Method and apparatus used in node for wireless communications

Abstract

Disclosed in the present application are a method and apparatus used in a node for wireless communications. The method comprises: a node receiving a first request; and as a response to the reception of the first request, generating a first result by means of a first model, wherein the first model is used for performing at least one of training or inference, the first result is a training result or an inference result, an identifier of the first model is a first identifier, the first identifier is associated with a plurality of sub-identifiers, the plurality of sub-identifiers respectively indicate a plurality of pieces of data, and the plurality of pieces of data comprise at least one of channel quality information data, codebook data and positioning assistance information data. The present application optimizes the design of a model identifier in a system using artificial intelligence and machine learning, and matching between the model identifier and data, thereby achieving flexible data sharing, and also increasing the speed of training and inference and optimizing the overall performance of the system.

Description

A method and apparatus for use in a node for wireless communication Technical Field

[0001] This application relates to transmission methods and apparatus in wireless communication systems, and more particularly to schemes and apparatus for model configuration in wireless communication systems. Background Technology

[0002] The application scenarios of future wireless communication systems are becoming increasingly diversified, and different application scenarios place different performance requirements on the system. To meet the diverse performance needs of various application scenarios, the 3GPP (3rd Generation Partner Project) RAN (Radio Access Network) #72 plenary meeting decided to research New Radio (NR) (or 5G). The 3GPP RAN #75 plenary meeting approved the WI (Work Item) for NR, initiating standardization work for NR. In NR R (release) 18, research on AI (Artificial Intelligence) / ML (Machine Learning) technologies was initiated to explore their impact on system performance and system design. Compared to traditional processing methods, AI / ML has characteristics such as being training-based and requiring deployment. Summary of the Invention

[0003] The applicant's research revealed that, with the introduction of AI / ML capabilities, existing data in current systems can be applied to AI / ML-enabled terminals or network devices to achieve training and inference functions. However, existing systems contain various types of data tailored to different application scenarios. How to integrate this data with AI / ML is a problem that needs to be researched and solved.

[0004] To address the aforementioned issues, this application discloses a solution. It should be noted that while many embodiments of this application are geared towards AI / ML, this application is also applicable to other solutions, such as traditional non-AI / ML-based solutions. Furthermore, employing a unified solution across different scenarios (including but not limited to AI / ML-based solutions) helps reduce hardware complexity and cost. Where there is no conflict, the embodiments and features in the first node of this application can be applied to the second node, and vice versa. Where there is no conflict, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0005] Specifically, the interpretation of terms, nouns, functions, and variables in this application (unless otherwise specified) can be found in the definitions of the TS38 and TS37 series of 3GPP (3rd Generation Partnership Project) Technical Specifications (TS). Where necessary, reference can be made to TS38.211, TS38.212, TS38.213, TS38.214, TS38.215, TS38.300, TS38.304, TS38.305, TS38.321, TS38.331, TS37.355, TS38.423, TS28.105, TR28.908, and TS38.843 in the 3GPP technical specifications to aid in understanding this application.

[0006] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS38 series.

[0007] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS37 series.

[0008] As an example, the interpretation of the terms in this application is based on the definitions in the 3GPP specification protocol TS40 series.

[0009] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS39 series.

[0010] As an example, the interpretation of the terms in this application is based on the definitions in the 3GPP specification protocol TS28 series.

[0011] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TR28 series.

[0012] As an example, the interpretation of the terms used in this application is based on the definitions in 3GPP specification protocol Rel-17.

[0013] As an example, the interpretation of the terms used in this application is based on the definitions in 3GPP specification protocol Rel-18.

[0014] As an example, the interpretation of the terms used in this application is based on the definitions in 3GPP specification protocol Rel-19.

[0015] As an example, the interpretation of the terms used in this application is based on the definitions in 3GPP specification protocol Rel-20.

[0016] This application discloses a method used in a first node of wireless communication, comprising:

[0017] Receive the first request;

[0018] In response to receiving the first request, a first result is generated using the first model;

[0019] Wherein, the first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

[0020] As an example, the problem this application aims to solve includes the problem of matching models and data in AI / ML scenarios.

