# US 2023/0053589 A1 · Quality metric signaling for beam strength prediction > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0053589 A1 - Document ID: US20230053589A1 - Status: Published application - Kind: A1 - Application number: 17/404,777 - Filed: 2021-08-17 - Published: 2023-02-23 - Earliest claimed: 2021-08-17 - Assignees: QUALCOMM Incorporated - Applicants: QUALCOMM Incorporated - Inventors: Hamed PEZESHKI; Tao LUO; Arumugam CHENDAMARAI KANNAN; Philip Aaron SISK; Taesang YOO; Mahmoud TAHERZADEH BOROUJENI - Web page: https://patentgrep.com/patent/US20230053589A1 ## CPC - H04W 24/10: Scheduling measurement reports {; Arrangements for measurement reports} - G06N 3/04: Architecture, e.g. interconnection topology - G06N 20/00: Machine learning - H04B 7/0632: {Channel quality parameters, e.g. channel quality indicator [CQI]} - H04W 72/044: based on the type of the allocated resource - H04W 72/542: using measured or perceived quality - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H04B: TRANSMISSION ## Abstract Certain aspects of the present disclosure provide techniques for predicting a strength of a transmission beam in a communication system. In one example, the disclosure describes a user equipment (UE) receiving a quality metric from a base station (BS), the quality metric indicating one or more tolerance levels for predicted beam strength as compared to actual beam strength at the UE. In some examples, the UE may transmit, to the BS, one or more indications of actual beam strength as measured at the UE at one or more time periods for one or more transmit beams of the BS. ## Claims ### Claim 1 A user equipment (UE), comprising: a memory; and a processor coupled to the memory, the processor and the memory configured to: receive a quality metric from a base station (BS), the quality metric indicating one or more tolerance levels for predicted beam strength as compared to actual beam strength at the UE; and transmit, to the BS, one or more indications of actual beam strength as measured at the UE at one or more time periods for one or more transmit beams of the BS. ### Claim 2 (depends on 1) The UE of claim 1, wherein the processor and the memory are further configured to: determine, prior to a first time period, a first predicted beam strength for a first transmit beam of the BS for the first time period based on a prediction mechanism; determine a first actual beam strength as measured at the UE at the first time period; determine whether a difference between the first predicted beam strength and the first actual beam strength is within a first tolerance level of the one or more tolerance levels; and take an action based at least in part on whether the difference is within the first tolerance level. ### Claim 3 (depends on 2) The UE of claim 2, wherein to take the action comprises to: transmit, to the BS, an indication of whether the difference is within the first tolerance level. ### Claim 4 (depends on 2) The UE of claim 2, wherein to take the action comprises to: update the prediction mechanism based at least in part on the difference not being within the first tolerance level for more than a threshold number of times. ### Claim 5 (depends on 2) The UE of claim 2, wherein the prediction mechanism comprises a machine learning model. ### Claim 6 (depends on 1) The UE of claim 1, wherein the one or more tolerance levels comprise a plurality of tolerance levels, each tolerance level associated with a different value range for at least one of predicted beam strength or actual beam strength. ### Claim 7 (depends on 6) The UE of claim 6, wherein the processor and the memory are further configured to: determine, prior to a first time period, a first predicted beam strength for a first transmit beam of the BS for the first time period based on a prediction mechanism; determine a first actual beam strength as measured at the UE at the first time period; determine whether a difference between the first predicted beam strength and the first actual beam strength is within a first tolerance level of the one or more tolerance levels, wherein the first tolerance level is associated with a first value range, and wherein at least one of the first predicted beam strength or the first actual beam strength is within the first value range; and take an action based at least in part on whether the difference is within the first tolerance level. ### Claim 8 (depends on 1) The UE of claim 1, wherein the one or more tolerance levels comprise a plurality of tolerance levels, each tolerance level associated with a different ranking for at least one of predicted beam strength or actual beam strength. ### Claim 9 (depends on 8) The UE of claim 8, wherein the processor and the memory are further configured to: determine, prior to a first time period, a first predicted beam strength for a first transmit beam of the BS for the first time period based on a prediction mechanism; determine a first actual beam strength as measured at the UE at the first time period; determine whether a difference between the first predicted beam strength and the first actual beam strength is within a first tolerance level of the one or more tolerance levels, wherein the first tolerance level is associated with a first ranking, and wherein at least one of the first predicted beam strength or the first actual beam strength has a value ranked at the first ranking among values of predicted beam strength or actual beam strength corresponding to a plurality of transmit beams of the BS; and take an action based at least in part on whether the difference is within the first tolerance level. ### Claim 10 (depends on 1) The UE of claim 1, wherein the one or more indications comprise one or more statistics for at least a first time period of the one or more time periods and for at least a first transmit beam of the one or more transmit beams of the BS, the one or more statistics comprising a percentage of time predicted beam strength at the UE is within the one or more tolerance levels of actual beam strength as measured at the UE. ### Claim 11 (depends on 1) The UE of claim 1, wherein the processor and the memory are further configured to receive an updated quality metric from the BS. ### Claim 12 (depends on 11) The UE of claim 11, wherein the updated quality metric is received in response to a mobility status change of the UE. ### Claim 13 A base station (BS), comprising: a memory; and a processor coupled to the memory, the processor and the memory configured to: transmit, to