个小区节点，或者所述第一设备为所述终端设备。
在一种可能的设计中，所述处理模块，具体用于：根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定所述终端设备的第一位置；根据所述终端设备的第一位置和所述M个小区节点的位置，确定所述M个第二信道估计信息。
关于第一信道估计信息指示的参数以及M个小区节点的定位可参照第一方面的描述，本公开对此不再进行赘述。
第六方面，本公开提供一种通信装置，该通信装置可以是为终端设备或者第m个小区节点，也可以是终端设备或者第m个小区节点中的装置，或者是能够和终端设备匹配使用的装置，或者能够和第m个小区节点匹配使用的装置。一种设计中，该通信装置可以包括执行第二方面中所描述的方法/操作/步骤/动作所一一对应的模块，该模块可以是硬件电路，也可是软件，也可以是硬件电路结合软件实现。一种设计中，该通信装置可以包括处理模块和通信模块。
一种示例：
处理模块，用于通过通信模块发送第m个第一信道估计信息，所述第m个第一信道估计信息属于M个第一信道估计信息，M为大于1的正整数，m为取遍1至M的正整数，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，所述M个第一信道估计信息中的至少一个第一信道估计信息用于确定M个第二信道估计信息，所述M个第二信道估计信息中第m个第二信道估计信息对应所述第m个小区节点与所述终端设备之间的信道；
通信模块，用于获取用于指示模型的信息；其中，在进行所述模型的训练时，所述模型的输入是根据所述第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
在一种可能的设计中，处理模块，还用于通过通信模块发送所述第m个小区节点与终端设备之间的信道的信道信息。
关于第一信道估计信息指示的参数以及M个小区节点的定位可参照第一方面的描述，本公开对此不再进行赘述。
第七方面，本公开提供一种通信装置，该通信装置可以是模型训练节点，如终端设备、第m个小区节点或人工智能(artificial Intelligence，AI)网元，也可以是模型训练节点中的装置，或者是能够和模型训练节点匹配使用的装置。一种设计中，该通信装置可以包括执行第三方面中所描述的方法/操作/步骤/动作所一一对应的模块，该模块可以是硬件电路，也可是软件，也可以是硬件电路结合软件实现。一种设计中，该通信装置可以包括处理模块和通信模块。
一种示例：
处理模块，用于确定K个信道信息，其中，所述K个信道信息中的第k个信道信息是K个小区节点中第k个小区节点与终端设备之间的信道的信道信息；其中，K为正整数，k为取遍1至K的正整数；
通信模块，用于获取K个第二信道估计信息，所述K个第二信道估计信息中第k个第二信道估计信息对应所述第k个小区节点与所述终端设备之间的信道，所述K个第二信道估计信息由M个第一信道估计信息中的至少一个第一信道估计信息确定，其中，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区中第m个小区节点与所述终端设备之间的信道的估计信息，所述K个小区包含于所述M个小区，M为大于1的正整数，m取遍1至M的正整数；
处理模块，还用于根据所述K个第二信道估计信息，进行模型的训练；其中，在进行所述模型的训练时，所述模型的输入是根据所述第k个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第k个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
在一种可能的设计中，通信模块，还用于发送训练请求信息，所述训练请求信息用于请求所述K个第二信道估计信息。
在一种可能的设计中，所述训练请求信息用于指示所述第二信道估计信息指示的参数类型。
在一种可能的设计中，通信模块，还用于发送所述第m个小区节点与所述终端设备之间的信道的第一信道估计信息。
关于第一信道估计信息指示的参数以及M个小区节点的定位可参照第一方面的描述，本公开对此不再进行赘述。
第八方面，本公开提供一种通信装置，该通信装置可以是终端设备或第t个小区节点。也可以是终端设备或第t个小区节点中的装置，或者是能够和终端设备匹配使用的装置，能够和第t个小区节点匹配使用的装置。一种设计中，该通信装置可以包括执行第四方面中所描述的方法/操作/步骤/动作所一一对应的模块，该模块可以是硬件电路，也可是软件，也可以是硬件电路结合软件实现。一种设计中，该通信装置可以包括处理模块和通信模块。
一种示例：
处理模块，用于确定第t个信道信息，其中，所述第t个信道信息是T个小区节点中第t个小区节点与终端设备之间的信道的信道信息；其中，T为大于1的正整数，m为取遍1至T的正整数；
处理模块，还用于根据所述第t个信道信息和模型，确定第t个第三信道估计信息，所述第t个第三信道估计信息对应所述第t个小区节点与所述终端设备之间的信道；其中，所述模型的输入是根据所述第t个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的输出包括所述第t个第三信道估计信息；
通信模块，用于发送所述第t个第三信道估计信息，所述第t个第三信道估计信息用于对所述终端设备进行定位。可选地，T和上述M的取值可以相同，也可以不同，不予限制。
在一种可能的设计中，通信模块，还用于获取用于指示所述模型的信息。
关于第三信道估计信息以及模型的定义可参照第四方面的描述，本公开对此不再进行赘述。
第九方面，本公开提供一种通信装置，所述通信装置包括处理器，用于实现上述第一方面所描述的方法。处理器与存储器耦合，存储器用于存储指令和数据，所述处理器执行所述存储器中存储的指令时，可以实现上述第一方面描述的方法。可选的，所述通信装置 还可以包括存储器；所述通信装置还可以包括通信接口，所述通信接口用于该装置与其它设备进行通信，示例性的，通信接口可以是收发器、电路、总线、模块、管脚或其它类型的通信接口。
在一种可能的设备中，该通信装置包括：
存储器，用于存储程序指令；
处理器，用于利用通信接口获取M个第一信道估计信息，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，M为大于1的正整数，m为取遍1至M的正整数；以及根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息，所述M个第二信道估计信息中的第m个第二信道估计信息对应所述第m个小区节点与所述终端设备之间的信道。
第十方面，本公开提供一种通信装置，所述通信装置包括处理器，用于实现上述第二方面至第四方面中任一方面所描述的方法。处理器与存储器耦合，存储器用于存储指令和数据，所述处理器执行所述存储器中存储的指令时，可以实现上述第二方面至第四方面中任一方面描述的方法。可选的，所述通信装置还可以包括存储器；所述通信装置还可以包括通信接口，所述通信接口用于该装置与其它设备进行通信，示例性的，通信接口可以是收发器、电路、总线、模块、管脚或其它类型的通信接口。
在第一种可能的设备中，该通信装置包括：
存储器，用于存储程序指令；
处理器，用于利用通信接口发送第m个第一信道估计信息，所述第m个第一信道估计信息属于M个第一信道估计信息，M为大于1的正整数，m为取遍1至M的正整数，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，所述M个第一信道估计信息中的至少一个第一信道估计信息用于确定M个第二信道估计信息，所述M个第二信道估计信息中第m个第二信道估计信息对应所述第m个小区节点与所述终端设备之间的信道；
以及，利用通信接口获取用于指示模型的信息；其中，在进行所述模型的训练时，所述模型的输入是根据所述第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
在第二种可能的设备中，该通信装置包括：
存储器，用于存储程序指令；
处理器，用于确定K个信道信息，其中，所述K个信道信息中的第k个信道信息是K个小区节点中第k个小区节点与终端设备之间的信道的信道信息；其中，K为正整数，k为取遍1至K的正整数；
处理器，还用于利用通信接口获取K个第二信道估计信息，所述K个第二信道估计信息中第k个第二信道估计信息对应所述第k个小区节点与所述终端设备之间的信道，所述K个第二信道估计信息由M个第一信道估计信息中的至少一个第一信道估计信息确定，其中，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区中第m个小区节点与所述终端设备之间的信道的估计信息，所述K个小区包含于所述M个小区，M为大于1的正整数，m取遍1至M的正整数；
处理器，还用于根据所述K个第二信道估计信息，进行模型的训练；其中，在进行所述模型的训练时，所述模型的输入是根据所述第k个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第k个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
在第三种可能的设备中，该通信装置包括：
存储器，用于存储程序指令；
处理器，用于：
确定第t个信道信息，其中，所述第t个信道信息是T个小区节点中第t个小区节点与终端设备之间的信道的信道信息；其中，T为大于1的正整数，t为取遍1至T的正整数；
根据所述第t个信道信息和模型，确定第t个第三信道估计信息，所述第t个第三信道估计信息对应所述第t个小区节点与所述终端设备之间的信道；其中，所述模型的输入是根据所述第t个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的输出包括所述第t个第三信道估计信息；
以及利用通信接口发送所述第t个第三信道估计信息，所述第t个第三信道估计信息用于对所述终端设备进行定位。
第十一方面，本公开提供了一种通信系统，包括如第五方面或第九方面中所描述的通信装置；以及如第六方面、第七方面、第八方面中至少一方面所描述的通信装置；
或者，包括如第五方面或第九方面中所描述的通信装置；以及如第十方面所描述的通信装置。
第十二方面，本公开还提供了一种计算机程序，当所述计算机程序在计算机上运行时，使得所述计算机执行上述第一方面至第四方面中任一方面提供的方法。
第十三方面，本公开还提供了一种计算机程序产品，包括指令，当所述指令在计算机上运行时，使得计算机执行上述第一方面至第四方面中任一方面提供的方法。
第十四方面，本公开还提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序或指令，当所述计算机程序或者指令在计算机上运行时，使得所述计算机执行上述第一方面至第四方面中任一方面提供的方法。
第十五方面，本公开还提供了一种芯片，所述芯片用于读取存储器中存储的计算机程序，执行上述第一方面至第四方面中任一方面提供的方法。
第十六方面，本公开还提供了一种芯片系统，该芯片系统包括处理器，用于支持计算机装置实现上述第一方面至第四方面中任一方面提供的方法。在一种可能的设计中，所述芯片系统还包括存储器，所述存储器用于保存该计算机装置必要的程序和数据。该芯片系统可以由芯片构成，也可以包含芯片和其他分立器件。
附图说明
图1A为本公开提供的通信系统的结构示意图之一；
图1B为本公开提供的通信系统的结构示意图之一；
图1C为本公开提供的通信系统的结构示意图之一；
图2为一种基于TDOA的定位方法的原理示意图；
图3为一种时域信道响应示意图；
图4为一种信号传输路径的结构示意图；
图5为本公开提供的通信系统的结构示意图之一；
图6A为神经元结构的一种示意图；
图6B为神经网络的层关系的一种示意图；
图7为本公开提供的一种模型训练框架的示意图；
图8为本公开提供的通信方法的流程示意图之一；
图9为一种位置分布示意图；
图10为本公开提供的一种基于模型的定位方法的流程示意图；
图11为本公开提供的通信方法的流程示意图之一；
图12为本公开提供的通信方法的流程示意图之一；
图13为本公开提供的通信装置的结构示意图之一；
图14为本公开提供的通信装置的结构示意图之一。
具体实施方式
为了使本公开的目的、技术方案和优点更加清楚，下面将结合附图对本公开作进一步地详细描述。
本公开如下涉及的至少一个(项)，指示一个(项)或多个(项)。多个(项)，是指两个(项)或两个(项)以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。另外，应当理解，尽管在本公开中可能采用术语第一、第二等来描述各对象、但这些对象不应限于这些术语。这些术语仅用来将各对象彼此区分开。
本公开如下描述中所提到的术语“包括”和“具有”以及它们的任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括其他没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。需要说明的是，本公开中，“示例性的”或者“例如”等词用于表示作例子、例证或说明。本公开中被描述为“示例性的”或者“例如”的任何方法或设计方案不应被解释为比其它方法或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。
