WO2024077461A1 - 一种波束确定方法、装置、设备及存储介质 - Google Patents

一种波束确定方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2024077461A1
WO2024077461A1 PCT/CN2022/124469 CN2022124469W WO2024077461A1 WO 2024077461 A1 WO2024077461 A1 WO 2024077461A1 CN 2022124469 W CN2022124469 W CN 2022124469W WO 2024077461 A1 WO2024077461 A1 WO 2024077461A1
Authority
WO
WIPO (PCT)
Prior art keywords
receiving
prediction model
optimal
pairs
beams
Prior art date
Application number
PCT/CN2022/124469
Other languages
English (en)
French (fr)
Inventor
李明菊
Original Assignee
北京小米移动软件有限公司
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 北京小米移动软件有限公司 filed Critical 北京小米移动软件有限公司
Priority to PCT/CN2022/124469 priority Critical patent/WO2024077461A1/zh
Priority to CN202280004077.9A priority patent/CN118202593A/zh
Publication of WO2024077461A1 publication Critical patent/WO2024077461A1/zh

Links

Images

Definitions

  • the present disclosure relates to the field of communication technology, and in particular to a beam determination method, apparatus, device and storage medium.
  • NR new radio
  • beam-based transmission and reception are required to ensure coverage due to the rapid attenuation of high-frequency channels.
  • the base station configures a reference signal resource set for beam measurement.
  • the terminal measures the reference signal resources in the reference signal resource set and then reports one or more stronger reference signal resource identifiers and the corresponding reference signal beam quality.
  • the terminal needs to measure the reference signal for each beam pair.
  • a receive beam and a transmit beam constitute a beam pair.
  • the beam quality of all beam pairs can be obtained by predicting with an artificial intelligence (AI) model.
  • AI artificial intelligence
  • the AI model is related to the number of receiving beams.
  • the output of the model is unchanged, but different terminals may support different numbers of receiving beams, so that the total number of beam pairs will also change. Therefore, how to ensure that terminals supporting different numbers of receiving beams can be applied to the same AI model to predict the beam quality of beam pairs is an urgent problem to be solved.
  • the present disclosure provides a beam determination method, apparatus, device and storage medium.
  • a beam determination method is provided, which is applied to a first device and includes: determining the number of receiving beams supported by a beam prediction model; and determining an optimal beam from an output of the beam prediction model based on the number of receiving beams supported by the beam prediction model.
  • a beam determination device configured on a first device and includes: a determination module, used to determine the number of receiving beams supported by a beam prediction model; the determination module is also used to determine the optimal beam from the output of the beam prediction model based on the number of receiving beams supported by the beam prediction model.
  • a beam determination device comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to: execute any one of the methods in the first aspect.
  • a non-temporary computer-readable storage medium When instructions in the storage medium are executed by a processor of a first device, the first device is enabled to execute any one of the methods in the first aspect.
  • the technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: through the number of receiving beams supported by the beam prediction model, the optimal beam can be determined from the output of the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • Fig. 1 is a schematic diagram of a wireless communication system according to an exemplary embodiment.
  • Fig. 2 is a flow chart of a beam determination method according to an exemplary embodiment.
  • Fig. 3 is a flow chart of another beam determination method according to an exemplary embodiment.
  • Fig. 4 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 5 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 6 is a flow chart of another beam determination method according to an exemplary embodiment.
  • Fig. 7 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 8 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 9 is a flow chart of another beam determination method according to an exemplary embodiment.
  • Fig. 10 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 11 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 12 is a flow chart of another beam determination method according to an exemplary embodiment.
  • Fig. 13 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 14 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 15 is a flow chart of another beam determination method according to an exemplary embodiment.
  • Fig. 16 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 17 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 18 is a flow chart of another beam determination method according to an exemplary embodiment.
  • Fig. 19 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 20 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • Fig. 21 is a flow chart of another beam determination method according to an exemplary embodiment.
  • Fig. 22 is a schematic diagram of a beam determination device according to an exemplary embodiment.
  • Fig. 23 is a schematic diagram of another beam determination device according to an exemplary embodiment.
  • Fig. 24 is a schematic diagram of a beam determination device according to an exemplary embodiment.
  • Fig. 25 is a schematic diagram of another beam determination device according to an exemplary embodiment.
  • the communication method involved in the present disclosure can be applied to the wireless communication system 100 shown in Figure 1.
  • the network system may include a network device 110 and a terminal 120.
  • the wireless communication system shown in Figure 1 is only for schematic illustration, and the wireless communication system may also include other network devices, for example, core network devices, wireless relay devices, and wireless backhaul devices, which are not shown in Figure 1.
  • the embodiment of the present disclosure does not limit the number of network devices and the number of terminals included in the wireless communication system.
  • the wireless communication system of the embodiment of the present disclosure is a network that provides wireless communication functions.
  • the wireless communication system can adopt different communication technologies, such as Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency-Division Multiple Access (OFDMA), Single Carrier FDMA (SC-FDMA), and Carrier Sense Multiple Access with Collision Avoidance.
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency-Division Multiple Access
  • SC-FDMA Single Carrier FDMA
  • Carrier Sense Multiple Access with Collision Avoidance According to the capacity, rate, delay and other factors of different networks, networks can be divided into 2G (English: Generation) networks, 3G networks, 4G networks or future evolution networks, such as the 5th Generation Wireless Communication System (5G) network. 5G
  • the network device 110 involved in the present disclosure may also be referred to as a wireless access network device.
  • the wireless access network device may be: a base station, an evolved Node B (eNB), a home base station, an access point (AP) in a wireless fidelity (WIFI) system, a wireless relay node, a wireless backhaul node or a transmission point (TP), etc. It may also be a gNB in an NR system, or it may also be a component or part of a device constituting a base station, etc.
  • the network device may also be a vehicle-mounted device.
  • V2X vehicle-to-everything
  • the terminal 120 involved in the present disclosure may also be referred to as a terminal device, a user equipment (UE), a mobile station (MS), a mobile terminal (MT), etc., which is a device that provides voice and/or data connectivity to users.
  • the terminal may be a handheld device with a wireless connection function, a vehicle-mounted device, etc.
  • some examples of terminals are: a smart phone (Mobile Phone), a pocket computer (Pocket Personal Computer, PPC), a handheld computer, a personal digital assistant (Personal Digital Assistant, PDA), a laptop computer, a tablet computer, a wearable device, or a vehicle-mounted device, etc.
  • V2X vehicle-to-everything
  • the terminal device may also be a vehicle-mounted device. It should be understood that the embodiments of the present disclosure do not limit the specific technology and specific device form adopted by the terminal.
  • the network device 110 and the terminal 120 may use any feasible wireless communication technology to achieve mutual data transmission.
  • the transmission channel corresponding to the data sent by the network device 110 to the terminal 120 is called a downlink channel (DL)
  • the transmission channel corresponding to the data sent by the terminal 120 to the network device 110 is called an uplink channel (UL).
  • DL downlink channel
  • UL uplink channel
  • the network device involved in the embodiments of the present disclosure may be a base station.
  • the network device may also be any other possible network device
  • the terminal may be any possible terminal, which is not limited by the present disclosure.
  • the network device configures a reference signal resource set for beam measurement.
  • the terminal measures the reference signal resources in the reference signal resource set and then reports one or more reference signal resource identifiers that are relatively strong, as well as the corresponding layer-1 reference signal received power (layer-1 reference signal received power, L1-RSRP) and/or layer-1 signal to interference plus noise ratio (layer-1 signal to interference plus noise ratio, L1-SINR).
  • the terminal needs to measure the reference signal for each beam pair.
  • a receiving beam and a transmitting beam constitute a beam pair.
  • the reference signal resource set configured by the network device contains X reference signals, and each reference signal corresponds to a different transmitting beam of the network device.
  • the terminal For each reference signal, the terminal needs to use all receiving beams to measure the reference signal to obtain the beam quality corresponding to all receiving beams respectively, and determine the best beam quality. Therefore, the number of beam pairs that the terminal needs to measure is A*B. Among them, A is the number of transmitting beams of the network device, and B is the number of receiving beams of the terminal.
  • the number of beam pairs that the terminal originally needs to measure is A*B.
  • the AI model the terminal only needs to measure part of the A*B beam pairs, such as 1/8 or 1/4 of the A*B beam pairs, and so on.
  • the measured beam quality of the beam pair is then input into the AI model, and the AI model can output at least one of the beam quality of the A*B beam pairs, the strongest beam pair among the A*B beam pairs, the strongest a transmit beams, and the strongest b receive beams. It can be understood that a is less than or equal to A, and b is less than or equal to B.
  • the AI model is related to the number of receiving beams. So whether to train different AI models for different numbers of receiving beams, or to train the same AI model, and how to instruct the terminal are issues that need to be solved.
  • the present disclosure provides a beam determination method, which can determine the optimal beam from the output of the beam prediction model through the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the first device is a terminal and the second device is a network device; or, when the first device is a network device, the second device is a terminal.
  • FIG. 2 is a flow chart of a beam determination method according to an exemplary embodiment. As shown in FIG. 2 , the method is applied to a terminal and may include the following steps:
  • step S11 the number of receiving beams supported by the beam prediction model is determined.
  • the terminal may determine the number of receive beams supported by the beam prediction model.
  • the terminal can directly determine the number of receiving beams supported by the beam prediction model.
  • the terminal can determine the number of receiving beams supported by the beam prediction model through indication information of the other device.
  • step S12 based on the number of receiving beams supported by the beam prediction model, an optimal beam is determined from the output of the beam prediction model.
  • the terminal may determine the optimal beam from the output of the beam prediction model based on the number of receiving beams supported by the beam prediction model determined in S11.
  • the optimal beam may be a beam with the best beam quality when the terminal communicates.
  • the optimal beam may include at least one of an optimal transmit beam, an optimal receive beam, and an optimal beam pair.
  • the optimal beam pair includes a transmit beam and a receive beam.
  • the optimal beam may include one optimal beam or multiple optimal beams.
  • the present invention can determine the optimal beam from the output of the beam prediction model through the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • FIG. 3 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG. 3 , determining the number of receiving beams supported by the beam prediction model in S11 may include the following steps:
  • step S21 first indication information sent by a network device is received.
  • the terminal may receive first indication information sent by the network device, wherein the first indication information is used to indicate the number of receiving beams supported by the beam prediction model.
  • the network device may be a device for which a beam prediction model is pre-trained.
  • step S22 the number of receiving beams supported by the beam prediction model is determined based on the first indication information.
  • the terminal may determine the number of receiving beams supported by the beam prediction model based on the first indication information received in S21.
  • the present disclosure can also determine the number of receiving beams supported by the beam prediction model through indication information from other devices, so that the optimal beam can be determined from the output of the beam prediction model based on the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the number of receiving beams supported by the beam prediction model may include: the maximum number of receiving beams supported by the beam prediction model; or one or more numbers of receiving beams supported by the beam prediction model.
  • the number of receiving beams that the beam prediction model can support may be the maximum number of receiving beams supported by the beam prediction model, for example, recorded as Rx_num.
  • the number of receiving beams that the beam prediction model can support can be one or more numbers of receiving beams.
  • the beam prediction model can support one or more different numbers of receiving beams, and the one or more numbers of receiving beams can correspond to one number of receiving beams or multiple different numbers of receiving beams that the beam prediction model can support.
  • the present disclosure determines the optimal beam from the output of the beam prediction model by the number of receiving beams that the beam prediction model can support, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the multiple numbers of receiving beams in response to the beam prediction model supporting multiple numbers of receiving beams, may include a first number and a second number, wherein the first number is the maximum number of receiving beams supported by the beam prediction model, the first number is N times the second number, the minimum value of the second number is 1, and N is a positive integer.
  • the beam prediction model may support multiple numbers of receive beams.
  • the multiple numbers of receive beams may include a first number indicating the maximum number of receive beams supported by the beam prediction model. It is understood that the first number may be Rx_num.
  • the multiple numbers of receive beams may include a second number, wherein the first number is N times the second number, the minimum value of the second number is 1, and N is a positive integer.
  • the multiple numbers of receiving beams may include one or more second numbers.
  • the multiple numbers of receiving beams may include Rx_num,
  • the number of receiving beams may include Rx_num,
  • the number of receiving beams may include Rx_num, ..., 1. It can be understood that the above is only an exemplary description, and the present disclosure does not limit how many second numbers are included in the multiple numbers of receiving beams, nor does it limit the multiple relationship between the specific second number and the first number.
  • the first number may be 2 n times the second number, where n is a non-negative integer.
  • the second number may be etc.
  • the beam prediction model in the present disclosure can support multiple different numbers of receiving beams, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the optimal beam is determined from the output of the beam prediction model, including: receiving second indication information sent by a network device; determining the optimal beam from the output of the beam prediction model based on the second indication information; or, determining the optimal beam from the output of the beam prediction model according to a predefined rule.
  • FIG4 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG4 , determining the optimal beam from the output of the beam prediction model in S12 may include the following steps:
  • step S31 second indication information sent by the network device is received.
  • the terminal may receive second indication information sent by the network device, where the second indication information is used to indicate the optimal beam.
  • the second indication information may be the beam identification range where the optimal beam is located.
  • the terminal may determine the optimal beam from the beams within the beam identification range where the optimal beam is located.
  • the second indication information may be the beam quality corresponding to the optimal beam.
  • it may also be any equivalent information used to indicate the optimal beam, which is not limited in the present disclosure.
  • the network device can use the beam prediction model to predict the optimal beam, and the network device indicates the predicted optimal beam to the terminal through the second indication information.
  • step S32 an optimal beam is determined from the output of the beam prediction model based on the second indication information.
  • the terminal may determine the optimal beam from the output of the beam prediction model based on the second indication information received in S31.
  • FIG5 is a flow chart of yet another beam determination method according to an exemplary embodiment.
  • step S41 the optimal beam is determined from the output of the beam prediction model according to predefined rules.
  • the terminal may determine the optimal beam from the output of the beam prediction model according to a predefined rule.
  • the output of the beam prediction model is all beam identifiers.
  • the terminal can determine the beam identifier range corresponding to the optimal beam according to predefined rules, and then determine the optimal beam from the beams within the beam identifier range corresponding to the optimal beam.
  • the optimal beam is predicted by using a beam prediction model on a network device, and the terminal may determine the beam identification range corresponding to the optimal beam by using predefined rules or indication information of the network device, and determine the optimal beam from the beams within the beam identification range corresponding to the optimal beam.
  • the terminal may also determine the beam quality corresponding to the optimal beam by using the indication information of the network device, and determine the optimal beam.
  • the optimal beam is predicted by using a beam prediction model on the terminal, and the terminal may determine the optimal beam from the beams output by the beam prediction model by using predefined rules.
  • the present disclosure can determine the optimal beam from the output of the beam prediction model through the indication information of the network device or the predefined rules, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • FIG6 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG6, determining the optimal beam from the output of the beam prediction model in S32 or S41 may include the following steps:
  • step S51 in response to the output of the beam prediction model including beam quality information of the maximum number of beam pairs supported by the beam prediction model, an optimal beam is determined from the output of the beam prediction model based on the number of receiving beams supported by the terminal.
  • the terminal in response to the output of the beam prediction model including beam quality information of the maximum number of beam pairs supported by the beam prediction model, such as the reference signal received power (RSRP) and/or signal to interference plus noise ratio (SINR) of the maximum number of beam pairs.
  • the maximum number may be the product of the number of transmit beams Tx_num of the network device and the maximum number of receive beams Rx_num supported by the beam prediction model, i.e., Tx_num ⁇ Rx_num.
  • the terminal may determine the optimal beam from the output of the beam prediction model based on the number of receive beams supported by the terminal. That is, the terminal may determine the optimal beam from the beam quality information of the maximum number of beam pairs based on the number of receive beams supported by the terminal.
  • the optimal beam can be determined from the output of the beam prediction model based on the number of receiving beams supported by the terminal, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • FIG7 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG7, in S51, based on the number of receiving beams supported by the terminal, determining the optimal beam from the output of the beam prediction model may include the following steps:
  • step S61 in response to the number of receiving beams supported by the terminal being the maximum number of receiving beams supported by the beam prediction model, an optimal beam is determined from the maximum number of beam pairs.
  • the terminal can determine the optimal beam from the maximum number of beam pairs.
  • the terminal determines one or more beam pairs with the best beam quality from the maximum number of beam pairs. If the optimal beam is the optimal receiving beam, the receiving beam corresponding to the one or more beam pairs with the best beam quality can be used as the optimal receiving beam. If the optimal beam is the optimal transmitting beam, the transmitting beam corresponding to the one or more beam pairs with the best beam quality can be used as the optimal transmitting beam. If the optimal beam is the optimal beam pair, the one or more beam pairs with the best beam quality can be used as the optimal beam pair.
  • the present invention can determine the optimal beam from the maximum number of beam pairs output by the beam prediction model when the number of receiving beams supported by the terminal is the maximum number of receiving beams supported by the beam prediction model, so that the beam prediction model can adapt to the terminal whose number of receiving beams is the maximum number of receiving beams supported by the beam prediction model.
  • FIG8 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG8, in S51, based on the number of receiving beams supported by the terminal, determining the optimal beam from the output of the beam prediction model may include the following steps:
  • step S71 in response to the number of receiving beams supported by the terminal being the third number, the maximum number of beam pairs are divided into M groups, and the optimal beam is determined from the beam pairs included in any one of the M groups.
  • the maximum number of beam pairs may be divided into M groups.
  • the terminal determines the optimal beam from the beam pairs included in any one of the M groups.
  • the third number is 1/M of the maximum number of receiving beams supported by the beam prediction model, and M is a positive integer.
  • the third quantity is When the number of receiving beams supported by the terminal is When the maximum number of beam pairs can be divided into M groups, each group can include The terminal can determine the optimal beam pair from the beam pairs contained in any one of the M groups. The beams are aligned to determine the optimal beam.
  • M is 2, then the third number is The maximum number of beam pairs can be divided into 2 groups, and the terminal can receive the beams from any of the 2 groups. In other words, the terminal determines the optimal beam from any half of the beam pairs in the maximum number of beam pairs.
  • M is 4, then the third number is The maximum number of beam pairs can be divided into 4 groups, and the terminal can receive the In other words, the terminal determines the optimal beam from one quarter of the beam pairs among the maximum number of beam pairs.
  • M is 2 n' .
  • n' is a non-negative integer.
  • the third number is etc.
  • the minimum value of the third number may be 1, that is, M is equal to Rx_num. Accordingly, dividing the maximum number of beam pairs into M groups may be dividing the maximum number of beam pairs into Rx_num groups.
  • the present invention discloses, when the number of receiving beams supported by the terminal is a partial number of receiving beams in the maximum number of receiving beams supported by the beam prediction model, grouping the maximum number of beam pairs, and determining the optimal beam from multiple beam pairs in any group, so that the beam prediction model can adapt to the terminal whose number of receiving beams is a partial number of receiving beams in the maximum number of receiving beams supported by the beam prediction model.
  • dividing the maximum number of beam pairs into M groups in S71 may include at least one of the following: dividing the maximum number of beam pairs into M groups according to the beam pairs, wherein the beam pair numbers of the beam pairs in each group are continuous or non-continuous; dividing the maximum number of beam pairs into M groups according to the receiving beams corresponding to the beam pairs, wherein the beam pairs corresponding to the same receiving beam belong to the same group; dividing the maximum number of beam pairs into M groups, wherein the beam pairs corresponding to the same receiving beam are divided into M small groups, and the M small groups correspond one-to-one to the M groups.
  • dividing the maximum number of beam pairs into M groups may be: dividing the maximum number of beam pairs into M groups according to the beam pairs. The beam pairs in each group have consecutive beam pair numbers.
  • the maximum number of beam pairs is divided into M groups according to the beam pairs.
  • the maximum number of beam pairs is 32 beam pairs and the M groups are 4 groups.
  • the 32 beam pairs can be divided into 4 groups according to the beam pairs, and each group can include 8 beam pairs.
  • the beam pair numbers of the 8 beam pairs in each group are continuous.
  • the beam pair number can be a beam pair identifier, and the identifier is, for example, an identity (ID) or an index.
  • the maximum number of beam pairs can be divided into 2 groups according to the beam pairs.
  • the beam pair numbers of the beam pairs in each group are continuous. That is, each group corresponds to half of the maximum number of beam pairs.
  • the 2 groups can correspond to the first half of the maximum number of beam pairs and the second half of the maximum number of beam pairs, respectively. It can be understood that the beam pair numbers of the beam pairs in the first half of the maximum number of beam pairs are all continuous, and the beam pair numbers of the beam pairs in the second half of the maximum number of beam pairs are all continuous.
  • M is 4 and the third quantity is
  • the maximum number of beam pairs can be divided into 4 groups according to the beam pairs.
  • the beam pair numbers of the beam pairs in each group are continuous. That is, each group corresponds to one quarter of the beam pairs in the maximum number of beam pairs. It can be understood that the beam pair numbers of one quarter of the beam pairs in the maximum number of beam pairs corresponding to any group are continuous.
