Methods and apparatus of data collection within connection state in mobile communications
The proposed data collection framework in mobile communications addresses inefficiencies by enabling efficient AI/ML data collection and reporting in CONNECTED states, optimizing model training and handling state transitions and abnormalities.
Patent Information
- Application Number
- PCT/CN2025/085644
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-03-29
- Filing Date
- 2025-03-28
- Publication Date
- 2025-10-02
AI Technical Summary
Existing mobile communication systems lack an efficient framework for data collection in the connection state, which is crucial for AI/ML model training and performance optimization, particularly in UE-side and network-side operations.
A method and apparatus for AI/ML related data collection in a CONNECTED state, involving UE transmitting capabilities to a network node, receiving a data collection configuration, and reporting collected data when conditions are met, with mechanisms for handling data collection during state transitions and abnormal cases.
Enhances data collection efficiency for AI/ML model training, ensuring robust data collection and reporting across various radio access technologies, supporting seamless transitions and handling abnormal conditions.
Smart Images

Figure CN2025085644_02102025_PF_FP_ABST
Abstract
Description
METHODS AND APPARATUS OF DATA COLLECTION WITHIN CONNECTION STATE IN MOBILE COMMUNICATIONSCROSS REFERENCE TO RELATED PATENT APPLICATION (S)
[0001] The present disclosure is part of a non-provisional application claiming the priority benefit of PCT Application No. PCT / CN2024 / 084884, filed 29 March 2024, the content of which herein being incorporated by reference in its entirety.TECHNICAL FIELD
[0002] The present disclosure is generally related to mobile communications and, more particularly, to data collection within connection state with respect to user equipment and network apparatus in mobile communications.BACKGROUND
[0003] Unless otherwise indicated herein, approaches described in this section are not prior art to the claims listed below and are not admitted as prior art by inclusion in this section.
[0004] Artificial intelligence (AI) and machine learning (ML) are increasingly vital in wireless networks for optimizing performance and user experience. Effective AI / ML model development relies heavily on robust data collection, a crucial step in the AI / ML lifecycle management (LCM) process. The quality and quantity of collected data directly influence model performance, necessitating a well-defined over-the-air data collection solution for both UE-side and network-side model inference, monitoring, and training. Consequently, developing an enhanced framework to collect data and measurement results from UEs for AI / ML model training is essential to reduce specification and implementation effort.SUMMARY
[0005] The following summary is illustrative only and is not intended to be limiting in any way. That is, the following summary is provided to introduce concepts, highlights, benefits and advantages of the novel and non-obvious techniques described herein. Select implementations are further described below in the detailed description. Thus, the following summary is not intended to identify essential features of the claimed subject matter, nor is it intended for use in determining the scope of the claimed subject matter.
[0006] An objective of the present disclosure is to propose solutions or schemes that address the aforementioned issue pertaining to data collection within connection state with respect to user equipment (UE) and network apparatus in mobile communications.
[0007] In one aspect, a method may involve an apparatus establishing a connection with a network node. The method may also involve the apparatus performing an artificial intelligence (AI) or machine learning (ML) related data collection procedure in a CONNECTED state. The AI or ML related data collection procedure may include transmitting an AI or ML related capability of the apparatus to the network node. The AI or ML related data collection procedure may also include receiving a data collection configuration from the network node. The AI or ML related data collection procedure may further include performing a data collection based on the data collection configuration, and reporting collected data to the network node in an event that a reporting condition is met.
[0008] In another aspect, an apparatus may comprise a transceiver which, during operation, wirelessly communicates with a network. The apparatus may also comprise a processor communicatively coupled to the transceiver. The processor, during operation, may perform operations comprising establishing a connection with a network node. The processor, during operation, may also perform operations comprising performing an AI or ML related data collection procedure in a CONNECTED state. The AI or ML related data collection procedure may include transmitting, via the transceiver, an AI or ML related capability of the apparatus to the network node. The AI or ML related data collection procedure may also include receiving, via the transceiver, a data collection configuration from the network node. The AI or ML related data collection procedure may further include performing a data collection based on the data collection configuration, and reporting, via the transceiver, collected data to the network node in an event that a reporting condition is met.
[0009] In another aspect, a method may involve a network node establishing a connection with a UE. The method may also involve the network node receiving an AI or ML related capability report from the UE. The method may also involve the network node transmitting a data collection configuration for an AI or ML related data collection procedure to the UE. The method may further involve the network node receiving data collected by the UE. In which, the data is collected while the UE is in a CONNECTED state.
[0010] It is noteworthy that, although description provided herein may be in the context of certain radio access technologies, networks and network topologies such as LTE, LTE-Advanced, LTE-Advanced Pro, 5G, NR, 5G-Advanced, Internet-of-Things (IoT) , Narrow Band Internet of Things (NB-IoT) , Industrial Internet of Things (IIoT) , beyond 5G (B5G) , and 6th Generation (6G) , the proposed concepts, schemes and any variation (s) / derivative (s) thereof may be implemented in, for and by other types of radio access technologies, networks and network topologies. Thus, the scope of the present disclosure is not limited to the examples described herein.BRIEF DESCRIPTION OF THE DRAWINGS
[0011] The accompanying drawings are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of the present disclosure. The drawings illustrate implementations of the disclosure and, together with the description, serve to explain the principles of the disclosure. It is appreciable that the drawings are not necessarily in scale as some components may be shown to be out of proportion than the size in actual implementation in order to clearly illustrate the concept of the present disclosure.
[0012] FIG. 1 is a diagram depicting an example scenario of a communication environment in which various solutions and schemes in accordance with implementations of the present disclosure.
[0013] FIG. 2 is a diagram depicting an example scenario of data collection within connection state in accordance with implementations of the present disclosure.
[0014] FIGs. 3A to 3G are diagrams depicting exemplary sub-procedures of AI or ML related data collection procedure in accordance with implementations of the present disclosure.
[0015] FIGs. 4A to 4C are diagrams depicting exemplary procedures to handle data collection configuration when radio resource control (RRC) connection is released in accordance with implementations of the present disclosure.
[0016] FIGs. 5A and 5B are diagrams depicting exemplary scenario and procedure related to data collection during handover (HO) in accordance with implementations of the present disclosure.
[0017] FIGs. 6A and 6B are diagrams depicting exemplary procedures related to abnormal case handling of data collection in accordance with implementations of the present disclosure.
