User equipment processing method

Abstract

A user equipment (UE) device includes a processing method or functionality for improved communication or processing. Beam information prediction, channel information prediction, channel information compression, channel demodulation or positioning may be improved by processing methods. A function or condition of support for a particular feature may be reported by a UE. The report may be a UE capability report. The UE may support a processing method / model identifier (ID) for the feature included in the report. The processing method can be used for managing reports and / or performance monitoring.

Description

Technical Field

[0001] This document generally relates to wireless communication. More specifically, user equipment (UE) devices may have processing methods or functions for improved communication or processing. Background Technology

[0002] Wireless communication technology is propelling the world towards an increasingly interconnected and networked society. Wireless communication relies on efficient network resource management and allocation between user mobile stations and wireless access network nodes (including but not limited to wireless base stations). Next-generation networks promise to provide high-speed, low-latency, and ultra-reliable communication capabilities, meeting the needs of diverse industries and users. User mobile stations or user equipment (UEs) are becoming increasingly complex, and the amount of data being communicated is constantly increasing. To improve communication, meet the reliability requirements of vertical industries, and support next-generation network services, improvements must be made to maintain and ensure service quality standards. Summary of the Invention

[0003] This document relates to methods, systems, and apparatuses for enabling user equipment (UE) devices to have processing methods or functions for improved communication or processing. Beam information prediction, channel information prediction, channel information compression, channel demodulation, or positioning can be improved through processing methods. The UE can report supported functions or conditions for specific features. This report can be a UE capability report. The UE can support processing methods or model identifiers (IDs) for the features included in the report. These processing methods can be used for management reporting, performance monitoring, activation, handover, and / or selection.

[0004] In one embodiment, the wireless communication method includes feature information of features reported by a wireless communication device in a user equipment (UE) capability report.

[0005] In another embodiment, a wireless communication device includes a processor and a memory, and the processor is configured to read code from the memory and implement any of the embodiments described above.

[0006] In another embodiment, a computer program product includes a computer-readable program medium on which code is stored, which, when executed by a processor, causes the processor to implement any of the embodiments described above.

[0007] In some embodiments, a wireless communication device includes a processor and a memory, wherein the processor is configured to read code from the memory and implement any method described in any embodiment of the various embodiments. In some embodiments, a computer program product includes a computer-readable program medium on which code is stored, which, when executed by a processor, causes the processor to implement any method described in any embodiment of the plurality of embodiments. The above and other aspects and their embodiments are described in more detail in the accompanying drawings, specification, and claims. Attached Figure Description

[0008] Figure 1 An example base station is shown.

[0009] Figure 2 An example random access (RA) messaging environment is shown.

[0010] Figure 3 An embodiment of a wireless network system architecture is shown.

[0011] Figure 4 Example artificial intelligence (AI) models or processing methods are shown.

[0012] Figure 5 Example features using this processing method or model are shown.

[0013] Figure 6 An example report shows the functionality supporting a feature from the user equipment (UE) to the network.

[0014] Figure 7 An example report shows the conditions for support for a feature from the user equipment (UE) to the network.

[0015] Figure 8 An example report is shown showing the functional identifier or model identifier for support of a feature from the user equipment (UE) to the network.

[0016] Figure 9 Example functions or processing methods for management are shown. Detailed Implementation

[0017] This disclosure will now be described in detail below with reference to the accompanying drawings, which form a part of this disclosure and illustrate specific examples of embodiments by way of illustration. However, it should be noted that this disclosure may be implemented in a variety of different forms, and therefore, the subject matter covered or claimed is intended to be construed as not being limited to any of the embodiments set forth below.

[0018] Throughout the specification and claims, terms may have suggestive or implied meanings that go beyond their explicitly stated meanings in the context. Similarly, the phrases “in one embodiment” or “in some embodiments” as used herein do not necessarily refer to the same embodiment, and the phrases “in another embodiment” or “in other embodiments” as used herein do not necessarily refer to different embodiments. For example, the claimed subject matter is intended to include, in whole or in part, exemplary embodiments or combinations of embodiments.

[0019] Generally, terms can be understood at least partially from their usage in context. For example, terms such as “and,” “or,” or “and / or” as used herein can encompass a variety of meanings, which can depend at least partially on the context in which they are used. Typically, “or,” if used to relate a list (e.g., A, B, or C), is intended to mean A, B, and C (used herein in an inclusive sense) and A, B, or C (used herein in an exclusive sense). Furthermore, depending at least partially on the context, the terms “one or more” or “at least one” as used herein can be used to describe any feature, structure, or characteristic in a singular sense, or can be used to describe a combination of features, structures, or characteristics in a plural sense. Similarly, terms such as “a,” “an,” or “the” can also be understood to convey either a singular or a plural usage, depending at least partially on the context. Moreover, again depending at least partially on the context, the terms “based on” or “determined by” can be understood not necessarily to convey an exclusive set of factors, but can allow for the presence of additional factors that are not necessarily explicitly described.