  • dividing the maximum number of beam pairs into M groups may be: dividing the maximum number of beam pairs into M groups according to the beam pairs, wherein the beam pair numbers of the beam pairs in each group are non-consecutive.
  • the maximum number of beam pairs is divided into M groups according to the beam pairs.
  • the maximum number of beam pairs is 32 beam pairs and the M groups are 4 groups.
  • the 32 beam pairs can be divided into 4 groups according to the beam pairs, and each group can include 8 beam pairs.
  • the beam pair numbers of the 8 beam pairs in each group are non-continuous.
  • the beam pair number can be a beam pair identifier, and the identifier is, for example, an ID or an index.
  • the maximum number of beam pairs may be divided into two groups according to the beam pairs.
  • the beam pair numbers of the beam pairs in each group are non-continuous. That is, each group corresponds to half of the maximum number of beam pairs.
  • the two groups may correspond to the half of the beam pairs with odd numbers and the half of the beam pairs with even numbers, respectively.
  • M is 4 and the third quantity is
  • the maximum number of beam pairs can be divided into 4 groups according to the beam pairs.
  • the beam pairs in each group are numbered non-continuously. That is to say, each group corresponds to one quarter of the beam pairs in the maximum number of beam pairs, and the beam pairs in each group are numbered non-continuously.
  • the beam pairs in group 1 can be numbered 1, 5, 9, 13; the beam pairs in group 2 can be numbered 2, 6, 10, 14; the beam pairs in group 3 can be numbered 3, 7, 11, 15; the beam pairs in group 4 can be numbered 4, 8, 12, 16.
  • the maximum number of beam pairs are divided into M groups according to the receiving beams corresponding to the beam pairs, wherein the beam pairs corresponding to the same receiving beam belong to the same group.
  • the maximum number of beam pairs are divided into M groups according to the receiving beams corresponding to the beam pairs.
  • the beam pairs corresponding to the same receiving beam belong to the same group.
  • the 32 beam pairs can be divided into 4 groups according to the receiving beams corresponding to the beam pairs.
  • the beam pairs corresponding to the same receiving beam belong to the same group.
  • the beam pairs contained in each of the 4 groups can correspond to one or more receiving beam groups.
  • the beam pairs contained in any one group correspond to the same receiving beam, or any one group can contain beam pairs corresponding to multiple receiving beams.
  • the beam pairs corresponding to the same receiving beam should belong to the same group.
  • the value of M should be less than or equal to the maximum number of receiving beams supported by the model.
  • the beam pair numbers of the beam pairs in each of the above-mentioned M groups may be continuous or non-continuous.
  • the beam pair numbers of the beam pairs in the group may be continuous.
  • the beam pair numbers of the beam pairs in the group may be continuous.
  • the beam pairs contained in any group correspond to receiving beams with receiving beam numbers of 1 and 2, the beam pair numbers of the beam pairs in the group may be continuous.
  • the beam pair numbers of the beam pairs in the group may be non-continuous.
  • the beam pairs contained in any group correspond to receiving beams with receiving beam numbers of 1 and 5
  • the beam pair numbers of the beam pairs in the group may be non-continuous. That is, the beam pairs in the group are numbered as follows: a receiving beam numbered 1 corresponds to a plurality of beam pairs with consecutive beam pair numbers, and a receiving beam numbered 5 corresponds to a plurality of beam pairs with consecutive beam pair numbers.
  • the receiving beam is the receiving beam of the terminal and the transmitting beam is the transmitting beam of the network device
  • the number of beam pairs corresponding to each receiving beam should be the same as the number of transmitting beams Tx_num of the network device.
  • the maximum number of receiving beams supported by the model is 8.
  • the maximum number of beam pairs can be divided into 2 groups according to the receiving beams corresponding to the beam pairs. Among them, the beam pairs corresponding to the same receiving beam belong to the same group. That is to say, each group corresponds to half of the maximum number of beam pairs, and each group contains beam pairs corresponding to 4 receiving beams.
  • the 4 receiving beams corresponding to each group can be 4 continuous receiving beams, or 4 non-continuous receiving beams.
  • the 4 receiving beams corresponding to the 2 groups can be receiving beam 1, receiving beam 2, receiving beam 3 and receiving beam 4, and receiving beam 5, receiving beam 6, receiving beam 7 and receiving beam 8.
  • the beam pair numbers of the beam pairs in the 2 groups can be continuous.
  • the 4 receiving beams corresponding to the 2 groups can be receiving beam 1, receiving beam 3, receiving beam 5 and receiving beam 7, and receiving beam 2, receiving beam 4, receiving beam 6 and receiving beam 8.
  • the beam pair numbers of the beam pairs in the two groups may be non-continuous.
  • the beam pair numbers of the beam pairs in one group are: multiple beam pairs with continuous beam pair numbers corresponding to receive beam 1, multiple beam pairs with continuous beam pair numbers corresponding to receive beam 3, multiple beam pairs with continuous beam pair numbers corresponding to receive beam 5, and multiple beam pairs with continuous beam pair numbers corresponding to receive beam 7;
  • the beam pair numbers of the beam pairs in the other group are: multiple beam pairs with continuous beam pair numbers corresponding to receive beam 2, multiple beam pairs with continuous beam pair numbers corresponding to receive beam 4, multiple beam pairs with continuous beam pair numbers corresponding to receive beam 6, and multiple beam pairs with continuous beam pair numbers corresponding to receive beam 8.
  • the maximum number of receiving beams supported by the model is 8.
  • the maximum number of beam pairs can be divided into 4 groups according to the receiving beams corresponding to the beam pairs. Among them, the beam pairs corresponding to the same receiving beam belong to the same group. That is to say, each group corresponds to one quarter of the maximum number of beam pairs, and each group contains beam pairs corresponding to 2 receiving beams.
  • the corresponding 2 receiving beams in each group can be 2 consecutive receiving beams, or 2 non-consecutive receiving beams.
  • the corresponding 2 receiving beams in the 4 groups can be receiving beam 1 and receiving beam 2, receiving beam 3 and receiving beam 4, receiving beam 5 and receiving beam 6, and receiving beam 7 and receiving beam 8.
  • the beam pair numbers of the beam pairs in the 4 groups can be consecutive.
  • the two receiving beams corresponding to the four groups may be receiving beam 1 and receiving beam 5, receiving beam 2 and receiving beam 6, receiving beam 3 and receiving beam 7, and receiving beam 4 and receiving beam 8, respectively; or receiving beam 1 and receiving beam 3, receiving beam 5 and receiving beam 7, receiving beam 2 and receiving beam 4, receiving beam 6 and receiving beam 8, etc., which are non-continuous situations.
  • the beam pair numbers of the beam pairs in the two groups may be non-continuous. That is, the beam pair numbers of the beam pairs in any group are multiple beam pairs with continuous beam pair numbers corresponding to multiple non-continuous receiving beams.
  • the maximum number of beam pairs are divided into M groups, wherein the beam pairs corresponding to the same receiving beam are divided into M small groups, and the M small groups correspond one-to-one to the M groups.
  • the maximum number of beam pairs is divided into M groups.
  • the beam pairs corresponding to the same receiving beam are divided into M small groups, and the M small groups correspond to the M groups one by one.
  • M groups are formed. Take the maximum number of beam pairs as 32 beam pairs, M groups as 4 groups, and the maximum number of receiving beams supported by the model as 8 as an example.
  • the 32 beam pairs can be divided into 4 groups.
  • the beam pairs corresponding to each receiving beam can be divided into 4 small groups.
  • the 4 groups can be composed of 4 small groups corresponding to each receiving beam.
  • receiving beam 1 is divided into 11 groups, 12 groups, 13 groups and 14 groups; receiving beam 2 is divided into 21 groups, 22 groups, 23 groups and 24 groups; ...; receiving beam 8 is divided into 81 groups, 82 groups, 83 groups and 84 groups.
  • Group 1 can be composed of 11 groups, 21 groups, ..., 81 groups;
  • Group 2 can be composed of 12 groups, 22 groups, ..., 82 groups;
  • Group 3 can be composed of 13 groups, 23 groups, ..., 83 groups;
  • Group 4 can be composed of 14 groups, 24 groups, ..., 84 groups.
  • the beam pair numbers of the multiple beam pairs corresponding to each group can be continuous or non-continuous.
  • the maximum number of receiving beams supported by the model is 8.
  • the maximum number of beam pairs can be divided into 2 groups according to the receiving beams corresponding to the beam pairs. Among them, the beam pairs corresponding to the same receiving beam are divided into 2 small groups. That is to say, each group corresponds to half of the maximum number of beam pairs, and the beam pairs corresponding to each receiving beam are divided into 2 small groups. Based on the 2 small groups corresponding to each receiving beam, 2 groups are formed.
  • the beam pair numbers of the multiple beam pairs corresponding to each small group can be continuous.
  • the multiple beam pairs with the beam pair numbers in the first half constitute a small group corresponding to the receiving beam
  • the multiple beam pairs with the beam pair numbers in the second half constitute another small group corresponding to the receiving beam.
  • the multiple beam pairs with beam pair numbers 1, 2, 3, and 4 constitute a small group
  • the multiple beam pairs with beam pair numbers 5, 6, 7, and 8 constitute another small group.
  • the beam pair numbers of the multiple beam pairs corresponding to each group may be non-continuous.
  • the multiple beam pairs with odd beam pair numbers constitute a group corresponding to the receiving beam
  • the multiple beam pairs with even beam pair numbers constitute another group corresponding to the receiving beam.
  • the multiple beam pairs with beam pair numbers 1, 3, 5, and 7 constitute one group
  • the multiple beam pairs with beam pair numbers 2, 4, 6, and 8 constitute another group.
  • 2 groups are formed.
  • Group 1 can be composed of group 1 corresponding to each of the 8 receiving beams
  • group 2 can be composed of group 2 corresponding to each of the 8 receiving beams.
  • the maximum number of receiving beams supported by the model is 8.
  • the maximum number of beam pairs can be divided into 4 groups according to the receiving beams corresponding to the beam pairs. Among them, the beam pairs corresponding to the same receiving beam are divided into 4 small groups. That is to say, each group corresponds to one-fourth of the maximum number of beam pairs, and the beam pairs corresponding to each receiving beam are divided into 4 small groups. Based on the 4 small groups corresponding to each receiving beam, 4 groups are formed.
  • the beam pair numbers of the multiple beam pairs corresponding to each small group can be continuous. For example, in the beam pairs corresponding to a receiving beam, multiple beam pairs with beam pair numbers of one-fourth consecutive constitute a small group corresponding to the receiving beam.
  • multiple beam pairs with beam pair numbers of 1 and 2 constitute group 1
  • multiple beam pairs with beam pair numbers of 3 and 4 constitute group 2
  • multiple beam pairs with beam pair numbers of 5 and 6 constitute group 3
  • multiple beam pairs with beam pair numbers of 7 and 8 constitute group 4.
  • the beam pair numbers of the multiple beam pairs corresponding to each small group can be non-continuous.
  • multiple beam pairs with beam pair numbers 1 and 5 constitute group 1
  • multiple beam pairs with beam pair numbers 2 and 6 constitute group 2
  • multiple beam pairs with beam pair numbers 3 and 7 constitute group 3
  • multiple beam pairs with beam pair numbers 4 and 8 constitute group 4.
  • multiple beam pairs with beam pair numbers 1 and 3 constitute group 1
  • multiple beam pairs with beam pair numbers 2 and 4 constitute group 2
  • multiple beam pairs with beam pair numbers 5 and 7 constitute group 3
  • multiple beam pairs with beam pair numbers 6 and 8 constitute group 4, and so on.
  • Four groups can be formed based on the four groups corresponding to each of the eight receiving beams.
  • Group 1 may be composed of group 1 corresponding to each of the 8 receiving beams
  • group 2 may be composed of group 2 corresponding to each of the 8 receiving beams
  • group 3 may be composed of group 3 corresponding to each of the 8 receiving beams
  • group 4 may be composed of group 4 corresponding to each of the 8 receiving beams.
  • the present disclosure provides a variety of different ways to group the maximum number of beam pairs, so that when the number of receiving beams supported by the terminal is part of the maximum number of receiving beams supported by the beam prediction model, the optimal beam can be determined from multiple beam pairs in any group, so that the beam prediction model can adapt to the terminal whose number of receiving beams is part of the maximum number of receiving beams supported by the beam prediction model.
  • FIG9 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG9, determining the optimal beam from the output of the beam prediction model in S32 or S41 may include the following steps:
  • step S81 in response to the output of the beam prediction model including candidate optimal beams, an optimal beam is determined according to the candidate optimal beams.
  • the beam prediction model may directly output the candidate optimal beams, and the terminal may determine the optimal beam from the candidate optimal beams output by the beam prediction model.
  • the output of the beam prediction model may include a beam identifier of the candidate optimal beam.
  • the terminal determines the optimal beam from the candidate optimal beams output by the beam prediction model according to the beam identifier of the candidate optimal beam.
  • the beam identifier may be, for example, a beam ID.
  • a candidate optimal transmit beam ID For example, at least one of a candidate optimal transmit beam ID, a candidate optimal receive beam ID, and a candidate optimal beam pair ID.
  • the output of the beam prediction model may include the beam quality of the candidate optimal beam, wherein the beam quality may include, for example, L1-RSRP and/or L1-SINR.
  • the present disclosure can determine the optimal beam from the candidate optimal beams based on the number of receiving beams supported by the terminal, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • FIG10 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG10 , determining the optimal beam according to the candidate optimal beams in S81 may include the following steps:
  • step S91 L minimum receiving beam groups are determined according to a ratio L between the maximum number of receiving beams supported by the beam prediction model and the minimum number of receiving beams.
  • the terminal may determine L minimum receiving beam groups according to a ratio L between the maximum receiving beam supported by the beam prediction model and the minimum receiving beam number, wherein each minimum receiving beam group corresponds to multiple beam pairs.
  • L can be determined to be 4, that is, 4 minimum receiving beam groups are determined.
  • Each minimum receiving beam group can contain multiple beam pairs. The multiple beam pairs contained in all minimum receiving beam groups constitute the maximum number of beam pairs supported by the beam prediction model.
  • step S92 the candidate optimal beams corresponding to each minimum receiving beam group output by the beam prediction model are determined.
  • the terminal determines the candidate optimal beams corresponding to each minimum receiving beam group output by the beam prediction model. In other words, the terminal can determine the candidate optimal beams corresponding to each minimum receiving beam group.
  • step S93 the optimal beam is determined based on the number of receiving beams supported by the terminal and the candidate optimal beams corresponding to each minimum receiving beam group.
  • the terminal may determine the optimal beam based on the number of receiving beams supported by the terminal and the candidate optimal beams corresponding to each minimum receiving beam group.
  • the terminal can determine the optimal beam based on the candidate optimal beams corresponding to some or all of the minimum receive beam groups, based on the number of receive beams supported by the terminal being greater than or equal to the minimum receive beam number.
  • the minimum number of receive beams supported by the beam prediction model is 2
  • the maximum number of receive beams supported by the beam prediction model is 8, and the minimum receive beam group is 4.
  • the optimal beam can be determined based on the candidate optimal beams corresponding to one minimum beam group, that is, the candidate optimal beam corresponding to one of the minimum beam groups is determined as the optimal beam.
  • the optimal beam can be determined based on the candidate optimal beams corresponding to two minimum beam groups, that is, the candidate optimal beams corresponding to two of the minimum beam groups are determined as the optimal beam.
  • the optimal beam can be determined based on the candidate optimal beams corresponding to all minimum beam groups, that is, the candidate optimal beams corresponding to all minimum beam groups are determined as the optimal beam.
  • the maximum number of beam pairs supported by the beam prediction model can be divided into multiple minimum receiving beam groups according to the maximum number of receiving beams and the minimum number of receiving beams supported by the beam prediction model.
  • the candidate optimal beams corresponding to one or more minimum receiving beam groups are used. Terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the minimum receiving beam group corresponds to multiple beam pairs, which can satisfy any of the following conditions: the beam pair numbers of the beam pairs within each minimum receiving beam group are continuous; the beam pairs corresponding to the same receiving beam belong to the same minimum receiving beam group; the beam pairs corresponding to the same receiving beam are divided into L small groups, and the L small groups correspond one-to-one to the L minimum receiving beam groups.
  • the beam pairs in each minimum receive beam group are numbered consecutively.
  • the beam pair numbers of the multiple beam pairs corresponding to each minimum receiving beam group are continuous.
  • the maximum number of beam pairs is 32 beam pairs, and L is 4, that is, 4 minimum receiving beam groups.
  • the 32 beam pairs can be divided into 4 groups according to the beam pairs, and each group can include 8 beam pairs.
  • the beam pair numbers of the 8 beam pairs in each group are continuous.
  • the beam pair number can be a beam pair ID.
  • the beam pairs within each minimum receive beam grouping are numbered non-consecutively.
  • the beam pair numbers of the multiple beam pairs corresponding to each minimum receiving beam group are non-continuous.
  • the maximum number of beam pairs is 32 beam pairs, and L is 4, that is, 4 minimum receiving beam groups.
  • the 32 beam pairs can be divided into 4 groups according to the beam pairs, and each group can include 8 beam pairs.
  • the beam pair numbers of the 8 beam pairs in each group are non-continuous.
  • the beam pairs of group 1 can be numbered 1, 5, 9, 13, 17, 21, 25, 29; the beam pairs of group 2 can be numbered 2, 6, 10, 14, 18, 22, 26, 30; the beam pairs of group 3 can be numbered 3, 7, 11, 15, 19, 23, 27, 31; the beam pairs of group 4 can be numbered 4, 8, 12, 16, 20, 24, 28, 32.
  • beam pairs corresponding to the same receive beam belong to the same minimum receive beam group.
  • the beam pairs corresponding to the same receiving beam can be divided into the same minimum receiving beam group.
  • the maximum number of beam pairs is 32 beam pairs, and L is 4, that is, 4 minimum receiving beam groups.
  • the 32 beams can be divided into 4 minimum receiving beam groups.
  • the beam pairs corresponding to the same receiving beam belong to the same minimum receiving beam group.
  • the beam pairs contained in each of the 4 minimum receiving beam groups can correspond to one or more receiving beam groups.
  • the beam pairs contained in any minimum receiving beam group correspond to the same receiving beam, or any minimum receiving beam group can contain beam pairs corresponding to multiple receiving beams.
  • the beam pairs corresponding to the same receiving beam should belong to the same group.
  • the value of L should be less than or equal to the maximum number of receiving beams supported by the model.
  • beam pairs corresponding to the same receiving beam are divided into L small groups, and the L small groups correspond one-to-one to the L smallest receiving beam groups.
  • the beam pairs corresponding to the same receiving beam can be divided into L groups.
  • the L groups correspond one to one to the L minimum receiving beam groups.
  • the L minimum receiving beam groups can be composed based on the L groups corresponding to each receiving beam. Assume that the maximum number of beam pairs is 32 beam pairs, L is 4, that is, 4 minimum receiving beam groups, and the number of receiving beams supported by the beam prediction model is 8. Then the beam pairs corresponding to each receiving beam can be divided into 4 groups.
  • the 4 minimum receiving beam groups can be composed of 4 groups corresponding to each receiving beam.
  • receiving beam 1 is divided into 11' group, 12' group, 13' group and 14' group; receiving beam 2 is divided into 21' group, 22' group, 23' group and 24' group; ...; receiving beam 8 is divided into 81' group, 82' group, 83' group and 84' group.
  • the minimum receiving beam grouping 1 can be composed of 11’ group, 21’ group, ..., 81’ group; the minimum receiving beam grouping 2 can be composed of 12’ group, 22’ group, ..., 82’ group; the minimum receiving beam grouping can be composed of 13’ group, 23’ group, ..., 83’ group; the minimum receiving beam grouping can be composed of 14’ group, 24’ group, ..., 84’ group.
  • the present disclosure provides a plurality of different ways of forming minimum beam groups, so that when the output of the beam prediction model includes a candidate optimal beam, the optimal beam can be determined based on the number of receiving beams supported by the terminal and the candidate optimal beam corresponding to the minimum beam group, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • FIG11 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG11, determining the optimal beam in S93 based on the number of receiving beams supported by the terminal and the candidate optimal beams corresponding to each minimum receiving beam group may include the following steps:
  • step S101 in response to the number of receiving beams supported by the terminal being K times the number of minimum receiving beams, an optimal beam is determined according to candidate optimal beams corresponding to the K minimum receiving beam groups.
  • the terminal may determine the optimal beam according to the candidate optimal beams corresponding to the K minimum receiving beam groups, that is, determine the candidate optimal beams corresponding to the K minimum receiving beam groups as the optimal beam.
  • K is a positive integer
  • the number of receiving beams supported by the terminal is less than or equal to the maximum number of receiving beams.
  • the terminal can determine the optimal beam based on the candidate optimal beam corresponding to any one of the minimum receiving beam groups, that is, determine the candidate optimal beam corresponding to one of the minimum receiving beam groups as the optimal beam. And one of the minimum receiving beam groups is the minimum receiving beam group corresponding to the 2 receiving beams supported by the terminal. When the number of receiving beams supported by the terminal is 4, it is obvious that K is 2.
  • the terminal can determine the optimal beam based on the candidate optimal beams corresponding to any two minimum receiving beam groups, that is, determine the candidate optimal beams corresponding to any two minimum receiving beam groups as the optimal beam.
  • the any two minimum receiving beam groups are the minimum receiving beam groups corresponding to the 4 receiving beams supported by the terminal. .
  • K is 4.
  • the number of the minimum receiving beam groups is also 4, so the terminal can determine the optimal beam according to the candidate optimal beams corresponding to all the minimum receiving beam groups, that is, determine the candidate optimal beams corresponding to all the minimum receiving beam groups as the optimal beam.
  • the number of receiving beams supported by the terminal is the maximum number of receiving beams Rx_num supported by the beam quality prediction model. Then the terminal determines the candidate optimal beams corresponding to all the minimum receiving beam groups as the optimal beams.
  • the terminal can determine the optimal beam according to the candidate optimal beam corresponding to half of the minimum receiving beam groups in all the minimum receiving beam groups.
  • the maximum number of receiving beams Rx_num supported by the beam prediction model is 8
  • the minimum receiving beams supported by the beam prediction model is 2
  • the number of receiving beams supported by the terminal is 4, and the minimum receiving beam groups are 4.
  • half of the minimum receiving beam groups in all the minimum receiving beam groups are 2, and K is 2.
  • the maximum number of receiving beams Rx_num supported by the beam prediction model is 8
  • the minimum receiving beam supported by the beam prediction model is 1, the number of receiving beams supported by the terminal is 4, and the minimum receiving beam groups are 8.
  • half of the minimum receiving beam groups in all the minimum receiving beam groups are 4, and K is 4.
  • the beam pair identifiers of the multiple beam pairs corresponding to the half-minimum receiving beam group may be continuous.
  • the half-minimum receiving beam group corresponds to continuous receiving beams. Assuming that the maximum number of receiving beams is 8, the half-minimum receiving beam group may correspond to the first half of the receiving beams, that is, receiving beam 1, receiving beam 2, receiving beam 3, and receiving beam 4.
  • the multiple beam pairs corresponding to the half-minimum receiving beam group are all beam pairs corresponding to receiving beam 1, all beam pairs corresponding to receiving beam 2, all beam pairs corresponding to receiving beam 3, and all beam pairs corresponding to receiving beam 4.
  • the other half-minimum receiving beam group may correspond to the second half of the receiving beams, that is, receiving beam 5, receiving beam 6, receiving beam 7, and receiving beam 8.
  • the multiple beam pairs corresponding to the half-minimum receiving beam group are all beam pairs corresponding to receiving beam 5, all beam pairs corresponding to receiving beam 6, all beam pairs corresponding to receiving beam 7, and all beam pairs corresponding to receiving beam 8.
  • the beam pair identifiers of the multiple beam pairs corresponding to the half minimum receiving beam group may be non-continuous.
  • the multiple beam pairs corresponding to the half minimum receiving beam group are the beam pairs with odd or even beam pair numbers among the beam pairs corresponding to all receiving beams.
  • the receiving beams corresponding to the half-minimum receiving beam grouping may be non-continuous receiving beams. Assuming that the maximum number of receiving beams supported by the beam prediction model is 8, the half-minimum receiving beam grouping may correspond to receiving beam 1, receiving beam 3, receiving beam 5, and receiving beam 7. The multiple beam pairs corresponding to the half-minimum receiving beam grouping are all beam pairs corresponding to receiving beam 1, all beam pairs corresponding to receiving beam 3, all beam pairs corresponding to receiving beam 5, and all beam pairs corresponding to receiving beam 7. The other half-minimum receiving beam grouping may correspond to receiving beam 2, receiving beam 4, receiving beam 6, and receiving beam 8. The multiple beam pairs corresponding to the half-minimum receiving beam grouping are all beam pairs corresponding to receiving beam 2, all beam pairs corresponding to receiving beam 4, all beam pairs corresponding to receiving beam 6, and all beam pairs corresponding to receiving beam 8.
