Method for configuring reference signal
Embodiments of this application provide a method for configuring a reference signal, to increase a rate of data transmission between an access network device and a terminal device. The method includes: An access network device determines a first reference signal pool, where the first reference signal pool includes one or more reference signals. The access network device sends first information to a first terminal device, where the first information indicates a first reference signal allocated to the first terminal device, the first reference signal is included in the first reference signal pool, and the first reference signal pool is obtained by the access network device by training a first neural network, or the first reference signal pool is obtained by another network-side node by training a first neural network and sent to the access network device.
1 . A method for configuring a reference signal, comprising:
receiving first information from an access network device, wherein the first information indicates a first reference signal allocated to a first terminal device, wherein
the first reference signal is comprised in a first reference signal pool, the first reference signal pool comprises one or more reference signals, and the first reference signal pool is obtained by training a first neural network.
2 . The method according to claim 1 , wherein
the first information comprises a sequence value of the first reference signal;
the first information comprises a compressed value of a sequence value of the first reference signal;
the first information comprises an offset value of a sequence value of the first reference signal relative to a sequence value of a reference signal previously configured for the first terminal device;
the first information comprises a compressed value of an offset value of a sequence value of the first reference signal relative to a sequence value of a reference signal previously configured for the first terminal device;
the first information indicates an index of the first reference signal pool in M1 reference signal pools and an index of the first reference signal in the first reference signal pool, wherein M1 is an integer greater than or equal to 1; or
the first information indicates an index of the first reference signal pool in M1 reference signal pools, an index of a reference signal group to which the first reference signal belongs in the first reference signal pool, and an index of the first reference signal in the reference signal group, wherein M1 is an integer greater than or equal to 1.
3 . The method according to claim 2 , wherein the method further comprises:
receiving information about the M1 reference signal pools from the access network device.
4 . A method for configuring a reference signal, comprising:
determining a first reference signal pool, wherein the first reference signal pool comprises one or more reference signals, and the first reference signal pool is obtained by training a first neural network; and
sending first information to a first terminal device, wherein the first information indicates a first reference signal allocated to the first terminal device, and the first reference signal is comprised in the first reference signal pool.
5 . The method according to claim 4 , wherein
the first information comprises a sequence value of the first reference signal;
the first information comprises a compressed value of a sequence value of the first reference signal;
the first information comprises an offset value of a sequence value of the first reference signal relative to a sequence value of a reference signal previously configured for the first terminal device; or
the first information comprises an offset value of a sequence value of the first reference signal relative to a sequence value of a reference signal previously configured for the first terminal device.
6 . The method according to claim 4 , wherein the determining a first reference signal pool comprises:
determining the first reference signal pool from M1 reference signal pools based on first feature information of N1 terminal devices, wherein the first terminal device is comprised in the N1 terminal devices, the M1 reference signal pools are obtained by training the first neural network, M1 is an integer greater than or equal to 1, and N1 is an integer greater than or equal to 2.
7 . The method according to claim 6 , wherein
the first information indicates an index of the first reference signal pool in the M1 reference signal pools and an index of the first reference signal in the first reference signal pool; or
the first information indicates an index of the first reference signal pool in the M1 reference signal pools, an index of a reference signal group to which the first reference signal belongs in the first reference signal pool, and an index of the first reference signal in the reference signal group.
8 . The method according to claim 6 , wherein the method further comprises:
receiving information about the M1 reference signal pools from the access network device.
9 . The method according to claim 6 , wherein
for each reference signal pool in the M1 reference signal pools, the reference signal pool is obtained by training the first neural network based on a training parameter and a training sample set, wherein
the training parameter comprises one or more of the following parameters: a quantity of reference signals in the reference signal pool, a sequence length of the reference signal in the reference signal pool, a sequence value range of the reference signal in the reference signal pool, grouping information of the reference signal in the reference signal pool, and a performance requirement of the reference signal in the reference signal pool; and
the training sample set comprises P1 training samples, wherein each training sample comprises one or more of the following parameters of each of N2 terminal devices: channel information and a data transmission state, P1 is an integer greater than or equal to 1, and N2 is an integer greater than or equal to 1.