[0020] Radio resource control (RRC) is a protocol layer at the IP level (Network Layer) between the UE and the base station. Various RRC states can exist, such as RRC_CONNECTED, RRC_INACTIVE, and RRC_IDLE. RRC messages are transmitted via the Packet Data Convergence Protocol (PDCP). As mentioned above, the UE can transmit data via either the Random Access Channel (RACH) protocol scheme or the Configured Grant (CG) scheme. CG can be used to reduce the waste of periodically allocated resources by enabling multiple devices to share periodic resources. The base station or node can allocate CG resources to eliminate packet transmission delays and improve the utilization of allocated periodic radio resources. The CG scheme is merely one example of a protocol scheme used for communication, and other examples (including but not limited to RACH) are possible. The wireless communication described herein can be implemented via radio access.

[0021] Figure 1 Example base station 102 is shown. Base station 102 may also be referred to as a wireless network node or a next-generation radio access network (NG-RAN) node. Base station 102 may also be identified as a nodeB (NB, e.g., eNB or gNB) in a mobile telecommunications context. The example base station may include wireless transmit / receive (Tx / Rx) circuitry 113 for receiving and transmitting with user equipment (UE) 104. The base station may also include network interface circuitry 116 that couples the base station to the core network 110, such as optical interconnect or wired interconnect, Ethernet and / or other data transmission media / protocols.

[0022] The base station may also include system circuitry 122. System circuitry 122 may include one or more processors 124 and / or memory 126. Memory 126 may include operations 128 and control parameters 130. Operations 128 may include instructions for execution on one or more processors in processor 124 to support base station operation. For example, operations may process random access transmission requests from multiple UEs. Control parameters 130 may include parameters or may support the execution of operations 128. For example, control parameters may include network protocol settings, random access message transmission and reception format rules, bandwidth parameters, radio frequency mapping allocation, and / or other parameters.

[0023] Figure 2 An example random access messaging environment 200 is illustrated. In this environment, UE 104 can communicate with base station 102 via random access channel 252. In this example, UE 104 supports one or more Subscriber Identity Modules (SIMs), such as SIM1 202. Electrical and physical interfaces 206 connect SIM1 202 to the rest of the user equipment hardware, for example, via system bus 210.

[0024] Mobile device 200 includes a communication interface 212, system logic 214, and user interface 218. System logic 214 may include any combination of hardware, software, firmware, or other logic. System logic 214 may be implemented, for example, using one or more systems-on-a-chip (SoC), application-specific integrated circuits (ASICs), discrete analog and digital circuits, and other circuits. System logic 214 is part of an implementation of any desired functionality in UE 104. In this regard, system logic 214 may include logic that facilitates operations such as: decoding and playing music and video (e.g., MP3, MP4, MPEG, AVI, FLAC, AC3, or WAV decoding and playback); running applications; accepting user input; saving and retrieving application data; establishing, maintaining, and terminating cellular phone calls or data connections (as an example, for internet connections); establishing, maintaining, and terminating wireless network connections, Bluetooth connections, or other connections; and displaying relevant information on user interface 218. User interface 218 and input 228 may include a graphical user interface, a touch-sensitive display, haptic feedback or other haptic output, voice or facial recognition input, buttons, switches, speakers, and other user interface elements. Additional examples of input 228 include microphones, video and still image cameras, temperature sensors, vibration sensors, rotation and orientation sensors, headphone and microphone input / output jacks, Universal Serial Bus (USB) connectors, memory card slots, radiation sensors (e.g., infrared radiation (IR) sensors), and other types of input.

[0025] System logic 214 may include one or more processors 216 and memory 220. Memory 220 stores, for example, control instructions 222 executed by processor 216 to achieve the desired functions of UE 104. Control parameters 224 provide and specify configuration and operational options for the control instructions 222. Memory 220 may also store any BT, WiFi, 3G, 4G, 5G, or other data 226 that UE 104 will send or has received via communication interface 212. In various embodiments, system power may be provided by a power storage device such as battery 282.

[0026] In communication interface 212, radio frequency (RF) transmit (Tx) and receive (Rx) circuitry 230 handles the transmission and reception of signals via one or more antennas 232. Communication interface 212 may include one or more transceivers. The transceiver may be a wireless transceiver, including modulation / demodulation circuitry, a digital-to-analog converter (DAC), a shaper, an analog-to-digital converter (ADC), filters, waveform shapers, preamplifiers, power amplifiers, and / or other logic for transmission and reception via one or more antennas or (for some devices) via a physical (e.g., wired) medium.

[0027] The transmitted and received signals can follow any of the following: various formats; various protocols; various modulations (e.g., QPSK, 16-QAM, 64-QAM, or 256-QAM); various frequency channels; various bit rates; and various encodings. As a specific example, communication interface 212 may include a transceiver supporting transmission and reception under 2G, 3G, BT, WiFi, Universal Mobile Telecommunications System (UMTS), High Speed ​​Packet Access (HSPA)+, and 4G / Long Term Evolution (LTE) standards. However, the techniques described below, whether derived from the 3rd Generation Partnership Project (3GPP), the GSM Association, 3GPP2, IEEE, or other partners or standards bodies, are applicable to other wireless communication technologies.

[0028] Figure 3An embodiment of a wireless network system architecture is illustrated. This architecture is merely an example, and more or fewer components may be present to implement the embodiments described herein. Interconnections or communications between the components are identified as N1, N2, N4, N6, N7, N8, N10, and N11, and these interconnections or communications may be referenced in the specification or other drawings. Figure 2 An example user equipment (“UE”) 104 is shown. UE 302 is a device that accesses a wireless network (e.g., 5GS) and obtains services through an NG-RAN node or base station 304. UE 302 interacts with the Access and Mobility Control Function (AMF) 306 of the core network via NAS signaling. Figure 1 An example base station or NG-RAN 102 is shown. Base station 304 can also be referred to as a next-generation radio access network (NG-RAN) node and can provide time synchronization signals to user equipment (UE). An AI model or processing method may exist as part of UE 302, and information can be provided by the UE to... Figure 3 The components shown are as described in the following embodiments.

