Method for performing data collection, user equipment and storage medium

Abstract

Embodiments of the present invention provide a method of performing data collection, user equipment and a storage medium, where the method comprises: receiving, by a user equipment (UE), a data collection configuration from a radio access network (RAN) node, where the data collection configuration configures an artificial intelligence-machine learning (AI-ML) model related parameter for the UE; performing data collection based on the data collection configuration to collect AI-ML model related data; and performing, by the RAN node, data transmission of the collected AI-ML model related data destined for the UE server. According to the invention, data collection can be carried out better.

Description

Technical Field

[0001] The present invention relates to wireless communications, and more particularly to data collection with radio access network (RAN) awareness. Background Art

[0002] Artificial intelligence (AI) and machine learning (ML) have been widely used in wireless networks to improve performance, user experience and reduce complexity / overhead. In traditional networks of 3GPP 5G new radio (NR), AI / ML techniques can be leveraged to address the challenges caused by the foreseen increase in complexity of air interface deployments, which applies to both the network and user equipment (UE). Data collection is a key step in AI / ML life cycle management (LCM), which provides the basis for creating effective and accurate models.

[0003] In wireless AI technology, offline training is the most viable option and the foundation of wireless AI. For UE-side models, training can be performed on the UE side or at a neutral site. However, it is impractical to perform UE-side model training within the UE due to the lack of a suitable training environment. This includes but is not limited to data availability, storage capacity, computing power, and compilation capabilities. For effective offline model training, data collection solutions should be designed to "reach" the UE side or a neutral site, such as an over the top (OTT) server. Moreover, a large amount of non-standardized / proprietary data should be collected, which can be customized according to various UE internal / external conditions and design choices (e.g., UE resource limitations, radio environment, feature engineering). In addition, the collected data should be sufficient for good model generalization.

[0004] Improvements and enhancements are needed to data collection under RAN awareness. Summary of the invention

[0005] An embodiment of the present invention provides a method for performing data collection, comprising: receiving, by a user equipment UE, a data collection configuration from a radio access network RAN ​​node, wherein the data collection configuration configures artificial intelligence-machine learning AI-ML model related parameters for the UE; performing data collection based on the data collection configuration to collect AI-ML model related data; and performing data transmission of the collected AI-ML model related data with a destination being a UE server through the RAN node.

[0006] An embodiment of the present invention provides a method for performing data collection, including: a RAN node receives a triggering event of a data collection request, wherein the data collection request instructs a UE to collect AI-ML model related data; sending a data collection configuration to the UE, wherein the data collection configuration configures AI-ML model related parameters for the UE; and performing data transmission for the AI-ML model related data collected by the UE through a data transmission channel between the UE and a UE server.

[0007] An embodiment of the present invention provides a user equipment, including: a transceiver, a transceiver used to transmit and receive signals in a wireless network; a configuration module, used to receive a data collection configuration from a RAN node, wherein the data collection configuration configures AI-ML model related parameters for the UE; a collection module, used to perform data collection based on the data collection configuration to collect AI-ML model related data; and a transmission module, which performs data transmission of the collected AI-ML model related data with a destination being a UE server through the RAN node.

[0008] An embodiment of the present invention provides a storage medium storing a program, which, when executed, enables a device to execute the steps of the method for executing data collection in the present application.

[0009] By utilizing the present invention, data collection can be better performed.

[0010] This summary is not intended to define the invention. The invention is defined by the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings illustrate embodiments of the present invention, wherein like numerals indicate like components.

[0012] Figure 1 4 is a system diagram of an exemplary wireless network supporting RAN-aware data collection according to an embodiment of the present invention.

[0013] Figure 2 This is an example process of UE server data collection under RAN awareness according to an embodiment of the present invention.

[0014] Figure 3 This is an example diagram of UE-side data collection triggering under RAN perception according to an embodiment of the present invention.

[0015] Figure 4 This is an example diagram of the transmission of assistance information for data collection under RAN awareness according to an embodiment of the present invention.

[0016] Figure 5A This is an example diagram of a data collection channel and a data flow for data collection under RAN awareness according to an embodiment of the present invention.