本公开提供的技术可以应用于各种通信系统，例如，该通信系统可以是第三代(3th generation，3G)通信系统(例如通用移动通信系统(universal mobile telecommunication system，UMTS))、第四代(4th generation，4G)通信系统(例如长期演进(long term evolution，LTE)系统)、第五代(5th generation，5G)通信系统、全球互联微波接入(worldwide interoperability for microwave access，WiMAX)或者无线局域网(wireless local area network，WLAN)系统、或者多种系统的融合系统，或者是未来的通信系统，例如第六代(6th generation，6G)通信系统等。其中，5G通信系统还可以称为新无线(new radio，NR)系统。通信系统中的一个网元可以向另一个网元发送信号或从另一个网元接收信号。其中信号可以包括信息、信令或者数据等。其中，网元也可以被替换为实体、网络实体、设备、通信设备、通信模块、节点、通信节点等等，本公开中以网元为例进行描述。
例如，通信系统可以包括至少一个终端设备和至少一个接入网设备，接入网设备可以向终端设备发送下行信号，和/或终端设备可以向接入网设备发送上行信号。此外可以理解 的是，若通信系统中包括多个终端设备，多个终端设备之间也可以互发信号，即信号的发送网元和信号的接收网元均可以是终端设备。
参见图1A示意一种通信系统100，作为示例，该通信系统100包括接入网设备110、接入网设备120、接入网设备130以及终端设备140。终端设备140可以发送上行信号给接入网设备110、接入网设备120以及接入网设备130中一个或多个接入网设备。接入网设备110、接入网设备120以及接入网设备130中一个或多个接入网设备可以向终端设备140发送下行信号。
下面对图1A所涉及的终端设备和接入网设备进行详细说明。
(1)接入网设备
接入网设备可以为基站(base station，BS)。接入网设备还可以称为网络设备、接入节点(access node，AN)、无线接入节点(radio access node，RAN)。其中，基站可能有多种形式，比如宏基站、微基站、中继站或接入点等。接入网设备可以与核心网(如LTE的核心网或者5G的核心网等)连接，接入网设备可以为终端设备提供无线接入服务。接入网设备例如包括但不限于以下至少一个：5G中的基站，如发送接收点(Transmission Reception Point，TRP)或下一代节点B(generation nodeB，gNB)、开放无线接入网(open radio access network，O-RAN)中的接入网设备或者接入网设备包括的模块、演进型节点B(evolved node B，eNB)、无线网络控制器(radio network controller，RNC)、节点B(node B，NB)、基站控制器(base station controller，BSC)、基站收发台(base transceiver station，BTS)、家庭基站(例如，home evolved nodeB，或home node B，HNB)、基带单元(base band unit，BBU)、收发点(transmitting and receiving point，TRP)、发射点(transmitting point，TP)、和/或移动交换中心等。或者，接入网设备还可以是无线单元(radio unit，RU)、集中单元(centralized unit，CU)、分布单元(distributed unit,DU)、集中单元控制面(CU control plane，CU-CP)节点、或集中单元用户面(CU user plane，CU-UP)节点。或者，接入网设备可以为车载设备、可穿戴设备或者未来演进的公共陆地移动网络(public land mobile network，PLMN)中的接入网设备等。
本公开中，用于实现接入网设备功能的通信装置可以是接入网设备，也可以是具有接入网设备部分功能的网络设备，也可以是能够支持接入网设备实现该功能的装置，例如芯片系统，硬件电路、软件模块、或硬件电路加软件模块，该装置可以被安装在接入网设备中或者和接入网设备匹配使用。本公开的方法中，以用于实现接入网设备功能的通信装置是接入网设备为例进行描述。
(2)终端设备
终端设备又称之为终端、用户设备(user equipment，UE)、移动台(mobile station，MS)、移动终端(mobile terminal，MT)等。终端设备可以是一种向用户提供语音和/或数据连通性的设备。终端设备可通过接入网设备与一个或多个核心网进行通信。终端设备可以被部署在陆地上，包括室内、室外、手持、和/或车载；也可以被部署在水面上(如轮船等)；还可以被部署在空中(例如飞机、气球和卫星上等)。终端设备包括具有无线连接功能的手持式设备、连接到无线调制解调器的其他处理设备或车载设备等。终端设备可以是便携式、袖珍式、手持式、计算机内置的或者车载的移动装置。一些终端设备的举例为：个人通信业务(personal communication service，PCS)电话、无绳电话、会话发起协议(session initiation protocol，SIP)话机、无线本地环路(wireless local loop，WLL)站、个人数字助 理(personal digital assistant，PDA)、无线网络摄像头、手机(mobile phone)、平板电脑、笔记本电脑、掌上电脑、移动互联网设备(mobile internet device，MID)、可穿戴设备如智能手表、虚拟现实(virtual reality，VR)设备、增强现实(augmented reality，AR)设备、工业控制(industrial control)中的无线终端、车联网系统中的终端、无人驾驶(self driving)中的无线终端、智能电网(smart grid)中的无线终端、运输安全(transportation safety)中的无线终端、智慧城市(smart city)中的无线终端如智能加油器，高铁上的终端设备以及智慧家庭(smart home)中的无线终端，如智能音响、智能咖啡机、智能打印机等。
本公开中，用于实现终端设备功能的通信装置可以是终端设备，也可以是具有终端部分功能的终端设备，也可以是能够支持终端设备实现该功能的装置，例如芯片系统，该装置可以被安装在终端设备中或者和终端设备匹配使用。本公开中，芯片系统可以由芯片构成，也可以包括芯片和其他分立器件。本公开提供的技术方案中，以用于实现终端设备功能的通信装置是终端设备或UE为例进行描述。
应理解，图1A所示的通信系统中各个设备的数量、类型仅作为示意，本公开并不限于此，实际应用中在通信系统中还可以包括更多的终端设备、更多的接入网设备，还可以包括其它网元，例如可以包括和核心网网元、和/或用于实现人工智能功能的网元。
本公开提供的方法涉及对终端设备的定位技术，参见图1B，在上述图1A所示的通信系统中引入了定位服务器150，该定位服务器150用于估算终端设备的位置。在对终端设备进行定位的场景中，定位服务器可以对终端设备和固定(即已知位置)的接入网设备之间的特征参数进行检测，获取终端设备和接入网设备之间的相对位置或角度信息，从而对终端设备的位置进行估算。其中，一些特征参数举例包括以下一项或多项：信号质量、距离、信号传输时延(或称信号传播时间)或者信号传输时延差、信号出发角度、或信号到达角度等；其中，信号质量可以由信噪比、信号强度、信号场强、信号能量、信号接收功率等中的一项或多项指标体现。
具体地，图1B中的定位服务器可以由位置管理服务功能(location management function，LMF)网元实现。参见图1C示意的一种通信系统，该通信系统中包括接入网设备、终端设备之外，以及核心网网元，如接入和移动管理功能(access and mobility management function，AMF)网元和位置管理服务功能(location management function，LMF)网元。在图1C示意的通信系统中，接入网设备可以是同一制式下的基站，也可以是不同网络制式下的基站。例如，图1C示意出一个5G基站，如gNB；以及一个可以接入5G核心网的4G基站，如ng-eNB。终端设备(图1C中以UE表示)和gNB之间可以通过NR-Uu接口进行通信，如利用NR-Uu接口传输定位相关的信令。终端设备和ng-eNB之间通过LTE-Uu接口进行通信，如利用LTE-Uu接口传输定位相关的信令。gNB和AMF之间通过NG-C接口进行通信，ng-eNB和AMF之间通过NG-C接口进行通信，例如NG-C接口可以用于传输定位相关的信令。AMF和LMF之间通过NL1接口进行通信，例如利用NL1接口传输定位相关的信令。
具体地，终端设备或者接入网设备中的一方发送参考信号；另一方测量参考信号获取信道信息，并根据该信道信息可以确定终端设备和接入网设备之间的特征参数，特征参数也可以被称为测量量，进而向LMF上报测量量。例如在下行定位场景中，接入网设备或者接入网设备在小区中向终端设备发送定位参考信号(positioning reference signal，PRS)，终端设备测量PRS获取下行信道信息，进而终端设备根据该下行信道信息确定测量量，并 将测量量上报给LMF用于终端设备的定位。例如在上行定位场景中，终端设备可以向接入网设备或在小区中向接入网设备发送探测参考信号(sounding reference signal，SRS)，接入网设备测量SRS获取上行信道信息，进而接入网设备根据该上行信道信息确定测量量，并将测量量上报给LMF用于终端设备的定位。
下面举例介绍一些定位方法：
一种基于到达时间差(time difference of arrival，TDOA)的定位方法，可以利用同步的至少三个接入网设备的位置对终端设备进行定位。如图2所示，三个接入网设备分别标记为eNB1、eNB2、eNB3，该3个接入网设备和终端设备之间的距离分别为d1、d2、d3，对应信号的传播时间分别为t1、t2、t3。例如，3个接入网设备分别向终端设备发送PRS，分别记为P1，P2，和P3。可以设定eNB1为参考节点，终端设备可以测量P2和P1的到达时间差，即t2-t1，也称为参考信号时间差(reference signal time difference,RSTD)。终端设备利用t2-t1可以推断出d2-d1，并获得一条曲线使得该曲线上的每个点都满足到eNB2和eNB1的距离差为d2-d1；类似地，终端设备可以测量P3和P1的到达时间差，即t3-t1，利用t3-t1可以推断出d3-d1，并获得另一条曲线满足该曲线上的每个点都满足到eNB3和eNB1的距离差为d3-d1。终端设备利用上述两个曲线的交点，即可以确定自身的位置。或者，终端设备可以将不同接入网设备与终端设备之间的信号传播时间、到达时间差、距离或者推断的距离差中的至少一个参数上报给LMF，则LMF可以确定上述两个曲线，以及两个曲线的交点，从而确定终端设备的位置。另外，由于不同接入网设备之间存在一定的同步误差，对应获取的到达时间差可以表示为一个区间范围，如对应图2示意曲线所处的区间以虚线表示，得到终端设备的位置处于两曲线所在区间之间的重叠部分。
具体地，可采用如下公式计算终端设备的位置：
其中，(xi,yi)表示eNBi的位置坐标，i的取值为1、2或者3；(x,y)表示待求终端设备的位置坐标，c表示光速。
上述描述的基于TDOA的定位方法，是根据接入网设备向终端设备发送PRS来进行定位，这种定位方法也可以称为下行-TODA(downlink-TODA，DL-TDOA)或观察到达时间差(observed time difference of arrival，OTDOA)。类似地，如果基于TDOA的定位方法是根据终端设备向接入网设备发送SRS来进行定位的方法，那么这种定位方法也可以称为上行-TODA(uplink-TODA，UL-TDOA)。