[0029] AMF 306 includes the following functions: registration management, connection management, reachability management, and mobility management. AMF 306 also performs access authentication and access authorization. AMF 306 is a NAS security endpoint and relays the Session Management NAS between UE 302 and Session Management Function (SMF) 308, etc. SMF 308 includes the following functions: session management (e.g., session establishment, modification, and release), UE IP address allocation and management (including optional authorization), selection and control of uplink functions, downlink data notification, etc. User plane function (UPF) 310 includes the following functions: anchor points for intra / inter-RAT mobility, packet routing and forwarding, service usage reporting, QoS processing for the user plane, downlink packet buffering, and downlink data notification triggering, etc. Unified Data Management (UDM) 312 manages the UE's subscription profile. The subscription includes data for mobility management (e.g., restricted areas) and session management (e.g., QoS profiles). The subscription data also includes slice selection parameters used by AMF 306 to select the appropriate SMF 308. AMF 306 and SMF 308 obtain subscriptions from UDM 312. Subscription data can be stored in a unified data repository using UDM 312, which uses this data when it receives a request from AMF 306 or SMF 308. The Policy Control Function (PCF) 314 includes functions such as supporting a unified policy framework to manage network behavior, providing policy rules to one or more control plane functions to enforce policy rules, and enabling front-end access to subscription information related to policy decisions in the user data repository. The Network Exposure Function (NEF) 316 is optionally deployed for exchanging information with external third parties. In one embodiment, the Application Function (AF) 316 can store application information in the unified data repository via the NEF. UPF 310 communicates with the data network 318.

[0030] Figure 4 An example artificial intelligence (AI) processing method is illustrated. AI can also be referred to as machine learning (ML). In the embodiments described below, Figures 1 to 3Wireless communication systems can be improved by increasing efficiency. For example, AI / ML can be used to improve the accuracy of channel state information (CSI). Furthermore, AI / ML can predict beam information in the spatial or temporal domains. Other examples may include, but are not limited to, channel information compression, channel information prediction, channel demodulation, and positioning. To support physical layer examples with AI / ML, the UE may be deployed with processing methods (e.g., processing methods refer to AI / ML models). In other words, in some embodiments, Figure 4 The processing method shown can be part of the UE. The network (e.g., base station or...) Figure 3 Other components (excluding the UE) can receive certain information about the UE's processing. This information may be referred to as feature information and may be necessary for the appropriate configuration of wireless communication using the processing method. The AI / ML processing method can allow the network to configure the necessary information for the corresponding processing method / function / model based on the feature information. In some embodiments, the UE's processing may include processing methods for various features / examples used for communication between the UE and the network.

[0031] Figure 4 Artificial intelligence / machine learning (AI / ML) processing methods are data-driven algorithms that apply AI / ML techniques to generate a set of outputs based on a set of inputs. As shown in the figure, there may be processing method inputs, which include the data fed into the processing method. There may also be processing method outputs, which include the outputs of the processing method. The processing method may include algorithms used to derive the relationship between the processing method inputs and the processing method outputs. The algorithm may include a processing method structure and / or processing method parameters. The processing method structure includes a description of the functions used in each layer of the processing method, and the processing method parameters include the variables / weights of these functions. The processing method can fit inputs to the processing method to obtain the expected output or prediction.

[0032] In the following embodiments, the processing method may further include (or be referred to as) a function, AI / ML model, or feature. This may include when the UE is able to perform a specific function, the processing method, the AI / ML model, or the feature. In some embodiments, the processing method may be applicable only to certain environments, and this may be referred to as generalization, where good generalization indicates that the processing method can be used in more environments or examples.

[0033] Figure 5 Example features of a case using this processing method are shown. In some embodiments, features (or groups of features) in the processing method may refer to Figure 5The examples / cases shown include information about each feature. Processing methods can be applied to each of these features to obtain output, such as making predictions. As a first example, beam information prediction can use measured beams to predict unmeasured beams. Beam information can include the UE's location. This may also be referred to as a serving beam measurement configuration and may include an indication to request reporting of reference signals. In another example, the serving beam measurement configuration may include an indication to request reporting of one or more reference signals serving the UE over a period of time. In yet another example, the serving beam measurement configuration may include an indication to request reporting of the UE's dwell time in each reported reference signal.

[0034] For simplicity, the features described below may be specific to beam information, but this is merely an example and can be applied to other examples, including those mentioned below. As a second example, channel information prediction may include using measured channels to predict unmeasured channels. As a third example, channel information compression may include using processing methods to compress channels to reduce feedback overhead. As a fourth example, channel demodulation may include using processing methods to demodulate data from various impairments. As a fifth example, positioning may include using processing methods to infer the UE's location or location-related information (e.g., timing information or angle information).