  • the terminal can determine the optimal beam according to the candidate optimal beam corresponding to one-quarter of the minimum receive beam groups in all the minimum receive beam groups. It can be understood that, assuming that the maximum number of receive beams Rx_num supported by the beam prediction model is 8, the minimum receive beams supported by the beam prediction model is 2, the number of receive beams supported by the terminal is 2, and the minimum receive beam grouping is 4. It can be understood that one-quarter of the minimum receive beam grouping in all the minimum receive beam groups is 1, and K is 1.
  • the maximum number of receive beams Rx_num supported by the beam prediction model is 8
  • the minimum receive beam supported by the beam prediction model is 1
  • the number of receive beams supported by the terminal is 2
  • the minimum receive beam grouping is 8. It can be understood that one-quarter of the minimum receive beam grouping in all the minimum receive beam groups is 2, and K is 2.
  • the beam pair identifiers of the multiple beam pairs corresponding to the quarter minimum receive beam grouping may be continuous.
  • the quarter minimum receive beam grouping corresponds to continuous receive beams. Assuming that the maximum number of receive beams supported by the beam prediction model is 8 and the minimum number of receive beams supported by the beam prediction model is 2, the minimum receive beam grouping may correspond to receive beam 1 and receive beam 2, receive beam 3 and receive beam 4, receive beam 5 and receive beam 6, and receive beam 7 and receive beam 8.
  • the multiple beam pairs corresponding to each minimum receive beam grouping may be all beam pairs corresponding to receive beam 1 and all beam pairs corresponding to receive beam 2, all beam pairs corresponding to receive beam 3 and all beam pairs corresponding to receive beam 4, all beam pairs corresponding to receive beam 5 and all beam pairs corresponding to receive beam 6, all beam pairs corresponding to receive beam 7 and all beam pairs corresponding to receive beam 8.
  • the beam pair identifiers of the multiple beam pairs corresponding to the quarter minimum receiving beam grouping may be non-continuous. Still taking the maximum number of receiving beams supported by the beam prediction model as 8 and the minimum number of receiving beams supported by the beam prediction model as 2 as an example.
  • the minimum number of receiving beam groups is 4, and the beam pairs corresponding to each receiving beam can be divided into 4 groups. For example, the multiple beam pairs corresponding to receiving beam 1 are divided into group 11", group 12", group 13" and group 14"; the multiple beam pairs corresponding to receiving beam 2 are divided into group 21", group 22", group 23" and group 24"; ...; the multiple beam pairs corresponding to receiving beam 8 are divided into group 81", group 82", group 83" and group 84".
  • the multiple beam pairs corresponding to the minimum receiving beam grouping 1 can be composed of group 11", group 21", ..., group 81"; the multiple beam pairs corresponding to the minimum receiving beam grouping 2 can be composed of group 12", group 22", ..., group 82"; the multiple beam pairs corresponding to the minimum receiving beam grouping 3 can be composed of group 13", group 23", ..., group 83"; the multiple beam pairs corresponding to the minimum receiving beam grouping 4 can be composed of group 14", group 24", ..., group 84".
  • the beam pair identifiers of the multiple beam pairs corresponding to each minimum receiving beam grouping are non-continuous.
  • the receiving beams corresponding to one quarter of the minimum receiving beam grouping may be non-continuous receiving beams. Assuming that the maximum number of receiving beams supported by the beam prediction model is 8 and the minimum number of receiving beams supported by the beam prediction model is 2, the minimum receiving beam grouping may correspond to receiving beam 1 and receiving beam 5, receiving beam 2 and receiving beam 6, receiving beam 3 and receiving beam 7, and receiving beam 4 and receiving beam 8.
  • the multiple beam pairs corresponding to the minimum receiving beam grouping may be all beam pairs corresponding to receiving beam 1 and all beam pairs corresponding to receiving beam 5, all beam pairs corresponding to receiving beam 2 and all beam pairs corresponding to receiving beam 6, all beam pairs corresponding to receiving beam 3 and all beam pairs corresponding to receiving beam 7, and all beam pairs corresponding to receiving beam 4 and all beam pairs corresponding to receiving beam 8.
  • the minimum receiving beam group may correspond to non-continuous receiving beam situations such as receiving beam 1 and receiving beam 3, receiving beam 2 and receiving beam 4, receiving beam 5 and receiving beam 7, and receiving beam 6 and receiving beam 8. Accordingly, the multiple beam pairs corresponding to the minimum receiving beam group may be all beam pairs corresponding to the corresponding receiving beams.
  • the network device can also determine the optimal beam using the methods of Figures 6 to 11 above.
  • the present disclosure can determine the optimal beam based on the different numbers of receiving beams supported by the terminal combined with the candidate optimal beams corresponding to the minimum beam grouping, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the present disclosure also provides a method for performing beam determination on a network device side.
  • FIG. 12 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG. 12 , the method is applied to a network device and may include the following steps:
  • step S111 the number of receiving beams supported by the beam prediction model is determined.
  • the network device may determine the number of receive beams supported by the beam prediction model.
  • step S112 based on the number of receiving beams supported by the beam prediction model, an optimal beam is determined from the output of the beam prediction model.
  • the network device may determine the optimal beam from the output of the beam prediction model based on the number of receiving beams supported by the beam prediction model determined in S111.
  • the optimal beam may be a beam with the best beam quality when the network device communicates.
  • the optimal beam may include at least one of an optimal transmit beam, an optimal receive beam, and an optimal beam pair.
  • the optimal beam pair includes a transmit beam and a receive beam.
  • the optimal beam may include one optimal beam or multiple optimal beams.
  • the present invention can determine the optimal beam from the output of the beam prediction model through the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • FIG. 13 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG. 13 , determining the number of receiving beams supported by the beam prediction model in S111 may include the following steps:
  • step S121 first indication information sent by a terminal is received.
  • the network device may receive first indication information sent by the terminal, wherein the first indication information is used to indicate the number of receiving beams supported by the beam prediction model.
  • step S122 the number of receiving beams supported by the beam prediction model is determined based on the first indication information.
  • the network device may determine the number of receiving beams supported by the beam prediction model based on the first indication information received in S121.
  • the present disclosure can also determine the number of receiving beams supported by the beam prediction model through indication information from other devices, so that the optimal beam can be determined from the output of the beam prediction model based on the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the number of receiving beams supported by the beam prediction model may include: the maximum number of receiving beams supported by the beam prediction model; or one or more numbers of receiving beams supported by the beam prediction model.
  • the number of receiving beams that the beam prediction model can support may be the maximum number of receiving beams supported by the beam prediction model, for example, recorded as Rx_num.
  • the number of receiving beams that the beam prediction model can support can be one or more numbers of receiving beams.
  • the beam prediction model can support one or more different numbers of receiving beams, and the one or more numbers of receiving beams can correspond to one number of receiving beams or multiple different numbers of receiving beams that the beam prediction model can support.
  • the present disclosure determines the optimal beam from the output of the beam prediction model by the number of receiving beams that the beam prediction model can support, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the multiple numbers of receiving beams in response to the beam prediction model supporting multiple numbers of receiving beams, may include a first number and a second number.
  • the first number is the maximum number of receiving beams supported by the beam prediction model, the first number is N times the second number, the minimum value of the second number is 1, and N is a positive integer.
  • the beam prediction model may support multiple numbers of receive beams.
  • the multiple numbers of receive beams may include a first number representing the maximum number of receive beams supported by the beam prediction model. It is understood that the first number may be Rx_num.
  • the multiple numbers of receive beams may include a second number, wherein the first number is N times the second number, the minimum value of the second number is 1, and N is a positive integer.
  • the first number may be 2 n times the second number, where n is a non-negative integer.
  • the beam prediction model in the present disclosure can support multiple different numbers of receiving beams, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the optimal beam is determined from the output of the beam prediction model, including: receiving second indication information sent by the terminal; determining the optimal beam from the output of the beam prediction model based on the second indication information; or, determining the optimal beam from the output of the beam prediction model according to a predefined rule.
  • FIG14 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG14 , determining the optimal beam from the output of the beam prediction model in S112 may include the following steps:
  • step S131 second indication information sent by the terminal is received.
  • the network device may receive second indication information sent by the terminal, where the second indication information is used to indicate the optimal beam.
  • the network device can use the beam prediction model to predict the optimal beam, and the network device indicates the predicted optimal beam to the terminal through the second indication information.
  • step S132 an optimal beam is determined from the output of the beam prediction model based on the second indication information.
  • the network device may determine the optimal beam from the output of the beam prediction model based on the second indication information received in S131.
  • FIG15 is a flow chart of another beam determination method according to an exemplary embodiment.
  • step S141 the optimal beam is determined from the output of the beam prediction model according to predefined rules.
  • the network device may determine the optimal beam from the output of the beam prediction model according to a predefined rule.
  • the optimal beam is predicted by using a beam prediction model on the terminal, and the network device may determine the beam identification range corresponding to the optimal beam by using predefined rules or indication information of the terminal, and determine the optimal beam from the beams within the beam identification range corresponding to the optimal beam.
  • the network device may also determine the beam quality corresponding to the optimal beam by using the indication information of the terminal, and determine the optimal beam.
  • the optimal beam is predicted by using a beam prediction model on the network device, and the network device may determine the optimal beam from the beams output by the beam prediction model by using predefined rules.
  • the present disclosure can determine the optimal beam from the output of the beam prediction model through the indication information of the terminal or the predefined rules, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • FIG16 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG16, determining the optimal beam from the output of the beam prediction model in S132 or S141 may include the following steps:
  • step S151 in response to the output of the beam prediction model including beam quality information of the maximum number of beam pairs supported by the beam prediction model, an optimal beam is determined from the output of the beam prediction model based on the number of receiving beams supported by the terminal.
  • the network device may determine the optimal beam from the output of the beam prediction model based on the number of receive beams supported by the terminal. That is, the network device may determine the optimal beam from the beam quality information of the maximum number of beam pairs based on the number of receive beams supported by the terminal.
  • RSRP reference signal received power
  • SINR signal to interference plus noise ratio
  • the optimal beam can be determined from the output of the beam prediction model based on the number of receiving beams supported by the terminal, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • FIG17 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG17 , in S151, based on the number of receiving beams supported by the terminal, determining the optimal beam from the output of the beam prediction model may include the following steps:
  • step S161 in response to the number of receiving beams supported by the terminal being the maximum number of receiving beams supported by the beam prediction model, an optimal beam is determined from the maximum number of beam pairs.
  • the network device can determine the optimal beam from the maximum number of beam pairs.
  • the present invention discloses that when the number of receiving beams supported by the terminal is the maximum number of receiving beams supported by the beam prediction model, the optimal beam can be determined from the maximum number of beam pairs output by the beam prediction model, so that the beam prediction model can adapt to the terminal whose number of receiving beams is the maximum number of receiving beams supported by the beam prediction model.
  • FIG18 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG18, in S151, based on the number of receiving beams supported by the terminal, determining the optimal beam from the output of the beam prediction model may include the following steps:
  • step S171 in response to the number of receiving beams supported by the terminal being the third number, the maximum number of beam pairs are divided into M groups, and the optimal beam is determined from the beam pairs included in any one of the M groups.
  • the maximum number of beam pairs may be divided into M groups.
  • the network device determines the optimal beam from the beam pairs included in any one of the M groups.
  • the third number is 1/M of the maximum number of receiving beams supported by the beam prediction model, and M is a positive integer.
  • M is 2, then the third number is The maximum number of beam pairs can be divided into 2 groups, and the network device can receive the data contained in any of the 2 groups. In other words, the network device determines the optimal beam from any half of the beam pairs in the maximum number of beam pairs.
  • M is 4, then the third number is The maximum number of beam pairs can be divided into 4 groups, and the network device can receive the data contained in any of the 4 groups. In other words, the network device determines the optimal beam from one quarter of the beam pairs among the maximum number of beam pairs.
  • M is 2 n' .
  • n' is a non-negative integer.
  • the third number is etc.
  • the minimum value of the third number may be 1, that is, M is equal to Rx_num. Accordingly, dividing the maximum number of beam pairs into M groups may be dividing the maximum number of beam pairs into Rx_num groups.
  • the present invention discloses, when the number of receiving beams supported by the terminal is a partial number of receiving beams in the maximum number of receiving beams supported by the beam prediction model, grouping the maximum number of beam pairs, and determining the optimal beam from multiple beam pairs in any group, so that the beam prediction model can adapt to the terminal whose number of receiving beams is a partial number of receiving beams in the maximum number of receiving beams supported by the beam prediction model.
  • dividing the maximum number of beam pairs into M groups in S71 may include at least one of the following: dividing the maximum number of beam pairs into M groups according to the beam pairs, wherein the beam pair numbers of the beam pairs in each group are continuous or non-continuous; dividing the maximum number of beam pairs into M groups according to the receiving beams corresponding to the beam pairs, wherein the beam pairs corresponding to the same receiving beam belong to the same group; dividing the maximum number of beam pairs into M groups, wherein the beam pairs corresponding to the same receiving beam are divided into M small groups, and the M small groups correspond one-to-one to the M groups.
  • dividing the maximum number of beam pairs into M groups may be: dividing the maximum number of beam pairs into M groups according to the beam pairs. The beam pairs in each group have consecutive numbers.
  • dividing the maximum number of beam pairs into M groups may be: dividing the maximum number of beam pairs into M groups according to the beam pairs, wherein the beam pair numbers of the beam pairs in each group are non-consecutive.
  • the maximum number of beam pairs are divided into M groups according to the receiving beams corresponding to the beam pairs, wherein the beam pairs corresponding to the same receiving beam belong to the same group.
  • the receiving beam is the receiving beam of the terminal and the transmitting beam is the transmitting beam of the network device
  • the number of beam pairs corresponding to each receiving beam should be the same as the number of transmitting beams Tx_num of the network device.
  • the maximum number of beam pairs are divided into M groups, wherein the beam pairs corresponding to the same receiving beam are divided into M small groups, and the M small groups correspond one-to-one to the M groups.
  • the beam pair numbers of the multiple beam pairs corresponding to each group can be continuous or non-continuous.
  • the present disclosure provides a variety of different ways to group the maximum number of beam pairs, so that when the number of receiving beams supported by the terminal is part of the maximum number of receiving beams supported by the beam prediction model, the optimal beam can be determined from multiple beam pairs in any group, so that the beam prediction model can adapt to the terminal whose number of receiving beams is part of the maximum number of receiving beams supported by the beam prediction model.
  • FIG19 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG19, determining the optimal beam from the output of the beam prediction model in S132 or S141 may include the following steps:
  • step S181 in response to the output of the beam prediction model including candidate optimal beams, an optimal beam is determined according to the candidate optimal beams.
  • the beam prediction model may directly output the candidate optimal beams, and the network device may determine the optimal beam from the candidate optimal beams output by the beam prediction model.
  • the output of the beam prediction model may include a beam identifier of the candidate optimal beam.
  • the network device determines the optimal beam from the candidate optimal beams output by the beam prediction model according to the beam identifier of the candidate optimal beam.
  • the beam identifier may be, for example, a beam ID.
  • a candidate optimal transmit beam ID For example, at least one of a candidate optimal transmit beam ID, a candidate optimal receive beam ID, and a candidate optimal beam pair ID.
  • the output of the beam prediction model may include the beam quality of the candidate optimal beam, wherein the beam quality may include, for example, L1-RSRP and/or L1-SINR.
  • the present disclosure can determine the optimal beam from the candidate optimal beams based on the number of receiving beams supported by the terminal, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • FIG20 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG20, determining the optimal beam according to the candidate optimal beams in S181 may include the following steps:
  • step S91 L minimum receiving beam groups are determined according to a ratio L between the maximum number of receiving beams supported by the beam prediction model and the minimum number of receiving beams.
  • the network device may determine L minimum receiving beam groups according to a ratio L between the maximum receiving beam supported by the beam prediction model and the minimum receiving beam number, wherein each minimum receiving beam group corresponds to multiple beam pairs.
  • step S92 the candidate optimal beams corresponding to each minimum receiving beam group output by the beam prediction model are determined.
  • the network device determines the candidate optimal beams corresponding to each minimum receiving beam group output by the beam prediction model. In other words, the network device can determine the candidate optimal beams corresponding to each minimum receiving beam group.
  • step S93 the optimal beam is determined based on the number of receiving beams supported by the terminal and the candidate optimal beams corresponding to each minimum receiving beam group.
  • the network device may determine the optimal beam based on the number of receiving beams supported by the terminal and the candidate optimal beams corresponding to each minimum receiving beam group.
  • the maximum number of beam pairs supported by the beam prediction model can be divided into multiple minimum receiving beam groups according to the maximum number of receiving beams and the minimum number of receiving beams supported by the beam prediction model.
  • the candidate optimal beams corresponding to one or more minimum receiving beam groups are used. This allows terminals supporting different numbers of receiving beams to use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • a minimum receiving beam group corresponds to multiple beam pairs, which can satisfy any of the following conditions: the beam pair numbers of the beam pairs within each minimum receiving beam group are continuous; the beam pairs corresponding to the same receiving beam belong to the same minimum receiving beam group; the beam pairs corresponding to the same receiving beam are divided into L small groups, and the L small groups correspond one-to-one to the L minimum receiving beam groups.
  • the beam pairs in each minimum receive beam group are numbered consecutively.
  • the beam pairs within each minimum receive beam grouping are non-consecutive in numbering.
  • beam pairs corresponding to the same receive beam belong to the same minimum receive beam group.
  • beam pairs corresponding to the same receiving beam are divided into L small groups, and the L small groups correspond one-to-one to the L smallest receiving beam groups.
  • the present disclosure provides a plurality of different ways of forming minimum beam groups, so that when the output of the beam prediction model includes a candidate optimal beam, the optimal beam can be determined based on the number of receiving beams supported by the terminal and the candidate optimal beam corresponding to the minimum beam group, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • FIG21 is a flow chart of another beam determination method according to an exemplary embodiment. As shown in FIG21, determining the optimal beam in S193 based on the number of receiving beams supported by the terminal and the candidate optimal beams corresponding to each minimum receiving beam group may include the following steps:
  • step S201 in response to the number of receiving beams supported by the terminal being K times the number of minimum receiving beams, an optimal beam is determined according to candidate optimal beams corresponding to the K minimum receiving beam groups.
  • the network device may determine the optimal beam according to the candidate optimal beams corresponding to the K minimum receiving beam groups, that is, determine the candidate optimal beams corresponding to the K minimum receiving beam groups as the optimal beam.
  • K is a positive integer
  • the number of receiving beams supported by the terminal is less than or equal to the maximum number of receiving beams.
  • the terminal can also determine the optimal beam using the methods of Figures 16 to 21 above.
  • the present disclosure can determine the optimal beam based on the different numbers of receiving beams supported by the terminal combined with the candidate optimal beams corresponding to the minimum beam grouping, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • a first device determines the number of receiving beams supported by a beam prediction model, wherein the first device is a terminal or a network device.
  • the first device receives indication information from the second device, where the indication information is used to indicate the number of receiving beams supported by the beam prediction model. If the first device is a terminal, the second device is a network device. If the first device is a network device, the second device is a terminal.
  • the first device trains a beam prediction model, so the first device can directly determine the number of receive beams supported by the beam prediction model.
  • the number of receiving beams supported by the beam prediction model includes: a maximum number of receiving beams Rx_num, or all supported numbers of receiving beams.
  • the total number of supported receive beams may be: Rx_num, Rx_num/2, Rx_num/4, Rx_num/8, ..., 1.
  • the first device determines the best N beam pairs from the output of the beam prediction model, and the determination method may be indicated by the second device or a default method.
  • the output of the beam prediction model is the RSRP of all beam pairs (the number of all beam pairs is the product of the network device transmit beam Tx_num and the maximum receive beam number Rx_num supported by the model).
  • the N beam pairs with the strongest RSRP are directly determined from all beam pairs.
  • the N beam pairs with the strongest RSRP are determined from half of all beam pairs.
  • the N beam pairs with the strongest RSRP are determined from 1/4 of all beam pairs.
  • half of the beam pairs may be:
  • the first half, or the second half i.e. the beam pair IDs in each group are continuous
  • each group contains the same number of beam pairs as Tx_num of the network device (i.e., all beam pairs in each group have the same receiving beams), and half of them are all beam pairs in the odd or even groups. For example, if Rx_num is 8, there are 8 groups, and half of them are beam pairs in groups 1, 3, 5, 7 or 2, 4, 6, 8. For example, if Tx_num of the network device is 32, there are 32 beam pairs in each group.
  • the 1/4 beam pair may be:
  • All beam pairs are divided into 4 groups, any of the 4 groups (i.e., the beam pair IDs in each group are continuous or discontinuous);
  • each group contains the same number of beam pairs as Tx_num of the network device, and 1/4 of them are all beam pairs in the Rx_num/4 group. For example, if Rx_num is 8, there are 8 groups, and 1/4 of them are beam pairs contained in groups 1, 5, 2, 6, 3, 7, or 4, 8.
  • the beam prediction model outputs the IDs of the best N beam pairs among all beam pairs.
  • the first device determines the optimal beam according to the IDs of the best N beam pairs.
  • the N best beam pair IDs output by the beam prediction model may be obtained by dividing all beam pairs into 4 groups, and outputting N/4 best beam pair IDs in each group.
  • all beam pairs are divided into 4 groups, which may include:
  • Each group contains beam pairs whose IDs are continuous;
  • the IDs of the beam pairs included in each group are not continuous;
  • each group contains the same number of beam pairs as Tx_num of the network device, and 1/4 of them are all beam pairs in the Rx_num/4 group. For example, if Rx_num is 8, there are 8 groups, and 1/4 of them are beam pairs contained in groups 1, 5, 2, 6, 3, 7, or 4, 8.
  • the IDs of the best N beam pairs are directly obtained.
  • the number of receiving beams of the terminal is Rx_num/2, only the best N/2 beam number pair IDs output from half of the beam pairs can be taken.
  • half of the beam pairs may include:
  • the first half, or the second half (corresponding beam pair IDs are continuous);
  • each group contains the same number of beam pairs as Tx_num of the network device, and half of them are all beam pairs contained in the odd or even groups. For example, if Rx_num is 8, there are 8 groups, and half of them are beam pairs contained in groups 1, 3, 5, 7 or 2, 4, 6, 8.
  • the number of receiving beams of the terminal is Rx_num/4, only the best N/4 beam pair IDs output from 1/4 of the beam pairs can be taken.
  • a 1/4 beam pair may include:
  • All beam pairs are divided into 4 groups, any one of the 4 groups (i.e., the beam pair IDs in each group are continuous or discontinuous);
  • each group contains the same number of beam pairs as Tx_num of the network device, and 1/4 of them are all beam pairs in the Rx_num/4 group. For example, if Rx_num is 8, there are 8 groups, and 1/4 of them are beam pairs contained in groups 1, 5, 2, 6, 3, 7, or 4, 8.
  • the present invention can determine the optimal beam from the output of the beam prediction model through the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the embodiments of the present disclosure also provide a beam determination apparatus and device.
  • the beam determination apparatus and device provided by the embodiments of the present disclosure include hardware structures and/or software modules corresponding to the execution of each function in order to realize the above functions.
  • the embodiments of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiments of the present disclosure.
  • Fig. 22 is a schematic diagram of a beam determination device according to an exemplary embodiment.
  • the device 200 is configured in a terminal, and includes: a determination module 201, used to determine the number of receiving beams supported by the beam prediction model; the determination module 201 is also used to determine the optimal beam from the output of the beam prediction model based on the number of receiving beams supported by the beam prediction model.
  • the present invention can determine the optimal beam from the output of the beam prediction model through the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the device 200 also includes: a receiving module 202, which is used to receive first indication information sent by a network device, and the first indication information is used to indicate the number of receiving beams supported by the beam prediction model; the determination module 201 is also used to determine the number of receiving beams supported by the beam prediction model based on the first indication information.
  • a receiving module 202 which is used to receive first indication information sent by a network device, and the first indication information is used to indicate the number of receiving beams supported by the beam prediction model
  • the determination module 201 is also used to determine the number of receiving beams supported by the beam prediction model based on the first indication information.
  • the present disclosure can also determine the number of receiving beams supported by the beam prediction model through indication information from other devices, so that the optimal beam can be determined from the output of the beam prediction model based on the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the number of receiving beams supported by the beam prediction model includes: the maximum number of receiving beams supported by the beam prediction model; or one or more numbers of receiving beams supported by the beam prediction model.
  • the present disclosure determines the optimal beam from the output of the beam prediction model by the number of receiving beams that the beam prediction model can support, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the multiple numbers of receiving beams include a first number and a second number; the first number is the maximum number of receiving beams supported by the beam prediction model, the first number is N times the second number, and the minimum value of the second number is 1, where N is a positive integer.
  • the beam prediction model in the present disclosure can support multiple different numbers of receiving beams, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the receiving module 202 is also used to receive second indication information sent by the network device; the determination module 201 is also used to determine the optimal beam from the output of the beam prediction model based on the second indication information; or, the determination module 201 is also used to determine the optimal beam from the output of the beam prediction model according to predefined rules.
  • the present disclosure can determine the optimal beam from the output of the beam prediction model through the indication information of the second device or the predefined rule, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the determination module 201 is further used to: in response to the output of the beam prediction model including beam quality information of the maximum number of beam pairs supported by the beam prediction model, determine the optimal beam from the output of the beam prediction model based on the number of receiving beams supported by the terminal.
  • the optimal beam can be determined from the output of the beam prediction model based on the number of receiving beams supported by the terminal, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the determination module 201 is further used to: in response to the number of receiving beams supported by the terminal being the maximum number of receiving beams supported by the beam prediction model, determine the optimal beam from the maximum number of beam pairs.
  • the present invention can determine the optimal beam from the maximum number of beam pairs output by the beam prediction model when the number of receiving beams supported by the terminal is the maximum number of receiving beams supported by the beam prediction model, so that the beam prediction model can adapt to the terminal whose number of receiving beams is the maximum number of receiving beams supported by the beam prediction model.
  • the determination module 201 is also used to: in response to the number of receiving beams supported by the terminal being a third number, divide the maximum number of beam pairs into M groups, and determine the optimal beam from the beam pairs contained in any one of the M groups, wherein the third number is 1/M of the maximum number of receiving beams supported by the beam prediction model, and M is a positive integer.
  • the present invention discloses, when the number of receiving beams supported by the terminal is a partial number of receiving beams in the maximum number of receiving beams supported by the beam prediction model, grouping the maximum number of beam pairs, and determining the optimal beam from multiple beam pairs in any group, so that the beam prediction model can adapt to the terminal whose number of receiving beams is a partial number of receiving beams in the maximum number of receiving beams supported by the beam prediction model.
  • the determination module 201 is also used to perform at least one of the following: dividing the maximum number of beam pairs into M groups according to the beam pairs, wherein the beam pair numbers of the beam pairs within each group are consecutive; dividing the maximum number of beam pairs into M groups according to the receiving beams corresponding to the beam pairs, wherein the beam pairs corresponding to the same receiving beam belong to the same group; dividing the maximum number of beam pairs into M groups, wherein the beam pairs corresponding to the same receiving beam are divided into M small groups, and the M small groups correspond one-to-one to the M groups.
  • the present disclosure provides a variety of different ways to group the maximum number of beam pairs, so that when the number of receiving beams supported by the terminal is part of the maximum number of receiving beams supported by the beam prediction model, the optimal beam can be determined from multiple beam pairs in any group, so that the beam prediction model can adapt to the terminal whose number of receiving beams is part of the maximum number of receiving beams supported by the beam prediction model.
  • the determination module 201 is further configured to: in response to the output of the beam prediction model including candidate optimal beams, determine the optimal beam according to the candidate optimal beams.
  • the present disclosure can determine the optimal beam from the candidate optimal beams based on the number of receiving beams supported by the terminal, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the determination module 201 is also used to: determine L minimum receiving beam groups based on the ratio L between the maximum number of receiving beams supported by the beam prediction model and the minimum number of receiving beams, wherein each minimum receiving beam group corresponds to multiple beam pairs; determine the candidate optimal beams corresponding to each minimum receiving beam group output by the beam prediction model; and determine the optimal beam based on the number of receiving beams supported by the terminal and the candidate optimal beams corresponding to each minimum receiving beam group.
  • the maximum number of beam pairs supported by the beam prediction model can be divided into multiple minimum receiving beam groups according to the maximum number of receiving beams and the minimum number of receiving beams supported by the beam prediction model.
  • the candidate optimal beams corresponding to one or more minimum receiving beam groups are used. This allows terminals supporting different numbers of receiving beams to use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • a minimum receiving beam group corresponds to multiple beam pairs, satisfying any of the following conditions: the beam pair numbers of the beam pairs within each minimum receiving beam group are continuous; the beam pairs corresponding to the same receiving beam belong to the same minimum receiving beam group; the beam pairs corresponding to the same receiving beam are divided into L small groups, and the L small groups correspond one-to-one to the L minimum receiving beam groups.
  • the present disclosure provides a plurality of different ways of forming minimum beam groups, so that when the output of the beam prediction model includes a candidate optimal beam, the optimal beam can be determined based on the number of receiving beams supported by the terminal and the candidate optimal beam corresponding to the minimum beam group, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the determination module 201 is also used to: in response to the number of receiving beams supported by the terminal being K times the minimum number of receiving beams, determine the optimal beam based on the candidate optimal beams corresponding to the K minimum receiving beam groups, where K is a positive integer and the number of receiving beams supported by the terminal is less than or equal to the maximum number of receiving beams.
  • the present disclosure can determine the optimal beam based on the different numbers of receiving beams supported by the terminal combined with the candidate optimal beams corresponding to the minimum beam grouping, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • Fig. 23 is a schematic diagram of another beam determination device according to an exemplary embodiment.
  • the device 300 is configured in a network device, and includes: a determination module 301, used to determine the number of receiving beams supported by the beam prediction model; the determination module 301 is also used to determine the optimal beam from the output of the beam prediction model based on the number of receiving beams supported by the beam prediction model.
  • the present invention can determine the optimal beam from the output of the beam prediction model through the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the device 300 also includes: a receiving module 302, which is used to receive first indication information sent by the terminal, and the first indication information is used to indicate the number of receiving beams supported by the beam prediction model; the determination module 301 is also used to determine the number of receiving beams supported by the beam prediction model based on the first indication information.
  • a receiving module 302 which is used to receive first indication information sent by the terminal, and the first indication information is used to indicate the number of receiving beams supported by the beam prediction model
  • the determination module 301 is also used to determine the number of receiving beams supported by the beam prediction model based on the first indication information.
  • the present disclosure can also determine the number of receiving beams supported by the beam prediction model through indication information from other devices, so that the optimal beam can be determined from the output of the beam prediction model based on the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the number of receiving beams supported by the beam prediction model includes: the maximum number of receiving beams supported by the beam prediction model; or one or more numbers of receiving beams supported by the beam prediction model.
  • the present disclosure determines the optimal beam from the output of the beam prediction model by the number of receiving beams that the beam prediction model can support, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the multiple numbers of receiving beams include a first number and a second number; the first number is the maximum number of receiving beams supported by the beam prediction model, the first number is N times the second number, and the minimum value of the second number is 1, where N is a positive integer.
  • the beam prediction model in the present disclosure can support multiple different numbers of receiving beams, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the receiving module 302 is further used to receive second indication information sent by the terminal; the determining module 301 is further used to determine the optimal beam from the output of the beam prediction model based on the second indication information; or, the determining module 301 is further used to determine the optimal beam from the output of the beam prediction model according to a predefined rule.
  • the present disclosure can determine the optimal beam from the output of the beam prediction model through the indication information of the second device or the predefined rule, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the determination module 301 is further used to: in response to the output of the beam prediction model including beam quality information of the maximum number of beam pairs supported by the beam prediction model, determine the optimal beam from the output of the beam prediction model based on the number of receiving beams supported by the terminal.
  • the optimal beam can be determined from the output of the beam prediction model based on the number of receiving beams supported by the terminal, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the determination module 301 is further used to: in response to the number of receiving beams supported by the terminal being the maximum number of receiving beams supported by the beam prediction model, determine the optimal beam from the maximum number of beam pairs.
  • the present invention can determine the optimal beam from the maximum number of beam pairs output by the beam prediction model when the number of receiving beams supported by the terminal is the maximum number of receiving beams supported by the beam prediction model, so that the beam prediction model can adapt to the terminal whose number of receiving beams is the maximum number of receiving beams supported by the beam prediction model.
  • the determination module 301 is also used to: in response to the number of receiving beams supported by the terminal being a third number, divide the maximum number of beam pairs into M groups, and determine the optimal beam from the beam pairs contained in any one of the M groups, wherein the third number is 1/M of the maximum number of receiving beams supported by the beam prediction model, and M is a positive integer.
  • the present invention discloses, when the number of receiving beams supported by the terminal is a partial number of receiving beams in the maximum number of receiving beams supported by the beam prediction model, grouping the maximum number of beam pairs, and determining the optimal beam from multiple beam pairs in any group, so that the beam prediction model can adapt to the terminal whose number of receiving beams is a partial number of receiving beams in the maximum number of receiving beams supported by the beam prediction model.
  • the determination module 301 is also used to perform at least one of the following: dividing the maximum number of beam pairs into M groups according to the beam pairs, wherein the beam pair numbers of the beam pairs within each group are consecutive; dividing the maximum number of beam pairs into M groups according to the receiving beams corresponding to the beam pairs, wherein the beam pairs corresponding to the same receiving beam belong to the same group; dividing the maximum number of beam pairs into M groups, wherein the beam pairs corresponding to the same receiving beam are divided into M small groups, and the M small groups correspond one-to-one to the M groups.
  • the present disclosure provides a variety of different ways to group the maximum number of beam pairs, so that when the number of receiving beams supported by the terminal is part of the maximum number of receiving beams supported by the beam prediction model, the optimal beam can be determined from multiple beam pairs in any group, so that the beam prediction model can adapt to the terminal whose number of receiving beams is part of the maximum number of receiving beams supported by the beam prediction model.
  • the determination module 301 is further configured to: in response to the output of the beam prediction model including candidate optimal beams, determine the optimal beam according to the candidate optimal beams.
  • the present disclosure can determine the optimal beam from the candidate optimal beams based on the number of receiving beams supported by the terminal, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the determination module 301 is also used to: determine L minimum receiving beam groups based on the ratio L between the maximum number of receiving beams supported by the beam prediction model and the minimum number of receiving beams, wherein each minimum receiving beam group corresponds to multiple beam pairs; determine the candidate optimal beams corresponding to each minimum receiving beam group output by the beam prediction model; and determine the optimal beam based on the number of receiving beams supported by the terminal and the candidate optimal beams corresponding to each minimum receiving beam group.
  • the maximum number of beam pairs supported by the beam prediction model can be divided into multiple minimum receiving beam groups according to the maximum number of receiving beams and the minimum number of receiving beams supported by the beam prediction model.
  • the candidate optimal beams corresponding to one or more minimum receiving beam groups are used. This allows terminals supporting different numbers of receiving beams to use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • a minimum receiving beam group corresponds to multiple beam pairs, satisfying any of the following conditions: the beam pair numbers of the beam pairs within each minimum receiving beam group are continuous; the beam pairs corresponding to the same receiving beam belong to the same minimum receiving beam group; the beam pairs corresponding to the same receiving beam are divided into L small groups, and the L small groups correspond one-to-one to the L minimum receiving beam groups.
  • the present disclosure provides a plurality of different ways of forming minimum beam groups, so that when the output of the beam prediction model includes a candidate optimal beam, the optimal beam can be determined based on the number of receiving beams supported by the terminal and the candidate optimal beam corresponding to the minimum beam group, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the determination module 301 is also used to: in response to the number of receiving beams supported by the terminal being K times the minimum number of receiving beams, determine the optimal beam based on the candidate optimal beams corresponding to the K minimum receiving beam groups, where K is a positive integer and the number of receiving beams supported by the terminal is less than or equal to the maximum number of receiving beams.
  • the present disclosure can determine the optimal beam based on the different numbers of receiving beams supported by the terminal combined with the candidate optimal beams corresponding to the minimum beam grouping, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • Fig. 24 is a schematic diagram of a beam determination device according to an exemplary embodiment.
  • device 400 may be any terminal such as a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.
  • device 400 may include one or more of the following components: a processing component 402 , a memory 404 , a power component 406 , a multimedia component 408 , an audio component 410 , an input/output (I/O) interface 412 , a sensor component 414 , and a communication component 416 .
  • the processing component 402 generally controls the overall operation of the device 400, such as operations associated with display, phone calls, data communications, camera operations, and recording operations.
  • the processing component 402 may include one or more processors 420 to execute instructions to complete all or part of the steps of the above-mentioned method.
  • the processing component 402 may include one or more modules to facilitate the interaction between the processing component 402 and other components.
  • the processing component 402 may include a multimedia module to facilitate the interaction between the multimedia component 408 and the processing component 402.
  • the memory 404 is configured to store various types of data to support operations on the device 400. Examples of such data include instructions for any application or method operating on the device 400, contact data, phone book data, messages, pictures, videos, etc.
  • the memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EPROM erasable programmable read-only memory
  • PROM programmable read-only memory
  • ROM read-only memory
  • magnetic memory flash memory
  • flash memory magnetic disk or optical disk.
  • the power component 406 provides power to the various components of the device 400.
  • the power component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 400.
  • the multimedia component 408 includes a screen that provides an output interface between the device 400 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.
  • the multimedia component 408 includes a front camera and/or a rear camera. When the device 400 is in an operating mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
  • the audio component 410 is configured to output and/or input audio signals.
  • the audio component 410 includes a microphone (MIC), and when the device 400 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal.
  • the received audio signal can be further stored in the memory 404 or sent via the communication component 416.
  • the audio component 410 also includes a speaker for outputting audio signals.
  • I/O interface 412 provides an interface between processing component 402 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.
  • the sensor assembly 414 includes one or more sensors for providing various aspects of status assessment for the device 400.
  • the sensor assembly 414 can detect the open/closed state of the device 400, the relative positioning of components, such as the display and keypad of the device 400, and the sensor assembly 414 can also detect the position change of the device 400 or a component of the device 400, the presence or absence of user contact with the device 400, the orientation or acceleration/deceleration of the device 400, and the temperature change of the device 400.
  • the sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
  • the sensor assembly 414 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor assembly 414 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • the communication component 416 is configured to facilitate wired or wireless communication between the device 400 and other devices.
  • the device 400 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof.
  • the communication component 416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel.
  • the communication component 416 also includes a near field communication (NFC) module to facilitate short-range communication.
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the device 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.
  • ASICs application-specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGAs field programmable gate arrays
  • controllers microcontrollers, microprocessors, or other electronic components to perform the above methods.
  • a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, which can be executed by a processor 420 of the device 400 to perform the above method.
  • the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
  • FIG25 is a schematic diagram of another beam determination device according to an exemplary embodiment.
  • device 500 may be provided as a base station, or a server.
  • device 500 includes a processing component 522, which further includes one or more processors, and a memory resource represented by a memory 532 for storing instructions executable by the processing component 522, such as an application.
  • the application stored in the memory 532 may include one or more modules, each corresponding to a set of instructions.
  • the processing component 522 is configured to execute instructions to perform the above method.
  • the device 500 may also include a power supply component 526 configured to perform power management of the device 500, a wired or wireless network interface 550 configured to connect the device 500 to a network, and an input/output (I/O) interface 558.
  • the device 500 may operate based on an operating system stored in the memory 532, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
  • the present invention can determine the optimal beam from the output of the beam prediction model through the number of receiving beams supported by the beam prediction model, so that terminals supporting different numbers of receiving beams can use the same beam prediction model to determine the optimal beam suitable for each terminal.
  • the present disclosure can use the same beam measurement model to obtain the best beam pair information for terminals supporting different numbers of receiving beams, thereby improving the generalization of the beam measurement model, so that one beam measurement model can be applicable to terminals with different numbers of receiving beams.
  • plural refers to two or more than two, and other quantifiers are similar thereto.
  • “And/or” describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and/or B may represent: A exists alone, A and B exist at the same time, and B exists alone.
  • the character “/” generally indicates that the associated objects before and after are in an “or” relationship.
  • the singular forms “a”, “the” and “the” are also intended to include plural forms, unless the context clearly indicates other meanings.
  • first, second, etc. are used to describe various information, but such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other, and do not indicate a specific order or degree of importance. In fact, the expressions “first”, “second”, etc. can be used interchangeably.
  • the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information.