一种基于信号到达角度(angle of arrival,AoA)或信号出发角度(angle of departure,AoD)的定位方法，可以利用同步的至少两个接入网设备的位置对终端设备进行定位。其中，这里的信号是接入网设备和终端设备之间传输的信号，AoA以及AoD均为相当于接入网设备来说的角度。即在根据接入网设备向终端设备发送PRS进行定位的场景中，可以由至少两个接入网设备向终端设备发送PRS，终端设备测量不同接入网设备发送的PRS确定各个接入网设备所对应的AoD，或者确定各个接入网设备对应的AoD与AoD参考值之间的角度差值。可选的，AoD参考值可以是至少两个接入网设备中一个接入网设备对应的AoD，或预设的AoD。终端设备将至少两个接入网设备对应的AoD或者角度差值上报给LMF，LMF可以根据至少两个接入网设备对应的AoD或者角度差值，确定终端设备的位置。在 根据终端设备向接入网设备发送SRS进行定位的场景中，可以由终端设备向至少两个接入网设备发送SRS，不同接入网设备测量来自终端设备的SRS确定各个接入网设备所对应的AoA，或者确定各个接入网设备对应的AoA与AoA参考值之间的角度差值。可选的，AoA参考值可以是至少两个接入网设备中一个接入网设备对应的AoA，或预设的AoA。各个接入网设备将自身对应的AoA或者角度差值上报给LMF，LMF可以根据至少两个接入网设备对应的AoA或者角度差值，确定终端设备的位置。
在实施上述定位方法时，LMF可以预先与终端设备或接入网设备交互定位配置信息，确定待定位的终端设备，参与终端设备定位的接入网设备，以及定位技术相关的配置。作为示例，定位技术相关的配置可以指示对终端设备定位所使用的定位方法、测量的参考信号是下行定位对应的PRS还是上行定位对应的SRS、和/或用于定位的测量量等。下面以DL-TDOA方法为例，介绍可以用于5G系统中的基于LTE定位协议(LTE positioning protocol,LPP)的定位流程。其中，LPP协议规定了终端设备和LMF之间交互信息的流程，即终端设备和LMF之间可以通过LPP消息交互信息。需要说明的是，按照终端设备-接入网设备-AMF-LMF的方式相连，LPP消息可以跨接入网设备和AMF进行透明传输实现终端设备和LMF之间的交互。
首先，终端设备和LMF交互定位配置信息。定位配置信息包括定位能力和定位辅助信息。这个过程可以是LMF或者终端设备触发。例如，当LMF触发定位辅助信息传输时，LMF决定需要提供给终端设备的定位辅助信息，并且向终端设备发送一条LPP提供辅助数据(LPP Provide Assistance Data)消息。又如，当终端设备触发定位辅助信息传输时，终端设备首先确定需要的定位辅助信息，并向LMF发送一条LPP请求辅助数据(LPP Request Assistance Data)消息，该LPP请求辅助数据消息可以用于指示终端设备需要的定位辅助信息。LMF向终端设备发送LPP提供辅助数据消息，以提供终端设备需要的定位辅助信息。其中，定位能力表示终端设备的以下至少一项内容：支持的定位方法、采用的协议和流程、可配置的参数等信息；定位辅助信息包括以下一个或多个参数：终端设备所在的物理小区的标识(identity，ID)、全局小区ID、接入网设备的ID、接入网设备的PRS配置、接入网设备的同步信号块(synchronization signal/physical broadcast channel block，SSB)信息、PRS的空间方向信息、接入网设备的地理位置坐标、接入网设备和参考节点的时间差等信息。
其次，终端设备和LMF交互定位信息，即将终端设备测量各个接入网设备发送的PRS确定的测量量(或称，定位测量结果)反馈给LMF，这个过程可以由终端设备或LMF触发。例如，当LMF触发定位信息交互时，LMF向终端设备发送LPP请求定位信息(LPP Request Location Information)消息，该LPP请求定位信息消息用于指示LMF需要的定位测量结果，测量配置信息，和/或要求的响应时间等信息。然后，终端设备在要求的响应时间之前向LMF发送LPP提供定位信息(LPP Provide Location Information)消息，以反馈测量量。当终端设备触发定位信息交互时，终端设备向LMF发送LPP提供定位信息消息，以反馈测量量。其中，测量量可以包括PRS的到达时间戳、PRS的传播时间、PRS对应的到达时间差、或PRS的接收信号功率等一项或多项信息。此外，测量量还可以包括用于标识接入网设备的信息，例如包括各测量量对应的物理小区ID、全局小区ID、和/或接入网设备ID等。
除了终端设备和LMF之间需要交互定位辅助信息和定位信息以外，接入网设备和 LMF之间也可以交互一些定位辅助信息。通常由LMF触发接入网设备和LMF之间交互定位辅助信息，相关流程可以参见但不限于NR定位协议A(NR positioning protocol A,NRPPa)的规定，接入网设备与LMF之间通过AMF相连，NRPPa协议对于AMF是透明的，NRPPa数据单元跨AMF透明传输使得接入网设备和LMF实现交互。接入网设备的定位辅助信息包括物理小区ID、全局小区ID、接入网设备的ID、接入网设备的PRS配置、接入网设备的SSB信息、PRS的空间方向信息、或接入网设备的地理位置坐标等一项或多项参数。LMF向接入网设备发送TRP信息请求(TRP Information Request)消息，TRP信息请求消息用于请求LMF需要的接入网设备的定位辅助信息，接入网设备向LMF发送TRP信息响应(TRP Information Response)消息，TRP信息响应消息用于指示LMF需要的接入网设备的定位辅助信息，或者接入网设备向LMF发送TRP信息失败(TRP Information Failure)消息，TRP信息失败消息用于指示失败原因。
在实际场景下，由于噪声和干扰的影响，测量参考信号确定的信号传播时间或者相关角度可能存在一定的测量误差，对应的定位结果也会存在一定误差。例如，图3示意了测量参考信号得到的时域信道响应在不同时域采样点上的功率|h(t)|^2。如图3所示，开始一段时域采样点的信号功率较弱，对应的是噪声信号；中间有一段时域采样点的信号功率较强，对应的是实际信号的多径响应。即实际场景下，需要在存在干扰和噪声的环境下判断实际信号的起始位置，从而获得准确的信号传播时间或相关角度。确定实际信号的起始位置也称为首径识别问题。此外，如果测量的参考信号是由非直射路径(non-line of sight,NLOS)传播的信号，会对终端设备的定位造成较大的估计误差。因此一般要求测量的参考信号是由直射路径(line of sight,LOS)传播的信号。其中，接入网设备和终端设备之间的NLOS是指接入网设备和终端设备之间存在障碍物，使得信号不能直射传播。接入网设备和终端设备之间的LOS是指接入网设备和终端设备之间的信号是直射传播。如图4示意，eNB和UE之间的LOS(虚线)被树木遮挡，实际到达的是经过墙面反射的NLOS(实线)，NLOS的距离(d2+d3)大于LOS的距离(d1)。如果在进行终端设备的定位时，将NLOS误认为是LOS，可能出现较大的测量误差。由此可见，LOS和NLOS的分类对于终端设备的定位十分重要。
对此，本公开利用人工智能(artificial Intelligence，AI)技术进行首径识别，根据获取的信道信息推导符合LOS传播的测量量，从而减少测量误差，提升定位精度。其中，AI可以通过各种可能的技术实现，例如通过机器学习(machine learning，ML)技术实现。在本公开中，前述通信系统也可以包括实现AI功能的网元。例如，可以在通信系统中已有网元内配置AI功能(如AI模块或者AI实体)来实现AI相关的操作。例如在5G新无线(new radio，NR)系统中，该已有网元可以是接入网设备(如gNB)、终端设备、核心网设备、或网管等。或者，也可以在通信系统中引入独立的网元来执行AI相关的操作。该独立的网元可以称为AI网元或者AI节点等，本公开对此名称不进行限制。在这种情况下，执行AI相关的操作的网元为内置AI功能(如AI模块或者AI实体)的网元。AI相关的操作还可以称为AI功能。AI功能的具体介绍请参见下文。AI网元可以与前述通信系统中包括的网元，如终端设备、接入网设备、核心网网元等建立通信连接。示例性的，参见图5，通信系统中包括终端设备、接入网设备、AMF网元、LMF网元，引入AI网元可以与终端设备、接入网设备、AMF网元、LMF网元之间建立直接或间接的通信连接。
为了便于理解，下面首先结合A1～A4，对本公开涉及的AI的部分用语进行介绍。 可以理解的是，该介绍并不作为对本公开的限定。
A1，AI模型
AI模型是AI功能的具体实现，AI模型表征了模型的输入和输出之间的映射关系，可以指将某种维度的输入映射到某种维度的输出的函数模型。AI模型可以是神经网络或者其他机器学习模型，如决策树、支持向量机等。本公开中，可以将AI模型简称为模型。本公开中，AI功能可以包括以下至少一项：数据收集(收集训练数据和/或推理数据)、数据预处理、模型训练(或称，模型学习)、模型检测、模型信息发布(配置模型信息)、模型推理、或推理结果发布。其中，推理又可以称为预测。模型检测可以用于检测训练得到的模型是否满足需求。本公开中，可以将AI模型简称为模型。
A2，机器学习
机器学习是实现人工智能的一种重要技术途径，如机器学习可以从原始数据中学习模型或规则，机器学习分为监督学习、非监督学习、强化学习。
监督学习依据已采集到的样本(或称样本值)和样本标签，利用机器学习算法学习样本到样本标签的映射关系，并用机器学习模型来表达学到的映射关系。训练机器学习模型的过程就是学习这种映射关系的过程。如信号检测中，样本为含噪声的接收信号，样本标签为该接收信号对应的真实星座点，机器学习期望通过训练学到样本与样本标签之间的映射关系。在训练时，通过计算模型的输出(即预测值)与样本标签的误差来优化模型参数。映射关系学习完成后，可以利用学到的映射关系来预测新样本的样本标签。监督学习学到的映射关系可以包括线性映射、非线性映射。根据样本标签的类型可将机器学习的任务分为分类任务和回归任务。
无监督学习依据采集到的样本，利用算法自行发掘样本的内在模式。无监督学习中有一类算法(如自编码器、对抗生成型网络等)可以将样本自身作为监督信号，模型学习从样本到样本的映射关系，训练时，通过计算模型的预测值与样本本身之间的误差来优化模型参数，实现自监督学习。自监督学习可用于信号压缩及解压恢复的应用场景。
强化学习是一类通过与环境交互来学习解决问题的策略的算法。与监督学习、无监督学习不同，强化学习并没有明确的样本标签，算法需要与环境进行交互，获取环境反馈的奖励信号，进而调整决策动作以获得更大的奖励信号数值。如在下行功率控制中，强化学习模型根据无线网络反馈的系统总吞吐率，调整各个终端的下行发送功率，进而期望获得更高的系统吞吐率。强化学习的目标也是学习环境状态与最优决策动作之间的映射关系。强化学习的训练是通过与环境的迭代交互而实现的。
A3，神经网络
神经网络是AI或机器学习技术的一种具体实现形式。根据通用近似定理，神经网络在理论上可以逼近任意连续函数，从而使得神经网络具备学习任意映射的能力。传统的通信系统需要借助丰富的专家知识来设计通信模块，而基于神经网络的深度学习通信系统可以从大量的数据集中自动发现隐含的模式结构，建立数据之间的映射关系，获得优于传统建模方法的性能。
神经网络的思想来源于大脑组织的神经元结构。例如，每个神经元都对其输入值进行加权求和运算，通过一个激活函数输出运算结果。如图6A所示，为神经元结构的一种示意图。假设神经元的输入为x＝[x0,x1,…,xn]，与各个输入对应的权值分别为w＝ [w,w1,…,wn]，其中，wi作为xi的权值，用于对xi进行加权。根据权值对输入值进行加权求和的偏置例如为b。激活函数的形式可以有多种，假设一个神经元的激活函数为：y＝f(z)＝max(0,z)，则该神经元的输出为： 再例如，一个神经元的激活函数为：y＝f(z)＝z，则该神经元的输出为：其中，b、wi、或xi可以是小数、整数(例如0、正整数或负整数)、或复数等各种可能的取值。神经网络中不同神经元的激活函数可以相同或不同。
神经网络一般包括多个层，每层可包括一个或多个神经元。通过增加神经网络的深度和/或宽度，能够提高该神经网络的表达能力或称函数拟合能力，为复杂系统提供更强大的信息提取和抽象建模能力。其中，神经网络的深度可以是指神经网络包括的层数，其中每层包括的神经元个数可以称为该层的宽度。在一种实现方式中，神经网络包括输入层和输出层。神经网络的输入层将接收到的输入信息经过神经元处理，将处理结果传递给输出层，由输出层得到神经网络的输出结果。在另一种实现方式中，神经网络包括输入层、隐藏层和输出层，神经网络的输入层将接收到的输入信息经过神经元处理，将处理结果传递给中间的隐藏层，隐藏层对接收的处理结果进行计算，得到计算结果，隐藏层将计算结果传递给输出层或者相邻的隐藏层，最终由输出层得到神经网络的输出结果。其中，一个神经网络可以包括一个隐藏层，或者包括多个依次连接的隐藏层，不予限制。
如上述已经介绍，每个神经元都对其输入值做加权求和运算，并加权求和结果通过一个函数(例如通常为非线性函数，但是也不排除为线性函数)产生输出。将神经网络中神经元加权求和运算的权值以及非线性函数称作神经网络的参数。以max{0,x}为非线性函数的神经元为例，执行操作的神经元的参数为权值为w＝[w,w1,…,wn],其中，加权求和的偏置为b。一个神经网络的所有神经元的参数构成这个神经网络的参数。