[0017] Figure 5B is an exemplary diagram of sending accumulated data sets to a UE server according to an embodiment of the present invention.

[0018] Figure 6 This is an exemplary overall process in which a UE server triggers a RAN node to perform UE-side data collection under RAN perception according to an embodiment of the present invention.

[0019] Figure 7 This is an exemplary overall process in which a UE server directly triggers a UE to perform data collection according to an embodiment of the present invention.

[0020] Figure 8 This is an exemplary overall process of data collection of 5GS triggered by UE server under RAN perception according to an embodiment of the present invention.

[0021] Fig. 9 This is an exemplary process of UE performing data collection under RAN awareness according to an embodiment of the present invention.

[0022] Fig.10 This is an exemplary process of a RAN node performing data collection under RAN awareness according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] Reference will now be made in detail to some embodiments of the present invention, examples of which are illustrated in the accompanying drawings.

[0024] Several aspects of telecommunication systems will now be presented with reference to various apparatus and methods. These apparatus and methods will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0025] Figure 11 is a system diagram of an exemplary wireless network supporting RAN-aware data collection according to an embodiment of the present invention. The wireless communication network 100 includes one or more fixed infrastructure units forming a network distributed over a geographical area. These basic units may also be referred to as access points, access terminals, base stations, node Bs, evolved node Bs (eNBs), next generation node Bs (gNBs), or other terms used in the art. For example, a base station serves multiple mobile stations within a service area (e.g., a cell or a cell sector). In some systems, one or more base stations are coupled to a controller to form an access network, wherein the access network is coupled to one or more core networks. gNB 102, gNB 107, and gNB 108 are base stations in a wireless network, and their service areas may or may not overlap. gNB 102 is connected to gNB 107 via an Xn interface 121. gNB 102 is connected to gNB 108 via an Xn interface 122. gNB 107 is connected to gNB 108 via an Xn interface 123. The core network (CN) entity 103 is connected to gNBs 102 and 107 via NG interfaces 125 and 126, respectively. The network entity CN 109 is connected to gNB 108 via NG connection 127. The exemplary CN 103 and CN 109 are connected to the AI ​​server 105 via the Internet 106. CN 103 and CN 109 include core components such as user plane function (UPF) and access and mobility management function (AMF). In one embodiment, the AI ​​server 105 is a UE server. According to some examples, the UE server can be inside a mobile network operator (MNO). According to other examples, the UE server can be outside the MNO and can also be referred to as an OTT server. In one example, the UE server is an OTT server on the UE side. In another example, the UE server is an OTT server on the network side or an OTT server on a neutral site. Please note that some of the following examples are described in the context of OTT servers, but they can also be applied to other types of UE servers.

[0026] Figure 1A general data collection framework for UE, RAN node / gNB, CN, and AI server (such as OTT server) is further described. CN 103 is the backbone of the wireless network and communicates with the UE server via the Internet 106. In one embodiment, CN 103 includes network nodes / entities / functions such as data collection application function (DCAF), CN, operations, administration, and maintenance (OAM), etc.

[0027] In an example 180, the UE performs data collection for an AI-ML model. Data collection is the process of collecting data for the purpose of AI / ML model training, data analysis, and inference through a network node, a management entity, a UE-side server, or a neutral server. Data collection allows data to reach the UE-side or a neutral site (i.e., a UE server) and collects enough data for model generalization. In step 181, the UE obtains a data collection configuration / trigger. In step 182, the UE collects AI-ML related data. In one embodiment, multiple UEs (e.g., UE 101a and UE 101b) perform AI-ML related data collection and transmit the collected AI-ML related data to a UE server 105 via a wireless network. In one embodiment, a RAN node (e.g., gNB 102) accumulates multiple AI-ML model related data sets from multiple UEs (e.g., UE 101a and UE 101b) and forwards the accumulated data sets via a wireless network 100. In another embodiment, the core network entity receives multiple AI-ML model-related data sets collected by multiple UEs (e.g., UE 101a and UE 101b) and forwards the accumulated data sets to the UE server 105. In one embodiment, the network entity accumulates multiple AI-ML model-related data sets from the same RAN node or different RAN nodes. In step 184, the UE establishes a data transmission channel for AI-ML-related data transmission. In step 185, the UE transmits AI-ML-related data through the established channel. In one embodiment, in step 183, the UE obtains assistance information and transmits the assistance information and AI-ML-related data through the established channel.