Landscapes

  • Optical Recording Or Reproduction (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本公开是关于一种波束确定方法、装置、设备及存储介质，包括：确定波束预测模型支持的接收波束数量；基于波束预测模型支持的接收波束数量，从波束预测模型的输出中确定最优波束。本公开通过波束预测模型所支持的接收波束数量，可以从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。

Description

一种波束确定方法、装置、设备及存储介质 技术领域
本公开涉及通信技术领域，尤其涉及一种波束确定方法、装置、设备及存储介质。
背景技术
在新无线网络(new radio，NR)中，特别是通信频段在频率范围(frequency range)2时，由于高频信道衰减较快，为了保证覆盖范围，需要使用基于波束(beam)的发送和接收。
传统的波束管理(beam management)过程，基站会配置用于波束测量的参考信号资源集合，终端对该参考信号资源集合中的参考信号资源进行测量，然后上报其中比较强的一个或多个参考信号资源标识，以及对应的参考信号的波束质量。相关技术中，终端需要针对每个波束对进行参考信号的测量。其中，一个接收波束和一个发送波束构成一个波束对。
在一些技术中，可以通过人工智能(artificial intelligence，AI)模型预测的方式，得到所有波束对的波束质量。但是，AI模型是与接收波束数量相关的。对于AI模型而言，模型的输出是不变的，但是对于不同的终端可能支持不同数量的接收波束，使得波束对总数也会变化。因此，如何保证支持不同数量接收波束的终端可以适用于相同的AI模型，来预测波束对的波束质量，是亟需解决的问题。
发明内容
为克服相关技术中存在的问题，本公开提供一种波束确定方法、装置、设备及存储介质。
根据本公开实施例的第一方面，提供一种波束确定方法，方法应用于第一设备，包括：确定波束预测模型支持的接收波束数量；基于波束预测模型支持的接收波束数量，从波束预测模型的输出中确定最优波束。
根据本公开实施例的第二方面，提供一种波束确定装置，装置配置于第一设备，包括：确定模块，用于确定波束预测模型支持的接收波束数量；确定模块还用于，基于波束预测模型支持的接收波束数量，从波束预测模型的输出中确定最优波束。
根据本公开实施例的第三方面，提供一种波束确定设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，处理器被配置为：执行第一方面中的任意一项方法。
根据本公开实施例的第四方面，提供一种非临时性计算机可读存储介质，当存储介质中的指令由第一设备的处理器执行时，使得第一设备能够执行第一方面中的任意一项方法。
本公开的实施例提供的技术方案可以包括以下有益效果：通过波束预测模型所支持的接收波束数量，可以从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
图1是根据一示例性实施例示出的一种无线通信系统示意图。
图2是根据一示例性实施例示出的一种波束确定方法流程图。
图3是根据一示例性实施例示出的另一种波束确定方法流程图。
图4是根据一示例性实施例示出的又一种波束确定方法流程图。
图5是根据一示例性实施例示出的再一种波束确定方法流程图。
图6是根据一示例性实施例示出的另一种波束确定方法流程图。
图7是根据一示例性实施例示出的又一种波束确定方法流程图。
图8是根据一示例性实施例示出的再一种波束确定方法流程图。
图9是根据一示例性实施例示出的另一种波束确定方法流程图。
图10是根据一示例性实施例示出的又一种波束确定方法流程图。
图11是根据一示例性实施例示出的再一种波束确定方法流程图。
图12是根据一示例性实施例示出的另一种波束确定方法流程图。
图13是根据一示例性实施例示出的又一种波束确定方法流程图。
图14是根据一示例性实施例示出的再一种波束确定方法流程图。
图15是根据一示例性实施例示出的另一种波束确定方法流程图。
图16是根据一示例性实施例示出的又一种波束确定方法流程图。
图17是根据一示例性实施例示出的再一种波束确定方法流程图。
图18是根据一示例性实施例示出的另一种波束确定方法流程图。
图19是根据一示例性实施例示出的又一种波束确定方法流程图。
图20是根据一示例性实施例示出的再一种波束确定方法流程图。
图21是根据一示例性实施例示出的另一种波束确定方法流程图。
图22是根据一示例性实施例示出的一种波束确定装置示意图。
图23是根据一示例性实施例示出的另一种波束确定装置示意图。
图24是根据一示例性实施例示出的一种波束确定设备示意图。
图25是根据一示例性实施例示出的另一种波束确定设备示意图。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。
本公开所涉及的通信方法可以应用于图1所示的无线通信系统100中。该网络系统可以包括网络设备110和终端120。可以理解的是，图1所示的无线通信系统仅是进行示意性说明，无线通信系统中还可包括其它网络设备，例如还可以包括核心网络设备、无线中继设备和无线回传设备等，在图1中未画出。本公开实施例对该无线通信系统中包括的网络设备数量和终端数量不做限定。
进一步可以理解的是，本公开实施例的无线通信系统，是一种提供无线通信功能的网络。无线通信系统可以采用不同的通信技术，例如码分多址(Code Division Multiple Access,CDMA)、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)、时分多址(Time Division Multiple Access，TDMA)、频分多址(Frequency Division Multiple Access，FDMA)、正交频分多址(Orthogonal Frequency-Division Multiple Access，OFDMA)、单载波频分多址(Single Carrier FDMA，SC-FDMA)、载波侦听多路访问/冲突避免(Carrier Sense Multiple Access with Collision Avoidance)。根据不同网络的容量、速率、时延等因素可以将网络分为2G(英文：Generation)网络、3G网络、4G网络或者未来演进网络，如第五代无线通信系统(The 5th Generation Wireless Communication System，5G)网络，5G网络也可称为是新无线网络(New Radio，NR)。为了方便描述，本公开有时会将无线通信网络简称为网络。
进一步的，本公开中涉及的网络设备110也可以称为无线接入网络设备。该无线接入网络设备可以是：基站、演进型基站(evolved Node B，eNB)、家庭基站、无线保真(Wireless Fidelity，WIFI)系统中的接入点(Access Point，AP)、无线中继节点、无线回传节点或者 传输点(Transmission Point，TP)等，还可以为NR系统中的gNB，或者，还可以是构成基站的组件或一部分设备等。当为车联网(V2X)通信系统时，网络设备还可以是车载设备。应理解，本公开的实施例中，对网络设备所采用的具体技术和具体设备形态不做限定。
进一步的，本公开中涉及的终端120，也可以称为终端设备、用户设备(User Equipment，UE)、移动台(Mobile Station，MS)、移动终端(Mobile Terminal，MT)等，是一种向用户提供语音和/或数据连通性的设备，例如，终端可以是具有无线连接功能的手持式设备、车载设备等。目前，一些终端的举例为：智能手机(Mobile Phone)、口袋计算机(Pocket Personal Computer，PPC)、掌上电脑、个人数字助理(Personal Digital Assistant，PDA)、笔记本电脑、平板电脑、可穿戴设备、或者车载设备等。此外，当为车联网(V2X)通信系统时，终端设备还可以是车载设备。应理解，本公开实施例对终端所采用的具体技术和具体设备形态不做限定。
本公开实施例中，网络设备110与终端120可以采用任意可行的无线通信技术以实现相互传输数据。其中，网络设备110向终端120发送数据所对应的传输通道称为下行信道(downlink，DL)，终端120向网络设备110发送数据所对应的传输通道称为上行信道(uplink，UL)。可以理解的是，本公开实施例中所涉及的网络设备可以是基站。当然网络设备还可以是其它任意可能的网络设备，终端可以是任意可能的终端，本公开不作限定。
在NR中，特别是通信频段在frequency range 2时，由于高频信道衰减较快，为了保证覆盖范围，需要使用基于beam的发送和接收。
传统的波束管理过程，网络设备会配置用于波束测量的参考信号资源集合，终端对该参考信号资源集合中的参考信号资源进行测量，然后上报其中比较强的一个或多个参考信号资源标识，以及对应的层-1参考信号接收功率(layer-1 reference signal received power，L1-RSRP)和/或层-1信号干扰噪声比(layer-1 signal to interference plus noise ratio，L1-SINR)。终端需要针对每个波束对进行参考信号的测量。其中，一个接收波束和一个发送波束构成一个波束对。例如，网络设备配置的参考信号资源集合中包含的X个参考信号，每个参考信号对应网络设备不同的发送波束。针对每个参考信号，终端需要使用所有接收波束来针对该参考信号进行测量，以获得所有接收波束分别对应的波束质量，并确定一个最好的波束质量。因此，终端需要测量的波束对的数量为A*B。其中，A为网络设备发送波束数量，B为终端接收波束数量。
在相关技术中，为了减少终端测量的波束对的数量，采用了基于AI模型预测的方式。例如，终端本来一共需要测量的波束对的数量为A*B个。由于有了AI模型，终端只需要测量A*B个波束对中的其中一部分，如，A*B的1/8、1/4个波束对等等。然后将测量的 波束对的波束质量输入到AI模型中，该AI模型即可输出A*B个波束对的波束质量、A*B个波束对中最强的波束对、最强的a个发送波束和最强的b个接收波束的至少一项。可以理解，a小于或等于A，b小于或等于B。
显然，AI模型是与接收波束数量相关的。那么针对不同接收波束数量是训练不同的AI模型，还是训练相同的AI模型，以及如何指示终端，是需要解决的问题。
如果只训练一个AI模型，那么对于接收波束数量不同的终端，其波束对总数是不同的。由于AI模型的输出是不变的，因此如何从AI模型的输出中获得各个不同的终端所需要的结果，是需要解决的问题。
因此，本公开提供了一种波束确定方法，通过波束预测模型所支持的接收波束数量，可以从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
应当注意，本公开以下所涉及实施例中，第一设备为终端，第二设备为网络设备；或者，第一设备为网络设备时，第二设备为终端。
图2是根据一示例性实施例示出的一种波束确定方法流程图，如图2所示，该方法应用于终端，可以包括以下步骤：
在步骤S11中，确定波束预测模型支持的接收波束数量。
在一些实施例中，终端可以确定波束预测模型所支持的接收波束数量。
例如，若波束预测模型在终端上训练得到，则终端可以直接确定波束预测模型支持的接收波束数量。又例如，若波束预测模型在除终端以外的其它设备上训练得到，则终端可以通过其它设备的指示信息，确定波束预测模型支持的接收波束数量。
在步骤S12中，基于波束预测模型支持的接收波束数量，从波束预测模型的输出中确定最优波束。
在一些实施例中，终端可以基于S11中确定的波束预测模型支持的接收波束数量，从波束预测模型的输出中，确定出最优波束。
在一些实施例中，最优波束可以是终端进行通信时波束质量最好的波束。最优波束可以包括最优发送波束、最优接收波束、最优波束对中的至少一个。其中，最优波束对中包括一个发送波束和一个接收波束。
在一些实施例中，最优波束可以包括一个最优波束，也可以包括多个最优波束。
本公开通过波束预测模型所支持的接收波束数量，可以从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，图3是根据一示例性实施例示出的另一种波束确定方法流程图，如图3所示，S11中确定波束预测模型支持的接收波束数量，可以包括以下步骤：
在步骤S21中，接收网络设备发送的第一指示信息。
在一些实施例中，终端可以接收网络设备发送的第一指示信息。其中，第一指示信息用于指示波束预测模型支持的接收波束数量。
例如，网络设备可以是预先训练波束预测模型的设备。
在步骤S22中，基于第一指示信息确定波束预测模型支持的接收波束数量。
在一些实施例中，终端可以基于S21中接收到的第一指示信息，确定波束预测模型支持的接收波束数量。
本公开还可以通过其它设备的指示信息确定波束预测模型所支持的接收波束数量，以便可以基于波束预测模型所支持的接收波束数量从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，波束预测模型支持的接收波束数量可以包括：波束预测模型支持的最大接收波束数量；或，波束预测模型支持的一个或多个接收波束数量。
在一些实施例中，波束预测模型可以支持的接收波束数量，可以是该波束预测模型所支持的最大接收波束数量。例如，记为Rx_num。
在一些实施例中，波束预测模型可以支持的接收波束数量，可以是一个或多个接收波束数量。例如，波束预测模型可能支持一种或多种不同的接收波束数量，则一个或多个接收波束数量可以分别对应波束预测模型可能支持的一个接收波束数量或多种不同的接收波束数量。
本公开通过波束预测模型可以支持的接收波束数量，从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，响应于波束预测模型支持多个接收波束数量，多个接收波束数量可以包括第一数量和第二数量。其中，第一数量为波束预测模型支持的最大接收波束数量，第一数量为第二数量的N倍，第二数量的最小值为1，N为正整数。
在一些实施例中，波束预测模型可以支持多个接收波束数量。多个接收波束数量中可以包括表示波束预测模型支持的最大接收波束数量的第一数量。可以理解，第一数量可以 为Rx_num。多个接收波束数量中可以包括第二数量，其中，第一数量为第二数量的N倍，第二数量的最小值为1，N为正整数。
例如，第二数量可以为
Figure PCTCN2022124469-appb-000001
如，
Figure PCTCN2022124469-appb-000002
等等。多个接收波束数量中可以包括一个或多个第二数量。例如，多个接收波束数量可以包括Rx_num、
Figure PCTCN2022124469-appb-000003
又例如，多个接收波束数量可以包括Rx_num、
Figure PCTCN2022124469-appb-000004
又例如，多个接收波束数量可以包括Rx_num、
Figure PCTCN2022124469-appb-000005
……、1。可以理解，上述仅为一种示例性描述，本公开不限定多个接收波束数量中的包括多少个第二数量，也不限定具体第二数量与第一数量之间的倍数关系。
在一些实施例中，第一数量可以为第二数量的2 n倍，其中n为非负整数。例如，第二数量可以为
Figure PCTCN2022124469-appb-000006
等等。
本公开中波束预测模型可以支持多个不同的接收波束数量，以使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，从波束预测模型的输出中确定最优波束，包括：接收网络设备发送的第二指示信息；基于第二指示信息从波束预测模型的输出中确定最优波束；或，根据预定义规则，从波束预测模型的输出中确定最优波束。
在一些实施方式中，图4是根据一示例性实施例示出的又一种波束确定方法流程图。如图4所示出的，S12中从波束预测模型的输出中确定最优波束，可以包括以下步骤：
在步骤S31中，接收网络设备发送的第二指示信息。
在一些实施例中，终端可以接收网络设备发送的第二指示信息。该第二指示信息用于指示最优波束。
例如，第二指示信息可以是最优波束所在的波束标识范围。终端可以从最优波束所在的波束标识范围内的波束中，确定最优波束。或者第二指示信息可以是最优波束对应的波束质量。当然，还可以是用于指示最优波束的任意等效信息，本公开不作限定。
可以理解，网络设备上可以使用波束预测模型预测得到最优波束，网络设备通过第二指示信息，向终端指示预测得到的最优波束。
在步骤S32中，基于第二指示信息从波束预测模型的输出中确定最优波束。
在一些实施例中，终端可以基于S31中接收到的第二指示信息，从波束预测模型的输出中确定最优波束。
在一些实施方式中，图5是根据一示例性实施例示出的再一种波束确定方法流程图。
在步骤S41中，根据预定义规则，从波束预测模型的输出中确定最优波束。
在一些实施例中，终端可以根据预先定义的预定义规则，从波束预测模型的输出中确定最优波束。
例如，波束预测模型的输出为所有波束标识，终端可以根据预定义规则确定出最优波束对应的波束标识范围，进而可以从最优波束对应的波束标识范围内的波束中，确定最优波束。
可以理解，一种情况可以是在网络设备上使用波束预测模型预测得到最优波束，终端可以利用预定义规则或网络设备的指示信息，确定最优波束对应的波束标识范围，并从最优波束对应的波束标识范围内的波束中确定最优波束。终端也可以利用网络设备的指示信息，确定最优波束对应的波束质量，并确定出最优波束。当然，另一种情况可以是，在终端上使用波束预测模型预测得最优波束，终端可以利用预定义规则，从波束预测模型输出的波束中确定最优波束。
本公开可以通过网络设备的指示信息或者预定义规则，从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，图6是根据一示例性实施例示出的另一种波束确定方法流程图。如图6所示，S32或S41中从波束预测模型的输出中确定最优波束，可以包括以下步骤：
在步骤S51中，响应于波束预测模型的输出包括波束预测模型支持的最大数量个波束对的波束质量信息，基于终端支持的接收波束数量，从波束预测模型的输出中确定最优波束。
在一些实施例中，响应于波束预测模型的输出包括波束预测模型支持的最大数量个波束对的波束质量信息，例如最大数量个波束对的参考信号接收功率(reference signal received power，RSRP)和/或信号干扰噪声比(signal to interference plus noise ratio，SINR)。其中，最大数量可以是网络设备发送波束数量Tx_num与波束预测模型所支持的最大接收波束数量Rx_num的乘积，即Tx_num×Rx_num。终端可以基于终端所支持的接收波束数量，从波束预测模型的输出中确定最优波束。也就是说，终端可以基于终端所支持的接收波束数量，从最大数量个波束对的波束质量信息中确定最优波束。
本公开在波束预测模型的输出包括波束预测模型支持的最大数量个波束对的波束质量信息时，可以基于终端支持的接收波束数量从波束预测模型的输出中确定最优波束。使 得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，图7是根据一示例性实施例示出的又一种波束确定方法流程图。如图7所示，S51中基于终端支持的接收波束数量，从波束预测模型的输出中确定最优波束，可以包括以下步骤：
在步骤S61中，响应于终端支持的接收波束数量为波束预测模型支持的最大接收波束数量，从最大数量个波束对中确定最优波束。
在一些实施例中，若终端支持的接收波束数量为波束预测模型支持的最大接收波束数量，则终端可以从最大数量个波束对中确定出最优波束。
例如，终端从最大数量个波束对中，确定出波束质量最好的一个或多个波束对。若最优波束为最优接收波束，则可以将波束质量最好的一个或多个波束对所对应的接收波束作为最优接收波束。若最优波束为最优发送波束，则可以将波束质量最好的一个或多个波束对所对应的发送波束作为最优发送波束。若最优波束为最优波束对，则可以将波束质量最好的一个或多个波束对作为最优波束对。
可以理解，如何确定波束质量最好的一个或多个波束对，可以利用现有方式实现，例如当波束质量满足相应条件时，可以认为对应波束对的波束质量最好。具体条件可以根据实际情况进行相应设置，本公开不作限定。
本公开在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量时，可以从波束预测模型输出的最大数量个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量的终端。
本公开实施例提供的波束确定方法中，图8是根据一示例性实施例示出的再一种波束确定方法流程图。如图8所示，S51中基于终端支持的接收波束数量，从波束预测模型的输出中确定最优波束，可以包括以下步骤：
在步骤S71中，响应于终端支持的接收波束数量为第三数量，将最大数量个波束对分成M个分组，从M个分组中任意一个分组包含的波束对中确定最优波束。
在一些实施例中，若终端支持的接收波束数量为第三数量，可以将最大数量个波束对划分成M个分组。终端从M个分组中任意一个分组包含的波束对中，确定最优波束。其中，第三数量为波束预测模型支持的最大接收波束数量的1/M，M为正整数。
例如，第三数量为
Figure PCTCN2022124469-appb-000007
当终端支持的接收波束数量为
Figure PCTCN2022124469-appb-000008
时，可以将最大数量个波束对划分为M个分组。其中，每个分组中可以包括
Figure PCTCN2022124469-appb-000009
个波束对。 终端可以基于M个分组中的任意一个分组，从该分组包含的波束对中确定出最优波束对。如，终端从M个分组中任意一个分组包含的
Figure PCTCN2022124469-appb-000010
个波束对中，确定最优波束。
在一些实施例中，M为2，则第三数量为
Figure PCTCN2022124469-appb-000011
可以将最大数量个波束对划分为2个分组，终端从2个分组中的任意一个分组包含的
Figure PCTCN2022124469-appb-000012
个波束对中，确定最优波束。换句话说，终端从最大数量个波束对中的任意一半波束对中确定最优波束。
在一些实施例中，M为4，则第三数量为
Figure PCTCN2022124469-appb-000013
可以将最大数量个波束对划分为4个分组，终端从4个分组中的任意一个分组包含的
Figure PCTCN2022124469-appb-000014
个波束对中，确定最优波束。换句话说，终端从最大数量个波束对中的四分之一波束对中确定最优波束。
在一些实施例中，M为2 n’。其中，n’为非负整数。例如，第三数量为
Figure PCTCN2022124469-appb-000015
Figure PCTCN2022124469-appb-000016
等等。
在一些实施例中，第三数量的最小值可以为1，即M等于Rx_num。相应的，将最大数量个波束对划分为M个分组，可以为将最大数量个波束对划分为Rx_num个分组。
可以理解，上述仅为一种示例性描述，本公开并不限定M的取值，M的具体取值可以根据实际情况进行选取。
本公开在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量中的部分接收波束数量时，对最大数量个波束对进行分组，并从任意一个分组内的多个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量中部分接收波束数量的终端。
本公开实施例提供的波束确定方法中，S71中将最大数量个波束对分成M个分组，可以包括以下至少一项：将最大数量个波束对按照波束对分成M个分组，其中，每个分组内的波束对的波束对编号连续或非连续；将最大数量个波束对按照波束对对应的接收波束分成M个分组，其中，同一个接收波束对应的波束对属于同一个分组；将最大数量个波束对分成M个分组，其中，同一个接收波束对应的波束对分成M个小组，M个小组与M个分组一一对应。
其中，在一些实施例中，将最大数量个波束对分成M个分组可以是：将最大数量个波 束对按照波束对分成M个分组。其中，每个分组内的波束对的波束对编号连续。
例如，将最大数量个波束对按照波束对划分为M个分组。以最大数量个波束对为32个波束对，M个分组为4个分组为例。可以将32个波束对按照波束对划分为4个分组，每个分组可以包括8个波束对。其中，每个分组中的8个波束对的波束对编号是连续的。一些实施例中，波束对编号可以是波束对标识，标识例如为身份标识(identity，ID)或索引(index)。
例如，M为2，第三数量为
Figure PCTCN2022124469-appb-000017
可以将最大数量个波束对按照波束对分成2个分组。其中，每个分组内的波束对的波束对编号连续。也就是说，每个分组对应最大数量个波束对的一半。2个分组可以分别对应最大数量个波束对的前一半和最大数量个波束对的后一半。可以理解，最大数量个波束对的前一半波束对的波束对编号均连续，最大数量个波束对的后一半波束对的波束对编号均连续。
例如，M为4，第三数量为
Figure PCTCN2022124469-appb-000018
可以将最大数量个波束对按照波束对分成4个分组。其中，每个分组内的波束对的波束对编号连续。也就是说，每个分组对应最大数量个波束对中的四分之一个波束对。可以理解，任意一个分组对应最大数量个波束对中的四分之一个波束对的波束对编号均连续。
在一些实施例中，将最大数量个波束对分成M个分组可以是：将最大数量个波束对按照波束对分成M个分组。其中，每个分组内的波束对的波束对编号非连续。
例如，将最大数量个波束对按照波束对划分为M个分组。以最大数量个波束对为32个波束对，M个分组为4个分组为例。可以将32个波束对按照波束对划分为4个分组，每个分组可以包括8个波束对。其中，每个分组中的8个波束对的波束对编号是非连续的。一些实施例中，波束对编号可以是波束对标识，标识例如为ID或index。
例如，M为2，第三数量为
Figure PCTCN2022124469-appb-000019
可以将最大数量个波束对按照波束对分成2个分组。其中，每个分组内的波束对的波束对编号非连续。也就是说，每个分组对应最大数量个波束对的一半。2个分组可以分别对应波束对编号为奇数的一半和波束对编号为偶数的一半。
例如，M为4，第三数量为
Figure PCTCN2022124469-appb-000020
可以将最大数量个波束对按照波束对分成4个分组。其中，每个分组内的波束对的波束对编号非连续。也就是说，每个分组对应最大数量个波束对中的四分之一个波束对，并且每个分组内的波束对的波束对编号非连续。假设最 大数量个波束对为16个，分组1内的波束对编号可以为1、5、9、13；分组2内的波束对编号可以为2、6、10、14；分组3内的波束对编号可以为3、7、11、15；分组4内的波束对编号可以为4、8、12、16。
在一些实施例中，将最大数量个波束对按照波束对对应的接收波束分成M个分组。其中，同一个接收波束对应的波束对属于同一个分组。
例如，按照波束对对应的接收波束，将最大数量个波束对划分为M个分组。其中，同一个接收波束对应的波束对属于同一个分组。例如，以最大数量个波束对为32个波束对，M个分组为4个分组为例。可以将32个波束对按照波束对对应的接收波束划分为4个分组。可以理解，同一个接收波束对应的波束对属于同一个分组。可以理解，4个分组中的每个分组内包含的波束对，可以对应一个或多个接收波束分组，例如，任意一个分组内包含的波束对对应同一个接收波束，或者，任意一个分组内可以包含多个接收波束对应的波束对。但应当注意，对于同一个接收波束对应的波束对应当属于同一个分组。同时，M的值应当小于或等于模型支持的最大接收波束数量。
例如，上述M个分组中每个分组内波束对的波束对编号可以是连续的，也可以是非连续的。例如，若任意一个分组内包含的波束对对应同一个接收波束，则该分组内波束对的波束对编号可以是连续的。又例如，若任意一个分组内包含的波束对对应多个接收波束，且多个接收波束的接收波束编号是连续的，则该分组内波束对的波束对编号可以是连续的。如，任意一个分组内包含的波束对对应接收波束编号为1、2的接收波束，则该分组内波束对的波束对编号可以是连续的。再例如，若任意一个分组内包含的波束对对应多个接收波束，且多个接收波束的接收波束编号是非连续的，则该分组内波束对的波束对编号可以是非连续的。如，任意一个分组内包含的波束对对应接收波束编号为1、5的接收波束，则该分组内波束对的波束对编号可以是非连续的。即该分组内波束对的波束对编号为，接收波束编号为1的接收波束对应波束对编号连续的多个波束对，以及接收波束编号为5的接收波束对应波束对编号连续的多个波束对。
可以理解，若接收波束为终端的接收波束，发送波束为网络设备的发送波束，则每个接收波束对应的波束对数量应当与网络设备发送波束数量Tx_num相同。
例如，M为2，第三数量为
Figure PCTCN2022124469-appb-000021
模型支持的最大接收波束数量为8。可以将最大数量个波束对按照波束对对应的接收波束分成2个分组。其中，同一个接收波束对应的波束对属于同一个分组。也就是说，每个分组对应最大数量个波束对的一半，且每个分组内包含4个接收波束对应的波束对。每个分组内对应的4个接收波束可以是连续的4个接收 波束，或者是非连续的4个接收波束。如，2个分组内对应的4个接收波束可以分别是接收波束1、接收波束2、接收波束3和接收波束4，以及接收波束5、接收波束6、接收波束7和接收波束8。在这种情况下，2个分组内的波束对的波束对编号可以是连续的。又如，2个分组内对应的4个接收波束可以分别是接收波束1、接收波束3、接收波束5和接收波束7，以及接收波束2、接收波束4、接收波束6和接收波束8。在这种情况下，2个分组内的波束对的波束对编号可以是非连续的。即其中一个分组内波束对的波束对编号为，接收波束1对应波束对编号连续的多个波束对、接收波束3对应波束对编号连续的多个波束对、接收波束5对应波束对编号连续的多个波束对和接收波束7对应波束对编号连续的多个波束对；另一个分组内波束对的波束对编号为，接收波束2对应波束对编号连续的多个波束对、接收波束4对应波束对编号连续的多个波束对、接收波束6对应波束对编号连续的多个波束对和接收波束8对应波束对编号连续的多个波束对。
例如，M为4，第三数量为
Figure PCTCN2022124469-appb-000022
模型支持的最大接收波束数量为8。可以将最大数量个波束对按照波束对对应的接收波束分成4个分组。其中，同一个接收波束对应的波束对属于同一个分组。也就是说，每个分组对应最大数量个波束对的四分之一，且每个分组内包含2个接收波束对应的波束对。每个分组内对应的2个接收波束可以是连续的2个接收波束，或者是非连续的2个接收波束。如，4个分组内对应的2个接收波束可以分别是接收波束1和接收波束2，以及接收波束3和接收波束4，以及接收波束5和接收波束6，以及接收波束7和接收波束8。在这种情况下，4个分组内的波束对的波束对编号可以是连续的。又如，4个分组内对应的2个接收波束分别可以是接收波束1和接收波束5，以及接收波束2和接收波束6，以及接收波束3和接收波束7，以及接收波束4和接收波束8；又或是接收波束1和接收波束3，以及接收波束5和接收波束7，以及接收波束2和接收波束4，以及接收波束6和接收波束8等等非连续的情况。在这种情况下，2个分组内的波束对的波束对编号可以是非连续的。即任意一个分组内波束对的波束对编号为多个非连续的接收波束对应的波束对编号连续的多个波束对。