[0021] As an example, the features to be addressed by this application include: classifying data according to type, enabling different types of data to be used by the same model, thereby improving the performance of the model.

[0022] As an example, the features of the above method include: configuring model identifiers and sub-identifiers to more flexibly associate the adopted data.

[0023] According to one aspect of this application, the above method is characterized in that at least one of the plurality of sub-identifiers is associated with a cell set, any cell in the cell set being able to use the data indicated by the at least one sub-identifier.

[0024] As an example, the features of the above method include: the data indicated by the sub-identifier can be shared between different cells, thereby improving data utilization and model accuracy.

[0025] According to one aspect of this application, the above method is characterized in that at least one of the plurality of sub-identifiers is associated with a second identifier, the second identifier identifying a second model, the second model being for at least one of training or inference, and the second model being different from the first model.

[0026] As an example, the features of the above method include: the model identifier used to identify the model and the sub-identifier used to identify the data are configured independently to ensure maximum configuration flexibility.

[0027] According to one aspect of this application, the above method is characterized in that the training of the first model and the training of any one of the multiple data corresponding to the multiple sub-identifiers are independent.

[0028] As an example, the features of the above method include: separating the training of data from the training of the model to ensure accuracy and independence.

[0029] According to one aspect of this application, the above method is characterized in that the channel quality information data includes CSI (Channel State Information).

[0030] As an example, the features of the above method include using the physical layer's CSI as part of the reference data for model training / prediction to improve performance.

[0031] According to one aspect of this application, the above method is characterized in that the codebook data is a statistical result of the codebook used by the first node within a given time window.

[0032] As an example, the features of the above method include using physical layer codebook information as part of the reference data for model training / prediction to improve performance.

[0033] According to one aspect of this application, the above method is characterized in that the location assistance information data includes at least one of positioning data or mobility data.

[0034] As an example, the features of the above method include: using high-level information as part of the reference data for model training / prediction to improve performance.

[0035] As an example, the features of the above method include: a model is trained / predicted simultaneously using physical layer data and high-level data to further improve the overall performance of the model.

[0036] According to one aspect of this application, the above method is characterized by comprising:

[0037] Send the first result.

[0038] As an example, the features of the above method include: sending the first result to the sender of the first request to improve system performance using an AI / ML approach.

[0039] This application discloses a method for use in a second node in wireless communication, comprising:

[0040] Send the first request;

[0041] Wherein, the recipient of the first request, as a response to receiving the first request, generates a first result through a first model; the first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

[0042] According to one aspect of this application, the above method is characterized in that at least one of the plurality of sub-identifiers is associated with a cell set, any cell in the cell set being able to use the data indicated by the at least one sub-identifier.

[0043] According to one aspect of this application, the above method is characterized in that at least one of the plurality of sub-identifiers is associated with a second identifier, the second identifier identifying a second model, the second model being for at least one of training or inference, and the second model being different from the first model.

[0044] According to one aspect of this application, the above method is characterized in that the training of the first model and the training of any one of the multiple data corresponding to the multiple sub-identifiers are independent.

[0045] According to one aspect of this application, the above method is characterized in that the channel quality information data includes CSI.

[0046] According to one aspect of this application, the above method is characterized in that the codebook data is a statistical result of the codebook used by the first node within a given time window.

[0047] According to one aspect of this application, the above method is characterized in that the location assistance information data includes at least one of positioning data or mobility data.

[0048] According to one aspect of this application, the above method is characterized by comprising:

[0049] Receive the first result.

[0050] This application discloses a device for use as a first node in wireless communication, comprising:

[0051] The first receiver receives the first request; in response to receiving the first request, it generates the first result through the first model.