[0028] In one example, the RAN node is aware of data collection. The entire UE-side data collection process may include processes such as data collection triggering, data collection configuration, measurement process, and data transmission process. The data collection trigger usually starts at the UE of the UE server / OTT server. In one embodiment, the UE server sends a data collection indication to the network, and the network indicates data collection to the UE. In one embodiment, the UE server sends a data collection indication to the UE at the application layer, and the UE requests the network to start the data collection process. Data configuration is an indication to the UE of the configuration required for data collection. In one embodiment, the data configuration and the data collection indication can be sent by the network together. The measurement process is a process in which the UE collects enough data for model training. In different embodiments, different measurement processes may be used, such as self-organizing network (SON) / minimization of drive tests (MDT), UE measurement reporting, or a new data collection process. The data transmission process is a way to establish a data collection channel from the UE to the UE server and transmit the collected data. In different embodiments, the data collection channel is located in the control plane (CP) or the user plane (UP). In one embodiment, the network indicates assistance information to the UE server for subsequent use. The assistance information may include use cases / functions of the data, scenario information, site information (location), RAN configuration information of the data, etc.

[0029] Figure 1 A simplified block diagram of a RAN node / base station, UE server, and mobile device / UE supporting data collection is further shown. The gNB / RAN node has an antenna 156 that transmits and receives radio signals. An RF transceiver circuit 153 coupled to the antenna receives RF signals from the antenna 156, converts the RF signals to baseband signals, and sends the baseband signals to the processor 152. The RF transceiver 153 also converts the baseband signals received from the processor 152 to RF signals and sends them to the antenna 156. The processor 152 processes the received baseband signals and calls different functional modules to perform functional features in the gNB 107. The memory 151 stores program instructions and data 155 to control the operation of the base station / gNB. The base station / gNB also includes a set of control modules 157 for performing functional tasks of communicating with the mobile station. These control modules can be implemented by circuits, software, firmware, or a combination of the above.

[0030] Figure 1Also included is a simplified block diagram of a UE (e.g., UE 101a). A UE may also be referred to as a mobile station, mobile terminal, mobile phone, smartphone, wearable device, IoT device, tablet, laptop, or other terms used in the art. The UE performs functions to perform data collection for AI-ML model training and includes a configuration module, a collection module, a transmission module, and an optional detection module. The UE interacts with the gNB over an air interface. The UE has an antenna 166 for sending and receiving radio signals. An RF transceiver circuit 163 coupled to the antenna receives an RF signal from the antenna 166, converts the RF signal to a baseband signal, and sends the baseband signal to the processor 162. The RF transceiver 163 also converts the baseband signal received from the processor 162 to an RF signal and sends it to the antenna 166. The processor 162 processes the received baseband signal and calls different functional modules to perform functional features in the UE 101a. The memory 161 stores program instructions and data 165 to control the operation of the UE 101a. Antenna 166 sends uplink transmissions and receives downlink transmissions from antenna 156 of the base station / gNB.

[0031] The UE also includes a set of control modules for performing functional tasks. These control modules can be implemented by circuits, software, firmware, or a combination thereof. The configuration module 191 receives a data collection configuration from a RAN node, wherein the data collection configuration configures AI-ML model-related parameters for the UE. The collection module 192 performs data collection according to the data collection configuration to collect AI-ML model-related data. The transmission module 193 performs data transmission of the collected AI-ML model-related data with the destination being a UE server through the RAN node. The detection module 194 receives a data collection request from a RAN node, a core network entity of a wireless network, or a UE server.

[0032] Figure 1 Also included is a simplified block diagram of a UE server (e.g., UE server 105). The UE server has a network interface module 173 that transmits and receives signals / messages over the network. A processor 172 processes received messages and calls different functional modules to perform functions in the UE server. A memory 171 stores program instructions and data 175 to control the operation of the UE server. The UE server also includes a set of control modules 177 that perform functional tasks of communicating with a mobile station. These control modules can be implemented by circuits, software, firmware, or a combination thereof.