a user equipment (UE), a quality metric indicative of one or more tolerance levels for predicted beam strength as compared to actual beam strength at the UE; and receive, from the UE, one or more indications of actual beam strength as measured at the UE at one or more time periods for one or more transmit beams of the BS. ### Claim 14 (depends on 13) The BS of claim 13, wherein the one or more indications of actual beam strength comprises an indication of whether a difference between predicted beam strength and actual beam strength is within a first tolerance level of the one or more tolerance levels. ### Claim 15 (depends on 13) The BS of claim 13, wherein the one or more tolerance levels comprise a plurality of tolerance levels, each tolerance level associated with a different value range for at least one of predicted beam strength or actual beam strength. ### Claim 16 (depends on 13) The BS of claim 13, wherein the one or more tolerance levels comprise a plurality of tolerance levels, each tolerance level associated with a different ranking for at least one of predicted beam strength or actual beam strength. ### Claim 17 (depends on 13) The BS of claim 13, wherein the one or more indications comprise one or more statistics for at least a first time period of the one or more time periods and for at least a first transmit beam of the one or more transmit beams of the BS, the one or more statistics comprising a percentage of time predicted beam strength at the UE is within the one or more tolerance levels of actual beam strength as measured at the UE. ### Claim 18 (depends on 13) The BS of claim 13, wherein the processor and the memory are further configured to transmit an updated quality metric to the UE. ### Claim 19 (depends on 18) The BS of claim 18, wherein the updated quality metric is transmitted in response to a mobility status change of the UE. ### Claim 20 A method of communication by a user equipment (UE), the method comprising: receiving a quality metric from a base station (BS), the quality metric indicating one or more tolerance levels for predicted beam strength as compared to actual beam strength at the UE; and transmitting, to the BS, one or more indications of actual beam strength as measured at the UE at one or more time periods for one or more transmit beams of the BS. ### Claim 21 (depends on 20) The method of claim 20, further comprising: determining, prior to a first time period, a first predicted beam strength for a first transmit beam of the BS for the first time period based on a prediction mechanism; determining a first actual beam strength as measured at the UE at the first time period; determining whether a difference between the first predicted beam strength and the first actual beam strength is within a first tolerance level of the one or more tolerance levels; and taking an action based at least in part on whether the difference is within the first tolerance level. ### Claim 22 (depends on 21) The method of claim 21, wherein taking the action further comprises transmitting, to the BS, an indication of whether the difference is within the first tolerance level. ### Claim 23 (depends on 21) The method of claim 21, wherein taking the action further comprises updating the prediction mechanism based at least in part on the difference not being within the first tolerance level for more than a threshold number of times. ### Claim 24 (depends on 21) The method of claim 21, wherein the prediction mechanism comprises a machine learning model. ### Claim 25 (depends on 20) The method of claim 20, wherein the one or more tolerance levels comprise a plurality of tolerance levels, each tolerance level associated with a different value range for at least one of predicted beam strength or actual beam strength. ### Claim 26 (depends on 25) The method of claim 25, further comprising: determining, prior to a first time period, a first predicted beam strength for a first transmit beam of the BS for the first time period based on a prediction mechanism; determining a first actual beam strength as measured at the UE at the first time period; determining whether a difference between the first predicted beam strength and the first actual beam strength is within a first tolerance level of the one or more tolerance levels, wherein the first tolerance level is associated with a first value range, and wherein at least one of the first predicted beam strength or the first actual beam strength is within the first value range; and taking an action based at least in part on whether the difference is within the first tolerance level. ### Claim 27 (depends on 20) The method of claim 20, wherein the one or more tolerance levels comprise a plurality of tolerance levels, each tolerance level associated with a different ranking for at least one of predicted beam strength or actual beam strength. ### Claim 28 (depends on 27) The method of claim 27, further comprising: determining, prior to a first time period, a first predicted beam strength for a first transmit beam of the BS for the first time period based on a prediction mechanism; determining a first actual beam strength as measured at the UE at the first time period; determining whether a difference between the first predicted beam strength and the first actual beam strength is within a first tolerance level of the one or more tolerance levels, wherein the first tolerance level is associated with a first ranking, and wherein at least one of the first predicted beam strength or the first actual beam strength has a value ranked at the first ranking among values of predicted beam strength or actual beam strength corresponding to a plurality of transmit beams of the BS; and taking an action based at least in part on whether the difference is within the first tolerance level. ### Claim 29 (depends on 20) The method of claim 20, wherein predicted beam strength comprises predicted reference signal received power (RSRP) and actual beam strength comprises actual RSRP. ### Claim 30 A non-transitory computer-readable medium having instructions stored thereon that, when executed by a user equipment (UE), cause the UE to perform operations comprising: receiving a quality metric from a base station (BS), the quality metric indicating one or more tolerance levels for predicted beam strength as compared to actual beam strength at the UE; and transmitting, to the BS, one or more indications of actual beam strength as measured at the UE at one or more time periods for one or more transmit beams of the BS.