[0035] Figure 6 This illustrates an example report from a User Equipment (UE) to the network regarding supported features for a specific characteristic. The UE reports to the network (NW) the features it supports for that characteristic. This report may be referred to as the feature information reported in the UE capability report. The NW may include... Figure 1 The base station or other components shown. In Type 1, the processing method associated with the supported function has been deployed at the UE. Alternatively, the supported function is available (e.g., ready to be used / activated) after the feature information is reported. In some embodiments, the function can be activated after the UE receives signaling from the NW, where the signaling can be RRC, MAC CE, or DCI. For Type 2, the processing method has not yet been deployed on the UE. Alternatively, the function is unavailable (e.g., not ready to be used / activated). As described above, the UE can report to the NW the functions it supports for a feature (i.e., feature information). In some embodiments, the functions supported for a feature are reported in the UE capability report. Specifically, the UE can report on functions X, Y, or Z, such as Figure 6 As shown. A function can be a processing method or how a processing method is deployed under that function. Features can also refer to things like... Figure 5 The use cases shown are examples of such use cases.

[0036] In some embodiments, each function may be associated with multiple conditions used to describe the applicability information of that function. Multiple conditions may exist for each function. In some embodiments, different functions may be associated with the same or different conditions. In some embodiments, conditions are used to indicate applicable parameters, scenarios, regions, and / or datasets for a function. For example, a processing method or model deployed for a function may have a generalization state or problem. Generalization can measure how well a processing method generalizes and how specific it is when making predictions or decisions. In other words, a processing method or model can function within the parameters, scenarios, regions, or datasets used to initialize and train the processing method. Conditions may include parameters, scenarios, regions, or datasets to which the processing method or function can be applied. In some embodiments, only applicable parameters are reported in the UE capability report. Applicable scenarios, regions, and / or datasets are reported after the UE capability report.

[0037] Parameters may include necessary / required configurations from the network for the application's processing methods or functions. This can be referred to as network configuration. This configuration consists of specific parameters that allow the function or processing method to operate. Figure 5 For example beam information prediction, there may be multiple example parameters, which include at least one of the following:

[0038] Frequency band;

[0039] • Carrier frequency;

[0040] ·bandwidth;

[0041] • Subcarrier spacing;

[0042] • Reference signal used for prediction;

[0043] • Reference signal used for measurement;

[0044] • The correlation between the reference signal used for prediction and the reference signal used for measurement;

[0045] • The number of beams to be reported to NW;

[0046] • The number of historical time instances used for time beam prediction;

[0047] • The number of future time instances used for time beam prediction;

[0048] • The number of beams required for time beam prediction that needs to be reported to NW at a given time instance; or

[0049] • The period of the reference signal.

[0050] for Figure 5The channel information prediction example may have multiple example parameters, which include at least one of the following:

[0051] Frequency band;

[0052] • Carrier frequency;

[0053] ·bandwidth;

[0054] • Subcarrier spacing;

[0055] • Reference signal used for prediction;

[0056] • Reference signal used for measurement;

[0057] • The correlation between the reference signal used for prediction and the reference signal used for measurement;

[0058] • The number of time instances to report to NW;

[0059] • The number of historical time instances used for time beam prediction;

[0060] • The number of future time instances used for time beam prediction;

[0061] • The codebook type used to report channels in future time instances; or

[0062] • The period of the reference signal.

[0063] for Figure 5 The channel information compression example may have multiple example parameters, which include at least one of the following:

[0064] Frequency band;

[0065] • Carrier frequency;

[0066] ·bandwidth;

[0067] • Subcarrier spacing;

[0068] • Reference signal used for measurement;

[0069] • The number of subbands (or the number of subbands used as input to the processing method);

[0070] • Subband granularity (e.g., by indicating the number of PRBs in the subband);

[0071] • The number of antenna ports (or the number of antenna ports used as inputs to the processing method);

[0072] • The number of layers (or the number of layers that serve as input to the processing method);

[0073] • Pairing ID (This pairing ID indicates the pairing information between the processing method used for channel information compression at the UE and another processing method used for channel information decompression at the network);

[0074] • Payload size (e.g., the reporting overhead required for a compressed channel to be reported to the network. Payload size is related to the output of the processing method. A processing method can support multiple payload sizes); or

[0075] • Quantization method (e.g., scalar quantization or vector quantization, which refers to how the compressed channel to be reported is quantized).

[0076] for Figure 5 The channel demodulation example may have multiple example parameters, which include at least one of the following:

[0077] Frequency band;

[0078] • Carrier frequency;

[0079] ·bandwidth;

[0080] • Subcarrier spacing;

[0081] • Reference signal used for measurement;

[0082] • The number of subbands (or the number of subbands used as input to the processing method);

[0083] • Subband granularity (e.g., by indicating the number of PRBs in the subband);

[0084] • The number of antenna ports (or the number of antenna ports used as inputs to the processing method);

[0085] • The number of layers (or the number of layers that serve as input to the processing method);

[0086] • The number of symbols in the data channel (e.g., PDSCH); or

[0087] • The time gap between the reference signaling and the data channel.