[0033] Figure 2This is an example process of UE server data collection under RAN awareness according to an embodiment of the present invention. One or more UEs (e.g., UE 201a, 201b, and 201c) are connected to RAN node / gNB 202. gNB 202 is connected to core network 203. Core network 203 includes network functions and / or entities, such as DCAF, OAM, and other network functions / entities. Core network 203 is connected to UE server 205. In one embodiment, data flows from UE 201a / 201b / 201c to UE server 205. In one embodiment, data is transmitted from UE to network entity / function in CN 203, which forwards the data to UE server 205. In one embodiment, the data transmission channel is a UP channel. In another embodiment, the data transmission channel from UE to network entity / function in CN 203 and from network entity / function in CN 203 to UE server 205 is through a control plane CP channel. In one embodiment 210, the collected AI-ML related data is non-standardized / standardized / proprietary data for various models, customized for internal and / or external conditions and design choices of the UE. In one embodiment, the design choices include UE resource limitations, radio environment and / or feature engineering. In one embodiment, the UE collects data related to the AI-ML model. The collected data includes one or more of the following elements: model input, model true value, data quality, and other information (e.g., AI-ML model related data for generalization of the AI-ML model). In one embodiment 220, the UE communicates with the RAN node / gNB via layer 1 (layer-1, L1) uplink control information (uplink control information, UCI), L2 MAC control element (control element, CE), radio resource control (radio resource control, RRC) message or a new radio bearer for AI to obtain data collection configuration and optional assistance information. In one embodiment 230, the assistance information is also transmitted to the UE server. The assistance information includes one or more of the following elements: use cases of AI-ML model related data, functions of AI-ML model related data, scenario information, location information, and RAN configuration information of AI-ML model related data. In one embodiment 250, data transmission related to AI-ML is authenticated. Authentication can be performed by a core network entity / function, OAM, or UE server. In one embodiment, a network node / entity / function (e.g., DCAF, CN, OAM, etc.) performs an authentication check and determines whether data collection and transmission to the UE server is allowed. In one embodiment, a network node / entity / function (e.g., DCAF, CN, OAM, etc.) also determines the type of data that is allowed to be collected and transmitted to the UE server.

[0034] Figure 3 301 is an example diagram of UE-side data collection triggering under RAN awareness according to an embodiment of the present invention. UE 301 is connected to RAN node 302 and 5GS / CN 303, which is connected to UE server 304. In one embodiment, data collection trigger 309 is initiated at UE server 304. In an exemplary example, data collection is performed under RAN awareness.

[0035] In one embodiment 310, the UE server 304 sends a data collection request to the RAN node 302 (step 311), and the RAN node 302 further transmits the data collection request to the UE 301. In one embodiment, the RAN node sends the data collection request together with the data collection configuration to the UE (step 312). In one embodiment, the data collection request is transmitted from the RAN node 302 to the UE 301 via RRC signaling. In one embodiment, the RAN node 302 sends the data collection request together with the data collection configuration to the UE.

[0036] In one embodiment 320, the UE server 304 sends a data collection indication to the UE 301 (step 321). In one embodiment, the UE server 304 sends a data collection indication / request to the UE 301 through the application layer. In step 322, after receiving the data collection indication / request from the UE server 304, the UE 301 sends a data collection request to the RAN node 302. In step 323, after receiving the data collection request from the UE, the RAN node 302 sends a data collection configuration. In one embodiment, the data collection configuration is pre-configured to the UE before the UE sends the data collection request.

[0037] In one embodiment 330, in step 331, the UE server 304 sends a data collection indication / request to the 5GS 303. In step 332, the 5GS 303 sends the data collection indication / request to the RAN node 302. In step 333, the RAN node 302 transmits the data collection indication / request to the UE 301. In one embodiment, the function of data collection triggering and assisting information collection in the 5GS is DCAF. In one embodiment, the RAN node 302 sends the data collection configuration together with the data collection indication / request to the UE 301.