[0018] FIG. 7 is a block diagram of an example communication system in accordance with an implementation of the present disclosure.
[0019] FIG. 8 is a flowchart of an example process in accordance with an implementation of the present disclosure.
[0020] FIG. 9 is a flowchart of another example process in accordance with an implementation of the present disclosure. DETAILED DESCRIPTION OF PREFERRED IMPLEMENTATIONS
[0021] Detailed embodiments and implementations of the claimed subject matters are disclosed herein. However, it shall be understood that the disclosed embodiments and implementations are merely illustrative of the claimed subject matters which may be embodied in various forms. The present disclosure may, however, be embodied in many different forms and should not be construed as limited to the exemplary embodiments and implementations set forth herein. Rather, these exemplary embodiments and implementations are provided so that description of the present disclosure is thorough and complete and will fully convey the scope of the present disclosure to those skilled in the art. In the description below, details of well-known features and techniques may be omitted to avoid unnecessarily obscuring the presented embodiments and implementations. Overview
[0022] Implementations in accordance with the present disclosure relate to various techniques, methods, schemes and / or solutions pertaining to data collection within connection state in mobile communications. According to the present disclosure, a number of possible solutions may be implemented separately or jointly. That is, although these possible solutions may be described below separately, two or more of these possible solutions may be implemented in one combination or another.
[0023] FIG. 1 illustrates an example scenario 100 of a communication environment in which various solutions and schemes in accordance with the present disclosure may be implemented. Scenario 100 involves a user equipment (UE) 110 in wireless communication with a wireless network consisting of an access network 125 and a core network (CN) 130. The wireless network may be a 5G NR network, 5G-Advanced network, 6G network, however, the present disclosure is not limited thereto. The UE 110 may be a smart phone, a wearable device, an IoT device, and a tablet, etc. Alternatively, the UE 110 may be a notebook (NB) or personal computer (PC) inserted or installed with a data card which includes a modem and radio frequency (RF) transceiver (s) to provide the functionality of wireless communication. The CN 130 may include entities such as user plane function (UPF) , access and mobility management function (AMF) , session management function (SMF) and unified data management (UDM) , etc. The access network 125 may include one or more base stations (BSs) , such as the BS 120. The BS 120 may be an evolved NodeBs (eNB) , a next generation NodeB (gNB) , or a transmission and reception point (TRP) . The BS 120 may provide communication coverage for a geographic coverage area where communications with the UE 110 is supported.
[0024] Scenario 100 further involves an operations, administration, and maintenance (OAM) device 140 and a UE server 150. The OAM device 140 may include a set of functions and protocols used to manage and maintain network equipment and services. The UE server 150 (may also be referred to as an over-the-top (OTT) server) is introduced for certain applications such as artificial intelligence (AI) , machine learning (ML) , or other applications that require model training. The UE server 150 is responsible for collecting and storing data reported by UEs (e.g., the UE 110) , and may also have functions for model training. The UE server 150 may be a UE-side server, which is over-the-top and may be transparent to 3rd Generation Partnership Project (3GPP) standard (i.e., 3GPP transparent) . Alternatively, the UE server 150 may be a UE-side server which is over-the-top but non-3GPP transparent. The deployment of the UE server 150 may be within or outside the OAM domain (e.g., may be in the CN domain) . The UE server 150 may receive and store the data or data files and build up the dataset for model training. The UE server 150 may also perform model training with the dataset. Specifically, the UE server 150 organizes the received data into a structured format, known as the dataset, which can be used for further analysis or processing. This might involve data cleaning, data transformation, and labeling.
[0025] FIG. 2 is a diagram depicting an example scenario of data collection within connection state in accordance with implementations of the present disclosure. As shown in scenario 200, after the UE 110 transitions from an INACTIVE / IDLE state (e.g., a radio resource control (RRC) INACTIVE / IDLE state) to a CONNECTED state (e.g., an RRC CONNECTED state) and establishes a connection (e.g., an RRC connection) with the BS 120 at time T1, the UE 110 may perform an AI / ML related data collection procedure when the UE 110 is in the CONNECTED state. That is, the AI / ML related data collection procedure may be performed from time T1 to time T6. To be specific, the UE 110 may transmit its AI or ML related capability to the BS 120, then receives a data collection configuration at time T2. The data collection configuration may be carried by at least one of an RRC message, a medium access control (MAC) -control element (CE) message, and a downlink control information (DCI) message. After that, from time T3 to time T4, the UE 110 may perform a data collection based on the data collection configuration. The UE 110 may store the collected data in a variable or in a data file. In the present disclosure, the collected data may also be referred to as measurement logs, logs, or collected data / logs. When a reporting condition is met (e.g., at time T5) , the UE 110 may report the collected data to the BS 120. The collected data may be further transmitted to the UE server 150 via one or a combination of the BS 120, the CN 120, and the OAM device 140. The collected data may be used for various AI / ML life cycle management (LCM) purposes, including model training, model inference, and model monitoring, across different use cases or AI / ML-enabled features of UE-side, network-side, and two-sided models. In one embodiment, after all the collected data are reported to the network, the UE 110 may transition to the INACTIVE / IDLE state based on network control. For example, the UE 110 may transition to the RRC INACTIVE / IDLE state upon receiving an RRC release message (e.g., RRCRelease) or an expiration of a timer.
[0026] FIGs. 3A to 3G are diagrams depicting exemplary sub-procedures of AI or ML related data collection procedure in accordance with implementations of the present disclosure. In sub-procedure 300a as shown in FIG. 3A, the UE 110 complies and transfers a UE capability report upon receiving a capability enquire (e.g., UECapabilityEnquiry) from the BS 120. The UE capability report (e.g., UECapabilityInformation) may include information related to one or a combination of a memory size, a remaining battery power, a carrier aggregation (CA) capability, a dual connectivity (DC) capability, a supported use case, an AI or ML enabled feature (e.g., AI-enabled beam management (BM) , AI-enabled channel state information (CSI) prediction, AI-enabled positioning, AI-enabled mobility, etc. ) , a supported data type to be collected (e.g., raw channel data, CSI information, UE position information, UE speed, etc. ) for different AI / ML-enabled features, and other information associated with the UE capability related to AI or ML. In one example, the UE capability report may further indicate whether data collecting / measurement logging in CONNECTED state is supported or not. In another example, the UE capability report may provide information on whether non-standardized data type can be collected. In yet another example, the UE capability report may provide information on the CA / DC capability for different bands and band combinations. Based on this information, the network may utilize the CA / DC capability of the UE 110 to collect the data and measurement logs across different frequencies.