本公开涉及的神经网络例如深度神经网络(deep neural network,DNN)。DNN一般具有多个隐藏层，在DNN中，DNN的模型参数包括每个神经元对应的权值。DNN可以使用监督学习或非监督学习策略来优化模型参数。根据网络的构建方式，DNN可以包括前馈神经网络(feedforward neural network,FNN)、卷积神经网络(convolutional neural networks,CNN)和递归神经网络(recurrent neural network,RNN)。以FNN为例，参见图6B示意一种神经网络结构，FNN的特点为相邻层的神经元两两之间完全相连。
CNN可以应用于处理具有类似网格结构的数据。其中，具有类似网格结构的数据可以包括时间序列数据(时间轴离散采样)和图像数据(二维离散采样)等。CNN的卷积层并不一次性利用全部的输入信息做卷积运算，而是设定一个或多个固定大小的窗，采用各个窗截取部分输入信息做卷积运算。这样的设计可以较大程度地降低模型参数的计算量。具体地，针对一个或多个固定大小的窗中的任意一个窗做卷积运算，可以理解为以该窗的系数(如加权系数)和该窗所截取的部分输入信息进行先乘后加运算。卷积运算后可以得到该窗对应的输出信息。其中，不同窗的系数可以是独立配置的。例如，不同窗可以配置不同的系数，这可以使得CNN更好的提取输入数据的特征。窗的系数可以包括卷积核。可选的，不同窗截取的部分输入信息的类型可以不同，示例性的，同一副图中的人和物可以理解为不同类型的信息，在设定两个固定大小的窗中一个窗可以截取该图中的人，另一个窗可以截取该图中的物。RNN是一种利用反馈时间序列信息的DNN网络。它的输入包括当前时 刻的新的输入值和RNN在前一时刻的输出值中的部分，其中前一时刻的输出值可以由激活函数和前一时刻的输入所确定。RNN适合获取在时间上具有相关性的序列特征，适用于语音识别、信道编译码等应用场景。
另外，在神经网络的训练过程中，可以定义损失函数。损失函数描述了神经网络的输出值与理想目标值之间的差距或差异，本公开并不限制损失函数的具体形式。神经网络的训练过程就是通过调整神经网络的参数，使得损失函数的取值小于门限，或者使得损失函数的取值满足目标需求的过程。调整神经网络的参数，例如调整如下参数中的至少一种：神经网络的层数、宽度、神经元的权值、或、神经元的激活函数中的参数。
本公开利用AI技术训练可以部署在测量量上报侧的模型。该模型用于从信道信息中提取测量量。该模型的输入类型可以包括信道信息，输出类型可以包括能够表征测量量的信息。其中，信道信息对应终端设备与接入网设备(或接入网设备的小区节点)之间的信道，信道信息可以是信道响应、信道特征矩阵、信道延迟分布或信道特征向量等。参见图7示意一种模型训练框架，在上行定位场景中，测量量上报侧可以为接入网设备或接入网设备的小区节点；在下行定位场景中，测量量上报侧可以为终端设备。测量量上报侧首先向LMF发送第一信道估计信息，该第一信道估计信息用于指示测量量上报侧通过测量信道信息所确定的测量量，第一信道估计信息还可以描述为第一测量信息。LMF根据获取的第一信道估计信息确定(或称反推导)对应的第二信道估计信息，该第二信道估计信息用于模型的训练。可选的，测量上报侧可以利用已有模型从信道信息中获取第一信道估计信息，LMF确定的第二信道估计信息用于对前述已有模型进行更新训练。
下面通过方案一～方案三对本公开提供的模型训练方案，进行详细说明。
方案一
参见图8示意一种通信方法，该方法主要包括如下流程。
可选的，S801，第一设备或者LMF中的一方发起模型的训练请求。
其中，该模型可部署于第一设备，用于从定位测量涉及的相关信道信息中提取用于终端设备定位的信道估计信息。信道估计信息可以表征前述介绍的测量量，具体将在后文S802中描述。
具体地，第一设备为终端设备，或者第一设备为M个小区节点第m个小区节点。其中，M个小区节点为参与模型训练，对终端设备进行定位的小区节点。M为大于1的正整数，m为取遍1至M的正整数。M个小区节点可以为同一接入网设备，即该接入网设备可以管理多个小区，在不同小区中可以相应地称为对应的小区节点；或者，M个小区节点也可以为不同接入网设备的小区节点，M个小区节点也可以描述为M个接入网设备；或者，M个小区节点中至少两个小区节点不属于同一个接入网设备。可选的，小区节点也可以描述为小区。另外需要说明的是，对于接入网设备只管理一个小区，例如接入网设备为微站或者小站的情况，该接入网设备的小区节点也可以理解为接入网设备本身。
一种可选的方式，可以是第一设备向LMF发送训练请求信息，以触发模型的训练过程。例如，第一设备为小区节点时，小区节点可以在搭建基础模型架构后，发送训练请求信息以请求训练适用于当前场景的模型。例如，第一设备为终端设备时，终端设备可以在位置发生较大变化时发起训练，如进入某个商场，或者到达新的城市。例如，终端设备或小区节点也可以周期性的发起训练以定期进行模型的更新。例如，终端设备或小区节点也可以在计算资源较为空闲的时候发起训练。
另一种可选的方式，可以是LMF向第一设备发送训练请求信息。具体地，LMF可以根据实际需求发起训练，例如LMF判断第一设备当前使用的模型效果差时发起模型的更新训练，或者LMF也可以周期性的发起训练，实现模型的定期更新。
上述可选方式中描述的训练请求信息，还可以称作第一请求信息或者其他的名称，本公开对此不做限制。
作为示例，图8在S801中示意出第一设备向LMF发送训练请求信息，以触发模型的训练过程。可以理解的是，第一设备为终端设备时，终端设备与LMF之间可按照LPP协议通信，图8中省略了在终端设备与LMF之间透明传输涉及的接入网设备、AMF；第一设备为小区节点时，小区节点所属接入网设备与LMF可按照NRPPa协议通信，图8中省略了在小区节点与LMF之间透明传输涉及的AMF。
S802，LMF获取M个第一信道估计信息。
其中，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息。具体地，所述M个第一信道估计信息中的第m个第一信道估计信息由M个小区节点中第m个小区节点与终端设备之间的信道的信道信息确定。
具体地，如图8示意，LMF可以从第一设备获取第m个第一信道估计信息。示例性的，在下行定位场景中，M个小区节点可以向终端设备发送参考信号如PRS；终端设备测量M个小区节点中第m个小区节点发送的PRS，获取第m个小区节点与终端设备之间的信道的信道信息；终端设备根据获取的信道信息确定第m个小区节点对应的测量量，终端设备向LMF发送该m个第一信道估计信息，该m个第一信道估计信息用于指示第m个小区节点对应的测量量。示例性的，在上行定位场景中，终端设备向M个小区节点中第m个小区节点发送参考信号如SRS；第m个小区节点测量终端设备发送的PRS，获取第m个小区节点与终端设备之间的信道的信道信息；第m个小区节点根据获取的信道信息确定第m个小区节点对应的测量量，第m个小区节点向LMF发送该m个第一信道估计信息，该m个第一信道估计信息用于指示第m个小区节点对应的测量量。可选的，LMF可以配置第一设备在训练阶段周期性的测量参考信号，直到第一设备收到训练结束的指示时停止测量。
具体地，第m个第一信道估计信息具体可以用于指示如下一个或多个参数：
(1)所述第m个小区节点与所述终端设备之间的距离。例如，第m个第一信道估计信息包括所述第m个小区节点与所述终端设备之间的距离；或者，第m个第一信道估计信息包括第m个距离差，第m个距离差表示所述第m个小区节点与所述终端设备之间的距离相对于参考距离的差值；其中，参考距离可以是预先设定的，或者是M个小区节点中的指定小区节点与终端设备之间的距离。
(2)所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差。例如，第m个第一信道估计信息包括所述第m个小区节点与所述终端设备之间的信号传输时延；或者，第m个第一信道估计信息包括第m个信号传输时延差(或称信号传输时间差)，第m个信号传输时延差表示所述第m个小区节点与所述终端设备之间的信号传输时延相对于参考时延的差值；其中，参考时延可以是预先设定的，或者是M个小区节点中的指定小区节点与终端设备之间的信号传输时延。
(3)所述第m个小区节点对应的信号出发角度(AoD)或信号到达角度(AoA)。例 如，在上行定位场景中，第m个第一信道估计信息包括所述第m个小区节点对应的信号到达角度，或者第m个第一信道估计信息包括第m个到达角度差，第m个到达角度差表示所述第m个小区节点与所述终端设备之间的信号到达角度相对于参考到达角度的差值；其中，参考到达角度可以是预先设定的，或者是M个小区节点中的一个小区节点对应的信号到达角度。又如，在下行定位场景中，第m个第一信道估计信息包括所述第m个小区节点对应的信号出发角度，或者第m个第一信道估计信息包括第m个出发角度差，第m个出发角度差表示所述第m个小区节点与所述终端设备之间的信号出发角度相对于参考出发角度的差值；其中，参考出发角度可以是预先设定的，或者是M个小区节点中的指定小区节点对应的信号出发角度。
(4)所述第m个小区节点与所述终端设备之间的信号质量；其中，信号质量的定义可参照前述内容理解，本公开对此不再进行赘述。
(5)所述第m个小区节点与所述终端设备之间的信号传输路径的类型。例如，信号传输路径的类型为直射路径或者非直射路径。
可选的，第一设备在向LMF发送第m个第一信道估计信息之前，可以与LMF交互定位配置信息。具体地，可参照前述终端设备和LMF交互定位配置信息的方式实施，本公开对此不再进行赘述。
可选的，第一设备可以多次测量信道信息确定第m个第一信道估计信息，向LMF多次发送第m个第一信道估计信息。对应的，LMF获取M个第一信道估计信息，包括：LMF一次或多次，获取M个第一信道估计信息。
S803，根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息。
其中，所述M个第二信道估计信息中的第m个第二信道估计信息对应M个小区节点中第m个小区节点与终端设备之间的信道。
具体地，第m个第二信道估计信息所指示的参数可以参考第一信道估计信息指示的参数理解，例如第m个第二信道估计信息可以指示如下一个或多个参数：所述第m个小区节点与所述终端设备之间的距离；所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；所述第m个小区节点对应的信号出发角度(AoD)或信号到达角度(AoA)；所述第m个小区节点与所述终端设备之间的信号质量；或，所述第m个小区节点与所述终端设备之间的实际信号传输路径的类型。
另外可以理解的是，在第m个第二个信道估计信息能够指示的参数中除实际信号传输路径的类型之外，其他参数是对应模拟第m个小区节点与终端设备之间的路径为LOS的情况所计算出的参数。前述所述第m个小区节点与所述终端设备之间的实际信号传输路径的类型，可能为LOS或者NLOS。
可选的，第m个第二信道估计信息所指示的参数类型和第m个第一信道估计信息所指示的参数类型可以相同，例如第m个第一信道估计信息所指示的参数包括如S802描述的(1)～(3)时，第m个第二信道估计信息所指示的参数包括如S802描述的(1)～(3)对应的标签。或者，第m个第二信道估计信息所指示的参数类型和第m个第一信道估计信息所指示的参数类型也可以不相同，例如第m个第一信道估计信息所指示的参数包括如S802描述的(1)～(3)时，第m个第二信道估计信息所指示的参数包括如S802描述的(1)～(2)对应的标签。有关第m个第二信道估计信息所指示的参数类型可以根据实 际模型的训练需求所决定，本公开对此不进行限制。
作为一种示例，对应S801第一设备在向LMF发送训练请求信息时，可以通过训练请求信息请求相关的第二信道估计信息。可选的，第一设备可以通过训练请求信息向LMF指定第二信道估计信息指示的参数，例如第一设备可以在训练请求信息中包括该第二信道估计信息指示的参数类型。此情况下，该第二信道估计信息指示的参数类型也可以理解为第一设备希望模型的输出所表征测量量的类型。
可选的，对应S802中LMF一次或多次获取M个第二信道估计信息，在一次或多次中的每一次，LMF可以参照如下方式确定对应的M个第二信道估计信息：LMF根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定所述终端设备的第一位置；LMF根据所述终端设备的第一位置和所述M个小区节点的位置，确定所述M个第二信道估计信息。
其中，第一位置可以是LMF结合M个小区节点的位置、以及M个第一信道估计信息中的至少一个第一信道估计信息，初步确定出终端设备的一个可信位置(或称可靠位置)。下面对确定第一位置的可选实施方式进行介绍。
一种可选的实施方式中，LMF可以根据所述M个第一信道估计信息和所述M个小区节点的位置，确定所述终端设备的多个第二位置。其中，所述多个第二位置中的第一部分位置位于第一区域，所述多个第二位置中的第二部分位置不位于所述第一区域，且所述第一部分位置的数量大于所述第二部分位置的数量。进而，LMF根据所述多个第二位置中的第一部分位置，确定所述终端设备的第一位置。