[0038] In one embodiment 340, in step 341, the UE server 304 sends a data collection indication / request to a core network entity (such as DCAF) of the 5GS 303. In step 342, the core network entity (such as DCAF) of the 5GS 303 transmits the data collection indication / request to the UE 301. In one embodiment, the core network entity (such as DCAF) of the 5GS 303 transmits the data collection indication / request to the UE 301 via non-access-stratum (NAS) signaling. In one embodiment, the core network entity (such as DCAF) of the 5GS 303 further notifies the RAN node 302 to send a data collection configuration to the UE 301. After receiving the notification, the RAN node 302 sends the data collection configuration to the UE 301.

[0039] Figure 4 4 is an example diagram of the transmission of assistance information for data collection under RAN awareness according to an embodiment of the present invention. UE 401 is connected to RAN node 402 and 5GS / CN 403, which is connected to UE server 404. In one embodiment, assistance information 409 is transmitted from RAN node 402 to UE server 404. In one embodiment, RAN node 402 provides assistance information for each UE (e.g., via unicast) or a group of UEs (e.g., via multicast). In one embodiment, the assistance information may include use cases / functions of the data, scenario information, site information (location), RAN configuration information of the data, etc. In one embodiment, the content of the assistance information may depend on the UE request or on the commercial agreement between the RAN and the UE server / OTT server.

[0040] In one embodiment 410, in step 411, assistance information is transmitted from the RAN node 402 to a core network entity (such as DCAF) of the 5GS 403. In step 412, the DCAF transmits the assistance information to the UE server / OTT server 404 after an authorization check. In one embodiment 420, in step 421, the RAN node 402 requests the core network entity (such as DCAF) of the 5GS 403 for authorization. In step 422, the RAN node 402 receives an authorization response from the core network entity (such as DCAF) of the 5GS 403. If the authorization response indicates that the authorization is successful, in step 423, the RAN node 402 transmits the assistance information to the UE 401. In step 424, the UE 401 transmits the assistance information to the UE server 404. In one embodiment 430, in step 431, the RAN node 402 transmits the assistance information to the core network entity (such as DCAF) of the 5GS 403. In step 432, the core network entity (such as DCAF) of 5GS 403 transmits the assistance information to UE 401 after the authorization check. In step 433, UE 401 transmits the assistance information to UE server 404. In different embodiments, UE 401 sends the assistance information to UE server 404 through a CP channel or a UP channel. In one embodiment 440, in step 441, RAN node 402 transmits the assistance information to UE 401. In one embodiment, RAN node 401 requests the core network entity (such as DCAF) of 5GS 403 for authorization before sending the assistance information to UE4 01. In another embodiment, in step 442, UE 401 transmits the assistance information to the core network entity (such as DCAF) of 5GS 403 for authorization check. In step 443, the core network entity (such as DCAF) of 5GS 403 transmits the assistance information to UE server 404 after the authorization check.

[0041] Figure 5A 5 is an example diagram of a data collection channel and a data flow for data collection under RAN perception according to an embodiment of the present invention. UE 501 is connected to RAN node 502 and 5GS / CN 503, which is connected to UE server 504. In step 509, UE 501 performs data collection to collect AI-ML model related data. The data flow is from the UE side to the UE server. In one embodiment, the UE server performs offline model training using data collected from a large number of UEs. In one embodiment, the collected data can be transmitted from the RAN node to the core network entity (such as DCAF) of 5GS 503 together with the assistance information.