[0027] As shown in FIG. 3B, the data collection configuration may be provided by bidirectional RRC signaling. Specifically, the BS 120 initiates sub-procedure 300b to the UE 110 in the RRC CONNECTED state by transmitting a bidirectional RRC message (e.g., RRCReconfiguration) . The UE 110 may store the data collection configuration and transmit a complete message (e.g., RRCReconfigurationComplete) back to the BS 120. In one embodiment, the data collection configuration may be reconfigured through an RRC reconfiguration procedure. In another embodiment, a release operation for the data collection configuration is realized by configuration clearance when a configuration release timer stops or an expiration condition is met. The configuration release timer is for controlling the validity of the data collection configuration, the UE 110 may start or restart the configuration release timer upon receiving the data collection configuration or reconfiguration. Once the configuration release timer expires or stops, the UE 110 may release the data collection configuration. The configuration release timer may be stopped when an RRC connection is released.
[0028] Alternatively, as shown in FIG. 3C, the data collection configuration may be provided by unidirectional RRC signaling. To be specific, the BS 120 may initiate sub-procedure 300c to the UE 110 in the RRC CONNECTED state by transmitting a unidirectional RRC message (e.g., LoggedMeasurementConfiguration) . A release operation for the data collection configuration in the UE 110 is realized by configuration replacement when the data collection configuration is overwritten. In one embodiment, a release operation for the data collection configuration is realized by configuration clearance when the configuration release timer stops or an expiration condition is met. For example, the UE 110 may start the configuration release timer upon receiving the data collection configuration. Once the configuration release timer expires or stops (e.g., when an RRC connection is released) , the UE 110 may release the data collection configuration.
[0029] In one embodiment, the data collection configuration may be stored in the UE inactive access stratum (AS) context, which may be retrieved by the latest serving cell when the UE 110 transitions from the INACTIVE state to the CONNECTED state.
[0030] In the present disclosure, the data collection configuration may correspond to one or a combination of a measurement quantity for different use cases, a data type, use case related information, a logging triggering event, a data collecting or logging duration, a data collecting or logging interval, a reporting triggering event, a reporting periodicity, a network absolute time stamp, a server internet protocol (IP) address, a server identifier (ID) (e.g., the IP address / ID of the UE server 150, and may be indicated by the OAM configuration) , a data collecting or logging reference (may be indicated by the OAM configuration) , a data collecting or logging session reference (may be indicated by the OAM configuration) , a logging area, a data collecting or logging public land mobile network (PLMN) list, a correlation between measurement samples (e.g., in frequency, temporal or spatial domain) , and vendor specific measurement information (e.g., whether to allow taking vendor specific measurements supported by configuration container) . In one embodiment, the data collection configuration may further specify the use case, AI / ML-enabled feature, or gNB / cell / UE configuration conditions targeted by the data collection session.
[0031] In one embodiment, the configuration associated with vendor specific measurement information is provided by a configuration container. Accordingly, the collected data / logs for the vendor specific measurement may be carried in a reporting container when reporting. For example, the configuration container may carry one or a combination of the use cases or AI / ML enabled feature, vendor specific ID, the specific format for reporting (e.g., abstract syntax notation one (ASN. 1) or extensible markup language (XML) ) .
[0032] In one embodiment, the correlation between measurement samples is configured. Specifically, certain measurement (s) may be designated as primary, and secondary measurement (s) shall be collected whenever a sample of a primary measurement is taken. For example, the serving cell measurement may be designated as primary, while neighboring cell measurements are designated as secondary. In another example, the primary measurement is the measurement on a specific frequency (e.g., the frequency of the serving cell) and the secondary measurements are the measurements on other frequencies, which are correlated to the primary measurement objective of the serving cell. In yet another example, the primary measurements are the measurements on a primary set of beams and the second measurements are the measurements on a secondary set of beams. In still another example, the primary measurement are the measurements on a primary set of timeslots / subframes / frames / time durations and the second measurement are the measurement on a secondary set of timeslots / subframes / frames / time durations. In the foregoing examples, the correlation between the primary measurement (s) and the secondary measurement (s) is assigned by an ID (e.g., correlation ID) .
[0033] In one embodiment, information elements (IEs) in the data collection configuration may include a measurement configuration part and a reporting configuration part. The measurement configuration part includes measurement configuration (s) relating to information about performing the data collection, such as the measurement quantity and the data type for different use cases, and the logging triggering event (s) , etc. The reporting configuration part includes report configuration (s) relating to information about reporting the collected data, including the reporting triggering event (s) , data recording session reference, and reporting periodicity, etc.
[0034] In one embodiment, for the configuration of the logging triggering event (s) , a periodic measurement trigger is supported, for which the logging interval is configurable. The parameter in the data collection configuration may specify the periodicity for storing minimization of drive test (MDT) measurement results. Alternatively, an event-based trigger is supported, for which the logging interval is configurable, which determines periodical logging of available data. Examples of such events may include enable of certain features, and measurement quantity-based event layer 1 (L1) , for which the event threshold, hysteresis, and time to trigger are configurable.
[0035] In another embodiment, for the configuration of the reporting triggering event (s) , an event-based trigger is supported. Examples of such events may include enable of certain features, measurement quantity-based event L1, event A1, A2, A3, A4, A5, A6, D1, or I1, for which the event threshold, hysteresis, and time to trigger are configurable. Data volume is above a threshold, which is configurable. Alternatively, a periodic report trigger is supported, for which the report periodicity, report amount, etc, are configurable.