示例性的，以TDOA的定位方法为例，M个第一信道估计信息中第m个第一信道估计信息指示的参数包括所述第m个小区节点与所述终端设备之间的信号传输时延。如图9示意一种定位场景，假设M为6，6个小区节点分别记作C1、C2、C3、C4、C5以及C6。其中，C6与终端设备之间的路径为NLOS，其余的小区节点与终端设备之间的路径为LOS。此情况下，LMF基于M个第一信道估计信息，利用6个小区节点中任意3个小区节点的位置估算终端设备的位置时，共可以得到20种可能的位置，这20个位置在图9中以“☆”示意。由于图9所示场景中只有一个NLOS，因此如果选取用于估算终端位置的3个小区节点与终端设备之间的路径都为LOS，也即在C1、C2、C3、C4、C5中任选3个，得到的10个位置是比较接近，均位于图9中虚线框区域(对应前述第一区域)内；而如果用于估算终端位置的3个小区节点包括C6，所得到的10个位置分散在虚线框区域之外。于是LMF可以根据虚线框内的10个位置确定终端设备的第一位置，例如，可以将虚线框内的10个位置进行平均化处理得到第一位置。
另一种可选的实施方式中，LMF可以根据N个第一信道估计信息和所述N个小区节点的位置，确定所述终端设备的第一位置；其中，N个第一信道估计信息与N个小区节点一一对应，所述N个小区节点包含于所述M个小区节点，N为小于或者等于M的正整数。所述N个小区节点中每个小区节点与所述终端设备之间的路径为直射路径。具体地，LMF可以根据M个第一信道估计信息，在M个小区节点中确定出对应直射路径的N个小区节点。
示例性的，以TDOA的定位方法为例，对应M个第一信道估计信息中第m个第一信道估计信息指示的参数包括所述第m个小区节点与所述终端设备之间的信号传输时延。首先，LMF可以在M个小区节点中任意选取3个小区节点，记3个小区节点中第i个小 区节点的位置坐标为(xi,yi,zi)，i取遍1至3的正整数。LMF利用选取的3个小区节点计算终端设备的位置坐标为(x,y,z)。进而LMF根据前述计算出的终端设备的位置坐标和第i个小区节点的位置坐标，计算终端设备和第i个小区节点之间的距离为以及可以计算出终端设备和第i个小区节点之间的信号传输时延为
对应S802，假设第m个第一信道估计信息包括第m个信号传输时延差，参考时延为前述M个小区节点中的指定小区节点与终端设备之间的信号传输时延。记该指定小区节点与终端设备之间的距离为t0，第一设备向LMF上报的前述3个小区节点中第i个小区节点对应的时间差测量量为Δτi，LMF计算的前述3个小区节点中第i个小区节点对应的信号传输时延差为Δti＝ti-t0。则会得到第i个小区节点对应的参数εi＝|Δti-Δτi|。其中，εi用于确定第i个小区节点与终端设备之间的路径为LOS还是NLOS。具体地，LMF可通过如下公式确定第i个小区节点与终端设备之间的路径为LOS还是NLOS：
其中，th为预设的阈值，可以理解εi≤th时，losi取值为1，表示Δti与Δτi之间的差异较小，第i个小区节点与终端设备之间的路径为LOS；εi＞th时，losi取值为0，表示Δti与Δτi之间的差异较大，第i个小区节点与终端设备之间的路径为NLOS。
LMF通过对比上报量和计算量的方式，可以从M个小区节点中选取对应直射路径的N个小区节点。此外，对应S802中描述，M个第一信道估计信息中第m个第一信道估计信息指示其他参数的情况，可以基于上述对比上报量和计算量的方式，确定小区节点和终端设备之间的信号传输路径的类型，本公开对此不再进行赘述。
示例性的，如果M个第一信道估计信息中第m个第一信道估计信息指示的参数包括所述第m个小区节点与所述终端设备之间的信号传输路径的类型；则LMF可以直接根据该第m个第一信道估计信息确定第m个小区节点对应的路径类型为直射路径或非直射路径，进而在M个小区节点中确定出对应直射路径的N个小区节点。
S804，LMF向第一设备发送K个第二信道估计信息，所述第一设备用于所述模型的训练。
其中，K个第二信道估计信息包含于S803中描述的M个第二信道估计信息，可以理解LMF向第一设备发送M个第二信道估计信息中的部分或全部第二信道估计信息，K为正整数，K小于或者等于M。K个第二信道估计信息中第k个第二信道估计信息对应K个小区节点中第k个小区节点与终端设备之间的信道，K个小区节点包含于前述M个小区节点，k取遍1至K的正整数。
具体地，如果所述第一设备为所述第m个小区节点，LMF向所述第一设备发送的K个第二信道估计信息只包括所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息，则第m个小区节点可基于第m个小区节点与终端设备之间的信道所对应的第二信道估计信息，训练对应的模型。在此情况下，k与m同义。
或者，如果所述第一设备为所述第m个小区节点，LMF向所述第一设备发送的K个第二信道估计信息为所述M个第二信道估计信息，则第m个小区节点可基于M个第二信道估计信息中的部分或全部第二信道估计信息，训练对应的模型。
或者，如果所述第一设备为所述第m个小区节点，LMF向所述第一设备发送的K个 第二信道估计信息为所述M个第二信道估计信息中的部分第二信道估计信息，则第m个小区节点可基于M个第二信道估计信息中的部分第二信道估计信息，训练对应的模型。
或者，如果所述第一设备为所述终端设备，LMF向所述第一设备送所述M个第二信道估计信息，则终端设备可基于M个第二信道估计信息，训练对应的模型。
可选的，第一设备可以自行决定根据M个第二信道估计信息中的部分还是全部第二信道估计信息进行模型的训练，或者描述为第一设备可以自行决定利用M个小区中部分还是全部小区对应的第二估计信息进行模型的训练，第一设备在向LMF发送训练请求信息时，指示请求的是K个第二信道估计信息，例如第一设备可以在训练请求信息中包括一个取值为K的指示信息。
可选的，对应S803中描述LMF多次获取M个第一信道估计信息的情况，LMF可以在获取到设定次数的M个第一信道估计信息时，统一发送对应次数的K个第二信道估计信息。或者，LMF可以每隔设定时间，根据设定时间内一次或多次获取的M个第一信道估计信息，统一发送对应次数的K个第二信道估计信息。其中，设定次数或者设定时间可以由第一设备配置给LMF，或者也可以是预先约定的，本公开对此不进行限制。通过这样的方式，能够减少信令开销。
S805，第一设备根据所述K个第二信道估计信息，进行模型的训练。
具体地，第一设备在训练模型时，可以采用监督学习进行训练。以测量的信道信息作为样本，并根据获取的第二信道估计信息确定样本标签，从而得到模型的训练数据集。训练相关的损失函数不予限定，例如可以由模型的结构类型、模型的训练数据集和/或模型的应用场景等因素确定。一些模型的结构类型举例如下：决策树、随机森林、支撑向量机或神经网络等，其中，神经网络例如为CNN、RNN、或FNN等。
具体地，第一设备可以获取K个信道信息，该K个信道信息中的第k个信道信息为K个小区节点中第k个小区节点与终端设备之间的信道的信道信息。对应S804，K个小区节点可以为1个或多个。如果第一设备为一个小区节点，前述K个小区节点可以包括第一设备，且K大于1时，第一设备可以从除自身之外的其他K-1个小区节点请求其与终端设备之间的信道的信道信息。在进行所述模型的训练时，所述模型的输入是根据所述第k个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第k个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。示例性的，如果信道信息为信道响应，则所述模型的输入可以包括所述第k个小区节点与终端设备之间的信道的信道响应、实虚部分分离后的信道响应、或者幅度相位分离后的信道响应等。
可选的，模型的功能与第二信道估计信息指示的参数类型有关。训练好的所述模型的输入类型包括信道信息，输出类型包括对应的第三信道估计信息，所述第三信道估计信息指示的参数类型与第二信道估计信息指示的参数类型相同；所述第三信道估计信息用于确定所述终端设备的第二位置。参见图10示意一种基于模型的定位方法，训练好的模型可以部署于终端设备或接入网设备(接入网设备的小区)，用于根据定位测量涉及的信道信息中确定用于终端设备定位的第三信道估计信息。进而终端设备或接入网设备(接入网设备的小区)可以将前述第三信道估计信息发送给LMF，LMF根据获取的第三信道估计信息计算终端设备的第二位置。
示例性的，如果第一设备可以确定T个小区节点中第t个小区节点与终端设备之间的 信道信息，则第一设备利用训练好的模型可以根据所述第t个小区节点与所述终端设备之间的信道的信道信息，确定第t个第三信道估计信息。其中，T为大于1的正整数，t为取遍1至T的正整数；可选地，T和上述M的取值可以相同，也可以不同，不予限制。
其中，当第二信道估计信息指示的参数类型包括小区节点与所述终端设备之间的距离时，第t个第三信道估计信息指示的参数包括：在LOS的条件下，第t个小区节点与所述终端设备之间的距离。其中，该距离还可以称为LOS距离。
当第二信道估计信息指示的参数类型包括小区节点与所述终端设备之间的信号传输时延或信号传输时延差时，第t个第三信道估计信息指示的参数包括：在LOS的条件下，第t个小区节点与所述终端设备之间的信号传输时延或信号传输时延差。其中，该信号传输时延还可以称为符合LOS传输的信号传输时延，该信号传输时延差还可以称为符合LOS传输的信号传输时延差。
当第二信道估计信息指示的参数类型包括相对于小区节点的信号出发角度或信号到达角度时，第t个第三信道估计信息指示的参数包括第t个小区节点对应的符合LOS传输的信号出发角度或信号到达角度。
当第二信道估计信息指示的参数类型包括小区节点与终端设备之间的信号传输路径的类型时，第t个第三信道估计信息指示的参数包括第t个小区节点与终端设备之间的实际信号传输路径的类型。
需要说明的是，以上示例的情况可能结合在一起出现。例如一种可能的情况，第二信道估计信息指示的参数类型包括小区节点与所述终端设备之间的信号传输时延，以及小区节点与终端设备之间的信号传输路径的类型。第一设备利用训练好的模型可以根据所述第t个小区节点与所述终端设备之间的信道的信道信息，确定第t个第三信道估计信息，该第t个第三信道估计信道信息指示的参数包括第t个小区节点与所述终端设备之间的符合LOS传输的信号传输时延，以及第t个小区节点与终端设备之间的实际信号传输路径的类型，例如该实际信号传输路径的类型为NLOS。
本方案中根据终端设备或小区节点测量得到信道估计信息，推导用于模型训练的标签，并将模型训练的标签提供给终端设备或小区节点，使得终端设备或小区节点训练模型。该训练方式更适合实际场景环境，能够提升模型的性能，从而提升定位精度。
在本公开的各示例中，参与模型训练的小区节点和参与模型推理的小区节点可以相同，也可以不同。例如利用第一组小区节点进行模型训练，将训练得到的模型用于第二组小区节点，第一组小区节点和第二组小区节点可以相同，也可以不同，不予限制。
在本公开的各示例中，参与模型训练的终端设备和参与模型推理的终端设备可以相同，也可以不同。例如利用终端A进行模型训练，将训练得到的模型用于终端B，终端A和终端B可以相同，也可以不同，不予限制。
方案二
参见图11示意一种通信方法，该方法主要包括如下流程。
可选的，S1101，第一设备或者LMF中的一方发起模型的训练请求。
该步骤可参照S801实施，本公开对此不再进行赘述。
S1102，LMF获取M个第一信道估计信息。
该步骤可参照S802实施，本公开对此不再进行赘述。
S1103，LMF根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息。
该步骤可参照S803实施，本公开对此不再进行赘述。
S1104，LMF获取M个小区节点与终端设备之间的信道的信道信息。
具体地，LMF从第一设备获取所述第m个小区节点与终端设备之间的信道的信道信息。对于第一设备测量所述第m个小区节点与终端设备之间的信道的信道信息可参照S802中描述的内容理解，本公开对此不再进行赘述。
S1105，LMF根据所述M个第二信道估计信息中的至少一个第二信道估计信息，进行模型的训练。
可选的，第一设备为第m个小区节点时，LMF可根据第m个第二信道估计信息，针对第m个小区节点训练对应的模型；其中，在进行所述模型的训练时，所述模型的输入是根据所述第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
或者可选的，LMF可根据K个第二信道估计信息，为K个小区节点训练同一个模型，K为小于或者等于M的正整数，K个小区节点包含于前述M个小区节点，是M个小区节点的部分节点或者全部节点，K个第二信道估计信息包含于M个第二信道估计信息。K个第二信道估计信息中第k个第二信道估计信息对应K个小区节点中第k个小区节点与终端设备之间的信道。其中，在进行所述模型的训练时，所述模型的输入是根据所述第k个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第k个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
或者可选的，第一设备为终端设备时，LMF可根据M个第二信道估计信息，训练模型。其中，在进行所述模型的训练时，所述模型的输入是根据所述M个小区节点中各个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述M个小区节点中各个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