[0042] In one embodiment 510, the data collection channel for collecting data is a control plane channel CP channel 518. In one embodiment, a new CP channel is established for AI-ML related data transmission. In one embodiment, the new control plane channel between UE 501 and RAN node 502 is layer 1 (layer-1, L1) uplink control information (uplink control information, UCI), L2 MAC control element (control element, CE), radio resource control (radioresource control, RRC) message or a new radio bearer for AI. In step 511, UE 501 transmits the collected data to RAN node 502. Optionally, UE 501 attaches assistance information to the data transmission. In step 512, RAN node 502 transmits the data to 5GS / CN 503. In step 513, 5GS / CN 503 transmits the data related to the AI-ML model to UE server 504. Optionally, RAN node 502 attaches assistance information to the data transmission. In one embodiment 520, the data collection channel for collecting data is a UP channel 528. In one embodiment, in step 521, the UE transmits the collected data to the network entity of 5GS 503. Optionally, UE 501 attaches assistance information to the data transmission. In one embodiment, the collected data is transmitted to the network entity (such as DCAF) of 5GS 503 via NAS signaling, and the new data collection channel is located at the NAS layer. In one embodiment 530, the collected data is transmitted to the UE server 504, and the new data collection channel is located at the application layer. In step 531, UE 501 transmits AI-ML model related data to UE server 504. Optionally, UE 501 attaches assistance information to the data transmission.

[0043] Figure 5B509b, UE 501 performs data collection to collect AI-ML model related data. In one embodiment 550, AI-ML model related data / datasets collected by multiple UEs (such as UE 501, UE 501b, and UE 501c) are accumulated and sent together to the UE server 504. In one embodiment, the RAN node 502 accumulates data sets from multiple UEs and sends the accumulated data sets to the UE server 504. In step 551, UE 501 transmits AI-ML model related data to the RAN node 502. In step 551b, UE 501b transmits AI-ML model related data to the RAN node 502. In step 551c, UE 501c transmits AI-ML model related data to the RAN node 502. In step 552, the RAN node 502 accumulates multiple AI-ML related data collected by multiple UEs. In step 553, the RAN node 502 sends the accumulated data set to the 5GS / CN 503. In step 554, the 5GS / CN 503 transmits the accumulated data set to the UE server 504.

[0044] In another embodiment 560, 5GS / CN 503 accumulates data sets from multiple UEs (such as UE 501, UE 501b, and UE 501c) and sends the accumulated data sets to UE server 504. In one embodiment, multiple AI-ML model-related data sets come from the same RAN node. In another embodiment, multiple AI-ML model-related data sets come from different RAN nodes. For example, in step 561b, UE 501b sends the collected AI-ML-related data to RAN node 502b. In step 562b, RAN node 502b sends the AI-ML-related data to 5GS / CN 503. In step 561c, UE 501c sends the collected AI-ML-related data to RAN node 502. In step 562c, RAN node 502 transmits the AI-ML-related data to 5GS / CN 503. In step 561, UE 501 sends the collected AI-ML-related data to RAN node 502. In step 562, the RAN node 502b transmits the AI-ML related data to the 5GS / CN 503. In step 563, the 5GS / CN 503 accumulates a plurality of AI-ML related data collected by a plurality of UEs, and transmits the accumulated data set to the UE server 504 in step 564.

[0045] In one exemplary embodiment, the UE receives a data collection configuration and a trigger, receives assistance information, and performs data transmission of the collected AI-ML model related data. Figure 4 As shown in Figure 5, there are different options for data collection configuration and trigger reception, assistance information reception, and data transmission processes. Different options for each step can be mixed to perform data collection under RAN awareness. Figure 6-8 An example progression of different options for each step is shown, and some other mix of options not depicted could also be used for data collection.

[0046] Figure 6 This is an exemplary overall process of a UE server triggering a RAN node to perform UE-side data collection under RAN perception according to an embodiment of the present invention. UE 601 is connected to RAN node 602 and 5GS / CN 603, which is connected to UE server 604. Before data collection starts, UE server 604 triggers data collection. In one embodiment, in step 611, UE server 604 sends a data collection request to RAN node 602. In step 612, RAN node 602 may send a data collection response to UE server 604. In step 621, RAN node 602 sends a data collection trigger / data collection request to UE 601 after receiving the data collection request from UE server 604. In one embodiment, RAN node 602 transmits a data collection configuration together with the data collection request to UE 601. In step 622, a data transmission channel may also be established between RAN node 602 and UE server 604. In step 631, UE 601 measures and collects data. In step 641, UE 601 transmits the collected data to RAN node 602. In step 652, the RAN node 602 transmits the collected data to the UE server 504. In one embodiment, the RAN node 602 combines the collected data and the assistance information and transmits them together to the UE server 604. In step 651, the RAN node 602 attaches the assistance information to the AI-ML model related data for transmission to the UE server 604. In step 652, the RAN node 602 transmits the AI-ML model related data (optionally together with the assistance information) to the UE server 604. In one embodiment, the data transmission from the UE to the RAN is performed through a measurement reporting process.