[0052] Wherein, the first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

[0053] This application discloses a device for a second node used in wireless communication, comprising:

[0054] The second transmitter sends the first request;

[0055] Wherein, the recipient of the first request, as a response to receiving the first request, generates a first result through a first model; the first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

[0056] As an example, compared with conventional solutions, this application has the following advantages, but is not limited to:

[0057] - Configure an AI / ML model with one identifier and multiple sub-identifiers. These sub-identifiers are associated with various types of data, thereby clarifying the relationship between the model and the data, so that a model can use multiple types of data as references.

[0058] - Data can be shared among multiple small areas to improve data utilization efficiency and thus enhance overall system performance;

[0059] - Data training and model training are performed independently to ensure performance;

[0060] - A model's data comes from multiple different layers to further improve the model's performance. Attached Figure Description

[0061] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0062] Figure 1 illustrates a flowchart of the first node transmission according to an embodiment of this application;

[0063] Figure 2 shows a schematic diagram of a network architecture according to an embodiment of this application;

[0064] Figure 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application;

[0065] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to an embodiment of this application;

[0066] Figure 5 shows a first flowchart of the transmission between a first node and a second node according to an embodiment of this application;

[0067] Figure 6 shows a schematic diagram of a first model according to an embodiment of this application;

[0068] Figure 7 shows a schematic diagram of a second model according to an embodiment of this application;

[0069] Figure 8 shows a schematic diagram of the deployment of a first model according to an embodiment of this application;

[0070] Figure 9 shows a schematic diagram of the structure of ML / AI according to an embodiment of this application;

[0071] Figure 10 shows a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application;

[0072] Figure 11 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application;

[0073] Figure 12 shows a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application;

[0074] Figure 13 shows a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application. Detailed Implementation

[0075] The technical solution of this application will be further described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0076] Example 1

[0077] Example 1 illustrates a flowchart of the first node transmission according to an embodiment of this application, as shown in Figure 1. In Figure 1, each block represents a step. In particular, the order of the steps in the blocks does not represent a specific temporal relationship between the steps.

[0078] The first node receives the first request in step 101; in step 102, as a response to receiving the first request, it generates the first result through the first model.

[0079] In Example 1, the first model is used for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

[0080] As one example, the first request includes a training request.

[0081] As one example, the first request includes a reasoning request.

[0082] As an example, the first request is a request for ML.

[0083] As an example, the first request is a request for AI.

[0084] As an example, the first node generates the first result through the first model.

[0085] As a sub-implementation of this embodiment, the first node includes the first model.

[0086] As an example, the first node generates the first result through the first model located in the network.

[0087] As a sub-implementation of this embodiment, the first node and the first model are connected via a network.

[0088] As a sub-example of this embodiment, the first model is located in the cloud.

[0089] As an example, the first model includes an AI model.

[0090] As an example, the first model includes an ML model.

[0091] As an example, the first model is for AI.

[0092] As an example, the first model is for ML.

[0093] As an example, the first model includes an ML entity.

[0094] As an example, the first model includes an MnS Producer.

[0095] As an example, the first request triggers the first model.

[0096] As an example, the first result includes the training result.

[0097] As an example, the first result includes the prediction result.

[0098] As an example, the first model is used for training.

[0099] As an example, the first model is used for reasoning.

[0100] As an example, the first model is used for training and inference.

[0101] As an example, the first identifier is a non-negative integer.

[0102] As an example, the first identifier is a positive integer.

[0103] As an example, the first identifier is an Identity.

[0104] As an example, the first identifier is an Identifier.

[0105] As an example, the first identifier is an index.

[0106] As one embodiment, the meaning of the first identifier being associated with multiple sub-identifiers includes: the signaling indicating the first identifier also indicating the multiple sub-identifiers.

[0107] As an example, the meaning of the first identifier being associated with multiple sub-identifiers includes: the first identifier and the multiple sub-identifiers are configured with the same signaling.

[0108] As an example, the meaning of the first identifier being associated with multiple sub-identifiers includes: the first identifier includes the multiple sub-identifiers.

[0109] As an example, any one of the plurality of sub-identifiers is a non-negative integer.

[0110] As an example, any one of the plurality of sub-identifiers is a positive integer.

[0111] As one example, the plurality of sub-identifiers respectively indicate the plurality of data.