S1106，LMF向第一设备发送用于指示模型的信息。
可以理解的是，第一设备为第m个小区节点时，LMF向第一设备发送的是该第m个小区对应的模型。根据S1105的介绍可以理解，该第m个小区对应的模型可以是特定于该小区的，或者是该小区和其他多个小区共用的，不予限定。
进一步，第一设备利用训练好的模型，从测量的信道信息中提取第三信道估计信息，第三估计信息用于确定终端设备的第二位置。具体地可参照方案一中的描述实施，本公开对此不再进行赘述。
本方案中，LMF根据终端设备或小区节点测量得到信道估计信息，推导用于模型训练的标签，训练模型，该方式更适合实际场景环境，能够提升模型的性能，进而LMF将训练好的模型提供给终端设备或小区节点，确定用于定位的信道估计信息，能够提升定位精度。
方案三
参见图12示意一种通信方法，该方法主要包括如下流程。
可选的，S1201，LMF获取训练请求信息。
具体地，可以由执行模型训练的第一设备向LMF发送训练请求信息，或者由测量量上报侧向LMF发送训练请求信息。其中，测量量上报侧可以是终端设备，或者接入网设备的小区节点。
示例性的，以第二设备表示测量量上报侧，图12中示意出LMF从第二设备获取训练请求信息，该训练请求信息的定义可以参照图8对应方案中的描述理解，本公开对此不再进行赘述。可选的，在进行训练模型时，利用M个小区节点的位置进行终端设备的位置估算。第二设备可以为M个小区节点中的第m个小区节点或终端设备，LMF可以从第二设备获取第m个第一信道估计信息。有关M个小区节点以及第一信道估计信息的定义可参照S801理解，本公开对此不再进行赘述。
S1202，LMF获取M个第一信道估计信息。
该步骤可参照S802实施，本公开对此不再进行赘述。
S1203，LMF根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息。
该步骤可参照S803实施，本公开对此不再进行赘述。
S1204，LMF向第一设备发送所述M个第二信道估计信息，所述第一设备用于所述模型的训练。
具体地，第一设备可以是除M个小区节点以及终端设备之外，具备模型训练功能的AI网元，LMF向所述第一设备送所述M个第二信道估计信息。
该步骤可参照S804实施，本公开对此不再进行赘述。
S1205，第一设备获取M个小区节点与终端设备之间的信道的信道信息。
示例性，第一设备可以从第二设备获取第m个小区节点与终端设备之间的信道的信道信息。
S1206，第一设备根据所述M个第二信道估计信息，进行模型的训练。
具体地，该步骤可参照S1105实施，本公开对此不再进行赘述。
S1207，第一设备向第二设备发送用于指示模型的信息。
具体地，该步骤可参照S1106实施，本公开对此不再进行赘述。
进一步，第二设备利用训练好的模型，从测量的信道信息中提取第三信道估计信息，第三估计信息用于确定终端设备的第二位置。具体地可参照方案一中的描述实施，本公开对此不再进行赘述。
本方案中，LMF根据终端设备或小区节点测量得到信道估计信息，推导用于模型训练的标签，并将该标签提供给单独的AI网元训练模型，该方式更适合实际场景环境，能够提升模型的性能，进而AI网元将训练好的模型提供给终端设备或小区节点，确定用于定位的信道估计信息，能够提升定位精度。
基于同一构思，参见图13，本公开提供了一种通信装置1300，该通信装置1300包括处理模块1301和通信模块1302。该通信装置1300可以是LMF，也可以是应用于LMF或者和LMF匹配使用，能够实现LMF侧执行的通信方法的通信装置；或者，该通信装置1300可以是第一设备，也可以是应用于第一设备或者和第一设备匹配使用，能够实现第一设备侧执行的通信方法的通信装置；或者，该通信装置1300可以是第二设备，也可以是应用于第二设备或者和第二设备匹配使用，能够实现第二设备侧执行的通信方法的通信装置。
其中，通信模块也可以称为收发模块、收发器、收发机、或收发装置等。处理模块也可以称为处理器，处理单板，处理单元、或处理装置等。可选的，通信模块用于执行上述方法中LMF侧或第一设备侧的发送操作和接收操作，可以将通信模块中用于实现接收功能的器件视为接收单元，将通信模块中用于实现发送功能的器件视为发送单元，即通信模块包括接收单元和发送单元。
该通信装置1300应用于LMF时，处理模块1301可用于实现图8、图11、或者图12所示示例中所述LMF的处理功能，通信模块1302可用于实现图8、图11、或者图12所述示例中所述LMF的收发功能。或者也可以参照发明内容中第五方面以及第九方面中可能的设计理解该通信装置。
该通信装置1300应用于第一设备或第二设备时，处理模块1301可用于实现图8、图11、或者图12所示的示例中第一设备或第二设备的处理功能，通信模块1302可用于实现图8、图11、或者图12所述示例中第一设备或第二设备的收发功能。其中，在图8、图11中，以第一设备表示终端设备或小区节点，在图12中以第一设备表示AI网元，第二设备表示终端设备或小区节点。也可以参照发明内容中第六方面以及第六方面中可能的设计理解该通信装置，或者也可以参照发明内容中第七方面以及第七方面中可能的设计理解该通信装置，或者也可以参照发明内容中第八方面以及第八方面中可能的设计理解该通信装置。
此外需要说明的是，前述通信模块和/或处理模块可通过虚拟模块实现，例如处理模块可通过软件功能单元或虚拟装置实现，通信模块可以通过软件功能或虚拟装置实现。或者，处理模块或通信模块也可以通过实体装置实现，例如若该装置采用芯片/芯片电路实现，所述通信模块可以是输入输出电路和/或通信接口，执行输入操作(对应前述接收操作)、输出操作(对应前述发送操作)；处理模块为集成的处理器或者微处理器或者集成电路。
本公开中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，另外，在本公开各个示例中的各功能模块可以集成在一个处理器中，也可以是单独物理存在，也可以两个或两个以上模块集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。
基于相同的技术构思，本公开还提供了一种通信装置1400。例如，该通信装置1400可以是芯片或者芯片系统。可选的，在本公开中芯片系统可以由芯片构成，也可以包含芯片和其他分立器件。
通信装置1400可用于实现前述示例描述的通信系统中任一网元的功能。通信装置1400可以包括至少一个处理器1410，该处理器1410与存储器耦合，可选的，存储器可以位于该装置之内，存储器可以和处理器集成在一起，存储器也可以位于该装置之外。例如，通信装置1400还可以包括至少一个存储器1420。存储器1420保存实施上述任一示例中必要计算机程序、计算机程序或指令和/或数据；处理器1410可能执行存储器1420中存储的计算机程序，完成上述任一示例中的方法。
通信装置1400中还可以包括通信接口1430，通信装置1400可以通过通信接口1430和其它设备进行信息交互。示例性的，所述通信接口1430可以是收发器、电路、总线、模块、管脚或其它类型的通信接口。当该通信装置1400为芯片类的装置或者电路时，该装置1400中的通信接口1430也可以是输入输出电路，可以输入信息(或称，接收信息)和输出信息(或称，发送信息)，处理器为集成的处理器或者微处理器或者集成电路或则 逻辑电路，处理器可以根据输入信息确定输出信息。
本公开中的耦合是装置、单元或模块之间的间接耦合或通信连接，可以是电性，机械或其它的形式，用于装置、单元或模块之间的信息交互。处理器1410可能和存储器1420、通信接口1430协同操作。本公开中不限定上述处理器1410、存储器1420以及通信接口1430之间的具体连接介质。
可选的，参见图14，所述处理器1410、所述存储器1420以及所述通信接口1430之间通过总线1440相互连接。所述总线1440可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended industry standard architecture，EISA)总线等。所述总线可以分为地址总线、数据总线、控制总线等。为便于表示，图14中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
在本公开中，处理器可以是通用处理器、数字信号处理器、专用集成电路、现场可编程门阵列或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件，可以实现或者执行本公开中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者任何常规的处理器等。结合本公开所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。
在本公开中，存储器可以是非易失性存储器，比如硬盘(hard disk drive，HDD)或固态硬盘(solid-state drive，SSD)等，还可以是易失性存储器(volatile memory)，例如随机存取存储器(random-access memory，RAM)。存储器是能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质，但不限于此。本公开中的存储器还可以是电路或者其它任意能够实现存储功能的装置，用于存储程序指令和/或数据。
在一种可能的实施方式中，该通信装置1400可以应用于第一设备，具体通信装置1400可以是第一设备，也可以是能够支持第一设备，实现上述涉及的任一示例中第一设备的功能的装置。存储器1420保存实现上述任一示例中的第一设备的功能的计算机程序(或指令)和/或数据。处理器1410可执行存储器1420存储的计算机程序，完成上述任一示例中第一设备执行的方法。应用于第一设备，该通信装置1400中的通信接口可用于与LMF进行交互，向LMF发送信息或者接收来自LMF的信息。
在一种可能的实施方式中，该通信装置1400可以应用于第二设备，具体通信装置1400可以是第二设备，也可以是能够支持第二设备，实现上述涉及的任一示例中第二设备的功能的装置。存储器1420保存实现上述任一示例中的第一设备的功能的计算机程序(或指令)和/或数据。处理器1410可执行存储器1420存储的计算机程序，完成上述任一示例中第二设备执行的方法。应用于第二设备，该通信装置1400中的通信接口可用于与LMF进行交互，向LMF发送信息或者接收来自LMF的信息。
在一种可能的实施方式中，该通信装置1400可以应用于LMF，具体通信装置1400可以是LMF，也可以是能够支持LMF，实现上述涉及的任一示例中LMF的功能的装置。存储器1420保存实现上述任一示例中的LMF的功能的计算机程序(或指令)和/或数据。处理器1410可执行存储器1420存储的计算机程序，完成上述任一示例中LMF执行的方法。应用于LMF，该通信装置1400中的通信接口可用于与第一设备或第二设备进行交互，例如向第一设备或第二设备发送信息，或者接收来自第一设备或第二设备的信息。
由于本示例提供的通信装置1400可应用于第一设备，完成上述第一设备执行的方法， 或者应用于第二设备，完成第二设备执行的方法，或者应用于LMF，完成LMF执行的方法。因此其所能获得的技术效果可参考上述方法示例，在此不再赘述。
基于以上示例，本公开提供了一种通信系统，包括终端设备、至少一个小区节点和LMF。可选的，还包括AI网元。其中，所述终端设备、至少一个小区节点、AI网元和LMF可以实现图8、图11、或者图12所示的示例中所提供的通信方法。具体地，在图8、图11中，以第一设备表示终端设备或小区节点，在图12中以第一设备表示AI网元，第二设备表示终端设备或小区节点。
本公开提供的技术方案可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本公开所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、LMF、终端设备、小区节点、AI网元或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机可以存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，数字视频光盘(digital video disc，DVD))、或者半导体介质等。
在本公开中，在无逻辑矛盾的前提下，各示例之间可以相互引用，例如方法示例之间的方法和/或术语可以相互引用，例如装置示例之间的功能和/或术语可以相互引用，例如装置示例和方法示例之间的功能和/或术语可以相互引用。
显然，本领域的技术人员可以对本公开进行各种改动和变型而不脱离本公开的范围。这样，倘若本公开的这些修改和变型属于本公开权利要求及其等同技术的范围之内，则本公开也意图包含这些改动和变型在内。