10 . The method according to claim 9 , wherein
the channel information is agreed on in a standard;
the channel information is obtained through uplink measurement;
the channel information is received from the N2 terminal devices; or
the channel information is obtained through inference by using a second neural network.
11 . The method according to claim 6 , wherein
the first feature information of the N1 terminal devices comprises one or more of the following information of each terminal device: location information, service feature information, data transmission state information, and channel information.
12 . The method according to claim 4 , wherein
the first reference signal pool is obtained by training the first neural network based on a training parameter and a training sample set, wherein
the training parameter comprises one or more of the following parameters: a quantity of reference signals in the first reference signal pool, a sequence length of the reference signal in the first reference signal pool, a sequence value range of the reference signal in the first reference signal pool, grouping information of the reference signal in the first reference signal pool, and a performance requirement of the reference signal in the first reference signal pool; and
the training sample set comprises P2 training samples, wherein each training sample comprises one or more of the following parameters of each of N1 terminal devices: channel information and a data transmission state, the first terminal device is comprised in the N1 terminal devices, P2 is an integer greater than or equal to 1, and N1 is an integer greater than or equal to 2.
13 . The method according to claim 12 , wherein the method further comprises:
receiving an uplink signal from each of the N1 terminal devices, and estimating the channel information of each terminal device in the N1 terminal devices based on the received uplink signal.
14 . The method according to claim 4 , wherein that the first reference signal pool is obtained by training a first neural network comprises:
the first reference signal pool is obtained through a first process, wherein the first process comprises:
operation 1: receiving N1 reference signals from N1 terminal devices, wherein each terminal device corresponds to one reference signal;
operation 2: determining N1 updated reference signals of the N1 reference signals based on reception information of the N1 reference signals by using the first neural network;
operation 3: separately indicating an updated reference signal of each terminal device to at least one terminal device in the N1 terminal devices; and
operation 4: stopping the first process when it is determined that a first condition is satisfied, wherein the N1 updated reference signals constitute the first reference signal pool; or otherwise, performing operation 1 again.
15 . The method according to claim 14 , wherein the first condition comprises:
a quantity of iterations of the first process satisfies a threshold requirement;
a duration of the first process satisfies a threshold requirement;
in the first process, a quantity of transmissions of the reference signal satisfies a threshold requirement;
in the first process, a quantity of undetected reference signals satisfies a threshold requirement;
in the first process, a missing detection rate of the reference signal satisfies a threshold requirement;
in the first process, a quantity of falsely alarmed reference signals satisfies a threshold requirement; or
in the first process, a false alarm rate of the reference signal satisfies a threshold requirement.
16 . The method according to claim 4 , wherein the method further comprises:
sending second information to a second terminal device, wherein the second information indicates a second reference signal allocated to the second terminal device, the second reference signal is comprised in the first reference signal pool, and the first terminal device and the second terminal device are comprised in the N1 terminal devices, wherein
based on the first terminal device and the second terminal device belonging to a same terminal device group in the N1 terminal devices, the first reference signal and the second reference signal belong to a same reference signal group in the first reference signal pool; or
based on the first terminal device and the second terminal device belonging to different terminal device groups in the N1 terminal devices, the first reference signal and the second reference signal belong to different reference signal groups in the first reference signal pool.
17 . The method according to claim 16 , wherein the method further comprises:
determining a terminal device group corresponding to the N1 terminal devices based on the first feature information of the N1 terminal devices, wherein the first feature information of the N1 terminal devices comprises one or more of the following information of each terminal device: the location information, the service feature information, the data transmission state information, and the channel information.
18 . A communication apparatus, comprising a processor and a memory, wherein the memory is coupled to the processor, and the processor is configured to perform the method according to claim 1 .
19 . A communication apparatus, comprising a processor and a memory, wherein the memory is coupled to the processor, and the processor is configured to perform the method according to claim 4 .
20 . A communication apparatus, comprising a processor and a communication interface, wherein the processor implements the method according to claim 1 through the communication interface.