[0047] Figure 7This is an exemplary overall process in which a UE server directly triggers a UE to perform data collection according to an embodiment of the present invention. UE 701 is connected to RAN node 702 and 5GS / CN 703, which is connected to UE server 704. Before data collection starts, UE server 704 triggers data collection. In step 711, UE server 704 sends a data collection request to UE 701 through the application layer (as shown in 320). In step 712, UE 701 requests data collection from RAN node 702. After receiving the data collection request, in step 722, RAN node 702 establishes a data transmission channel to UE server 704. In step 721, RAN node 702 sends data collection configuration and data collection trigger / request to UE 701. In one embodiment, in step 713, optionally, UE 701 sends a data collection response to UE server 704 after receiving a data collection trigger from the RAN node. In step 731, UE 701 measures and collects data. In step 741, UE 701 transmits the collected data to RAN node 702. In step 752, the RAN node 702 transmits the collected data to the UE server 704. In one embodiment, the RAN node 702 combines the collected data with the assistance information and transmits them together to the UE server 704. Optionally, in step 751, the RAN node 702 attaches the assistance information to the data related to the AI-ML model for transmission to the UE server 704. In step 752, the RAN node 702 transmits the AI-ML model related data (optionally together with the assistance information) to the UE server 704. In one embodiment, the data transmission from the UE to the RAN is performed through a measurement reporting process.

[0048] Figure 8This is an exemplary overall process of data collection of 5GS triggered by UE server under RAN perception according to an embodiment of the present invention. UE 801 is connected to RAN node 802 and 5GS / CN 803, which is connected to UE server 804. Before data collection starts, UE server 804 triggers data collection. In step 811, UE server 804 sends a data collection request to a network entity (e.g., DCAF) of 5GS 804. In step 821, 5GS 803 sends the data collection request to RAN node 802. In one embodiment, in step 821, 5GS 803 sends an assistance information request together or separately to RAN node 802. In step 830, RAN node 802 sends a data collection trigger / request to UE 801 (as shown in 330). In one embodiment, RAN node 802 sends a data collection configuration together with the data collection request to UE 801. In one embodiment, in step 821, DCAF responds to UE server 804. In step 822, a data transmission channel between UE server 804 and DCAF 803 is established. In step 831, UE 801 measures and collects data. In step 841, UE 801 transmits the collected data to RAN node 802. In step 851, RAN node 802 transmits the collected data to DCAF 803 (as shown in 510). In one embodiment, in step 832, RAN node 802 combines the collected data and assistance information and transmits them to DCAF 803. In one embodiment, DCAF 803 combines the data and assistance information collected from different UEs in RAN and transmits them together to UE server after authorization check. In one embodiment, the assistance information is transmitted from RAN node 802 to DCAF 803 separately, and transmitted from DCAF 803 to UE server 804.

[0049] Fig. 9 This is an exemplary process of UE performing data collection under RAN perception according to an embodiment of the present invention. In step 901, the UE receives a data collection configuration from a RAN node, wherein the data collection configuration configures AI-ML model related parameters for the UE. In step 902, the UE performs data collection based on the data collection configuration to collect AI-ML model related data. In step 903, the UE performs data transmission of the collected AI-ML model related data with the destination being a UE server through the RAN node.

[0050] Fig.10This is an exemplary process of a RAN node performing data collection under RAN perception according to an embodiment of the present invention. In step 1001, the RAN node receives a triggering event of a data collection request, wherein the data collection request instructs the UE to collect AI-ML model related data. In step 1002, the RAN node sends a data collection configuration to the UE, wherein the data collection configuration configures AI-ML model related parameters for the UE. In step 1003, the RAN node performs data transmission for the AI-ML model related data collected by the UE through a data transmission channel between the UE and the UE server.