[0088] for Figure 5 The positioning example may have multiple example parameters, which include at least one of the following:

[0089] Frequency band;

[0090] • Carrier frequency;

[0091] ·bandwidth;

[0092] • Subcarrier spacing;

[0093] • Reference signal used for measurement;

[0094] • The number of antenna ports (or the number of antennas used as inputs to the processing method);

[0095] • One or more Transmission Reception Point (TRP) identifiers;

[0096] • Input measurement type (e.g., power delay profile (PDP) and channel impulse response (CIR) as inputs to the processing method);

[0097] • The number of paths (e.g., the number of paths that serve as input to the processing method (or the number of delayed taps));

[0098] • Path granularity (e.g., the time interval (or delay tap) between two consecutive paths);

[0099] • Output measurement type (e.g., as output of a processing method):

[0100] οUE position;

[0101] Time of flight (TOF): The time it takes for the UE to travel through the air between the TRP;

[0102] o Line-of-sight indicator: Confidence level of the link between TRP and UE for line-of-sight;

[0103] ο Angle information: such as angle of arrival, angle of departure; or

[0104] Reference signal time difference (RSTD): The relative time difference between two TRPs.

[0105] The conditions for applicable scenarios may include at least one of the following:

[0106] • Physical cell identification (PCI): Through PCI, the processing methods or functions are only applicable to specific scenarios, such as physical cells;

[0107] • Cell Global Identity (e.g., NR Cell Global Identity (NGCI)); or

[0108] • Scene identifier (ID). This can also be called the implementation ID / classification ID, which can implicitly indicate some implementation of the NW or UE. For example, it can refer to a specific NW antenna height, NW antenna layout, NW antenna radiation pattern, or NW antenna downtilt angle. Antenna information can be private information that is not shared, so it can be virtualized through this ID.

[0109] Conditions can be applied to an area that includes at least a region ID. For example, it can refer to a specific geographical region. A cell can be divided into multiple regions, and each region can be identified by a region ID. In another example, indoor and outdoor areas can have different region IDs. Specific processing methods may require certain regions. Each region can be defined by each ID.

[0110] The criteria for an applicable dataset can include at least a dataset ID. This can refer to a sample of data used to initialize or train a processing method or function. Specifically, an AI / ML processing method is a data-driven approach that may only be applicable to data with a similar distribution or correlation to the data used to train the processing method. In other words, the processing method can be trained on data and then only applied to new environments with data states similar to those used for training.

[0111] The types have been discussed above. An example embodiment of type 2 is described below. In some embodiments, a function is only available, used, or activated after the processing method associated with a specific function has been downloaded or delivered from another entity. In some embodiments, the UE reports to the NW that the function can be used or activated (or available). For example, the processing method associated with a specific function may be downloaded after a UE capability report is submitted. In this case, the function is available after the UE capability report is submitted. In some embodiments, the NW requests the UE to download the processing method associated with a specific function. Furthermore, the request signaling may include a processing method / model ID that is indicated or linked to the processing method the NW expects the UE to download. Additionally, the UE may send confirmation information to the network that the corresponding processing method / model has been downloaded / deployed.

[0112] In some embodiments, the UE requests the NW to transmit a processing method associated with a function. In some embodiments, the request signaling may include a processing method / model ID that indicates or links to the processing method the UE expects the NW to transmit. In some embodiments, the UE may indicate to the NW the processing method / model structure it supports. Based on this indication, the NW may only transmit processing methods with the same or similar processing method structure as indicated by the UE. Furthermore, the NW may only transmit the corresponding processing method parameters to the UE. In some embodiments, the UE may indicate the processing method description language it supports (e.g., PyTorch or TensorFlow).

[0113] In some embodiments, the UE may indicate storage information supported by the UE and / or computational complexity information regarding the processing method, which may include storage information that can be related to the number of processing method parameters in the processing method and / or the number of bits used to quantize the processing method parameters. Alternatively, the computational complexity information may be related to the computational complexity of a single operation of the processing method (e.g., the number of floating-point operations).

[0114] Figure 7 This example illustrates a report from a User Equipment (UE) to the network regarding conditions for supporting a feature. In this example, the UE reports to the NW the conditions under which it supports a feature. As mentioned above, the reported content can be referred to as feature information. Figure 7 On the left, the UE reports multiple conditions (e.g., applicable parameters, scene, region, or dataset as described above). Figure 7In the middle of the feature information report, following the reporting of feature information, there may be a report with supported functions. This report may include conditions and / or selected conditions associated with the function. In some embodiments, the UE reports to the NW in the UE capability report the conditions that the UE supports for a feature. In some embodiments, these conditions are used to indicate the applicable parameters, scenarios, regions, and / or datasets when deploying or implementing a function on the UE. Each of the multiple conditions includes at least one candidate value. In some embodiments, the function may be reported by the UE or configured by the NW after reporting feature information. In some embodiments, each function may include multiple conditions (or combinations of conditions) used to indicate the applicability information of the function, including the applicable parameters, scenarios, regions, and / or datasets of the function, which should be based on the conditions included in the feature information. Each of the multiple conditions for the function may include at least one candidate value for that condition. For example, in the feature information report, one condition is the number of reference signals used for measurement. There are two candidate values: 8 or 16. Therefore, if the condition is indicated in the function, at least one candidate value for that condition should be indicated. In some embodiments, more than one candidate value may be indicated in the function. For example, by indicating multiple candidate values ​​for a condition, the processing method of a function can work in a variety of environments.