[0112] As one example, the multiple data points correspond to multiple different types of data.

[0113] As one example, the multiple data points correspond to multiple databases.

[0114] As an example, the first request indicates the first identifier.

[0115] As an example, the first request indicates the plurality of sub-identifiers associated with the first identifier.

[0116] As an example, the first request indicates at least one of the plurality of sub-identifiers associated with the first identifier.

[0117] As an example, the input to the first model includes the plurality of data.

[0118] As an example, the input to the first model includes at least one of the plurality of data.

[0119] As an example, the generation of the first result through the first model depends on the plurality of data.

[0120] As an example, the generation of the first result through the first model depends on at least one of the plurality of data.

[0121] As an example, a message is received indicating at least one of the plurality of sub-identifiers; the input of the first model includes the data indicated by the at least one sub-identifier.

[0122] As an example, the first node determines at least one sub-identifier from the plurality of sub-identifiers; the input of the first model includes the data indicated by the at least one sub-identifier.

[0123] Example 2

[0124] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in Figure 2.

[0125] Figure 2 illustrates network architecture 200. Network architecture 200 is the network architecture for LTE (Long-Term Evolution), LTE-A (Long-Term Evolution Advanced), 5G systems, 5G-Advanced, and future 6G systems. The network architecture for LTE, LTE-A, 5G systems, 5G-Advanced, and future 6G systems is referred to as EPS (Evolved Packet System). The 5G NR or LTE network architecture may be referred to as 5GS (5G System) / EPS or some other suitable terminology; the 6G network architecture may be referred to as 6GS (6G System) / EPS or some other suitable terminology. Network architecture 200 may include one or more UEs 201, RAN (Next Generation Radio Access Network) 202, core network 210, HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet services 230. Network architecture 200 can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown in Figure 2, network architecture 200 provides packet-switched services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks providing circuit-switched services. RAN 202 includes node B 203 and other nodes 204. Node 203 provides user and control plane protocol termination toward UE 201. Node 203 can be connected to other nodes 204 via an Xn interface (e.g., backhaul). Node 203 may also be referred to as a base station, base transceiver station, wireless base station, wireless transceiver, transceiver function, Basic Service Set (BSS), Extended Service Set (ESS), TRP (Transmitter Receiver Point), or some other suitable term. Node 203 provides UE 201 with an access point to core network 210; core network 210 is 5GC (5G Core Network) / EPC (Evolved Packet Core), or core network 210 is 6GC.Examples of UE 201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, GPS devices, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband physical network devices, machine-type communication devices, land vehicles, automobiles, wearable devices, or any other similar functional devices. Those skilled in the art may also refer to UE 201 as a mobile station, subscriber station, mobile unit, subscriber unit, radio unit, remote unit, mobile device, radio communication device, remote device, mobile subscriber station, access terminal, mobile terminal, radio terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term. Node 203 is connected to core network 210 via an S1 / NG interface. The core network 210 includes the MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MMEs / AMFs / SMFs 214, the S-GW (Service Gateway) / UPF (User Plane Function) 212, and the P-GW (Packet Data Network Gateway) / UPF 213. The MME / AMF / SMF 211 is the control node that handles signaling between the UE 201 and the 5G-CN / EPC 210. Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through the S-GW / UPF 212, which is itself connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation and other functions. The P-GW / UPF 213 connects to Internet service 230. Internet service 230 includes carrier-compliant Internet protocol services, specifically including the Internet, intranet, IMS (IP Multimedia Subsystem), and packet switching services.

[0126] As an example, the first node in this application includes the UE 201.

[0127] As an example, the second node in this application includes the node 203.

[0128] As an example, node 203 is a macrocell base station.

[0129] As an example, node 203 is a microcell base station.

[0130] As an example, node 203 is a pico cell base station.

[0131] As an example, node 203 is a femtocell.

[0132] As an example, node 203 is a base station device that supports large latency differences.

[0133] As one example, node 203 is a flight platform device.

[0134] As one example, node 203 is a satellite device.

