# US 2023/0276338 A1 · In-vehicle machine learning service discovery in perceptive wireless communications > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0276338 A1 - Document ID: US20230276338A1 - Status: Published application - Kind: A1 - Application number: 17/652,673 - Filed: 2022-02-25 - Published: 2023-08-31 - Earliest claimed: 2022-02-25 - Assignees: QUALCOMM Incorporated - Applicants: QUALCOMM Incorporated - Inventors: Kapil GULATI; Qing LI; Kyle Chi GUAN; Himaja KESAVAREDDIGARI; Hong CHENG; Junyi LI - Web page: https://patentgrep.com/patent/US20230276338A1 ## CPC - H04W 24/02: Arrangements for optimising operational condition - H04W 40/12: based on transmission quality or channel quality - G06N 20/00: Machine learning - H04L 41/16: using machine learning or artificial intelligence - H04W 4/20: Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel - H04W 4/38: for collecting sensor information - H04W 4/50: Service provisioning or reconfiguring - H04W 76/10: Connection setup - H04W 16/28: using beam steering - H04W 76/14: Direct-mode setup - H04W 92/18: between terminal devices - 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 - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A first UE and a second UE may exchange information relating to one or more machine learning data services. The one or more machine learning data services may be provided by the second UE. The first UE and the second UE may pair with each other for the one or more machine learning data services. The second UE may perform machine learning inference using at least one machine learning inference model, and may transmit the inference result (e.g., a link quality prediction) associated with a link between a network node and the first UE to the network node. The network node may switch (the direction of) the network node beam if the inference result predicts that the degree of link quality degradation associated with a current network node beam is going to be greater than a prespecified threshold. ## Claims ### Claim 1 An apparatus for wireless communication at a first UE, comprising: a memory; and at least one processor coupled to the memory and configured to: exchange information relating to one or more machine learning services with a second UE, the one or more machine learning services being provided by the second UE; and pair with the second UE for the one or more machine learning services. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein to exchange the information relating to the one or more machine learning services with the second UE, the at least one processor is further configured to: transmit, to the second UE, a service discovery request message indicating that the first UE is searching for a machine learning service provider; and receive, from the second UE, a service discovery response message based on the service discovery request message. ### Claim 3 (depends on 2) The apparatus of claim 2, wherein the service discovery request message indicates at least one of a machine learning service user ID associated with the first UE or that the first UE is a user of the one or more machine learning services. ### Claim 4 (depends on 2) The apparatus of claim 2, wherein the service discovery response message indicates at least one of a machine learning service provider status associated with the second UE, a machine learning service provider ID associated with the second UE, information about the one or more machine learning services provided by the second UE, a machine learning application ID, a machine learning service ID, an indication of a machine learning service type, or an indication of one or more machine learning service parameters, the machine learning service type corresponds to at least one of sensor data collection, feature extraction, or inference, and the one or more machine learning service parameters correspond to at least one of a data input format, a machine learning feature extraction model supported by the second UE, or a machine learning inference model supported by the second UE. ### Claim 5 (depends on 2) The apparatus of claim 2, wherein to pair with the second UE for the one or more machine learning services, the at least one processor is further configured to: transmit, to the second UE, a pairing request message based on the received service discovery response message or a capability of the first UE, the pairing request message including at least one of a machine learning application ID, a machine learning service ID, a machine learning service provider ID associated with the second UE, an indication of a machine learning service type, an indication of a machine learning feature extraction model supported by the second UE, an indication of a machine learning inference model supported by the second UE, or a machine learning service user ID associated with the first UE; and receive, from the second UE, a pairing acknowledgement message based on the pairing request message. ### Claim 6 (depends on 1) The apparatus of claim 1, wherein to exchange the information relating to the one or more machine learning services with the second UE, the at least one processor is further configured to: receive, from the second UE, a service discovery request message indicating that the second UE is searching for a machine learning service user; and transmit, to the second UE, a service discovery response message based on the service discovery request message. ### Claim 7 (depends on 6) The apparatus of claim 6, wherein the service discovery request message indicates at least one of a machine learning service provider ID associated with the second UE or that the second UE is a provider of the one or more machine learning services. ### Claim 8 (depends on 6) The apparatus of claim 6, wherein the service discovery response message indicates at least one of a machine learning service user status associated with the first UE, a machine learning service user ID associated with the first UE, a machine learning application identifier ID, a machine learning service ID, an indication of a machine learning service type, or an indication of one or more machine learning service parameters, the machine learning service type corresponds to at least one of sensor data collection, feature extraction, or inference, and the one or more machine learning service parameters correspond to at least one of a data input format, a machine learning feature extraction mode supported by the second UE, or a machine learning inference model supported by the second UE. ### Claim 9 (depends on 6) The apparatus of claim 6, wherein to pair with the second UE for the one or more machine learning services, the at least one processor is further configured to: receive, from the second UE, a pairing request message based on the transmitted service discovery response message or a capability of the second UE, the pairing request message including at least one of a machine learning application ID, a machine learning service ID, a machine learning service user ID associated with the first UE, an indication of a machine learning service type, an indication of a machine learning feature extraction model supported by the second UE, an indication of a machine learning inference model supported by the second UE, or a machine learning service provider ID associated with the second UE; and transmit, to the second UE, a pairing acknowledgement message based on the pairing request message. ### Claim 10 (depends on 1) The apparatus of claim 1, wherein to exchange the information relating to the one or more machine learning services with the second UE, the at least one processor is further configured to: transmit, to the second UE, a service discovery announcement message indicating that the first UE is searching for the one or more machine learning services, the service discovery announcement message including at least one of a machine learning application ID, a machine learning service ID, a machine learning service user ID associated with the first UE, an indication of a machine learning service type, or an indication of one or more machine learning service parameters, wherein the machine learning service type corresponds to at least one of sensor data collection, feature extraction, or inference, and the one or more machine learning service parameters correspond to at least one of a data input format, a machine learning feature extraction model supported by the second UE, or a machine learning inference model supported by the second UE. ### Claim 11 (depends on 10) The apparatus of claim 10, wherein to pair with the second UE for the one or more machine learning services, the at least one processor is further configured to: receive, from the second UE, a pairing request message based on at least one of the transmitted service discovery announcement message, a machine learning service provider ID associated with the second UE, or a capability of the second UE; and transmit, to the second UE, a pairing acknowledgement message based on the pairing request message. ### Claim 12 (depends on 1) The apparatus of claim 1, wherein to exchange the information relating to the one or more machine learning services with the second UE, the at least one processor is further configured to: receive, from the second UE, a service announcement message indicating the one or more machine learning services, the service announcement message including at least one of a machine learning application ID, a machine learning service ID, a machine learning service provider ID associated with the second UE, an indication of a machine learning service type, or an indication of one or more machine learning service parameters, wherein the machine learning service type corresponds to at least one of sensor data collection, feature extraction, or inference, and the one or more machine learning service parameters correspond to at least one of a data input format, a machine learning feature extraction model supported by the second UE, or a machine learning inference model supported by the second UE. ### Claim 13 (depends on 12) The apparatus of claim 12, wherein to pair with the second UE for the one or more machine learning services, the at least one processor is further configured to: transmit, to the second UE, a pairing request message based on at least one of the received service announcement message, a machine learning service user ID associated with the first UE, or a capability of the first UE; and receive, from the second UE, a pairing acknowledgement message based on the pairing request message. ### Claim 14 (depends on 1) The apparatus of claim 1, further comprising a transceiver coupled to the at least one processor, the at least one processor being further configured to: receive, from a network node, an indication to switch to a different beam for communicating with the network node based at least in part on one or more machine learning inference models. ### Claim 15 A method of wireless communication at a first UE, comprising: exchanging information relating to one or more machine learning services with a second UE, the one or more machine learning services being provided by the second UE; and pairing with the second UE for the one or more machine learning services. ### Claim 16 An apparatus for wireless communication at a second UE, comprising: a memory; and at least one processor coupled to the memory and configured to: exchange information relating to one or more machine learning services with a first UE, the one or more machine learning services being provided by the second UE; and pair with the first UE for the one or more machine learning services. ### Claim 17 (depends on 16) The apparatus of claim 16, wherein to exchange the information relating to the one or more machine learning services with the first UE, the at least one processor is further configured to: transmit, to the first UE, a service discovery request message indicating that the second UE is searching for a machine learning service user; and receive, from the first UE, a service discovery response message based on the service discovery request message. ### Claim 18 (depends on 17) The apparatus of claim 17, wherein the service discovery request message indicates at least a machine learning service provider ID associated with the second UE or that the second UE is a provider of the one or more machine learning services. ### Claim 19 (depends on 17) The apparatus of claim 17, wherein the service discovery response message includes at least one of a machine learning application ID, a machine learning service ID, a machine learning service user ID associated with the first UE, an indication of a machine learning service type, or an indication of one or more machine learning service parameters, the machine learning service type corresponds to at least one of sensor data collection, feature extraction, or inference, and the one or more machine learning service parameters correspond to at least one of a data input format, a machine learning feature extraction model supported by the second UE, or a machine learning inference model supported by the second UE. ### Claim 20 (depends on 17) The apparatus of claim 17, wherein to pair with the first UE for the one or more machine learning services, the at least one processor is further configured to: transmit, to the first UE, a pairing request message based on the received service discovery response message or a capability of