[0115] In some embodiments, this functionality includes two types. Also regarding... Figure 6 These types are described. In Type 1, the supported functions do not have processing methods passed from the NW. Instead, the function is available (e.g., ready to be used or activated) after the supported function is reported. This could be when the processing method for the function has already been deployed on the UE. The UE reports the functions it supports and the corresponding conditions associated with those functions. Furthermore, based on the UE's report of conditions, each of the multiple conditions for the function includes at least one candidate value for that condition. In some embodiments, the UE reports the functions it supports after the UE capability report. In some embodiments, the function can be activated after the UE receives signaling from the NW, where the signaling can be RRC, MAC CE, or DCI.

[0116] In Type 2, the functionality supported by the processing method is passed from the NW. Alternatively, the functionality is configured by the network (e.g., the processing method for that functionality is passed from the network). This can be similar to... Figure 6Type 2. The processing method should be transmitted from the network. The network provides applicability information for the function (e.g., a combination of conditions). In some embodiments, the processing method associated with the function is transmitted from the NW. Additionally, the NW provides corresponding conditions associated with the function. Based on the UE's report of the conditions, each of the multiple conditions for the function may include at least one candidate value for that condition. In some embodiments, the UE may report to the network that the UE is unable to implement and / or deploy the function / processing method. For example, when the UE is unable to deploy the processing method transmitted from the NW. In some embodiments, the UE may report that the function may be available (or ready to be used and / or activated) after receiving the processing method.

[0117] In some embodiments, the NW requests the UE to download a processing method associated with a function. The request signaling may include a processing method / model ID that is indicated and / or linked to the processing method the NW expects the UE to download. Furthermore, the NW provides corresponding conditions associated with the function. Based on the UE's report of the conditions, each of a plurality of conditions for the function includes at least one candidate value for that condition.

[0118] In some embodiments, the UE requests the NW to transmit a processing method associated with a function. The UE may provide corresponding conditions associated with the function. Based on the UE's report of conditions, each of a plurality of conditions for the function includes at least one candidate value for that condition. In some embodiments, the request signaling may include a processing method / model identifier (ID) that is indicated and / or linked to the processing method the UE expects the NW to transmit. In some embodiments, the UE may indicate to the NW a processing method structure supported by the UE. The NW may only transmit processing methods having the same or similar processing method structure as indicated by the UE. Additionally, the NW may only transmit the corresponding processing method parameters to the eUE. In some embodiments, the UE may indicate a processing method description language supported by the UE (e.g., PyTorch or TensorFlow).

[0119] In some embodiments, the UE may indicate storage information supported by the UE and computational complexity information regarding the processing method. This information may include storage information relating to the number of processing method parameters and / or the number of bits used to quantize the processing method parameters. This information may also include computational complexity information (e.g., the number of floating-point operations) relating to the computational complexity of a single operation of the processing method.

[0120] Figure 8An example report of a function or processing method / model identifier supporting a feature from a User Equipment (UE) to the Network (NW) is shown. As described above, the content of the report can be referred to as feature information. The UE reports to the NW: for a specific feature, the function or processing method / model identifier (ID) that the UE supports. The processing method may already be stored in the network NW, so the NW has information about the applicability of the corresponding processing method (e.g., conditions). The UE reports to the NW in its UE capability report: for a feature, the function ID or processing method / model ID that the UE supports. In some embodiments, the function or processing method (including conditions (e.g., applicable parameters, scenarios, regions, and / or datasets) and / or processing methods associated with the function) may already be stored / registered / identified at the NW. Each of a plurality of functions or processing methods has been assigned an ID to identify it. The UE may report the function or processing method / model ID to the NW. The NW can then identify the function or processing method by checking the corresponding function or processing method / model ID.

[0121] In some embodiments, the feature information report includes two types. Also regarding... Figure 8These types are described below. In Type 1, the processing method associated with the processing method / model ID has been deployed and / or implemented on the UE. Alternatively, the processing method indicated in the processing method ID is available (e.g., ready to be used / activated). In some embodiments, the function or processing method may be activated after the UE receives signaling from the NW, where the signaling may be RRC, MAC CE, or DCI. For Type 2, the processing method associated with the processing method / model ID has not yet been deployed / implemented on the UE. Alternatively, the processing method indicated in the processing method ID is unavailable (e.g., not yet ready to be used / activated). In some embodiments, the function or processing method may only be available (used or activated) after the processing method associated with the processing method / model ID has been downloaded or delivered from another entity. In some embodiments, the UE reports to the NW that the function or processing method may be available / used / activated. For example, the processing method associated with the processing method ID is downloaded after a UE capability report is submitted. In some embodiments, the NW requests the UE to download the processing model associated with the function or processing method / model ID. In some embodiments, the UE requests the NW to transmit a processing method associated with a function or processing method / model ID. In some embodiments, the request signaling may include a processing method / model ID that is indicated or linked to the processing method the UE expects the NW to transmit. In some embodiments, the UE may indicate to the NW a processing method structure it supports. The NW may only transmit processing methods with the same or similar processing method structure as indicated by the UE. The NW may only transmit the corresponding processing method parameters to the UE based on the processing method structure. In some embodiments, the UE may indicate a processing method description language it supports (e.g., PyTorch or TensorFlow).