Claims (59)

  1. 一种通信方法，其特征在于，包括：
    获取M个第一信道估计信息，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，M为大于1的正整数，m为取遍1至M的正整数；
    根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息，所述M个第二信道估计信息中的第m个第二信道估计信息对应所述第m个小区节点与所述终端设备之间的信道。
  2. 如权利要求1所述的方法，其特征在于，所述第二信道估计信息用于模型的训练；其中，在进行所述模型的训练时，所述模型的输入是根据所述第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与所述终端设备之间的信道所对应的第二信道估计信息确定的。
  3. 如权利要求1或2所述的方法，其特征在于，还包括：
    向第一设备发送K个第二信道估计信息，所述K个第二信道估计信息包含于所述M个第二信道估计信息，K为正整数。
  4. 如权利要求3所述的方法，其特征在于，还包括：
    从所述第一设备获取训练请求信息，所述训练请求信息用于请求所述K个第二信道估计信息。
  5. 如权利要求4所述的方法，其特征在于，所述训练请求信息用于指示所述第二信道估计信息指示的参数类型。
  6. 如权利要求1-5任一项所述的方法，其特征在于，所述获取M个第一信道估计信息，包括：
    从第一设备获取所述第m个第一信道估计信息；其中，所述第一设备为所述第m个小区节点，或者所述第一设备为所述终端设备。
  7. 如权利要求1-6任一项所述的方法，其特征在于，所述根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息，包括：
    根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定所述终端设备的第一位置；
    根据所述终端设备的第一位置和所述M个小区节点的位置，确定所述M个第二信道估计信息。
  8. 如权利要求7所述的方法，其特征在于，所述根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定所述终端设备的第一位置，包括：
    根据所述M个第一信道估计信息和所述M个小区节点的位置，确定所述终端设备的多个第二位置；其中，所述多个第二位置中的第一部分位置位于第一区域，所述多个第二位置中的第二部分位置不位于所述第一区域，且所述第一部分位置的数量大于所述第二部分位置的数量；
    根据所述多个第二位置中的第一部分位置，确定所述终端设备的第一位置；或者，
    根据N个第一信道估计信息和N个小区节点的位置，确定所述终端设备的第一位置；其中，所述N个第一信道估计信息与所述N个小区节点一一对应，所述N个小区节点包 含于所述M个小区节点，N为小于或者等于M的正整数；所述N个小区节点中每个小区节点与所述终端设备之间的路径为直射路径。
  9. 如权利要求1-8任一项所述的方法，其特征在于，所述第m个第一信道估计信息用于指示以下中的一个或多个参数：所述第m个小区节点与所述终端设备之间的距离；所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；所述第m个小区节点对应的信号出发角度或信号到达角度；所述第m个小区节点与所述终端设备之间的信号质量；所述第m个第一信道估计信息用于指示所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径或者非直射路径。
  10. 如权利要求1-9任一项所述的方法，其特征在于，所述第m个第二信道估计信息用于指示以下至少一项：
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的距离；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点对应的信号出发角度或信号到达角度；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的信号质量；
    所述第m个小区节点与所述终端设备之间的实际信号传输路径为直射路径或者非直射路径。
  11. 如权利要求1-10任一项所述的方法，其特征在于，所述M个小区节点属于一个接入网设备，或者所述M个小区节点中至少两个小区节点所属的接入网设备不同。
  12. 一种通信方法，其特征在于，包括：
    发送第m个第一信道估计信息，所述第m个第一信道估计信息属于M个第一信道估计信息，M为大于1的正整数，m为取遍1至M的正整数，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，所述M个第一信道估计信息中的至少一个第一信道估计信息用于确定M个第二信道估计信息，所述M个第二信道估计信息中第m个第二信道估计信息对应所述第m个小区节点与所述终端设备之间的信道；
    获取用于指示模型的信息；其中，在进行所述模型的训练时，所述模型的输入是根据所述第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
  13. 如权利要求12所述的方法，其特征在于，还包括：发送所述第m个小区节点与终端设备之间的信道的信道信息。
  14. 如权利要求12或13所述的方法，其特征在于，所述第m个第一信道估计信息用于指示以下中的一个或多个参数：所述第m个小区节点与所述终端设备之间的距离；所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；所述第m个小区节点对应的信号出发角度或信号到达角度；所述第m个小区节点与所述终端设备之间的信号质量；所述第m个第一信道估计信息用于指示所述第m个小区节点与所述终端设 备之间的信号传输路径为直射路径或者非直射路径。
  15. 如权利要求12-14任一项所述的方法，其特征在于，所述第m个第二信道估计信息用于指示以下至少一项：
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的距离；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点对应的信号出发角度或信号到达角度；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的信号质量；
    所述第m个小区节点与所述终端设备之间的实际信号传输路径为直射路径或者非直射路径。
  16. 如权利要求12-15任一项所述的方法，其特征在于，所述M个小区节点属于一个接入网设备，或者所述M个小区节点中至少两个小区节点所属的接入网设备不同。
  17. 一种通信方法，其特征在于，包括：
    确定K个信道信息，其中，所述K个信道信息中的第k个信道信息是K个小区节点中第k个小区节点与终端设备之间的信道的信道信息；其中，K为正整数，k为取遍1至K的正整数；
    获取K个第二信道估计信息，所述K个第二信道估计信息中第k个第二信道估计信息对应所述第k个小区节点与所述终端设备之间的信道，所述K个第二信道估计信息由M个第一信道估计信息中的至少一个第一信道估计信息确定，其中，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区中第m个小区节点与所述终端设备之间的信道的估计信息，所述K个小区包含于所述M个小区，M为大于1的正整数，m取遍1至M的正整数；
    根据所述K个第二信道估计信息，进行模型的训练；其中，在进行所述模型的训练时，所述模型的输入是根据所述第k个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第k个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
  18. 如权利要求17所述的方法，其特征在于，还包括：
    发送训练请求信息，所述训练请求信息用于请求所述K个第二信道估计信息。
  19. 如权利要求18所述的方法，其特征在于，所述训练请求信息用于指示所述第二信道估计信息指示的参数类型。
  20. 如权利要求17或18所述的方法，其特征在于，还包括：
    发送所述第m个小区节点与所述终端设备之间的信道的第一信道估计信息。
  21. 如权利要求17-20任一项所述的方法，其特征在于，所述第m个第一信道估计信息用于指示以下中的一个或多个参数：所述第m个小区节点与所述终端设备之间的距离；所述第m个小区节点与所述终端设备之间的信号传输时延；所述第m个小区节点对应的信号出发角度或信号到达角度；所述第m个小区节点与所述终端设备之间的信号质量； 所述第m个第一信道估计信息用于指示所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径或者非直射路径。
  22. 如权利要求17-21任一项所述的方法，其特征在于，所述第k个第二信道估计信息用于指示以下至少一项：
    在所述第k个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第k个小区节点与所述终端设备之间的距离；
    在所述第k个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第k个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；
    在所述第k个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第k个小区节点对应的信号出发角度或信号到达角度；
    在所述第k个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第k个小区节点与所述终端设备之间的信号质量；
    所述第k个小区节点与所述终端设备之间的实际信号传输路径为直射路径或者非直射路径。
  23. 如权利要求17-22任一项所述的方法，其特征在于，所述M个小区节点属于一个接入网设备，或者所述M个小区节点中至少两个小区节点所属的接入网设备不同。
  24. 一种通信方法，其特征在于，包括：
    确定第t个信道信息，其中，所述第t个信道信息是T个小区节点中第t个小区节点与终端设备之间的信道的信道信息；其中，T为大于1的正整数，t为取遍1至T的正整数；
    根据所述第t个信道信息和模型，确定第t个第三信道估计信息，所述第t个第三信道估计信息对应所述第t个小区节点与所述终端设备之间的信道；其中，所述模型的输入是根据所述第t个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的输出包括所述第t个第三信道估计信息；
    发送所述第t个第三信道估计信息，所述第t个第三信道估计信息用于对所述终端设备进行定位。
  25. 如权利要求24所述的方法，其特征在于，所述第t个第三信道估计信息用于指示如下的一个或多个参数：所述第t个小区节点与所述终端设备之间的直射路径LOS的长度距离；所述第t个小区节点与所述终端设备之间符合LOS传输的信号传输时延或信道传输时延差；所述第t个小区节点对应的符合LOS传输的信号出发角度或信号到达角度；所述第t个小区节点与所述终端设备之间符合LOS传输的信号质量；所述第t个小区节点与所述终端设备之间的实际信号传输路径的类型；或，所述第t个小区节点与所述终端设备之间的实际信号传输路径的类型，其中，所述类型为LOS或非直射路径NLOS。
  26. 如权利要求24或25所述的方法，其特征在于，在进行所述模型的训练时，所述模型的输入是根据M个小区节点中第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的；
    其中，M为大于1的正整数，M与T的取值相同或者不相同，m为取遍1至M的正整数；m取所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息是由M个第一信道估计信息中的至少一个第一信道估计信息确定的，所述M个第一信道估计信息 中第m个第一信道估计信息是所述M个小区节点中第m个小区节点与终端设备之间的信道的估计信息。
  27. 一种通信装置，其特征在于，包括：
    通信模块，用于获取M个第一信道估计信息，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，M为大于1的正整数，m为取遍1至M的正整数；
    处理模块，用于根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定M个第二信道估计信息，所述M个第二信道估计信息中的第m个第二信道估计信息对应所述第m个小区节点与所述终端设备之间的信道。
  28. 如权利要求27所述的装置，其特征在于，所述第二信道估计信息用于模型的训练；其中，在进行所述模型的训练时，所述模型的输入是根据所述第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与所述终端设备之间的信道所对应的第二信道估计信息确定的。
  29. 如权利要求27或28所述的装置，其特征在于，所述通信模块，还用于向第一设备发送K个第二信道估计信息，所述K个第二信道估计信息包含于所述M个第二信道估计信息，K为正整数。
  30. 如权利要求29所述的装置，其特征在于，所述通信模块，还用于从所述第一设备获取训练请求信息，所述训练请求信息用于请求所述K个第二信道估计信息。
  31. 如权利要求30所述的装置，其特征在于，所述训练请求信息用于指示所述第二信道估计信息指示的参数类型。
  32. 如权利要求27-31任一项所述的装置，其特征在于，所述通信模块，还用于从第一设备获取所述第m个第一信道估计信息；其中，所述第一设备为所述第m个小区节点，或者所述第一设备为所述终端设备。
  33. 如权利要求27-32任一项所述的装置，其特征在于，所述处理模块，具体用于：
    根据所述M个第一信道估计信息中的至少一个第一信道估计信息，确定所述终端设备的第一位置；
    根据所述终端设备的第一位置和所述M个小区节点的位置，确定所述M个第二信道估计信息。
  34. 如权利要求33所述的装置，其特征在于，所述处理模块，具体用于：
    根据所述M个第一信道估计信息和所述M个小区节点的位置，确定所述终端设备的多个第二位置；其中，所述多个第二位置中的第一部分位置位于第一区域，所述多个第二位置中的第二部分位置不位于所述第一区域，且所述第一部分位置的数量大于所述第二部分位置的数量；
    根据所述多个第二位置中的第一部分位置，确定所述终端设备的第一位置；或者，
    根据N个第一信道估计信息和N个小区节点的位置，确定所述终端设备的第一位置；其中，所述N个第一信道估计信息与所述N个小区节点一一对应，所述N个小区节点包含于所述M个小区节点，N为小于或者等于M的正整数；所述N个小区节点中每个小区节点与所述终端设备之间的路径为直射路径。
  35. 如权利要求27-34任一项所述的装置，其特征在于，所述第m个第一信道估计信息 用于指示以下中的一个或多个参数：所述第m个小区节点与所述终端设备之间的距离；所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；所述第m个小区节点对应的信号出发角度或信号到达角度；所述第m个小区节点与所述终端设备之间的信号质量；所述第m个第一信道估计信息用于指示所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径或者非直射路径。
  36. 如权利要求27-35任一项所述的装置，其特征在于，所述第m个第二信道估计信息用于指示以下至少一项：
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的距离；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点对应的信号出发角度或信号到达角度；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的信号质量；
    所述第m个小区节点与所述终端设备之间的实际信号传输路径为直射路径或者非直射路径。
  37. 如权利要求27-36任一项所述的装置，其特征在于，所述M个小区节点属于一个接入网设备，或者所述M个小区节点中至少两个小区节点所属的接入网设备不同。
  38. 一种通信装置，其特征在于，包括：
    处理模块，用于通过通信模块发送第m个第一信道估计信息，所述第m个第一信道估计信息属于M个第一信道估计信息，M为大于1的正整数，m为取遍1至M的正整数，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区节点中第m个小区节点与终端设备之间的信道的估计信息；其中，所述M个第一信道估计信息中的至少一个第一信道估计信息用于确定M个第二信道估计信息，所述M个第二信道估计信息中第m个第二信道估计信息对应所述第m个小区节点与所述终端设备之间的信道；
    所述通信模块，用于获取用于指示模型的信息；其中，在进行所述模型的训练时，所述模型的输入是根据所述第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
  39. 如权利要求38所述的装置，其特征在于，所述处理模块，还用于通过所述通信模块发送所述第m个小区节点与终端设备之间的信道的信道信息。
  40. 如权利要求38或39所述的装置，其特征在于，所述第m个第一信道估计信息用于指示以下中的一个或多个参数：所述第m个小区节点与所述终端设备之间的距离；所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；所述第m个小区节点对应的信号出发角度或信号到达角度；所述第m个小区节点与所述终端设备之间的信号质量；所述第m个第一信道估计信息用于指示所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径或者非直射路径。
  41. 如权利要求38-40任一项所述的装置，其特征在于，所述第m个第二信道估计信息 用于指示以下至少一项：
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的距离；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点对应的信号出发角度或信号到达角度；
    在所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第m个小区节点与所述终端设备之间的信号质量；
    所述第m个小区节点与所述终端设备之间的实际信号传输路径为直射路径或者非直射路径。
  42. 如权利要求38-41任一项所述的装置，其特征在于，所述M个小区节点属于一个接入网设备，或者所述M个小区节点中至少两个小区节点所属的接入网设备不同。
  43. 一种通信装置，其特征在于，包括：
    处理模块，用于确定K个信道信息，其中，所述K个信道信息中的第k个信道信息是K个小区节点中第k个小区节点与终端设备之间的信道的信道信息；其中，K为正整数，k为取遍1至K的正整数；
    通信模块，用于获取K个第二信道估计信息，所述K个第二信道估计信息中第k个第二信道估计信息对应所述第k个小区节点与所述终端设备之间的信道，所述K个第二信道估计信息由M个第一信道估计信息中的至少一个第一信道估计信息确定，其中，所述M个第一信道估计信息中的第m个第一信道估计信息是M个小区中第m个小区节点与所述终端设备之间的信道的估计信息，所述K个小区包含于所述M个小区，M为大于1的正整数，m取遍1至M的正整数；
    所述处理模块，还用于根据所述K个第二信道估计信息，进行模型的训练；其中，在进行所述模型的训练时，所述模型的输入是根据所述第k个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第k个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的。
  44. 如权利要求43所述的装置，其特征在于，所述通信模块，还用于发送训练请求信息，所述训练请求信息用于请求所述K个第二信道估计信息。
  45. 如权利要求44所述的装置，其特征在于，所述训练请求信息用于指示所述第二信道估计信息指示的参数类型。
  46. 如权利要求43或44所述的装置，其特征在于，所述通信模块，还用于发送所述第m个小区节点与所述终端设备之间的信道的第一信道估计信息。
  47. 如权利要求43-46任一项所述的装置，其特征在于，所述第m个第一信道估计信息用于指示以下中的一个或多个参数：所述第m个小区节点与所述终端设备之间的距离；所述第m个小区节点与所述终端设备之间的信号传输时延；所述第m个小区节点对应的信号出发角度或信号到达角度；所述第m个小区节点与所述终端设备之间的信号质量；所述第m个第一信道估计信息用于指示所述第m个小区节点与所述终端设备之间的信号传输路径为直射路径或者非直射路径。
  48. 如权利要求43-47任一项所述的装置，其特征在于，所述第k个第二信道估计信息用于指示以下至少一项：
    在所述第k个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第k个小区节点与所述终端设备之间的距离；
    在所述第k个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第k个小区节点与所述终端设备之间的信号传输时延或信号传输时延差；
    在所述第k个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第k个小区节点对应的信号出发角度或信号到达角度；
    在所述第k个小区节点与所述终端设备之间的信号传输路径为直射路径的情况下，所述第k个小区节点与所述终端设备之间的信号质量；
    所述第k个小区节点与所述终端设备之间的实际信号传输路径为直射路径或者非直射路径。
  49. 如权利要求43-48任一项所述的装置，其特征在于，所述M个小区节点属于一个接入网设备，或者所述M个小区节点中至少两个小区节点所属的接入网设备不同。
  50. 一种通信装置，其特征在于，包括：
    处理模块，用于确定第t个信道信息，其中，所述第t个信道信息是T个小区节点中第t个小区节点与终端设备之间的信道的信道信息；其中，T为大于1的正整数，t为取遍1至T的正整数；
    处理模块，还用于根据所述第t个信道信息和模型，确定第t个第三信道估计信息，所述第t个第三信道估计信息对应所述第t个小区节点与所述终端设备之间的信道；其中，所述模型的输入是根据所述第t个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的输出包括所述第t个第三信道估计信息；
    通信模块，用于发送所述第t个第三信道估计信息，所述第t个第三信道估计信息用于对所述终端设备进行定位。
  51. 如权利要求50所述的装置，其特征在于，所述第t个第三信道估计信息用于指示如下的一个或多个参数：所述第t个小区节点与所述终端设备之间的直射路径LOS的长度距离；所述第t个小区节点与所述终端设备之间符合LOS传输的信号传输时延或信道传输时延差；所述第t个小区节点对应的符合LOS传输的信号出发角度或信号到达角度；所述第t个小区节点与所述终端设备之间符合LOS传输的信号质量；所述第t个小区节点与所述终端设备之间的实际信号传输路径的类型；或，所述第t个小区节点与所述终端设备之间的实际信号传输路径的类型，其中，所述类型为LOS或非直射路径NLOS。
  52. 如权利要求50或51所述的装置，其特征在于，在进行所述模型的训练时，所述模型的输入是根据M个小区节点中第m个小区节点与终端设备之间的信道的信道信息确定的，所述输入对应的标签是根据所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息确定的；
    其中，M为大于1的正整数，M与T的取值相同或者不相同，m为取遍1至M的正整数；m取所述第m个小区节点与终端设备之间的信道所对应的第二信道估计信息是由M个第一信道估计信息中的至少一个第一信道估计信息确定的，所述M个第一信道估计信息中第m个第一信道估计信息是所述M个小区节点中第m个小区节点与终端设备之间的信 道的估计信息。
  53. 一种通信装置，其特征在于，包括：
    处理器，所述处理器和存储器耦合，所述处理器用于调用所述存储器存储的计算机程序指令，以执行如权利要求1-11任一项所述的方法。
  54. 一种通信装置，其特征在于，包括：
    处理器，所述处理器和存储器耦合，所述处理器用于调用所述存储器存储的计算机程序指令，以执行如权利要求12-16任一项所述的方法。
  55. 一种通信装置，其特征在于，包括：
    处理器，所述处理器和存储器耦合，所述处理器用于调用所述存储器存储的计算机程序指令，以执行如权利要求17-23任一项所述的方法。
  56. 一种通信装置，其特征在于，包括：
    处理器，所述处理器和存储器耦合，所述处理器用于调用所述存储器存储的计算机程序指令，以执行如权利要求24-26任一项所述的方法。
  57. 一种通信系统，其特征在于，
    包括权利要求27-37以及53中任一项所述的通信装置，以及以下中的一个或多个通信装置：
    权利要求38-42以及54中任一项所述的通信装置；
    权利要求43-49以及55中任一项所述的通信装置；
    权利要求50-52以及56中任一项所述的通信装置。
  58. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有指令，当所述指令在计算机上运行时，使得计算机执行以下中的一个或多个方法：如权利要求1-11任一项所述的方法；如权利要求12-16任一项所述的方法；如权利要求17-23任一项所述的方法；如权利要求24-26任一项所述的方法。
  59. 一种计算机程序产品，其特征在于，包括指令，当所述指令在计算机上运行时，使得计算机执行以下中的一个或多个方法：如权利要求1-11任一项所述的方法；如权利要求12-16任一项所述的方法；如权利要求17-23任一项所述的方法；如权利要求24-26任一项所述的方法。
PCT/CN2023/078190 2022-02-28 2023-02-24 一种通信方法及装置 WO2023160656A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210191893.7 2022-02-28
CN202210191893.7A CN116709170A (zh) 2022-02-28 2022-02-28 一种通信方法及装置