the second UE, the pairing request message including at least one of a machine learning application ID, a machine learning service ID, a machine learning service user ID associated with the first UE, an indication of a machine learning service type, or an indication of one or more supported machine learning inference models; and receive, from the first UE, a pairing acknowledgement message based on the pairing request message. ### Claim 21 (depends on 16) The apparatus of claim 16, wherein to exchange the information relating to the one or more machine learning services with the first UE, the at least one processor is further configured to: receive, from the first UE, a service discovery request message indicating that the first UE is searching for a machine learning service provider; and transmit, to the first UE, a service discovery response message based on the service discovery request message. ### Claim 22 (depends on 21) The apparatus of claim 21, wherein the service discovery request message indicates at least one of a machine learning service user ID associated with the first UE or that the first UE is a user of the one or more machine learning services. ### Claim 23 (depends on 21) The apparatus of claim 21, wherein the service discovery response message includes at least one of a machine learning application ID, a machine learning service ID, a machine learning service provider ID associated with the second UE, an indication of a machine learning service type, or an indication of one or more machine learning service parameters, the machine learning service type corresponds to at least one of sensor data collection, feature extraction, or inference, and the one or more machine learning service parameters correspond to at least one of a data input format, a machine learning feature extraction model supported by the second UE, or a machine learning inference model supported by the second UE. ### Claim 24 (depends on 21) The apparatus of claim 21, wherein to pair with the first UE for the one or more machine learning services, the at least one processor is further configured to: receive, from the first UE, a pairing request message based on the transmitted service discovery response message or a capability of the first UE, the pairing request message including at least one of a machine learning application ID, a machine learning service ID, a machine learning service provider ID associated with the second UE, an indication of a machine learning service type, or an indication of one or more supported machine learning inference models; and transmit, to the first UE, a pairing acknowledgement message based on the pairing request message. ### Claim 25 (depends on 16) The apparatus of claim 16, wherein to exchange the information relating to the one or more machine learning services with the first UE, the at least one processor is further configured to: transmit, to the first UE, a service announcement message indicating the one or more machine learning services, the service announcement message including at least one of a machine learning application ID, a machine learning service ID, a machine learning service provider ID associated with the second UE, an indication of a machine learning service type, or an indication of one or more machine learning service parameters, wherein the machine learning service type corresponds to at least one of sensor data collection, feature extraction, or inference, and the one or more machine learning service parameters correspond to at least one of a data input format, a machine learning feature extraction model supported by the second UE, or a machine learning inference model supported by the second UE. ### Claim 26 (depends on 25) The apparatus of claim 25, wherein to pair with the first UE for the one or more machine learning services, the at least one processor is further configured to: receive, from the first UE, a pairing request message based on at least one of the transmitted service announcement message, a machine learning service user ID associated with the first UE, or a capability of the first UE; and transmit, to the first UE, a pairing acknowledgement message based on the pairing request message. ### Claim 27 (depends on 16) The apparatus of claim 16, wherein to exchange the information relating to the one or more machine learning services with the first UE, the at least one processor is further configured to: receive, from the first UE, a service discovery announcement message indicating the one or more machine learning services, the service discovery announcement message including at least one of a machine learning application ID, a machine learning service ID, a machine learning service user ID associated with the first UE, an indication of a machine learning service type, or an indication of one or more machine learning service parameters, wherein the machine learning service type corresponds to at least one of sensor data collection, feature extraction, or inference, and the one or more machine learning service parameters correspond to at least one of a data input format, a machine learning feature extraction model supported by the second UE, or a machine learning inference model supported by the second UE. ### Claim 28 (depends on 27) The apparatus of claim 27, wherein to pair with the first UE for the one or more machine learning services, the at least one processor is further configured to: transmit, to the first UE, a pairing request message based on at least one of the received service discovery announcement message, a machine learning service provider ID associated with the second UE, or a capability of the second UE; and receive, from the first UE, a pairing acknowledgement message based on the pairing request message. ### Claim 29 (depends on 16) The apparatus of claim 16, further comprising a transceiver coupled to the at least one processor, the at least one processor being further configured to: transmit, to a network node, an inference result indicative of an upcoming blockage associated with a beam or a beam steering direction used for communication between the network node and the first UE, wherein the inference result is generated based on one or more machine learning inference models, and at least one machine learning inference model component in the one or more machine learning inference models is associated with the beam or the beam steering direction. ### Claim 30 A method of wireless communication at a second UE, comprising: exchanging information relating to one or more machine learning services with a first UE, the one or more machine learning services being provided by the second UE; and pairing with the first UE for the one or more machine learning services.