[0122] Figure 9 Example function and processing method management is illustrated. As described, functions (e.g., the function may be associated with a processing method) or processing methods are mapped to identifiers (IDs). In some embodiments, the identifier is determined by NW configuration. The function / processing method can be assigned an identifier by the NW. The network can assign an ID, and the UE can use the identifier to perform management reporting or performance monitoring based on the corresponding function / processing method. The ID can be used to switch processing methods. In some embodiments, functions and / or processing methods can be mapped to identifiers. In some embodiments, the identifier can be determined by UE reporting. For example, when the UE reports a function / processing method it supports, the UE can also report the identifier for each function / processing method. Additionally, the identifier can be implicitly determined by the reporting order / sequence of the UE's functions / processing methods.

[0123] In some embodiments, the identifier is unique within a specific feature, a specific group of features, or a use case. In some embodiments, the identifier may span multiple features (or groups of features). For example, the identifier may be unique within an RRC configuration. In some embodiments, the identifier may be associated with a measurement report (e.g., a CSI report or a beamforming report). For example, in a measurement configuration from the network, the network may indicate the function / processing method for obtaining the corresponding measurement report by indicating the corresponding identifier. In another example, the UE may provide feedback via a measurement report and indicate the function / processing method for obtaining the corresponding measurement report by indicating the corresponding identifier.

[0124] In some embodiments, the identifier may be associated with a performance monitoring procedure. For example, due to the generalization nature of a processing method, it may not be able to execute properly in a new environment (if the processing method is not general enough). Therefore, the NW may initiate a performance monitoring procedure for the function / processing method. During this performance monitoring procedure, the UE may need to report the performance status of the function / processing method. The performance status may include some metrics related to the predictive accuracy of the processing method. The corresponding identifier may be associated with the performance monitoring procedure.

[0125] In some embodiments, the identifier is associated with an activation / deactivation command for activating / deactivating a processing method or function. For example, the NW can use the identifier to activate / deactivate a function or processing method. In some embodiments, the UE can send a request to the NW to activate / deactivate a function or processing method by indicating the corresponding identifier. Alternatively, the UE can send an indication to the NW that a function or processing method is unavailable / inapplicable (or not yet ready to be used / activated) by indicating the corresponding identifier. In one embodiment, the activation / deactivation command may be MAC CE or DCI signaling. In some embodiments, the identifier is associated with a selection command for selecting one or more functions or processing methods that can be activated. For example, the NW can use the identifier to select one or more functions or processing methods for activation purposes. In some embodiments, a function / processing method can only be activated if a function / processing method is selected in the selection command. In some embodiments, the selection command may be MAC CE or DCI signaling. In some embodiments, a second identifier is associated with a switching command for switching from one processing method or function to a different processing method or different function. For example, the NW can use the identifier to switch between one function or processing method and another function or processing method. For example, in control signaling, the NW instructs the UE to activate a function or processing method using one identifier and to activate another function or processing method using another identifier. In some embodiments, the handover command may be MAC CE or DCI signaling. In some embodiments, the bit width of the signaling used for activation / deactivation commands, selection commands, or handover commands is fixed or related to the number of identifiers (e.g., the total number of functions and / or processing methods).

[0126] In some embodiments, the NW configures necessary resource settings and / or reporting settings based on conditions associated with corresponding functions or processing methods. Each resource setting may include a configuration of a reference signal list. It can be used for measurement reporting or performance monitoring based on functions or processing methods. Each reporting setting is associated with at least one resource setting (e.g., for channel / interference measurements) and contains one or more parameters for a measurement report. These one or more parameters may include codebook configurations (e.g., codebook subset restrictions, time-domain behavior, frequency granularity of CQI and PMI, measurement restriction configurations), and CSI-related quantities to be reported by the UE, such as Layer Indicator (LI), L1-RSRP, L1-SINR, CRI, and SSB Resource Indicator (SSBRI). Functions or processing methods can be associated with reporting settings by indicating corresponding identifiers.

[0127] The systems and processes described above can be encoded in a signal-carrying medium, a computer-readable medium (e.g., memory), programmed within a device (e.g., one or more integrated circuits, one or more processors), or processed by a controller or computer. The data can be analyzed in a computer system and used to generate a spectrometer. If the method is executed by software, the software can reside in a memory that communicates with the transmitter, such as a storage device, synchronizer, communication interface, or non-volatile or volatile memory, or be connected via an interface to such a storage device, synchronizer, communication interface, or non-volatile or volatile memory. A circuit or electronic device is designed to transmit data to another location. The memory can include an ordered list of executable instructions for implementing logical functions. The described logical functions or any system elements can be implemented via optical circuitry, digital circuitry, source code, analog circuitry, or analog sources (e.g., analog electrical, audio, or video signals or combinations thereof). The software can be implemented in any computer-readable or signal-carrying medium for use by or connection to an instruction-executable system, apparatus, or device. Such a system may include a computer-based system, a processor-integrated system, or another system that can selectively obtain instructions from an instruction-executable system, apparatus, or device that can also execute instructions.

[0128] "Computer-readable medium," "machine-readable medium," "signal propagation medium," and / or "signal-carrying medium" can include any device that includes, stores, transmits, propagates, or transmits software for use by, or in conjunction with, an instruction-executable system, apparatus, or device. Machine-readable media may optionally be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, devices, or propagation media. A non-exhaustive list of examples of machine-readable media would include: an electrically connected "electronic device" with one or more wires, a portable magnetic disk or optical disk, volatile memory (e.g., random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory), or optical fiber. Since software can be electrically stored as an image or other format (e.g., by optical scanning) and then compiled, and / or interpreted or otherwise processed, machine-readable media can also include tangible media on which software is printed. The processed medium can then be stored in computer and / or machine memory.