[0036] FIGs. 3D and 3E illustrate different exemplary sub-procedures for data collection process. Generally, the UE 110 starts the data collection when one or more collection start criteria are satisfied and stops the data collection when one or more collection stop criteria are satisfied. The UE 110 may store the collected data in a variable or a data file during the data collection process. The collection start criteria may include one or a combination of reception of a data collection activation command / message (e.g., through RRC MAC-CE, or DCI) , enabling of a target use case or AI or ML feature, moving to a new cell which is in the configured data collecting / logging area, being in an associated PLMN, battery power being equal to or above a power threshold (e.g., in a high-battery state) , having a good radio condition (e.g., T310 timer is stopped when a layer 3 (L3) reference signal received power (RSRP) is equal to or above a RSRP threshold) , and configuration of the BS 120 or UE 110 matching a data collection target. The collection stop criteria may include one or a combination of reception of a data collection deactivation command / message (e.g., through RRC MAC-CE, or DCI) , a data collection timer being expired, memory full, disabling of a target use case or AI or ML feature, being outside of a data collection or logging area, being outside of an associated PLMN, battery power being below a threshold (e.g., in a low-battery state) , having a bad radio condition (e.g., T310 timer is running when a L3 RSRP is below a RSRP threshold) , and configuration of the BS 120 or UE 110 not matching a data collection target. As shown in sub-procedure 300d, the data collection configuration may indicate whether to start / stop the data collection explicitly (e.g., by an indication / flag) . That is, the UE 110 may start and stop the data collection as indicated by the network. In sub-procedure 300e, the data collection is enabled by the network and the UE 110 may start the data collection timer upon receiving such indication / flag, and stop the data collection when the data collection timer expires.
[0037] In the present disclosure, the collected data may include information corresponding to one or a combination of a use case, an AI or ML enabled feature, a physical cell identity (PCI) of a logged cell, a carrier frequency, a signal quality measurement, a RSRP, a reference signal received quality (RSRQ) , a received signal strength indicator (RSSI) , a L1-RSRP, a beam index, a position information of the apparatus, a time stamp, a channel matrix, a CSI feedback, a channel impulse response (CIR) , a power delay profile (PDP) , a performance indicator (e.g., system level key performance indicators (KPI) or immediate KPI such as throughput, prediction accuracy, handover failure (HOF) rate, etc. ) , a vendor specific measurement in reporting container, and a correlation between measurement samples (e.g., the correlation between the primary measurement samples and the secondary measurement samples in form of, for example, correlation ID) .
[0038] FIGs. 3F and 3G illustrate different exemplary sub-procedures for reporting the collected data. The UE 110 may report the collected data to the BS 120 when receiving a reporting message from the BS 129 or when a preconfigured event is satisfied, and the collected data may be reported through an RRC message or a data radio bearer (DRB) . More specifically, the UE 110 may establish or modify the DRB according to the data collection configuration, and a priority is assigned to the DRB. For example, the DRB configured for reporting the collected data has the lowest priority than other DRBs. As shown in sub-procedure 300f, when the BS 120 decides to retrieve the data / logs collected by the UE 110, it may initiate a UE Information procedure by transmitting an RRC message (e.g., UEInformationRequest) . Then the UE 110 sends the collected data / logs through another RRC message (e.g., UEInformationResponse) . In one embodiment, transport of collected data / logs in multiple RRC messages is supported. With every request, the BS 120 may receive a part of the total collected data / logs. To indicate the collected data / logs is a segment, the UE 110 may include a data availability indicator in UEInformationResponse message to convey the information that further collected data / logs is available. In multiple RRC transmissions for segmented data / logs reporting, a first-in first-out (FIFO) order is followed. That is, the UE 110 may provide the oldest available measurement entries in the earliest message. In one example, each reported part is self-decodable (i.e., interpretable) even if all the other parts are not available. On the other hand, as shown in sub-procedure 300g, the UE 110 may check whether the reporting triggering event (s) configured by the BS 120 is met. When at least one reporting triggering event is met, the UE 110 may start the data / logs reporting. For example, the UE 110 may send the availability indication or report data / logs when the memory for the collected data / logs is equal to or below a threshold (i.e., low memory) . In one embodiment, the collected data / logs are transmitted through an RRC message (e.g., MeasurementReport) .
[0039] In sub-procedure 300f or 300g, the collected data may be reported through the DRB. In one example, the DRB is suspended by default, until a resume indication / request is received from the BS 120 before data reporting. Then the UE 110 resumes the DRB for reporting the collected data / logs. In another example, the DRB is resumed by default. The UE 110 may indicate the availability of the collected data / logs through a scheduling request (SR) or a buffer status report (BSR) procedure and sends the collected data / logs through a logical channel prioritization (LCP) procedure when uplink (UL) grant is received from the BS 120. In one example, if the reporting triggering event is configured, the UE 110 indicates the availability of the collected data / logs through the SR / BSR procedure when the event is satisfied (e.g., the stored data / logs volume is above a threshold) .
[0040] In one embodiment, when the BS 120 provides a new data collection configuration, any previously configured logged measurement configuration will be entirely replaced by the new one. Moreover, the collected data / logs corresponding to the previous configuration will be cleared at the same time. It is left up to the network to retrieve any relevant data before providing a new data collection configuration. However, under abnormal circumstances, the collected data / logs may remain unretrieved by the BS 120 before a new data collection configuration is received by the UE 110. In one example, if the collected data / logs are still present, the UE 110 may discard them upon receiving the new data collection configuration. In another example, if the BS 120 fails to retrieve the previously stored collected data / logs before sending a new data collection configuration, the UE 110 may keep the collected data / logs associated with the previous data collection configuration and start the data collecting / logging according to the new configuration. In yet another example, the UE 110 may differentiate the old collected data / logs and new collected data / logs with an indication. The indication may be a leap in the time stamp, or a field indicating a new collected data / logs follows.
[0041] FIGs. 4A to 4C are diagrams depicting exemplary procedures to handle data collection configuration when RRC connection is released in accordance with implementations of the present disclosure. In this embodiment, the data collection configuration may include a measurement configuration and a report configuration. In procedure 400a, the UE 110 releases both the measurement configuration and the report configuration when the RRC connection is released. The UE 110 may discard any collected data. In procedure 400b, the UE 110 releases the measurement configuration but keeps the report configuration when the RRC connection is released. In procedure 400c, the UE 110 retains both the measurement and report configurations when the RRC connection is released. In procedure 400b or 400c, the UE 110 may keep the collected data, if any.
[0042] More specifically, in normal operation, prior to transmitting an RRC release message, the BS 120 should have retrieved all collected data / logs previously stored in the UE 110, ensuring that no residual data or logs are left behind. It is the network's responsibility to collect any pertinent data before issuing the RRC release message. Under abnormal circumstances, the collected data / logs stored at the UE 110 may remain uncollected before the RRC connection is released. In one embodiment, if the previously stored collected data / logs are still present, the UE 110 may discard them upon transitioning to the RRC INACTIVE / IDLE state. In another embodiment, if the BS 120 fails to retrieve the previously stored collected data / logs before the UE 110 transitions to the RRC INACTIVE / IDLE state, the UE 110 preserves the unretrieved data / logs for a predefined duration (e.g., 48 hours) , starting from the RRC connection release. The UE 110 maintains the collected data / logs for this duration until the BS 120 retrieves them upon the UE's return to the RRC CONNECTED state, or the timer expires, whichever occurs first. In this case, the UE 110 sends a data availability indication to the BS 120 upon transitioning to the RRC CONNECTED state again. After the predefined duration (e.g., 48 hours) expires, the UE 110 may retain or discard any remaining stored data / logs. In one embodiment, If the report configuration is retained when the UE 110 releases the RRC connection, the handling of the report configuration may be consistent with the handling of previously stored collected data / logs.