在一些实施例中，将最大数量个波束对分成M个分组，其中，同一个接收波束对应的波束对分成M个小组，M个小组与M个分组一一对应。
例如，将最大数量个波束对划分为M个分组。其中，同一个接收波束对应的波束对分成M个小组，M个小组与M个分组一一对应。基于每个接收波束对应的M个小组，构成M个分组。以最大数量个波束对为32个波束对，M个分组为4个分组，模型支持的最大接收波束数量为8为例。可以将32个波束对划分为4个分组。其中，每个接收波束对应 的波束对可以划分为4个小组。4个分组可以由每个接收波束对应的4个小组构成。如，接收波束1分为11小组、12小组、13小组和14小组；接收波束2分为21小组、22小组、23小组和24小组；……；接收波束8分为81小组、82小组、83小组和84小组。分组1可以由11小组、21小组、……、81小组构成；分组2可以由12小组、22小组、……、82小组构成；分组3可以由13小组、23小组、……、83小组构成；分组4可以由14小组、24小组、……、84小组构成。
可以理解，每个小组对应的多个波束对的波束对编号可以是连续的，也可以是非连续的。
例如，M为2，第三数量为
Figure PCTCN2022124469-appb-000023
模型支持的最大接收波束数量为8。可以将最大数量个波束对按照波束对对应的接收波束分成2个分组。其中，同一个接收波束对应的波束对分成2个小组。也就是说，每个分组对应最大数量个波束对的一半，针对每个接收波束对应的波束对分成2个小组。基于每个接收波束对应的2个小组，构成2个分组。每个小组对应的多个波束对的波束对编号可以是连续的，例如，一个接收波束对应的波束对中，波束对编号为前一半的多个波束对构成该接收波束对应的一个小组，波束对编号为后一半的多个波束对构成该接收波束对应的另一个小组。假设一个接收波束对应的8个波束对，波束对编号为1、2、3、4的多个波束对构成一个小组，波束对编号为5、6、7、8的多个波束对构成另一个小组。每个小组对应的多个波束对的波束对编号可以是非连续的，例如，一个接收波束对应的波束对中，波束对编号为奇数的多个波束对构成该接收波束对应的一个小组，波束对编号为偶数的多个波束对构成该接收波束对应的另一个小组。假设一个接收波束对应的8个波束对，波束对编号为1、3、5、7的多个波束对构成一个小组，波束对编号为2、4、6、8的多个波束对构成另一个小组。基于8个接收波束中各接收波束对应的2个小组，构成2个分组。分组1可以由8个接收波束中各接收波束对应的小组1构成，以及分组2可以由8个接收波束中各接收波束对应的小组2构成。
例如，M为4，第三数量为
Figure PCTCN2022124469-appb-000024
模型支持的最大接收波束数量为8。可以将最大数量个波束对按照波束对对应的接收波束分成4个分组。其中，同一个接收波束对应的波束对分成4个小组。也就是说，每个分组对应最大数量个波束对的四分之一，针对每个接收波束对应的波束对分成4个小组。基于每个接收波束对应的4个小组，构成4个分组。每个小组对应的多个波束对的波束对编号可以是连续的，例如，一个接收波束对应的波束对中，波束对编号为连续四分之一的多个波束对构成该接收波束对应的一个小组。假设一个接收波束对应的8个波束对，波束对编号为1、2的多个波束对构成小组1，波束对编号 为3、4的多个波束对构成小组2，波束对编号为5、6的多个波束对构成小组3，波束对编号为7、8的多个波束对构成小组4。每个小组对应的多个波束对的波束对编号可以是非连续的。假设一个接收波束对应的8个波束对，波束对编号为1、5的多个波束对构成小组1，波束对编号为2、6的多个波束对构成小组2，波束对编号为3、7的多个波束对构成小组3，波束对编号为4、8的多个波束对构成小组4。又或者，波束对编号为1、3的多个波束对构成小组1，波束对编号为2、4的多个波束对构成小组2，波束对编号为5、7的多个波束对构成小组3，波束对编号为6、8的多个波束对构成小组4等等非连续情况。可以基于8个接收波束中各接收波束对应的4个小组，构成4个分组。分组1可以由8个接收波束中各接收波束对应的小组1构成，以及分组2可以由8个接收波束中各接收波束对应的小组2构成，分组3可以由8个接收波束中各接收波束对应的小组3构成，以及分组4可以由8个接收波束中各接收波束对应的小组4构成。
本公开提供了多种不同将最大数量个波束对进行分组的方式，使得在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量中的部分接收波束数量时，可以从任意一个分组内的多个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量中部分接收波束数量的终端。
本公开实施例提供的波束确定方法中，图9是根据一示例性实施例示出的另一种波束确定方法流程图。如图9所示，S32或S41中从波束预测模型的输出中确定最优波束，可以包括以下步骤：
在步骤S81中，响应于波束预测模型的输出包括候选最优波束，根据候选最优波束确定最优波束。
在一些实施例中，波束预测模型可以直接输出候选最优波束。终端则可以从波束预测模型输出的候选最优波束中确定出最优波束。
在一些实施例中，波束预测模型的输出可以包括候选最优波束的波束标识。终端根据候选最优波束的波束标识，从波束预测模型输出的候选最优波束中确定最优波束。波束标识例如可以是波束ID。例如，候选最优发送波束ID、候选最优接收波束ID、候选最优波束对ID中的至少一项。
在一些实施例中，波束预测模型的输出可以包括候选最优波束的波束质量。其中，波束质量例如可以包括L1-RSRP和/或L1-SINR。
本公开在波束预测模型的输出包括候选最优波束时，可以基于终端支持的接收波束数量从候选最优波束中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，图10是根据一示例性实施例示出的另一种波束确定方法流程图。如图10所示，S81中根据候选最优波束确定最优波束，可以包括以下步骤：
在步骤S91中，根据波束预测模型所支持的最大接收波束数量与最小接收波束数量之间的比值L，确定L个最小接收波束分组。
在一些实施例中，终端可以根据波束预测模型所支持的最大接收波束与最小接收波束数量之间的比值L，确定L个最小接收波束分组。其中，每个最小接收波束分组对应多个波束对。
例如，若波束预测模型所支持的最大接收波束为8，最小接收波束数量为2，则可以确定L为4，即确定4个最小接收波束分组。每个最小接收波束分组可以包含多个波束对。所有最小接收波束分组包含的多个波束对构成了波束预测模型所支持的最大数量个波束对。
在步骤S92中，确定波束预测模型输出的各个最小接收波束分组分别对应的候选最优波束。
在一些实施例中，终端确定波束预测模型输出的各个最小接收波束分组分别对应的候选最优波束。也就是说，终端可以确定出每个最小接收波束分组各自对应的候选最优波束。
在步骤S93中，基于终端支持的接收波束数量和各个最小接收波束分组分别对应的候选最优波束，确定最优波束。
在一些实施例中，终端可以基于终端支持的接收波束数量和各个最小接收波束分组分别对应的候选最优波束，确定最优波束。
例如，当终端可以基于终端支持的接收波束数量大于或等于最小接收波束数量时，可以基于部分或全部最小接收波束分组分别对应的候选最优波束，确定最优波束。如，波束预测模型所支持的最小接收波束数量为2，波束预测模型所支持的最大接收波束数量为8，最小接收波束分组为4。当终端支持的接收波束数量为2时，可以基于1个最小波束分组对应的候选最优波束，确定最优波束，即将其中1个最小波束分组对应的候选最优波束确定为最优波束。当终端支持的接收波束数量为4时，可以基于2个最小波束分组对应的候选最优波束，确定最优波束，即将其中2个最小波束分组对应的候选最优波束确定为最优波束。当终端支持的接收波束数量为8时，可以基于所有最小波束分组对应的候选最优波束，确定最优波束，即将所有最小波束分组对应的候选最优波束确定为最优波束。
本公开在波束预测模型的输出包括候选最优波束时，可以根据波束预测模型所支持的最大接收波束数量与最小接收波束数量，将波束预测模型支持的最大数量个波束对划分为 多个最小接收波束分组。以便基于终端支持的接收波束数量，利用一个或多个最小接收波束分组对应的候选最优波束，确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，最小接收波束分组对应多个波束对，可以满足以下任意一项：每个最小接收波束分组内的波束对的波束对编号连续；同一个接收波束对应的波束对属于同一个最小接收波束分组；将同一个接收波束对应的波束对分成L个小组，L个小组与L个最小接收波束分组一一对应。
其中，在一些实施例中，每个最小接收波束分组内的波束对的波束对编号连续。
例如，基于L划分最小接收波束分组时，每个最小接收波束分组对应的多个波束对的波束对编号连续。例如，最大数量个波束对为32个波束对，L为4，即4个最小接收波束分组。则可以将32个波束对按照波束对划分为4个分组，每个分组可以包括8个波束对。其中，每个分组中的8个波束对的波束对编号是连续的。一些实施例中，波束对编号可以是波束对ID。
在一些实施例中，每个最小接收波束分组内的波束对的波束对编号非连续。
例如，基于L划分最小接收波束分组时，每个最小接收波束分组对应的多个波束对的波束对编号非连续。例如，最大数量个波束对为32个波束对，L为4，即4个最小接收波束分组。则可以将32个波束对按照波束对划分为4个分组，每个分组可以包括8个波束对。其中，每个分组中的8个波束对的波束对编号是非连续的。例如，分组1的波束对编号可以为1、5、9、13、17、21、25、29；分组2的波束对编号可以为2、6、10、14、18、22、26、30；分组3的波束对编号可以为3、7、11、15、19、23、27、31；分组4的波束对编号可以为4、8、12、16、20、24、28、32。
在一些实施例中，同一个接收波束对应的波束对属于同一个最小接收波束分组。
例如，基于L划分最小接收波束分组时，可以将同一个接收波束对应的波束对划分至同一个最小接收波束分组内。例如，最大数量个波束对为32个波束对，L为4，即4个最小接收波束分组。可以将32个波束划分为4个最小接收波束分组。可以理解，同一个接收波束对应的波束对属于同一个最小接收波束分组。可以理解，4个最小接收波束分组中的每个最小接收波束分组内包含的波束对，可以对应一个或多个接收波束分组。例如，任意一个最小接收波束分组内包含的波束对对应同一个接收波束，或者，任意一个最小接收波束分组内可以包含多个接收波束对应的波束对。但应当注意，对于同一个接收波束对应的波束对应当属于同一个分组。同时，L的值应当小于或等于模型支持的最大接收波束数量。
在一些实施例中，将同一个接收波束对应的波束对分成L个小组，L个小组与L个最小接收波束分组一一对应。
例如，基于L划分最小接收波束分组时，可以将同一个接收波束对应的波束对分成L个小组。其中，L个小组与L个最小接收波束分组一一对应。则L个最小接收波束分组可以基于每个接收波束对应的L个小组构成。假设，最大数量个波束对为32个波束对，L为4，即4个最小接收波束分组，波束预测模型所支持的接收波束数量为8。则可以将每个接收波束对应的波束对分成4个小组。4个最小接收波束分组可以由每个接收波束对应的4个小组构成。如，接收波束1分为11’小组、12’小组、13’小组和14’小组；接收波束2分为21’小组、22’小组、23’小组和24’小组；……；接收波束8分为81’小组、82’小组、83’小组和84’小组。最小接收波束分组1可以由11’小组、21’小组、……、81’小组构成；最小接收波束分组2可以由12’小组、22’小组、……、82’小组构成；最小接收波束分组可以由13’小组、23’小组、……、83’小组构成；最小接收波束分组可以由14’小组、24’小组、……、84’小组构成。
本公开提供了多种不同最小波束分组的组成方式，使得在波束预测模型的输出包括候选最优波束时，可以基于终端支持的接收波束数量和最小波束分组对应的候选最优波束确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，图11是根据一示例性实施例示出的又一种波束确定方法流程图。如图11所示，S93中基于终端支持的接收波束数量和各个最小接收波束分组分别对应的候选最优波束，确定最优波束，可以包括以下步骤：
在步骤S101中，响应于终端支持的接收波束数量为最小接收波束数量的K倍，根据K个最小接收波束分组对应的候选最优波束，确定最优波束。
在一些实施例中，当终端支持的接收波束数量为最小接收波束数量的K倍时，终端可以根据K个最小接收波束分组对应的候选最优波束，确定最优波束，即将其中K个最小接收波束分组对应的候选最优波束确定为最优波束。其中，K为正整数，终端支持的接收波束数量小于或等于最大接收波束数量。
例如，若波束预测模型所支持的最小接收波束数量为2，波束预测模型所支持的最大接收波束数量为8，当终端支持的接收波束数量为2时，显然K为1。终端可以根据任意一个最小接收波束分组对应的候选最优波束，确定最优波束，即将其中一个最小接收波束分组对应的候选最优波束确定为最优波束。且该其中一个最小接收波束分组为终端支持的2个接收波束对应的最小接收波束分组。当终端支持的接收波束数量为4时，显然K为2。 终端可以根据任意两个最小接收波束分组对应的候选最优波束，确定最优波束，即将任意两个最小接收波束分组对应的候选最优波束确定为最优波束。且该任意两个最小接收波束分组为终端支持的4个接收波束对应的最小接收波束分组。。当终端支持的接收波束数量为8时，显然K为4。该情况中最小接收波束分组的数量也为4，则终端可以根据全部最小接收波束分组对应的候选最优波束，确定最优波束，即将全部最小接收波束分组对应的候选最优波束确定为最优波束。。
例如，终端支持的接收波束数量为波束质量预测模型支持的最大接收波束数量Rx_num。则终端根据全部最小接收波束分组对应的候选最优波束，确定为最优波束。
例如，终端支持的接收波束数量为
Figure PCTCN2022124469-appb-000025
则终端可以根据全部最小接收波束分组中的一半最小接收波束分组对应的候选最优波束，确定为最优波束。可以理解，假设波束预测模型所支持的最大接收波束数量Rx_num为8，波束预测模型所支持的最小接收波束为2，终端支持的接收波束数量为4，最小接收波束分组为4个。可以理解，全部最小接收波束分组中的一半最小接收波束分组为2个，K为2。假设波束预测模型所支持的最大接收波束数量Rx_num为8，波束预测模型所支持的最小接收波束为1，终端支持的接收波束数量为4，最小接收波束分组为8个。可以理解，全部最小接收波束分组中的一半最小接收波束分组为4个，K为4。
如，一半最小接收波束分组内对应的多个波束对的波束对标识可以是连续的，如一半最小接收波束分组对应连续的接收波束，假设最大接收波束数量为8，则一半最小接收波束分组可以对应前一半接收波束，即接收波束1、接收波束2、接收波束3和接收波束4。该一半最小接收波束分组内对应的多个波束对为接收波束1对应的全部波束对、接收波束2对应的全部波束对、接收波束3对应的全部波束对和接收波束4对应的全部波束对。另一半最小接收波束分组可以对应后一半接收波束，即接收波束5、接收波束6、接收波束7和接收波束8。该一半最小接收波束分组内对应的多个波束对为接收波束5对应的全部波束对、接收波束6对应的全部波束对、接收波束7对应的全部波束对和接收波束8对应的全部波束对。
又如，一半最小接收波束分组内对应的多个波束对的波束对标识可以是非连续的。如一半最小接收波束分组对应的多个波束对，为所有接收波束对应的波束对中波束对编号为奇数或偶数的波束对。
再如，一半最小接收波束分组对应的接收波束可以是非连续的接收波束，假设波束预测模型所支持的最大接收波束数量为8，一半最小接收波束分组可以对应接收波束1、接 收波束3、接收波束5和接收波束7。该一半最小接收波束分组内对应的多个波束对为接收波束1对应的全部波束对、接收波束3对应的全部波束对、接收波束5对应的全部波束对和接收波束7对应的全部波束对。另一半最小接收波束分组可以对应接收波束2、接收波束4、接收波束6和接收波束8。该一半最小接收波束分组内对应的多个波束对为接收波束2对应的全部波束对、接收波束4对应的全部波束对、接收波束6对应的全部波束对和接收波束8对应的全部波束对。
例如，终端支持的接收波束数量为
Figure PCTCN2022124469-appb-000026
则终端可以根据全部最小接收波束分组中的四分之一最小接收波束分组对应的候选最优波束，确定最优波束。可以理解，假设波束预测模型所支持的最大接收波束数量Rx_num为8，波束预测模型所支持的最小接收波束为2，终端支持的接收波束数量为2，最小接收波束分组为4个。可以理解，全部最小接收波束分组中的四分之一最小接收波束分组为1个，K为1。假设波束预测模型所支持的最大接收波束数量Rx_num为8，波束预测模型所支持的最小接收波束为1，终端支持的接收波束数量为2，最小接收波束分组为8个。可以理解，全部最小接收波束分组中的四分之一最小接收波束分组为2个，K为2。
如，四分之一最小接收波束分组内对应的多个波束对的波束对标识可以是连续的，如四分之一最小接收波束分组对应连续的接收波束，假设波束预测模型所支持的最大接收波束数量为8，波束预测模型所支持的最小接收波束数量为2，则最小接收波束分组可以对应接收波束1和接收波束2，以及接收波束3和接收波束4，以及接收波束5和接收波束6，以及接收波束7和接收波束8。各最小接收波束分组内对应的多个波束对可以为接收波束1对应的全部波束对和接收波束2对应的全部波束对，以及接收波束3对应的全部波束对和接收波束4对应的全部波束对，以及接收波束5对应的全部波束对和接收波束6对应的全部波束对，以及接收波束7对应的全部波束对和接收波束8对应的全部波束对。
又如，四分之一最小接收波束分组内对应的多个波束对的波束对标识可以是非连续的。仍以波束预测模型所支持的最大接收波束数量为8，波束预测模型所支持的最小接收波束数量为2为例。最小接收波束分组数量为4，可以将各接收波束对应的波束对划分为4小组。如，接收波束1对应的多个波束对分为小组11”、小组12”、小组13”和小组14”；接收波束2对应的多个波束对分为小组21”、小组22”、小组23”和小组24”；……；接收波束8对应的多个波束对分为小组81”、小组82”、小组83”和小组84”。则最小接收波束分组1对应的多个波束对可以由小组11”、小组21”、……、小组81”构成；最小接收波束分组2对应的多个波束对可以由小组12”、小组22”、……、小组82”构成；最小 接收波束分组3对应的多个波束对可以由小组13”、小组23”、……、小组83”构成；最小接收波束分组4对应的多个波束对可以由小组14”、小组24”、……、小组84”构成。显然，每个最小接收波束分组内对应的多个波束对的波束对标识是非连续的。
再如，四分之一最小接收波束分组对应的接收波束可以是非连续的接收波束，假设波束预测模型所支持的最大接收波束数量为8，波束预测模型所支持的最小接收波束数量为2，最小接收波束分组可以对应接收波束1和接收波束5，接收波束2和接收波束6，接收波束3和接收波束7，以及接收波束4和接收波束8。最小接收波束分组内对应的多个波束对可以为接收波束1对应的全部波束对和接收波束5对应的全部波束对，以及接收波束2对应的全部波束对和接收波束6对应的全部波束对，以及接收波束3对应的全部波束对和接收波束7对应的全部波束对，以及接收波束4对应的全部波束对和接收波束8对应的全部波束对。又或者最小接收波束分组可以对应接收波束1和接收波束3，接收波束2和接收波束4，接收波束5和接收波束7，以及接收波束6和接收波束8等等非连续接收波束情况。相应的，最小接收波束分组内对应的多个波束对可以为相应接收波束对应的全部波束对。
可以理解，若网络设备发送的第二指示信息直接指示最优波束，则网络设备同样可以采用上述图6至图11的方式确定最优波束。
本公开可以基于终端支持的不同接收波束数量结合最小波束分组对应的候选最优波束，确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
基于相同构思，本公开还提供了网络设备侧执行波束确定方法。
图12是根据一示例性实施例示出的另一种波束确定方法流程图，如图12所示，该方法应用于网络设备，可以包括以下步骤：
在步骤S111中，确定波束预测模型支持的接收波束数量。
在一些实施例中，网络设备可以确定波束预测模型所支持的接收波束数量。
在步骤S112中，基于波束预测模型支持的接收波束数量，从波束预测模型的输出中确定最优波束。
在一些实施例中，网络设备可以基于S111中确定的波束预测模型支持的接收波束数量，从波束预测模型的输出中，确定出最优波束。
在一些实施例中，最优波束可以是网络设备进行通信时波束质量最好的波束。最优波束可以包括最优发送波束、最优接收波束、最优波束对中的至少一个。其中，最优波束对中包括一个发送波束和一个接收波束。
在一些实施例中，最优波束可以包括一个最优波束，也可以包括多个最优波束。
本公开通过波束预测模型所支持的接收波束数量，可以从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，图13是根据一示例性实施例示出的又一种波束确定方法流程图，如图13所示，S111中确定波束预测模型支持的接收波束数量，可以包括以下步骤：
在步骤S121中，接收终端发送的第一指示信息。
在一些实施例中，网络设备可以接收终端发送的第一指示信息。其中，第一指示信息用于指示波束预测模型支持的接收波束数量。
在步骤S122中，基于第一指示信息确定波束预测模型支持的接收波束数量。
在一些实施例中，网络设备可以基于S121中接收到的第一指示信息，确定波束预测模型支持的接收波束数量。
本公开还可以通过其它设备的指示信息确定波束预测模型所支持的接收波束数量，以便可以基于波束预测模型所支持的接收波束数量从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，波束预测模型支持的接收波束数量可以包括：波束预测模型支持的最大接收波束数量；或，波束预测模型支持的一个或多个接收波束数量。
在一些实施例中，波束预测模型可以支持的接收波束数量，可以是该波束预测模型所支持的最大接收波束数量。例如，记为Rx_num。
在一些实施例中，波束预测模型可以支持的接收波束数量，可以是一个或多个接收波束数量。例如，波束预测模型可能支持一种或多种不同的接收波束数量，则一个或多个接收波束数量可以分别对应波束预测模型可能支持的一个接收波束数量或多种不同的接收波束数量。
本公开通过波束预测模型可以支持的接收波束数量，从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，响应于波束预测模型支持多个接收波束数量，多个接收波束数量可以包括第一数量和第二数量。其中，第一数量为波束预测模型支持的 最大接收波束数量，第一数量为第二数量的N倍，第二数量的最小值为1，N为正整数。
在一些实施例中，波束预测模型可以支持多个接收波束数量。多个接收波束数量中可以包括表示波束预测模型支持的最大接收波束数量的第一数量。可以理解，第一数量可以为Rx_num。多个接收波束数量中可以包括第二数量，其中，第一数量为第二数量的N倍，第二数量的最小值为1，N为正整数。
在一些实施例中，第一数量可以为第二数量的2 n倍，其中n为非负整数。
本公开中波束预测模型可以支持多个不同的接收波束数量，以使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，从波束预测模型的输出中确定最优波束，包括：接收终端发送的第二指示信息；基于第二指示信息从波束预测模型的输出中确定最优波束；或，根据预定义规则，从波束预测模型的输出中确定最优波束。
在一些实施方式中，图14是根据一示例性实施例示出的再一种波束确定方法流程图。如图14所示出的，S112中从波束预测模型的输出中确定最优波束，可以包括以下步骤：
在步骤S131中，接收终端发送的第二指示信息。
在一些实施例中，网络设备可以接收终端发送的第二指示信息。该第二指示信息用于指示最优波束。
可以理解，网络设备上可以使用波束预测模型预测得到最优波束，网络设备通过第二指示信息，向终端指示预测得到的最优波束。
在步骤S132中，基于第二指示信息从波束预测模型的输出中确定最优波束。
在一些实施例中，网络设备可以基于S131中接收到的第二指示信息，从波束预测模型的输出中确定最优波束。
在一些实施方式中，图15是根据一示例性实施例示出的另一种波束确定方法流程图。
在步骤S141中，根据预定义规则，从波束预测模型的输出中确定最优波束。
在一些实施例中，网络设备可以根据预先定义的预定义规则，从波束预测模型的输出中确定最优波束。
可以理解，一种情况可以是在终端上使用波束预测模型预测得到最优波束，网络设备可以利用预定义规则或终端的指示信息，确定最优波束对应的波束标识范围，并从最优波束对应的波束标识范围内的波束中确定最优波束。网络设备也可以利用终端的指示信息，确定最优波束对应的波束质量，并确定出最优波束。当然，另一种情况可以是，在网络设备上使用波束预测模型预测得最优波束，网络设备可以利用预定义规则，从波束预测模型输出的波束中确定最优波束。
本公开可以通过终端的指示信息或者预定义规则，从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，图16是根据一示例性实施例示出的又一种波束确定方法流程图。如图16所示，S132或S141中从波束预测模型的输出中确定最优波束，可以包括以下步骤：
在步骤S151中，响应于波束预测模型的输出包括波束预测模型支持的最大数量个波束对的波束质量信息，基于终端支持的接收波束数量，从波束预测模型的输出中确定最优波束。
在一些实施例中，响应于波束预测模型的输出包括波束预测模型支持的最大数量个波束对的波束质量信息，例如最大数量个波束对的参考信号接收功率(reference signal received power，RSRP)和/或信号干扰噪声比(signal to interference plus noise ratio，SINR)。其中，最大数量可以是网络设备发送波束数量Tx_num与波束预测模型所支持的最大接收波束数量Rx_num的乘积，即Tx_num×Rx_num。网络设备可以基于终端所支持的接收波束数量，从波束预测模型的输出中确定最优波束。也就是说，网络设备可以基于终端所支持的接收波束数量，从最大数量个波束对的波束质量信息中确定最优波束。
本公开在波束预测模型的输出包括波束预测模型支持的最大数量个波束对的波束质量信息时，可以基于终端支持的接收波束数量从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，图17是根据一示例性实施例示出的再一种波束确定方法流程图。如图17所示，S151中基于终端支持的接收波束数量，从波束预测模型的输出中确定最优波束，可以包括以下步骤：
在步骤S161中，响应于终端支持的接收波束数量为波束预测模型支持的最大接收波束数量，从最大数量个波束对中确定最优波束。
在一些实施例中，若终端支持的接收波束数量为波束预测模型支持的最大接收波束数量，则网络设备可以从最大数量个波束对中确定出最优波束。
可以理解，如何确定波束质量最好的一个或多个波束对，可以利用现有方式实现，例如当波束质量满足相应条件时，可以认为对应波束对的波束质量最好。具体条件可以根据实际情况进行相应设置，本公开不作限定。
本公开在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量时，可以 从波束预测模型输出的最大数量个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量的终端。
本公开实施例提供的波束确定方法中，图18是根据一示例性实施例示出的另一种波束确定方法流程图。如图18所示，S151中基于终端支持的接收波束数量，从波束预测模型的输出中确定最优波束，可以包括以下步骤：
在步骤S171中，响应于终端支持的接收波束数量为第三数量，将最大数量个波束对分成M个分组，从M个分组中任意一个分组包含的波束对中确定最优波束。
在一些实施例中，若终端支持的接收波束数量为第三数量，可以将最大数量个波束对划分成M个分组。网络设备从M个分组中任意一个分组包含的波束对中，确定最优波束。其中，第三数量为波束预测模型支持的最大接收波束数量的1/M，M为正整数。
在一些实施例中，M为2，则第三数量为
Figure PCTCN2022124469-appb-000027
可以将最大数量个波束对划分为2个分组，网络设备从2个分组中的任意一个分组包含的
Figure PCTCN2022124469-appb-000028
个波束对中，确定最优波束。换句话说，网络设备从最大数量个波束对中的任意一半波束对中确定最优波束。
在一些实施例中，M为4，则第三数量为
Figure PCTCN2022124469-appb-000029
可以将最大数量个波束对划分为4个分组，网络设备从4个分组中的任意一个分组包含的
Figure PCTCN2022124469-appb-000030
个波束对中，确定最优波束。换句话说，网络设备从最大数量个波束对中的四分之一波束对中确定最优波束。
在一些实施例中，M为2 n’。其中，n’为非负整数。例如，第三数量为
Figure PCTCN2022124469-appb-000031
Figure PCTCN2022124469-appb-000032
等等。
在一些实施例中，第三数量的最小值可以为1，即M等于Rx_num。相应的，将最大数量个波束对划分为M个分组，可以为将最大数量个波束对划分为Rx_num个分组。
可以理解，上述仅为一种示例性描述，本公开并不限定M的取值，M的具体取值可以根据实际情况进行选取。
本公开在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量中的部分接收波束数量时，对最大数量个波束对进行分组，并从任意一个分组内的多个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收 波束数量中部分接收波束数量的终端。
本公开实施例提供的波束确定方法中，S71中将最大数量个波束对分成M个分组，可以包括以下至少一项：将最大数量个波束对按照波束对分成M个分组，其中，每个分组内的波束对的波束对编号连续或非连续；将最大数量个波束对按照波束对对应的接收波束分成M个分组，其中，同一个接收波束对应的波束对属于同一个分组；将最大数量个波束对分成M个分组，其中，同一个接收波束对应的波束对分成M个小组，M个小组与M个分组一一对应。
其中，在一些实施例中，将最大数量个波束对分成M个分组可以是：将最大数量个波束对按照波束对分成M个分组。其中，每个分组内的波束对的波束对编号连续。
在一些实施例中，将最大数量个波束对分成M个分组可以是：将最大数量个波束对按照波束对分成M个分组。其中，每个分组内的波束对的波束对编号非连续。
在一些实施例中，将最大数量个波束对按照波束对对应的接收波束分成M个分组。其中，同一个接收波束对应的波束对属于同一个分组。
可以理解，若接收波束为终端的接收波束，发送波束为网络设备的发送波束，则每个接收波束对应的波束对数量应当与网络设备发送波束数量Tx_num相同。
