# US 2022/0044091 A1 · Neural network functions for positioning of a user equipment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2022/0044091 A1 - Document ID: US20220044091A1 - Status: Published application - Kind: A1 - Application number: 17/391,347 - Filed: 2021-08-02 - Published: 2022-02-10 - Earliest claimed: 2020-08-04 - Assignees: QUALCOMM Incorporated - Applicants: QUALCOMM Incorporated - Inventors: Jay Kumar SUNDARARAJAN; Taesang YOO; Naga BHUSHAN; Pavan Kumar VITTHALADEVUNI; June NAMGOONG; Krishna Kiran MUKKAVILLI; Tingfang JI - Web page: https://patentgrep.com/patent/US20220044091A1 ## CPC - G01S 5/0027: {of actual mobile position, i.e. position determined on mobile} - G06N 3/04: Architecture, e.g. interconnection topology - G01S 5/0236: {Assistance data, e.g. base station almanac} - G01S 5/0278: {involving statistical or probabilistic considerations (G01S5/0252, G01S5/0294 take precedence)} - G06F 1/12: Synchronisation of different clock signals {provided by a plurality of clock generators} - G06F 18/213: Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods - G06F 18/24133: {Distances to prototypes} - G06N 3/045: Combinations of networks - G06N 3/0499: Feedforward networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - H04W 64/00: Locating users or terminals {or network equipment} for network management purposes, e.g. mobility management - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) ## Abstract In an aspect, a BS obtains at least one neural network function configured to facilitate a UE to derive a likelihood of at least one set of positioning measurement features being present at a candidate set of positioning estimates for the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures. The BS transmits the at least one neural network function to the UE. In another aspect, the UE obtains positioning measurement data associated with a location of the UE (e.g., locally the UE, or remotely from the BS). The UE determines a positioning estimate for the UE based at least in part upon the positioning measurement data and the at least one neural network function. ## Claims ### Claim 1 A method of operating a user equipment (UE), comprising: obtaining at least one neural network function configured to derive a likelihood of at least one set of positioning measurement features being present at a candidate set of positioning estimates for the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures; obtaining positioning measurement data associated with a location of the UE; and determining a positioning estimate for the UE based at least in part upon the positioning measurement data and the at least one neural network function. ### Claim 2 (depends on 1) The method of claim 1, wherein the at least one neural network function comprises a UE-feature processing neural network function. ### Claim 3 (depends on 2) The method of claim 2, wherein the positioning measurement data comprises a set of positioning measurements at the UE, and wherein the determining comprises: detecting a set of positioning measurement features based on the set of positioning measurements at the UE; and deriving a likelihood of the set of positioning measurement features being present at the candidate set of positioning estimates for the UE based at least in part upon the UE-feature processing neural network function, wherein the positioning estimate for the UE is based in part upon the derived likelihoods. ### Claim 4 (depends on 2) The method of claim 2, wherein the at least one neural network function comprises at least one additional UE-feature processing neural network function. ### Claim 5 (depends on 2) The method of claim 2, wherein the UE-feature processing neural network function is configured to derive the likelihoods based on at least one of: a clock drift at the UE, a hardware group delay at the UE, a model of UE, or a combination thereof. ### Claim 6 (depends on 1) The method of claim 1, wherein the at least one neural network function comprises a base station (BS)-feature processing neural network function. ### Claim 7 (depends on 6) The method of claim 6, wherein the positioning measurement data comprises a set of positioning measurement features based on a set of positioning measurements at one or more BSs, and wherein the determining comprises: deriving a likelihood of the set of positioning measurement features being present at the candidate set of positioning estimates for the UE based at least in part upon the BS-feature processing neural network function, wherein the positioning estimate for the UE is based in part upon the derived likelihoods. ### Claim 8 (depends on 7) The method of claim 7, wherein the at least one neural network function comprises at least one additional BS-feature processing neural network function. ### Claim 9 (depends on 6) The method of claim 6, wherein the at least one neural network function further comprises a UE-feature processing neural network function. ### Claim 10 (depends on 9) The method of claim 9, wherein the positioning measurement data comprises a first set of positioning measurement features based on a first set of positioning measurements at one or more BSs, and a second set of positioning measurement features based on a second set of positioning measurements at the UE, further comprising: deriving a likelihood of the first and second sets of positioning measurement features being present at the candidate set of positioning estimates for the UE based at least in part upon the UE-feature processing neural network function and the BS-feature processing neural network function, wherein the positioning estimate for the UE is based in part upon the derived likelihoods. ### Claim 11 (depends on 6) The method of claim 6, wherein the BS-feature processing neural network function is configured to derive the likelihoods based on at least one of: a location of at least one BS, a downtilt of the at least one BS, a transmit power of the at least one BS, a clock synchronization error between two or more BSs, a clock drift of the at least one BS, a hardware group delay of the at least one BS, a base station almanac (BSA) error associated with the at least one BS, or any combination thereof. ### Claim 12 (depends on 1) The method of claim 1, wherein the candidate set of positioning