[0043] FIGs. 5A and 5B are diagrams depicting exemplary scenario and procedure related to data collection during handover (HO) in accordance with implementations of the present disclosure. As shown in scenario 500a, the source cell 510 may retrieve the collected data / logs by transmitting a reporting message or waiting for a preconfigured event to be satisfied. After the HO is completed, the target cell 520 may retrieve the collected data / logs. More specifically, as shown in procedure 500b, when the network is about to perform the HO for the UE 110, the source cell 510 will coordinate with the target cell 520 regarding the data collection configuration. The data collection configuration for the UE 110 may be propagated during the UE context retrieving process of the HO procedure. After the HO, the UE 110 transmits a data availability indication to the target cell 520 to indicate the availability of the previously stored collected data / logs. The target cell 520 may then decide whether to retrieve the remaining data / logs or let the UE 110 release them. In one embodiment, data retrieval and reporting may use the UE Information procedure. In another embodiment, if a DRB is used for data / log reporting, the reporting of the collected data / logs may continue with packet data convergence protocol (PDCP) data recovery or PDCP re-establishment if the DRB is not released. Otherwise, the previously stored collected data / logs are discarded if the DRB is released by the target cell 520.
[0044] FIGs. 6A and 6B are diagrams depicting exemplary procedures related to abnormal case handling of data collection in accordance with implementations of the present disclosure. When a HOF or a radio link failure (RLF) occurs, the UE 110 may trigger an RRC re-establishment procedure, and release the data collection configuration when initiating the RRC re-establishment procedure. In one embodiment, as shown in procedure 600a, the UE 110 discards the previously stored collected data / logs when initiating the RRC Re-establishment procedure. In another embodiment, as shown in procedure 600b, the UE 110 keeps the previously stored collected data / logs when initiating the RRC Re-establishment procedure. When the UE 110 receives an RRC re-establishment / setup message (e.g., RRCReestablishment / RRCSetup) , the UE 110 transmits a data availability indication to the BS 120 to indicate the availability of the collected data / logs. The data availability indication may be transmitted in an RRC re-establishment complete / setup complete message (e.g., RRCReestablishmentComplete / RRCSetupComplete) . Then, the BS 120 may decide whether to retrieve the remaining data / logs. Illustrative Implementations
[0045] FIG. 7 illustrates an example communication system 700 having at least an example communication apparatus 710 and an example network apparatus 720 in accordance with an implementation of the present disclosure. Each of the communication apparatus 710 and network apparatus 720 may perform various functions to implement schemes, techniques, processes and methods described herein pertaining to data collection within connection state in mobile communications, including scenarios / schemes described above as well as processes 800 and 900 described below.
[0046] Communication apparatus 710 may be a part of an electronic apparatus, which may be a UE such as a portable or mobile apparatus, a wearable apparatus, a wireless communication apparatus or a computing apparatus. For instance, communication apparatus 710 may be implemented in a smartphone, a smartwatch, a personal digital assistant, a digital camera, or a computing equipment such as a tablet computer, a laptop computer or a notebook computer. Communication apparatus 710 may also be a part of a machine type apparatus, which may be an IoT, NB-IoT, or IIoT apparatus such as an immobile or a stationary apparatus, a home apparatus, a wire communication apparatus or a computing apparatus. For instance, communication apparatus 710 may be implemented in a smart thermostat, a smart fridge, a smart door lock, a wireless speaker or a home control center. Alternatively, communication apparatus 710 may be implemented in the form of one or more integrated-circuit (IC) chips such as, for example and without limitation, one or more single-core processors, one or more multi-core processors, one or more reduced-instruction set computing (RISC) processors, or one or more complex-instruction-set-computing (CISC) processors. Communication apparatus 710 may include at least some of those components shown in FIG. 7 such as a processor 712, for example. Communication apparatus 710 may further include one or more other components not pertinent to the proposed scheme of the present disclosure (e.g., internal power supply, display device and / or user interface device) , and, thus, such component (s) of communication apparatus 710 are neither shown in FIG. 7 nor described below in the interest of simplicity and brevity.
[0047] Network apparatus 720 may be a part of a network apparatus, which may be a network node such as a satellite, a base station, a small cell, a router or a gateway. For instance, network apparatus 720 may be implemented in an eNB in an LTE network, in a gNB in a 5G / NR, IoT, NB-IoT or IIoT network or in a satellite or base station in a 6G network. Network apparatus 720 may include at least some of those components shown in FIG. 7 such as a processor 722, for example. Processor 722 may further include protocol stacks and a set of control functional modules and circuits. Network apparatus 720 may further include one or more other components not pertinent to the proposed scheme of the present disclosure (e.g., internal power supply, display device and / or user interface device) , and, thus, such component (s) of network apparatus 720 are neither shown in FIG. 7 nor described below in the interest of simplicity and brevity.
[0048] In one aspect, each of the processor 712 and processor 722 may be implemented in the form of one or more single-core processors, one or more multi-core processors, or one or more CISC processors. That is, even though a singular term “a processor” is used herein to refer to processor 712 and processor 722, each of the processor 712 and processor 722 may include multiple processors in some implementations and a single processor in other implementations in accordance with the present disclosure. In another aspect, each of the processor 712 and processor 722 may be implemented in the form of hardware (and, optionally, firmware) with electronic components including, for example and without limitation, one or more transistors, one or more diodes, one or more capacitors, one or more resistors, one or more inductors, one or more memristors and / or one or more varactors that are configured and arranged to achieve specific purposes in accordance with the present disclosure. In other words, in at least some implementations, each of the processor 712 and processor 722 is a special-purpose machine specifically designed, arranged and configured to perform specific tasks in a device (e.g., as represented by communication apparatus 710) and a network (e.g., as represented by network apparatus 720) in accordance with various implementations of the present disclosure.