Publications (1)

Publication Number Publication Date
WO2023160656A1 true WO2023160656A1 (zh) 2023-08-31

Family

ID=87764845

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/078190 WO2023160656A1 (zh) 2022-02-28 2023-02-24 一种通信方法及装置

Country Status (2)

Country Link
CN (1) CN116709170A (zh)
WO (1) WO2023160656A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150049703A1 (en) * 2012-03-28 2015-02-19 Nec Corporation Communication channel quality estimating method, wireless communications system, base station, and program
CN109219947A (zh) * 2016-03-25 2019-01-15 高通股份有限公司 信道状态信息参考信号传输
CN112152948A (zh) * 2019-06-28 2020-12-29 华为技术有限公司 一种无线通信处理的方法和装置
CN113243135A (zh) * 2018-12-25 2021-08-10 华为技术有限公司 获取下行信道信息的方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150049703A1 (en) * 2012-03-28 2015-02-19 Nec Corporation Communication channel quality estimating method, wireless communications system, base station, and program
CN109219947A (zh) * 2016-03-25 2019-01-15 高通股份有限公司 信道状态信息参考信号传输
CN113243135A (zh) * 2018-12-25 2021-08-10 华为技术有限公司 获取下行信道信息的方法和装置
CN112152948A (zh) * 2019-06-28 2020-12-29 华为技术有限公司 一种无线通信处理的方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
HUAWEI: "CQI and PMI resource management", 3GPP DRAFT; R1-074233, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. RAN WG1, no. Shanghai, China; 20071002, 2 October 2007 (2007-10-02), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , XP050107759 *

Also Published As

Publication number Publication date
CN116709170A (zh) 2023-09-05

Similar Documents

Publication Publication Date Title
EP3844982A1 (en) Method and apparatus for location services
KR102154481B1 (ko) 딥러닝을 이용한 대규모 mimo 시스템의 빔포밍 장치 및 방법
US11012133B2 (en) Efficient data generation for beam pattern optimization
EP3990939B1 (en) Method and apparatus for localization
WO2022073207A1 (zh) 模型评估方法及装置
US20230362039A1 (en) Neural network-based channel estimation method and communication apparatus
WO2022174642A1 (zh) 基于空间划分的数据处理方法和通信装置
WO2023125660A1 (zh) 一种通信方法及装置
US20240314727A1 (en) Positioning method, model training method, and first device
Hashem et al. Deepnar: Robust time-based sub-meter indoor localization using deep learning
Vankayala et al. Deep-learning based proactive handover for 5G/6G mobile networks using wireless information
Jiang et al. Sensing aided reconfigurable intelligent surfaces for 3gpp 5g transparent operation
Wang et al. Mobile device localization in 5G wireless networks
WO2022048921A1 (en) Hierarchical positioning for low cost and low power asset tracking
Liu et al. D-Fi: Domain adversarial neural network based CSI fingerprint indoor localization
WO2023160656A1 (zh) 一种通信方法及装置
US12015966B2 (en) Method and apparatus for sensor selection for localization and tracking
WO2023160633A1 (zh) 一种通信方法及装置
WO2021237463A1 (en) Method and apparatus for position estimation
Almutairi et al. Deep Transfer Learning for Cross-Device Channel Classification in mmWave Wireless
Lin et al. Multi-camera view based proactive bs selection and beam switching for v2x
WO2024193453A1 (zh) 定位方法、通信装置及存储介质
WO2024207485A1 (zh) 无线通信的方法及设备
WO2023231842A1 (zh) 感知方式切换方法、装置、终端及网络侧设备
Bouazizi et al. A Novel Approach for Inter-User Distance Estimation in 5G mmWave Networks Using Deep Learning

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23759278

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023759278

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2023759278

Country of ref document: EP

Effective date: 20240905