[0129] The illustrations of the embodiments described herein are intended to provide a general understanding of the structure of various embodiments. The illustrations are not intended to be a complete description of all elements and features of apparatuses and systems utilizing the structures or methods described herein. Many other embodiments will be apparent to those skilled in the art upon review of this disclosure. Other embodiments may be utilized and derived from this disclosure, allowing for structural and logical substitutions and changes without departing from the scope of this disclosure. Furthermore, the illustrations are representative only and may not be drawn to scale. Some scales within the illustrations may be exaggerated, while others may be minimized. Therefore, this disclosure and the accompanying drawings should be considered illustrative rather than restrictive.

[0130] One or more embodiments of this disclosure may be referred to herein, individually and / or collectively, by the term "invention," merely for convenience and not intended to voluntarily limit the scope of this application to any particular invention or inventive concept. Furthermore, although specific embodiments have been shown and described herein, it should be understood that any subsequent arrangement designed to achieve the same or similar purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all subsequent adaptations or variations of the various embodiments. Combinations of the above embodiments and other embodiments not specifically described herein will be apparent to those skilled in the art upon review of the specification.

[0131] The phrase "coupled with" is defined as meaning a direct connection or an indirect connection via one or more intermediate components. Such intermediate components may include both hardware-based and software-based components. The arrangement and type of components may be varied without departing from the spirit or scope of the claims described herein. Additional, different, or fewer components may be provided.

[0132] The subject matter disclosed above should be considered illustrative rather than restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other embodiments falling within the true spirit and scope of the invention. Therefore, to the fullest extent permitted by law, the scope of the invention will be determined by the broadest permissible interpretation of the claims and their equivalents, and should not be limited or restricted by the foregoing detailed description. While various embodiments of the invention have been described, it will be apparent to those skilled in the art that many more embodiments and implementations are possible within the scope of the invention. Therefore, the invention is not limited except as provided in the appended claims and their equivalents.

Claims

1. A wireless communication method, comprising: The feature information of the features reported by the wireless communication device in the User Equipment (UE) Capability Report.

2. The method according to claim 1, wherein, The feature information includes the functionalities supported for the feature.

3. The method according to claim 2, wherein, The supported functions are associated with multiple conditions that have applicability information for the supported functions.

4. The method according to claim 3, wherein, The multiple conditions indicate at least one of the parameter information, scene information, area information, or data information of the function.

5. The method according to claim 3, wherein, The multiple conditions include at least one of the following: candidate values ​​for the parameter; a classification identifier; a region identifier; or a dataset identifier.

6. The method according to claim 2, wherein, After the reported feature information is provided, the supported functionality becomes available.

7. The method according to claim 2, further comprising: The wireless communication device receives a processing method corresponding to the supported functions.

8. The method according to claim 7, wherein, After receiving the processing method, the supported functions are available.

9. The method according to claim 1, wherein, The feature information includes multiple conditions for the feature.

10. The method according to claim 9, wherein, Each of the multiple conditions includes at least one candidate value.

11. The method according to claim 1, further comprising: The feature information is reported by the wireless communication device, and the feature information includes multiple conditions.

12. The method of claim 11, further comprising: After reporting the feature information, the wireless communication device reports a first function supported for the feature.

13. The method according to claim 11, wherein, Based on the aforementioned conditions, the supported first function is associated with the applicability information of the first function.

14. The method according to claim 11, wherein, After the first supported feature is reported, the first supported feature becomes available.

15. The method of claim 9, further comprising: The wireless communication device receives a configuration for a second function, wherein the configuration includes applicability information for the second function based on the plurality of conditions.

16. The method of claim 14, further comprising: Receive the processing method associated with the second function.

17. The method according to claim 15, wherein, The second function becomes available after the processing method is received.

18. The method according to claim 1, wherein, The feature information includes a first identifier associated with the processing method.

19. The method of claim 17, wherein, The processing method is available after the reported feature information is provided.

20. The method of claim 17, further comprising: The processing method corresponding to the first identifier is received by the wireless communication device.

21. The method according to claim 19, wherein, The processing method becomes available after it is received.

22. The method according to claim 1, further comprising: The wireless communication device receives a second identifier associated with the processing method or function.

23. The method according to claim 22, wherein, The first identifier or the second identifier is determined based on the feature information.

24. The method according to claim 22, wherein, The first identifier or the second identifier is specific to the feature.

25. The method according to claim 22, wherein, The second identifier is associated with an activation command used to activate the processing method or the function.

26. The method according to claim 22, wherein, The second identifier is associated with a switching command for switching from the processing method or the function to a different processing method or a different function.

27. The method according to claim 21, wherein, The second identifier is associated with a selection command for choosing from other processing methods or other supporting functions that can be activated.

28. The method according to claim 21, wherein, The second identifier is associated with the reporting settings.

29. A wireless communication device, comprising a processor and a memory, wherein, The processor is configured to read code from the memory and implement the method according to any one of claims 1 to 28.

30. A computer program product comprising a computer-readable program medium having code stored on the computer-readable program medium, the code, when executed by a processor, causing the processor to perform the method according to any one of claims 1 to 28.

Images