[0051] Although the present invention has been described in connection with certain specific embodiments for teaching purposes, the present invention is not limited thereto. Therefore, various modifications, adaptations and combinations of various features of the described embodiments may be practiced without departing from the scope of the present invention as defined in the claims.

Claims

1. A method for performing data collection, comprising: Receiving, by a user equipment UE, a data collection configuration from a radio access network RAN ​​node, wherein the data collection configuration configures artificial intelligence-machine learning AI-ML model related parameters for the UE; Performing data collection based on the data collection configuration to collect AI-ML model related data; and Data transmission of collected AI-ML model related data destined for the UE server is performed through the RAN node.

2. The method for performing data collection as claimed in claim 1, further comprising: A data collection request is received from the RAN node, a core network entity of the wireless network, or the UE server.

3. The method of performing data collection as claimed in claim 2, wherein the data collection configuration is received from the RAN node together with the data collection request.

4. The method for performing data collection as claimed in claim 2, wherein the data collection request is received from the UE server or the core network entity, and the method further comprises: A data collection request is sent to the RAN node. The method for performing data collection as claimed in claim 1 , wherein the data transmission is performed through a measurement reporting process.

6. The method for performing data collection as claimed in claim 1, wherein the data transmission is performed through a new control plane channel or through a new application layer channel.

7. The method for performing data collection as claimed in claim 6, wherein the new control plane channel between the UE and the RAN node is a layer 1 uplink control information, a layer 2 MAC control element, a radio resource control message or a new radio bearer for AI.

8. The method for performing data collection as claimed in claim 1, further comprising: Receive AI-ML model assistance information.

9. The method for performing data collection as described in claim 8, wherein the assistance information includes one or more of the following elements: use cases of the AI-ML model related data, functions of the AI-ML model related data, scenario information, location information, and RAN configuration information of the AI-ML model related data.

10. The method for performing data collection as claimed in claim 8, wherein the assistance information is received from the RAN node or a core network entity of the wireless network.

11. A method for performing data collection, comprising: A triggering event of receiving a data collection request by the RAN node, wherein the data collection request instructs the UE to collect AI-ML model related data; Sending a data collection configuration to the UE, wherein the data collection configuration configures AI-ML model related parameters for the UE; and Data transmission is performed for the AI-ML model related data collected by the UE through the data transmission channel between the UE and the UE server.

12. The method for performing data collection as claimed in claim 11, wherein the triggering event is a data collection request received from the UE server or a core network entity of a wireless network, and the data collection request is forwarded to the UE.

13. The method for performing data collection as claimed in claim 12, wherein the data collection request is forwarded to the UE together with the data collection configuration. The method for performing data collection as claimed in claim 11 , wherein the triggering event is a data collection request from the UE.

15. The method for performing data collection as claimed in claim 11, further comprising: Transmitting AI-ML model assistance information to a core network entity of the wireless network.

16. The method for performing data collection as claimed in claim 11, further comprising: The AI-ML model assistance information is transmitted to the UE via unicast, or the AI-ML model assistance information is transmitted to the UE and one or more other UEs via multicast.

17. The method for performing data collection as claimed in claim 16, further comprising: Sending an authorization request to the wireless network; as well as A response to the authorization request is received.

18. The method of claim 11, wherein the RAN node transmits the AI-ML model related data collected by the UE together with the AI-ML model assistance information to the UE server.

19. The method for performing data collection as claimed in claim 11, further comprising: Accumulating one or more AI-ML model related data sets collected by one or more other UEs; The one or more AI-ML model related data sets are transmitted together with the AI-ML model related data collected by the UE.

20. A user equipment, comprising: Transceivers, which are used to transmit and receive signals in wireless networks; A configuration module, configured to receive a data collection configuration from a RAN node, wherein the data collection configuration configures AI-ML model related parameters for the UE; A collection module, used to perform data collection based on the data collection configuration to collect AI-ML model related data; as well as A transmission module performs data transmission of collected AI-ML model related data destined for a UE server through the RAN node.

21. A storage medium storing a program, which, when executed, enables a user device to execute the steps of the method for executing data collection according to any one of claims 1 to 10.

Images