在一些实施例中，将最大数量个波束对分成M个分组，其中，同一个接收波束对应的波束对分成M个小组，M个小组与M个分组一一对应。
可以理解，每个小组对应的多个波束对的波束对编号可以是连续的，也可以是非连续的。
本公开提供了多种不同将最大数量个波束对进行分组的方式，使得在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量中的部分接收波束数量时，可以从任意一个分组内的多个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量中部分接收波束数量的终端。
本公开实施例提供的波束确定方法中，图19是根据一示例性实施例示出的又一种波束确定方法流程图。如图19所示，S132或S141中从波束预测模型的输出中确定最优波束，可以包括以下步骤：
在步骤S181中，响应于波束预测模型的输出包括候选最优波束，根据候选最优波束确定最优波束。
在一些实施例中，波束预测模型可以直接输出候选最优波束。网络设备则可以从波束预测模型输出的候选最优波束中确定出最优波束。
在一些实施例中，波束预测模型的输出可以包括候选最优波束的波束标识。网络设备 根据候选最优波束的波束标识，从波束预测模型输出的候选最优波束中确定最优波束。波束标识例如可以是波束ID。例如，候选最优发送波束ID、候选最优接收波束ID、候选最优波束对ID中的至少一项。
在一些实施例中，波束预测模型的输出可以包括候选最优波束的波束质量。其中，波束质量例如可以包括L1-RSRP和/或L1-SINR。
本公开在波束预测模型的输出包括候选最优波束时，可以基于终端支持的接收波束数量从候选最优波束中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，图20是根据一示例性实施例示出的再一种波束确定方法流程图。如图20所示，S181中根据候选最优波束确定最优波束，可以包括以下步骤：
在步骤S91中，根据波束预测模型所支持的最大接收波束数量与最小接收波束数量之间的比值L，确定L个最小接收波束分组。
在一些实施例中，网络设备可以根据波束预测模型所支持的最大接收波束与最小接收波束数量之间的比值L，确定L个最小接收波束分组。其中，每个最小接收波束分组对应多个波束对。
在步骤S92中，确定波束预测模型输出的各个最小接收波束分组分别对应的候选最优波束。
在一些实施例中，网络设备确定波束预测模型输出的各个最小接收波束分组分别对应的候选最优波束。也就是说，网络设备可以确定出每个最小接收波束分组各自对应的候选最优波束。
在步骤S93中，基于终端支持的接收波束数量和各个最小接收波束分组分别对应的候选最优波束，确定最优波束。
在一些实施例中，网络设备可以基于终端支持的接收波束数量和各个最小接收波束分组分别对应的候选最优波束，确定最优波束。
本公开在波束预测模型的输出包括候选最优波束时，可以根据波束预测模型所支持的最大接收波束数量与最小接收波束数量，将波束预测模型支持的最大数量个波束对划分为多个最小接收波束分组。以便基于终端支持的接收波束数量，利用一个或多个最小接收波束分组对应的候选最优波束，确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，最小接收波束分组对应多个波束对，可以满足 以下任意一项：每个最小接收波束分组内的波束对的波束对编号连续；同一个接收波束对应的波束对属于同一个最小接收波束分组；将同一个接收波束对应的波束对分成L个小组，L个小组与L个最小接收波束分组一一对应。
其中，在一些实施例中，每个最小接收波束分组内的波束对的波束对编号连续。
在一些实施例中，每个最小接收波束分组内的波束对的波束对编号非连续。
在一些实施例中，同一个接收波束对应的波束对属于同一个最小接收波束分组。
在一些实施例中，将同一个接收波束对应的波束对分成L个小组，L个小组与L个最小接收波束分组一一对应。
本公开提供了多种不同最小波束分组的组成方式，使得在波束预测模型的输出包括候选最优波束时，可以基于终端支持的接收波束数量和最小波束分组对应的候选最优波束确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开实施例提供的波束确定方法中，图21是根据一示例性实施例示出的另一种波束确定方法流程图。如图21所示，S193中基于终端支持的接收波束数量和各个最小接收波束分组分别对应的候选最优波束，确定最优波束，可以包括以下步骤：
在步骤S201中，响应于终端支持的接收波束数量为最小接收波束数量的K倍，根据K个最小接收波束分组对应的候选最优波束，确定最优波束。
在一些实施例中，当终端支持的接收波束数量为最小接收波束数量的K倍时，网络设备可以根据K个最小接收波束分组对应的候选最优波束，确定最优波束，即将其中K个最小接收波束分组对应的候选最优波束确定为最优波束。其中，K为正整数，终端支持的接收波束数量小于或等于最大接收波束数量。
可以理解，若终端发送的第二指示信息直接指示最优波束，则终端同样可以采用上述图16至图21的方式确定最优波束。
本公开可以基于终端支持的不同接收波束数量结合最小波束分组对应的候选最优波束，确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
可以理解，图12至图21中网络设备侧实施的波束确定方法，其相应步骤实施例的具体实现过程可以参考图2至图11中终端侧的相应描述，本公开不再赘述。
本公开以下将结合实际应用对上述各实施方案进行描述。
一种实施方式中，第一设备确定波束预测模型所支持的接收波束数量。其中，第一设备为终端或网络设备。
一些实施例中，第一设备接收第二设备的指示信息，该指示信息用于指示波束预测模型所支持的接收波束数量。若第一设备为终端，则第二设备为网络设备。若第一设备为网络设备，则第二设备为终端。
一些实施例中，第一设备训练波束预测模型，因此，第一设备可以直接确定波束预测模型所支持的接收波束数量
一种实施方式中，波束预测模型所支持的接收波束数量包括：最大接收波束数量Rx_num，或所有可支持的接收波束数量。
一些实施例中，所有可支持的接收波束数量可以为：Rx_num，Rx_num/2，Rx_num/4，Rx_num/8，……，1。
一种实施方式中，第一设备从波束预测模型的输出中确定出最佳N个波束对，确定方法可以是第二设备指示或默认方法。
一种实施方式中，若波束预测模型的输出为所有波束对的RSRP(所有波束对的数量为网络设备发送波束Tx_num与模型支持的最大接收波束数量Rx_num的乘积)。
若终端接收波束数量为Rx_num,则直接从所有波束对中确定RSRP最强的N个波束对。
若终端接收波束数量为Rx_num/2,则从所有波束对中的其中一半波束对中确定RSRP最强的N个波束对。
若终端接收波束数量为Rx_num/4,则从所有波束对中的其中1/4波束对中确定RSRP最强的N个波束对。
一些实施例中，若终端接收波束数量为Rx_num/2，则一半波束对可以为：
前一半，或后一半(即每组内波束对ID均连续)；
或奇数编号的一半，或偶数编号的一半(即每组内波束对ID均不连续)；
或将所有波束对分为Rx_num组，每组包含的波束对数量为网络设备的Tx_num个波束对(即每组包含的所有波束对对应的接收波束一样)，一半为奇数组或偶数组包含的所有波束对。比如Rx_num为8，则有8组，一半为1,3,5,7组或2,4,6,8组中包含的波束对。比如网络设备的Tx_num为32的话，每组里有32个波束对。
一些实施例中，若终端接收波束数量为Rx_num/4，则1/4波束对可以为：
所有波束对分为4组，4组中的任意一组(即每组内波束对ID均连续或均不连续)；
或将所有波束对分为Rx_num组，每组包含的波束对数量为网络设备的Tx_num个波束对，1/4为其中Rx_num/4组中所有波束对。比如Rx_num为8，则有8组，1/4为1,5组或2,6组或3,7组或4,8组中包含的波束对。
一种实施方式中，波束预测模型输出为所有波束对中的最优N个波束对的ID。第一设备根据最佳N个波束对的ID确定最优波束。
一种实施方式中，若波束预测模型支持的接收波束数量为Rx_num,Rx_num/2,和Rx_num/4。则波束预测模型输出的N个最佳波束对ID可以是将所有波束对分为4组，每组输出N/4个最佳波束数对ID。
一些实施例中，所有波束对分为4组，可以包括：
每组包含波束对ID均连续；
每组包含波束对ID均不连续；
或将所有波束对分为Rx_num组，每组包含的波束对数量为网络设备的Tx_num个波束对，1/4为其中Rx_num/4组中所有波束对。比如Rx_num为8，则有8组，1/4为1,5组或2,6组或3,7组或4,8组中包含的波束对。
一些实施例中，若终端接收波束数量为Rx_num,则直接获得最佳N个波束对的ID。
一些实施例中，若终端接收波束数量为Rx_num/2,则将只能取其中一半波束对中输出的最佳N/2个波束数对ID。
一些实施例中，一半波束对可以包括：
前一半，或后一半(对应波束对ID均连续)；
或奇数编号的一半，或偶数编号的一半(对应波束对ID均不连续)；
或将所有波束对分为Rx_num组，每组包含的波束对数量为网络设备的Tx_num个波束对，一半为奇数组或偶数组包含的所有波束对。比如Rx_num为8，则有8组，一半为1,3,5,7组或2,4,6,8组中包含的波束对。
一些实施例中，若终端接收波束数量为Rx_num/4,则只能取其中1/4波束对中输出的最佳N/4个波束对ID。
一些实施例中，1/4波束对可以包括：
所有波束对分为4组，4组中的任一一组(即每组内波束对ID均连续或均不连续)；
或将所有波束对分为Rx_num组，每组包含的波束对数量为网络设备的Tx_num个波束对，1/4为其中Rx_num/4组中所有波束对。比如Rx_num为8，则有8组，1/4为1,5组或2,6组或3,7组或4,8组中包含的波束对。
本公开通过波束预测模型所支持的接收波束数量，可以从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
需要说明的是，本领域内技术人员可以理解，本公开实施例上述涉及的各种实施方式 /实施例中可以配合前述的实施例使用，也可以是独立使用。无论是单独使用还是配合前述的实施例一起使用，其实现原理类似。本公开实施中，部分实施例中是以一起使用的实施方式进行说明的。当然，本领域内技术人员可以理解，这样的举例说明并非对本公开实施例的限定。
基于相同的构思，本公开实施例还提供一种波束确定装置、设备。
可以理解的是，本公开实施例提供的波束确定装置、设备为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。结合本公开实施例中所公开的各示例的单元及算法步骤，本公开实施例能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。本领域技术人员可以对每个特定的应用来使用不同的方法来实现所描述的功能，但是这种实现不应认为超出本公开实施例的技术方案的范围。
图22是根据一示例性实施例示出的一种波束确定装置示意图。参照图22，该装置200配置于终端，包括：确定模块201，用于确定波束预测模型支持的接收波束数量；确定模块201还用于，基于波束预测模型支持的接收波束数量，从波束预测模型的输出中确定最优波束。
本公开通过波束预测模型所支持的接收波束数量，可以从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，装置200还包括：接收模块202，用于接收网络设备发送的第一指示信息，第一指示信息用于指示波束预测模型支持的接收波束数量；确定模块201还用于，基于第一指示信息确定波束预测模型支持的接收波束数量信息。
本公开还可以通过其它设备的指示信息确定波束预测模型所支持的接收波束数量，以便可以基于波束预测模型所支持的接收波束数量从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，波束预测模型支持的接收波束数量包括：波束预测模型支持的最大接收波束数量；或，波束预测模型支持的一个或多个接收波束数量。
本公开通过波束预测模型可以支持的接收波束数量，从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，响应于波束预测模型支持多个接收波束数量，多个接收波束数量 包括第一数量和第二数量；第一数量为波束预测模型支持的最大接收波束数量，第一数量为第二数量的N倍，第二数量的最小值为1，其中，N为正整数。
本公开中波束预测模型可以支持多个不同的接收波束数量，以使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，接收模块202还用于，接收网络设备发送的第二指示信息；确定模块201还用于，基于第二指示信息从波束预测模型的输出中确定最优波束；或，确定模块201还用于，根据预定义规则，从波束预测模型的输出中确定最优波束。
本公开可以通过第二设备的指示信息或者预定义规则，从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，确定模块201还用于：响应于波束预测模型的输出包括波束预测模型支持的最大数量个波束对的波束质量信息，基于终端支持的接收波束数量，从波束预测模型的输出中确定最优波束。
本公开在波束预测模型的输出包括波束预测模型支持的最大数量个波束对的波束质量信息时，可以基于终端支持的接收波束数量从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，确定模块201还用于：响应于终端支持的接收波束数量为波束预测模型支持的最大接收波束数量，从最大数量个波束对中确定最优波束。
本公开在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量时，可以从波束预测模型输出的最大数量个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量的终端。
在一个实施方式中，确定模块201还用于：响应于终端支持的接收波束数量为第三数量，将最大数量个波束对分成M个分组，从M个分组中任意一个分组包含的波束对中确定最优波束，其中，第三数量为波束预测模型支持的最大接收波束数量的1/M，M为正整数。
本公开在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量中的部分接收波束数量时，对最大数量个波束对进行分组，并从任意一个分组内的多个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量中部分接收波束数量的终端。
在一个实施方式中，确定模块201还用于执行以下至少一项：将最大数量个波束对按 照波束对分成M个分组，其中，每个分组内的波束对的波束对编号连续；将最大数量个波束对按照波束对对应的接收波束分成M个分组，其中，同一个接收波束对应的波束对属于同一个分组；将最大数量个波束对分成M个分组，其中，同一个接收波束对应的波束对分成M个小组，M个小组与M个分组一一对应。
本公开提供了多种不同将最大数量个波束对进行分组的方式，使得在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量中的部分接收波束数量时，可以从任意一个分组内的多个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量中部分接收波束数量的终端。
在一个实施方式中，确定模块201还用于：响应于波束预测模型的输出包括候选最优波束，根据候选最优波束确定最优波束。
本公开在波束预测模型的输出包括候选最优波束时，可以基于终端支持的接收波束数量从候选最优波束中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，确定模块201还用于：根据波束预测模型所支持的最大接收波束数量与最小接收波束数量之间的比值L，确定L个最小接收波束分组，其中，每个最小接收波束分组对应多个波束对；确定波束预测模型输出的各个最小接收波束分组分别对应的候选最优波束；基于终端支持的接收波束数量和各个最小接收波束分组分别对应的候选最优波束，确定最优波束。
本公开在波束预测模型的输出包括候选最优波束时，可以根据波束预测模型所支持的最大接收波束数量与最小接收波束数量，将波束预测模型支持的最大数量个波束对划分为多个最小接收波束分组。以便基于终端支持的接收波束数量，利用一个或多个最小接收波束分组对应的候选最优波束，确定优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，最小接收波束分组对应多个波束对，满足以下任意一项：每个最小接收波束分组内的波束对的波束对编号连续；同一个接收波束对应的波束对属于同一个最小接收波束分组；将同一个接收波束对应的波束对分成L个小组，L个小组与L个最小接收波束分组一一对应。
本公开提供了多种不同最小波束分组的组成方式，使得在波束预测模型的输出包括候选最优波束时，可以基于终端支持的接收波束数量和最小波束分组对应的候选最优波束确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，确定模块201还用于：响应于终端支持的接收波束数量为最小接收波束数量的K倍，根据K个最小接收波束分组对应的候选最优波束，确定最优波束，其中，K为正整数，终端支持的接收波束数量小于或等于最大接收波束数量。
本公开可以基于终端支持的不同接收波束数量结合最小波束分组对应的候选最优波束，确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
图23是根据一示例性实施例示出的另一种波束确定装置示意图。参照图23，该装置300配置于网络设备，包括：确定模块301，用于确定波束预测模型支持的接收波束数量；确定模块301还用于，基于波束预测模型支持的接收波束数量，从波束预测模型的输出中确定最优波束。
本公开通过波束预测模型所支持的接收波束数量，可以从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，装置300还包括：接收模块302，用于接收终端发送的第一指示信息，第一指示信息用于指示波束预测模型支持的接收波束数量；确定模块301还用于，基于第一指示信息确定波束预测模型支持的接收波束数量信息。
本公开还可以通过其它设备的指示信息确定波束预测模型所支持的接收波束数量，以便可以基于波束预测模型所支持的接收波束数量从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，波束预测模型支持的接收波束数量包括：波束预测模型支持的最大接收波束数量；或，波束预测模型支持的一个或多个接收波束数量。
本公开通过波束预测模型可以支持的接收波束数量，从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，响应于波束预测模型支持多个接收波束数量，多个接收波束数量包括第一数量和第二数量；第一数量为波束预测模型支持的最大接收波束数量，第一数量为第二数量的N倍，第二数量的最小值为1，其中，N为正整数。
本公开中波束预测模型可以支持多个不同的接收波束数量，以使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，接收模块302还用于，接收终端发送的第二指示信息；确定模块 301还用于，基于第二指示信息从波束预测模型的输出中确定最优波束；或，确定模块301还用于，根据预定义规则，从波束预测模型的输出中确定最优波束。
本公开可以通过第二设备的指示信息或者预定义规则，从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，确定模块301还用于：响应于波束预测模型的输出包括波束预测模型支持的最大数量个波束对的波束质量信息，基于终端支持的接收波束数量，从波束预测模型的输出中确定最优波束。
本公开在波束预测模型的输出包括波束预测模型支持的最大数量个波束对的波束质量信息时，可以基于终端支持的接收波束数量从波束预测模型的输出中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，确定模块301还用于：响应于终端支持的接收波束数量为波束预测模型支持的最大接收波束数量，从最大数量个波束对中确定最优波束。
本公开在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量时，可以从波束预测模型输出的最大数量个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量的终端。
在一个实施方式中，确定模块301还用于：响应于终端支持的接收波束数量为第三数量，将最大数量个波束对分成M个分组，从M个分组中任意一个分组包含的波束对中确定最优波束，其中，第三数量为波束预测模型支持的最大接收波束数量的1/M，M为正整数。
本公开在终端支持的接收波束数量为波束预测模型支持的最大接收波束数量中的部分接收波束数量时，对最大数量个波束对进行分组，并从任意一个分组内的多个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量中部分接收波束数量的终端。
在一个实施方式中，确定模块301还用于执行以下至少一项：将最大数量个波束对按照波束对分成M个分组，其中，每个分组内的波束对的波束对编号连续；将最大数量个波束对按照波束对对应的接收波束分成M个分组，其中，同一个接收波束对应的波束对属于同一个分组；将最大数量个波束对分成M个分组，其中，同一个接收波束对应的波束对分成M个小组，M个小组与M个分组一一对应。
本公开提供了多种不同将最大数量个波束对进行分组的方式，使得在终端支持的接收 波束数量为波束预测模型支持的最大接收波束数量中的部分接收波束数量时，可以从任意一个分组内的多个波束对中确定最优波束，使得波束预测模型可以适配接收波束数量为波束预测模型支持的最大接收波束数量中部分接收波束数量的终端。
在一个实施方式中，确定模块301还用于：响应于波束预测模型的输出包括候选最优波束，根据候选最优波束确定最优波束。
本公开在波束预测模型的输出包括候选最优波束时，可以基于终端支持的接收波束数量从候选最优波束中确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，确定模块301还用于：根据波束预测模型所支持的最大接收波束数量与最小接收波束数量之间的比值L，确定L个最小接收波束分组，其中，每个最小接收波束分组对应多个波束对；确定波束预测模型输出的各个最小接收波束分组分别对应的候选最优波束；基于终端支持的接收波束数量和各个最小接收波束分组分别对应的候选最优波束，确定最优波束。
本公开在波束预测模型的输出包括候选最优波束时，可以根据波束预测模型所支持的最大接收波束数量与最小接收波束数量，将波束预测模型支持的最大数量个波束对划分为多个最小接收波束分组。以便基于终端支持的接收波束数量，利用一个或多个最小接收波束分组对应的候选最优波束，确定优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，最小接收波束分组对应多个波束对，满足以下任意一项：每个最小接收波束分组内的波束对的波束对编号连续；同一个接收波束对应的波束对属于同一个最小接收波束分组；将同一个接收波束对应的波束对分成L个小组，L个小组与L个最小接收波束分组一一对应。
本公开提供了多种不同最小波束分组的组成方式，使得在波束预测模型的输出包括候选最优波束时，可以基于终端支持的接收波束数量和最小波束分组对应的候选最优波束确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
在一个实施方式中，确定模块301还用于：响应于终端支持的接收波束数量为最小接收波束数量的K倍，根据K个最小接收波束分组对应的候选最优波束，确定最优波束，其中，K为正整数，终端支持的接收波束数量小于或等于最大接收波束数量。
本公开可以基于终端支持的不同接收波束数量结合最小波束分组对应的候选最优波束，确定最优波束。使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确 定出适用于各终端的最优波束。
关于上述实施例中的装置200和装置300，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
图24是根据一示例性实施例示出的一种波束确定设备示意图。例如，设备400可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等任意终端。
参照图24，设备400可以包括以下一个或多个组件：处理组件402，存储器404，电力组件406，多媒体组件408，音频组件410，输入/输出(I/O)接口412，传感器组件414，以及通信组件416。
处理组件402通常控制设备400的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件402可以包括一个或多个处理器420来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件402可以包括一个或多个模块，便于处理组件402和其他组件之间的交互。例如，处理组件402可以包括多媒体模块，以方便多媒体组件408和处理组件402之间的交互。
存储器404被配置为存储各种类型的数据以支持在设备400的操作。这些数据的示例包括用于在设备400上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器404可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电力组件406为设备400的各种组件提供电力。电力组件406可以包括电源管理系统，一个或多个电源，及其他与为设备400生成、管理和分配电力相关联的组件。
多媒体组件408包括在所述设备400和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件408包括一个前置摄像头和/或后置摄像头。当设备400处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件410被配置为输出和/或输入音频信号。例如，音频组件410包括一个麦克风 (MIC)，当设备400处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器404或经由通信组件416发送。在一些实施例中，音频组件410还包括一个扬声器，用于输出音频信号。
I/O接口412为处理组件402和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件414包括一个或多个传感器，用于为设备400提供各个方面的状态评估。例如，传感器组件414可以检测到设备400的打开/关闭状态，组件的相对定位，例如所述组件为设备400的显示器和小键盘，传感器组件414还可以检测设备400或设备400一个组件的位置改变，用户与设备400接触的存在或不存在，设备400方位或加速/减速和设备400的温度变化。传感器组件414可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件414还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件414还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件416被配置为便于设备400和其他设备之间有线或无线方式的通信。设备400可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件416经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件416还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，设备400可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器404，上述指令可由设备400的处理器420执行以完成上述方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
图25是根据一示例性实施例示出的另一种波束确定设备示意图。例如，设备500可以被提供为一基站，或者是服务器。参照图25，设备500包括处理组件522，其进一步包括一个或多个处理器，以及由存储器532所代表的存储器资源，用于存储可由处理组件522执行的指令，例如应用程序。存储器532中存储的应用程序可以包括一个或一个以上的每 一个对应于一组指令的模块。此外，处理组件522被配置为执行指令，以执行上述方法。
设备500还可以包括一个电源组件526被配置为执行设备500的电源管理，一个有线或无线网络接口550被配置为将设备500连接到网络，和一个输入输出(I/O)接口558。设备500可以操作基于存储在存储器532的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
本公开通过波束预测模型所支持的接收波束数量，可以从波束预测模型的输出中确定最优波束，使得支持不同数量接收波束的终端可以利用同一个波束预测模型，确定出适用于各终端的最优波束。
本公开可以针对支持不同接收波束数量的终端，使用同一个波束测量模型获得最佳波束对信息。从而提高了波束测量模型的泛化性，使得一个波束测量模型能适用于接收波束数量不同的终端。
进一步可以理解的是，本公开中“多个”是指两个或两个以上，其它量词与之类似。“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。单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。
进一步可以理解的是，术语“第一”、“第二”等用于描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开，并不表示特定的顺序或者重要程度。实际上，“第一”、“第二”等表述完全可以互换使用。例如，在不脱离本公开范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。
进一步可以理解的是，本公开中涉及到的“响应于”“如果”等词语的含义取决于语境以及实际使用的场景，如在此所使用的词语“响应于”可以被解释成为“在……时”或“当……时”或“如果”或“若”。
进一步可以理解的是，本公开实施例中尽管在附图中以特定的顺序描述操作，但是不应将其理解为要求按照所示的特定顺序或是串行顺序来执行这些操作，或是要求执行全部所示的操作以得到期望的结果。在特定环境中，多任务和并行处理可能是有利的。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其它实施方案。本申请旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利范围来限制。