[0049] In some implementations, communication apparatus 710 may also include a memory 714 coupled to processor 712 and capable of being accessed by processor 712 and storing data therein. In some implementations, communication apparatus 710 may further include a transceiver 716 coupled to processor 712 and capable of wirelessly transmitting and receiving data.
[0050] In some implementations, network apparatus 720 may further include a memory 724 coupled to processor 722 and capable of being accessed by processor 722 and storing data therein, and a transceiver 726 coupled to processor 722 and capable of wirelessly transmitting and receiving data. Accordingly, communication apparatus 710 and network apparatus 720 may wirelessly communicate with each other via transceiver 716 and transceiver 726, respectively.
[0051] For illustrative purposes and without limitation, descriptions of capabilities of the communication apparatus 710 and network apparatus 720 are provided below with process 800 and process 900. In which, communication apparatus 710 is implemented in or as a communication apparatus or a UE, and network apparatus 720 is implemented in or as a network node of a communication network (e.g., a base station) . Illustrative Processes
[0052] FIG. 8 illustrates an example process 800 in accordance with an implementation of the present disclosure. Process 800 may be an example implementation of above scenarios / schemes, whether partially or completely, with respect to data collection within connection state in mobile communications. Process 800 may represent an aspect of implementation of features of communication apparatus 710. Process 800 may include one or more operations, actions, or functions as illustrated by one or more of blocks 810 and 820. Although illustrated as discrete blocks, various blocks of process 800 may be divided into additional blocks, combined into fewer blocks, or eliminated, depending on the desired implementation. Moreover, the blocks of process 800 may be executed in the order shown in FIG. 8 or, alternatively, in a different order. Process 800 may be implemented by communication apparatus 710 or any suitable UE (e.g., UE 110) or machine type devices. Solely for illustrative purposes and without limitation, process 800 is described below in the context of communication apparatus 710 as a UE. Process 800 may begin at block 810.
[0053] At block 810, process 800 may involve processor 712 of communication apparatus 710 establishing a connection with a network node (e.g., network apparatus 720) . Process 800 may proceed from block 810 to block 820.
[0054] At block 820, process 800 may involve processor 712 performing an AI / ML related data collection procedure in a CONNECTED state. The AI / ML related data collection procedure may include transmitting an AI / ML related capability of communication apparatus 710 to the network node via transceiver 716, receiving a data collection configuration from the network node via transceiver 716, performing a data collection based on the data collection configuration, and reporting collected data to the network node in an event that a reporting condition is met.
[0055] In some implementations, the AI / ML related capability of communication apparatus 710 may include one or a combination of a memory size, a remaining battery power, a CA capability, a DC capability, a supported use case, an AI / ML enabled feature, and a supported data type for collection.
[0056] In some implementations, the data collection configuration is carried by at least one of an RRC message, a MAC-CE message, and a DCI message.
[0057] In some implementations, the data collection configuration is released based on a configuration release timer or is reconfigured through a reconfiguration procedure.
[0058] In some implementations, the data collection configuration corresponds to one or a combination of a measurement quantity, a data type, use case related information, a logging triggering event, a data collecting or logging duration, a data collecting or logging interval, a reporting triggering event, a reporting periodicity, a network absolute time stamp, a server IP address, a server ID, a data collecting or logging reference, a data collecting or logging session reference, a logging area, a data collecting or logging PLMN list, a correlation between measurement samples, and vendor specific measurement information.
[0059] In some implementations, process 800 may involve processor 712 starting the data collection in an event that one or more collection start criteria are satisfied.
[0060] In some implementations, process 800 may involve processor 712 stopping the data collection in an event that one or more collection stop criteria are satisfied.
[0061] In some implementations, process 800 may involve processor 712 storing the collected data in a variable or in a data file.
[0062] In some implementations, the collection start criteria may include one or a combination of reception of a data collection activation command from the network node, enabling of a target use case or AI or ML feature, moving to a new cell, being in an associated PLMN, battery power being equal to or above a threshold, having a first radio condition (e.g., an L3 RSRP that is equal to or above a RSRP threshold, and / or a T310 timer that is stopped) , and configuration of the network node or communication apparatus 710 matching a data collection target.
[0063] In some implementations, the collection stop criteria may include one or a combination of reception of a data collection deactivation command from the network node, a data collection timer being expired, memory full, disabling of a target use case or AI or ML feature, being outside of a data collection or logging area, being outside of an associated PLMN, battery power being below a threshold, having a second radio condition (e.g., an L3 RSRP that is below a RSRP threshold, and / or a T310 timer that is running) , and configuration of the network node or communication apparatus 710 not matching a data collection target.
[0064] In some implementations, the reporting condition is met by receiving a reporting message from the network node or in an event that a preconfigured event is satisfied.
[0065] In some implementations, the collected data is reported to the network node through an RRC message or a DRB.
[0066] In some implementations, the DRB is suspended by default, and a resume request is received from the network node before reporting the collected data through the DRB.
[0067] In some implementations, the DRB is resumed by default, and communication apparatus 710 transmits a data availability indication through an SR or a BSR.
[0068] In some implementations, the collected data may include information corresponding to one or a combination of a use case, an AI / ML enabled feature, a PCI of a logged cell, a carrier frequency, a signal quality measurement, a RSRP, a RSRQ, a RSSI, an L1-RSRP, a beam index, a position information of communication apparatus 710, a time stamp, a channel matrix, a CSI feedback, a CIR, a PDP, a performance indicator, a vendor specific measurement in reporting container, and a correlation between measurement samples.
[0069] In some implementations, the connection is a radio resource control (RRC) connection. Process 800 may further involve processor 712 releasing at least one of a measurement configuration and a report configuration specified for the data collection configuration in an event that the RRC connection is released.
[0070] In some implementations, the connection is a radio resource control (RRC) connection. Process 800 may further involve processor 712 discarding the collected data previously stored in communication apparatus 710 in an event that the RRC connection is released.
[0071] In some implementations, the connection is a radio resource control (RRC) connection. Process 800 may further involve processor 712 keeping the collected data previously stored in communication apparatus 710 in an event that the RRC connection is released.
[0072] In some implementations, the collected data previously stored in communication apparatus 710 is kept for a duration associated with a data retention timer.
[0073] In some implementations, process 800 may further involve processor 712 transmitting, via transceiver 716, a data availability indication to a target cell in an event that an HO associated with the target cell is completed.
[0074] In some implementations, process 800 may further involve processor 712 releasing the data collection configuration in an event that an RRC re-establishment procedure is initiated.