estimates is implicitly indicated to the UE in association with the at least one neural network function, or wherein the candidate set of positioning estimates is explicitly indicated to the UE in association with the at least one neural network function. ### Claim 13 (depends on 1) The method of claim 1, wherein the at least one neural network function is specific to: a particular base station (BS) or group of BSs, a carrier, a location region, a positioning measurement type or group of positioning measurement types, a beam or group of beams, or any combination thereof. ### Claim 14 (depends on 1) The method of claim 1, wherein the positioning estimate comprises: a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a Global Navigation Satellite System (GNSS) position estimate, a sensor-based position estimate, or any combination thereof. ### Claim 15 (depends on 1) The method of claim 1, wherein the obtaining comprises receipt of the at least one neural network function from a base station, a server, or a combination thereof. ### Claim 16 (depends on 1) The method of claim 1, wherein the at least one neural network function configured to facilitate the UE to derive the likelihood of the at least one set of positioning measurement features being present at the candidate set of positioning estimates for the UE in association with one or more other positioning measurement features. ### Claim 17 A method of operating a base station (BS), comprising: obtaining at least one neural network function configured to facilitate a user equipment (UE) to derive a likelihood of at least one set of positioning measurement features being present at a candidate set of positioning estimates for the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures; and transmitting the at least one neural network function to the UE. ### Claim 18 (depends on 17) The method of claim 17, wherein the at least one neural network function is generated dynamically at the BS or another network component. ### Claim 19 (depends on 17) The method of claim 17, wherein the at least one neural network function comprises a UE-feature processing neural network function. ### Claim 20 (depends on 19) The method of claim 19, wherein the at least one neural network function comprises at least one additional UE-feature processing neural network function. ### Claim 21 (depends on 19) The method of claim 19, wherein the UE-feature processing neural network function is configured to derive the likelihoods based on at least one of: a clock drift at the UE, a hardware group delay at the UE, a model of UE, or a combination thereof. ### Claim 22 (depends on 19) The method of claim 19, wherein the at least one neural network function comprises one or more base station (BS)-feature processing neural network functions. ### Claim 23 (depends on 22) The method of claim 22, wherein the at least one neural network function further comprises one or more UE-feature processing neural network functions. ### Claim 24 (depends on 22) The method of claim 22, wherein the one or more BS-feature processing neural network functions are configured to derive the likelihoods based on at least one of: a location of at least one BS, a downtilt of the at least one BS, a transmit power of the at least one BS, a clock synchronization error between two or more BSs, a clock drift of the at least one BS, a hardware group delay of the at least one BS, a base station almanac (BSA) error associated with the at least one BS, or any combination thereof. ### Claim 25 (depends on 17) The method of claim 17, wherein the candidate set of positioning estimates is implicitly indicated to the UE in association with the at least one neural network function, or wherein the candidate set of positioning estimates is explicitly indicated to the UE in association with the at least one neural network function. ### Claim 26 (depends on 17) The method of claim 17, wherein the at least one neural network function is specific to: a particular base station (BS) or group of BSs, a carrier, a location region, a positioning measurement type or group of positioning measurement types, a beam or group of beams, or any combination thereof. ### Claim 27 (depends on 17) The method of claim 17, wherein the at least one neural network function is configured to facilitate the UE to determine one or more: a wireless wide area network (WWAN) position estimate, a wireless local area network (WLAN) position estimate, a Global Navigation Satellite System (GNSS) position estimate, a sensor-based position estimate, or any combination thereof. ### Claim 28 (depends on 17) The method of claim 17, wherein the obtaining comprises generation of the at least one neural network function at the base station, or wherein the obtaining comprises receipt of the at least one neural network function from a core network component or an external server. ### Claim 29 A user equipment (UE), comprising: a memory; at least one transceiver; and at least one processor communicatively coupled to the memory and the at least one transceiver, the at least one processor configured to: obtain at least one neural network function configured to derive a likelihood of at least one set of positioning measurement features being present at a candidate set of positioning estimates for the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures; obtain positioning measurement data associated with a location of the UE; and determine a positioning estimate for the UE based at least in part upon the positioning measurement data and the at least one neural network function. ### Claim 30 A base station (BS), comprising: a memory; at least one transceiver; and at least one processor communicatively coupled to the memory and the at least one transceiver, the at least one processor configured to: obtain at least one neural network function configured to facilitate a user equipment (UE) to derive a likelihood of at least one set of positioning measurement features being present at a candidate set of positioning estimates for the UE, the at least one neural network function being generated dynamically based on machine-learning associated with one or more historical measurement procedures; and transmit, via the at least one transceiver, the at least one neural network function to the UE.