Claims (18)

  1. 一种波束确定方法，其特征在于，所述方法应用于第一设备，包括：
    确定波束预测模型支持的接收波束数量；
    基于所述波束预测模型支持的接收波束数量，从所述波束预测模型的输出中确定最优波束。
  2. 根据权利要求1所述的方法，其特征在于，所述确定波束预测模型支持的接收波束数量信息，包括：
    接收第二设备发送的第一指示信息，所述第一指示信息用于指示所述波束预测模型支持的接收波束数量；
    基于所述第一指示信息确定波束预测模型支持的接收波束数量信息。
  3. 根据权利要求1或2所述的方法，其特征在于，所述波束预测模型支持的接收波束数量包括：
    所述波束预测模型支持的最大接收波束数量；或，
    所述波束预测模型支持的一个或多个接收波束数量。
  4. 根据权利要求3所述的方法，其特征在于，响应于所述波束预测模型支持多个接收波束数量，所述多个接收波束数量包括第一数量和第二数量；
    所述第一数量为所述波束预测模型支持的最大接收波束数量，所述第一数量为所述第二数量的N倍，所述第二数量的最小值为1，其中，N为正整数。
  5. 根据权利要求1-4中任意一项所述的方法，其特征在于，所述从所述波束预测模型的输出中确定最优波束，包括：
    接收第二设备发送的第二指示信息；基于所述第二指示信息从所述波束预测模型的输出中确定最优波束；或，
    根据预定义规则，从所述波束预测模型的输出中确定最优波束。
  6. 根据权利要求5所述的方法，其特征在于，所述从所述波束预测模型的输出中确定最优波束，包括：
    响应于所述波束预测模型的输出包括所述波束预测模型支持的最大数量个波束对的波束质量信息，基于终端支持的接收波束数量，从所述波束预测模型的输出中确定所述最优波束。
  7. 根据权利要求6所述的方法，其特征在于，所述基于终端支持的接收波束数量，从所述波束预测模型的输出中确定最优波束，包括：
    响应于所述终端支持的接收波束数量为所述波束预测模型支持的最大接收波束数量， 从所述最大数量个波束对中确定所述最优波束。
  8. 根据权利要求6所述的方法，其特征在于，所述基于终端支持的接收波束数量，从所述波束预测模型的输出中确定最优波束，包括：
    响应于所述终端支持的接收波束数量为第三数量，将所述最大数量个波束对分成M个分组，从所述M个分组中任意一个分组包含的波束对中确定所述最优波束，其中，所述第三数量为所述波束预测模型支持的最大接收波束数量的1/M，M为正整数。
  9. 根据权利要求8所述的方法，其特征在于，所述将所述最大数量个波束对分成M个分组，包括以下至少一项：
    将所述最大数量个波束对按照波束对分成M个分组，其中，每个分组内的波束对的波束对编号连续或不连续；
    将所述最大数量个波束对按照波束对对应的接收波束分成M个分组，其中，同一个接收波束对应的波束对属于同一个分组；
    将所述最大数量个波束对分成M个分组，其中，同一个接收波束对应的波束对分成M个小组，所述M个小组与所述M个分组一一对应。
  10. 根据权利要求5所述的方法，其特征在于，所述从所述波束预测模型的输出中确定最优波束，包括：
    响应于所述波束预测模型的输出包括候选最优波束，根据所述候选最优波束确定所述最优波束。
  11. 根据权利要求10所述的方法，其特征在于，所述根据所述候选最优波束确定所述最优波束，包括：
    根据所述波束预测模型所支持的最大接收波束数量与最小接收波束数量之间的比值L，确定L个最小接收波束分组，其中，每个最小接收波束分组对应多个波束对；
    确定所述波束预测模型输出的各个最小接收波束分组分别对应的候选最优波束；
    基于终端支持的接收波束数量和所述各个最小接收波束分组分别对应的候选最优波束，确定所述最优波束。
  12. 根据权利要求11所述的方法，其特征在于，所述最小接收波束分组对应多个波束对，满足以下任意一项：
    每个最小接收波束分组内的波束对的波束对编号连续；
    同一个接收波束对应的波束对属于同一个最小接收波束分组；
    将同一个接收波束对应的波束对分成L个小组，所述L个小组与所述L个最小接收波束分组一一对应。
  13. 根据权利要求11或12所述的方法，其特征在于，所述基于终端支持的接收波束数量和所述各个最小接收波束分组分别对应的候选最优波束，确定所述最优波束，包括：
    响应于所述终端支持的接收波束数量为最小接收波束数量的K倍，根据K个最小接收波束分组对应的候选最优波束，确定所述最优波束，其中，K为正整数，所述终端支持的接收波束数量小于或等于所述最大接收波束数量。
  14. 根据权利要求1-13中任意一项所述的方法，其特征在于，所述第一设备为终端，第二设备为网络设备。
  15. 根据权利要求1-13中任意一项所述的方法，其特征在于，所述第一设备为网络设备，第二设备为终端。
  16. 一种波束确定装置，其特征在于，所述装置配置于第一设备，包括：
    确定模块，用于确定波束预测模型支持的接收波束数量；
    所述确定模块还用于，基于所述波束预测模型支持的接收波束数量，从所述波束预测模型的输出中确定最优波束。
  17. 一种波束确定设备，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为：执行权利要求1至15中任意一项所述的方法。
  18. 一种非临时性计算机可读存储介质，当所述存储介质中的指令由第一设备的处理器执行时，使得所述第一设备能够执行权利要求1至15中任意一项所述的方法。
PCT/CN2022/124469 2022-10-10 2022-10-10 一种波束确定方法、装置、设备及存储介质 WO2024077461A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2022/124469 WO2024077461A1 (zh) 2022-10-10 2022-10-10 一种波束确定方法、装置、设备及存储介质
CN202280004077.9A CN118202593A (zh) 2022-10-10 2022-10-10 一种波束确定方法、装置、设备及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/124469 WO2024077461A1 (zh) 2022-10-10 2022-10-10 一种波束确定方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2024077461A1 true WO2024077461A1 (zh) 2024-04-18

Family

ID=90668537

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/124469 WO2024077461A1 (zh) 2022-10-10 2022-10-10 一种波束确定方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN118202593A (zh)
WO (1) WO2024077461A1 (zh)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107733505A (zh) * 2016-08-12 2018-02-23 电信科学技术研究院 一种波束赋形训练方法、终端和基站
US20200169311A1 (en) * 2017-08-30 2020-05-28 Telefonaktiebolaget Lm Ericsson (Publ) Wireless device for determining a best antenna beam and method thereof
CN112073106A (zh) * 2020-08-14 2020-12-11 清华大学 毫米波波束预测方法及装置、电子设备、可读存储介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107733505A (zh) * 2016-08-12 2018-02-23 电信科学技术研究院 一种波束赋形训练方法、终端和基站
US20200169311A1 (en) * 2017-08-30 2020-05-28 Telefonaktiebolaget Lm Ericsson (Publ) Wireless device for determining a best antenna beam and method thereof
CN112073106A (zh) * 2020-08-14 2020-12-11 清华大学 毫米波波束预测方法及装置、电子设备、可读存储介质

Also Published As

Publication number Publication date
CN118202593A (zh) 2024-06-14

Similar Documents

Publication Publication Date Title
WO2021159515A1 (zh) 数据传输方法及数据传输装置
US20210336737A1 (en) Measurement configuration method, apparatus, devices, system, and storage medium
WO2021087825A1 (zh) 波束失败检测资源分配方法、装置及存储介质
WO2023070563A1 (zh) 传输配置指示状态确定方法、装置及存储介质
WO2021258370A1 (zh) 一种通信处理方法、通信处理装置及存储介质
WO2021226746A1 (zh) 数据传输方法、数据传输装置及存储介质
EP4002738A1 (en) Resource allocation method and apparatus, and storage medium
WO2020258041A1 (zh) 数据传输方法、装置、系统及存储介质
WO2019090723A1 (zh) 数据传输方法及装置
US11902945B2 (en) Method, device, and system for transmitting data in divided transmission blocks
WO2024077461A1 (zh) 一种波束确定方法、装置、设备及存储介质
WO2023279262A1 (zh) 一种消息配置方法、消息配置装置及存储介质
US20230180175A1 (en) Positioning measurement method, positioning measurement apparatus and storage medium
WO2021179126A1 (zh) 控制信令检测方法、控制信令检测装置及存储介质
WO2024082312A1 (zh) 传输配置指示状态的确定方法、装置及存储介质
WO2023039785A1 (zh) 一种调度方法、调度装置及存储介质
WO2024092786A1 (zh) 一种通信方法、装置、设备及存储介质
WO2024113276A1 (zh) 一种通信定位方法、装置、设备及存储介质
WO2024077460A1 (zh) 一种波束预测方法、装置、设备及存储介质
WO2024130590A1 (zh) 一种传输配置指示状态的确定方法、装置及存储介质
WO2024119381A1 (zh) 一种波束指示方法、装置、设备及存储介质
WO2024130613A1 (zh) 一种传输配置指示状态的确定方法、装置及存储介质
WO2024082314A1 (zh) 传输配置指示状态的确定方法、装置及存储介质
WO2024130747A1 (zh) 一种资源限制指示方法、装置及存储介质
WO2024087258A1 (zh) 波束失败检测参考信号资源的确定方法、装置及存储介质