[0075] In some implementations, process 800 may further involve processor 712 discarding the collected data previously stored in communication apparatus 710 in an event that the RRC re-establishment procedure is initiated.
[0076] In some implementations, process 800 may further involve processor 712 transmitting, via transceiver 716, a data availability indication to the network node during the RRC re-establishment procedure.
[0077] FIG. 9 illustrates an example process 900 in accordance with an implementation of the present disclosure. Process 900 may be an example implementation of above scenarios / schemes, whether partially or completely, with respect to data collection within connection state in mobile communications. Process 900 may represent an aspect of implementation of features of network apparatus 720. Process 900 may include one or more operations, actions, or functions as illustrated by one or more of blocks 910.920, 930, and 940. Although illustrated as discrete blocks, various blocks of process 900 may be divided into additional blocks, combined into fewer blocks, or eliminated, depending on the desired implementation. Moreover, the blocks of process 900 may be executed in the order shown in FIG. 9 or, alternatively, in a different order. Process 900 may be implemented by network apparatus 720 or any base stations (e.g., BS 120) or network nodes. Solely for illustrative purposes and without limitation, process 900 is described below in the context of network apparatus 720. Process 900 may begin at block 910.
[0078] At block 910, process 900 may involve processor 722 of network apparatus 720 establishing a connection with a UE (e.g., communication apparatus 710) . Process 900 may proceed from block 910 to block 920.
[0079] At block 920, process 900 may involve processor 722 receiving, via transceiver 726, an AI / ML related capability report from the UE. Process 900 may proceed from block 920 to block 930.
[0080] At block 930, process 800 may involve processor 712 transmitting, via transceiver 726, a data collection configuration for an AI / ML related data collection procedure to the UE. Process 900 may proceed from block 930 to block 940.
[0081] At block 940, process 800 may involve processor 712 receiving, via transceiver 716, data collected by the UE. The data is collected while theUE is in a CONNECTED state.
[0082] In some implementations, the data collection configuration is carried by at least one of an RRC message, a MAC-CE message, and a DCI message.
[0083] In some implementations, the data collection configuration corresponds to one or a combination of a measurement quantity, a data type, use case related information, a logging triggering event, a data collecting or logging duration, a data collecting or logging interval, a reporting triggering event, a reporting periodicity, a network absolute time stamp, a server IP address, a server ID, a data collecting or logging reference, a data collecting or logging session reference, a logging area, a data collecting or logging PLMN list, a correlation between measurement samples, and vendor specific measurement information. Additional Notes
[0084] The herein-described subject matter sometimes illustrates different components contained within, or connected with, different other components. It is to be understood that such depicted architectures are merely examples, and that in fact many other architectures can be implemented which achieve the same functionality. In a conceptual sense, any arrangement of components to achieve the same functionality is effectively "associated" such that the desired functionality is achieved. Hence, any two components herein combined to achieve a particular functionality can be seen as "associated with" each other such that the desired functionality is achieved, irrespective of architectures or intermedial components. Likewise, any two components so associated can also be viewed as being "operably connected" , or "operably coupled" , to each other to achieve the desired functionality, and any two components capable of being so associated can also be viewed as being "operably couplable" , to each other to achieve the desired functionality. Specific examples of operably couplable include but are not limited to physically mateable and / or physically interacting components and / or wirelessly interactable and / or wirelessly interacting components and / or logically interacting and / or logically interactable components.
[0085] Further, with respect to the use of substantially any plural and / or singular terms herein, those having skill in the art can translate from the plural to the singular and / or from the singular to the plural as is appropriate to the context and / or application. The various singular / plural permutations may be expressly set forth herein for sake of clarity.
[0086] Moreover, it will be understood by those skilled in the art that, in general, terms used herein, and especially in the appended claims, e.g., bodies of the appended claims, are generally intended as “open” terms, e.g., the term “including” should be interpreted as “including but not limited to, ” the term “having” should be interpreted as “having at least, ” the term “includes” should be interpreted as “includes but is not limited to, ” etc. It will be further understood by those within the art that if a specific number of an introduced claim recitation is intended, such an intent will be explicitly recited in the claim, and in the absence of such recitation no such intent is present. For example, as an aid to understanding, the following appended claims may contain usage of the introductory phrases "at least one" and "one or more" to introduce claim recitations. However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the indefinite articles "a" or "an" limits any particular claim containing such introduced claim recitation to implementations containing only one such recitation, even when the same claim includes the introductory phrases "one or more" or "at least one" and indefinite articles such as "a" or "an, " e.g., “a” and / or “an” should be interpreted to mean “at least one” or “one or more; ” the same holds true for the use of definite articles used to introduce claim recitations. In addition, even if a specific number of an introduced claim recitation is explicitly recited, those skilled in the art will recognize that such recitation should be interpreted to mean at least the recited number, e.g., the bare recitation of "two recitations, " without other modifiers, means at least two recitations, or two or more recitations. Furthermore, in those instances where a convention analogous to “at least one of A, B, and C, etc. ” is used, in general such a construction is intended in the sense one having skill in the art would understand the convention, e.g., “a system having at least one of A, B, and C” would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc. In those instances where a convention analogous to “at least one of A, B, or C, etc. ” is used, in general such a construction is intended in the sense one having skill in the art would understand the convention, e.g., “a system having at least one of A, B, or C” would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc. It will be further understood by those within the art that virtually any disjunctive word and / or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms. For example, the phrase “A or B” will be understood to include the possibilities of “A” or “B” or “A and B. ”
[0087] From the foregoing, it will be appreciated that various implementations of the present disclosure have been described herein for purposes of illustration, and that various modifications may be made without departing from the scope and spirit of the present disclosure. Accordingly, the various implementations disclosed herein are not intended to be limiting, with the true scope and spirit being indicated by the following claims.
Claims
1.A method, comprising:establishing, by a processor of an apparatus, a connection with a network node; andperforming, by the processor, an artificial intelligence (AI) or machine learning (ML) related data collection procedure in a CONNECTED state, wherein the AI or ML related data collection procedure comprises:transmitting an AI or ML related capability of the apparatus to the network node;receiving a data collection configuration from the network node;performing a data collection based on the data collection configuration; andreporting collected data to the network node in an event that a reporting condition is met.2.The method of Claim 1, wherein the AI or ML related capability of the apparatus comprises one or a combination of a memory size, a remaining battery power, a carrier aggregation (CA) capability, a dual connectivity (DC) capability, a supported use case, an AI or ML enabled feature, and a supported data type for collection.3.The method of Claim 1, wherein the data collection configuration is carried by at least one of a radio resource control (RRC) message, a medium access control (MAC) -control element (CE) message, and a downlink control information (DCI) message.4.The method of Claim 1, wherein the data collection configuration is released based on a configuration release timer or is reconfigured through a reconfiguration procedure.5.The method of Claim 1, wherein the data collection configuration corresponds to one or a combination of a measurement quantity, a data type, use case related information, a logging triggering event, a data collecting or logging duration, a data collecting or logging interval, a reporting triggering event, a reporting periodicity, a network absolute time stamp, a server internet protocol (IP) address, a server identifier (ID) , a data collecting or logging reference, a data collecting or logging session reference, a logging area, a data collecting or logging public land mobile network (PLMN) list, a correlation between measurement samples, and vendor specific measurement information.6.The method of Claim 1, wherein the performing of the data collection further comprises:starting the data collection in an event that one or more collection start criteria are satisfied;stopping the data collection in an event that one or more collection stop criteria are satisfied; orstoring the collected data in a variable or in a data file.7.The method of Claim 6, wherein the one or more collection start criteria comprise one or a combination of:reception of a data collection activation command from the network node;enabling of a target use case or AI or ML feature;moving to a new cell;being in an associated public land mobile network (PLMN) ;battery power being equal to or above a threshold;having a first radio condition, comprising a layer 3 (L3) reference signal received power (RSRP) that is equal to or above a RSRP threshold, and / or a T310 timer that is stopped; andconfiguration of the network node or the apparatus matching a data collection target.8.The method of Claim 6, wherein the one or more collection stop criteria comprise one or a combination of:reception of a data collection deactivation command from the network node;a data collection timer being expired;memory full;disabling of a target use case or AI or ML feature;being outside of a data collection or logging area;being outside of an associated public land mobile network (PLMN) ;battery power being below a threshold;having a second radio condition, comprising a layer 3 (L3) reference signal received power (RSRP) that is below a RSRP threshold, and / or a T310 timer that is running; andconfiguration of the network node or the apparatus not matching a data collection target.9.The method of Claim 1, wherein the reporting condition is met by receiving a reporting message from the network node or in an event that a preconfigured event is satisfied.10.The method of Claim 1, wherein the collected data is reported to the network node through a radio resource control (RRC) message or a data radio bearer (DRB) .11.The method of Claim 10, wherein:the DRB is suspended by default, and a resume request is received from the network node before reporting the collected data through the DRB; orthe DRB is resumed by default, and the apparatus transmits a data availability indication through a scheduling request (SR) or a buffer status report (BSR) .12.The method of Claim 1, wherein the collected data comprises information corresponding to one or a combination of a use case, an AI or ML enabled feature, a physical cell identity (PCI) of a logged cell, a carrier frequency, a signal quality measurement, a reference signal received power (RSRP) , a reference signal received quality (RSRQ) , a received signal strength indicator (RSSI) , a leyer 1 (L1) -RSRP, a beam index, a position information of the apparatus, a time stamp, a channel matrix, a channel state information (CSI) feedback, a channel impulse response (CIR) , a power delay profile (PDP) , a performance indicator, a vendor specific measurement in reporting container, and a correlation between measurement samples.13.The method of Claim 1, wherein the connection is a radio resource control (RRC) connection, and the method further comprises:releasing, by the processor, at least one of a measurement configuration and a report configuration specified for the data collection configuration in an event that the RRC connection is released.14.The method of Claim 1, wherein the connection is a radio resource control (RRC) connection, and the method further comprises:discarding, by the processor, the collected data previously stored in the apparatus in an event that the RRC connection is released; orkeeping, by the processor, the collected data previously stored in the apparatus in an event that the RRC connection is released.15.The method of Claim 1, wherein the collected data previously stored in the apparatus is kept for a duration associated with a data retention timer.16.The method of Claim 1, further comprising:transmitting, by the processor, a data availability indication to a target cell in an event that a handover (HO) associated with the target cell is completed.17.The method of Claim 1, further comprising:releasing, by the processor, the data collection configuration in an event that a radio resource control (RRC) re-establishment procedure is initiated.18.The method of Claim 17, further comprising:discarding, by the processor, the collected data previously stored in the apparatus in an event that the RRC re-establishment procedure is initiated; ortransmitting, by the processor, a data availability indication to the network node during the RRC re-establishment procedure.19.A method, comprising:establishing, by a processor of a network node, a connection with a user equipment (UE) ;receiving, by the processor, an artificial intelligence (AI) or machine learning (ML) related capability report from the UE;transmitting, by the processor, a data collection configuration for an AI or ML related data collection procedure to the UE; andreceiving, by the processor, data collected by the UE, wherein the data is collected while the UE is in a CONNECTED state.20.The method of Claim 19, wherein:the data collection configuration is carried by at least one of a radio resource control (RRC) message, a medium access control (MAC) -control element (CE) message, and a downlink control information (DCI) message; orthe data collection configuration corresponds to one or a combination of a measurement quantity, a data type, use case related information, a logging triggering event, a data collecting or logging duration, a data collecting or logging interval, a reporting triggering event, a reporting periodicity, a network absolute time stamp, a server internet protocol (IP) address, a server identifier (ID) , a data collecting or logging reference, a data collecting or logging session reference, a logging area, a data collecting or logging public land mobile network (PLMN) list, a correlation between measurement samples, and vendor specific measurement information.21.An apparatus, comprising:a transceiver which, during operation, communicates wirelessly; anda processor communicatively coupled to the transceiver such that, during operation, the processor performs operations comprising:establishing a connection with a network node; andperforming an artificial intelligence (AI) or machine learning (ML) related data collection procedure in a CONNECTED state, wherein the AI or ML related data collection procedure comprises:transmitting, via the transceiver, an AI or ML related capability of the apparatus to the network node;receiving, via the transceiver, a data collection configuration from the network node;performing a data collection based on the data collection configuration; andreporting, via the transceiver, collected data to the network node in an event that a reporting condition is met.
Citation Information
Patent Citations
AI / ML data collection and usage possibly for MDTs
US11622291B2
Method and apparatus for reporting ai network model support capability, method and apparatus for receiving ai network model support capability, and storage medium, user equipment and base station
WO2022028450A1