[0135] As one embodiment, the node 203 is a test device (e.g., a transceiver device simulating part of the functions of a base station, a signaling tester).

[0136] As an example, the UE 201 includes a mobile phone.

[0137] As an example, the UE 201 is a vehicle including a car.

[0138] As an example, the wireless link from the UE 201 to the node 203 is an uplink, which is used to perform uplink transmissions.

[0139] As an example, the radio link from node 203 to UE 201 is a downlink, which is used to perform downlink transmissions.

[0140] As one embodiment, the wireless link between the node 203 and the UE 201 includes a cellular link.

[0141] As an example, the node 203 and the UE 201 are connected via the Uu air interface.

[0142] As an example, the sender of the first request includes the node 203.

[0143] As an example, the recipient of the first request includes the UE 201.

[0144] As an example, the sender of the first result includes the UE 201.

[0145] As an example, the recipient of the first result includes the node 203.

[0146] As an example, the first model is maintained in the UE 201.

[0147] As an example, the first model is maintained at node 203.

[0148] As an example, the first model is maintained in both the UE 201 and the node 203.

[0149] As an example, the sender and receiver of the first request are both located in node 203.

[0150] As an example, both the sender and receiver of the first request are located in the UE 201.

[0151] As an example, the UE 201 supports AI.

[0152] As an example, the UE 201 supports ML.

[0153] As an example, the gNB 203 supports AI.

[0154] As an example, the gNB 203 supports ML.

[0155] As an example, the UE 201 supports a 5G system.

[0156] As one example, the node 203 supports a 5G system.

[0157] As an example, the UE 201 supports at least a 6G system.

[0158] As an example, the node 203 supports at least a 6G system.

[0159] Example 3

[0160] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application, as shown in Figure 3.

[0161] Figure 3 is a schematic diagram illustrating an embodiment of the wireless protocol architecture for the user plane 350 and the control plane 300. Figure 3 shows the wireless protocol architecture for the control plane 300 between a first communication node device (UE or RSU in V2X, onboard equipment or onboard communication module) and a second node device (gNB, RSU in UE or V2X, onboard equipment or onboard communication module), or between two UEs, using three layers: Layer 1 (L1), Layer 2 (L2), and Layer 3 (L3). L1 is the lowest layer and implements various PHY (Physical layer) signal processing functions. L1 will be referred to herein as PHY 301. L2 305 is above PHY 301 and is responsible for the link between the first node device and the second node device, or between two UEs, through PHY 301. L2 305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the second node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. It also provides security through encrypted data packets and supports cross-cell mobility between the second communication node devices and the first communication node device. The RLC sublayer 303 provides upper-layer packet segmentation and reassembly, retransmission of lost packets, and packet reordering to compensate for out-of-order reception due to HARQ (Hybrid Automatic Repeat reQuest). The MAC sublayer 302 provides multiplexing between logical and transport channels. It is also responsible for allocating various radio resources (e.g., resource blocks) within a cell between the first communication node devices. The MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control) sublayer 306 in L3 of the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and using RRC signaling between the second communication node device and the first communication node device to configure the lower layer.The wireless protocol architecture of user plane 350 includes Layer 1 (L1) and Layer 2 (L2). The wireless protocol architecture for the first and second communication node devices in user plane 350 is largely the same as the corresponding layers and sublayers in control plane 300 for Physical Layer 351, PDCP sublayer 354 in L2 355, RLC sublayer 353 in L2 355, and MAC sublayer 352 in L2 355. However, PDCP sublayer 354 also provides header compression for upper-layer packets to reduce wireless transmission overhead. L2 355 in user plane 350 also includes SDAP (Service Data Adaptation Protocol) sublayer 356. SDAP sublayer 356 is responsible for mapping between QoS (Quality of Service) streams and Data Radio Bearers (DRBs) to support service diversity. Although not illustrated, the first communication node device may have several upper layers above L2355, including a network layer (e.g., IP (Internet Protocol) layer) terminating at the P-GW on the network side and an application layer terminating at the other end of the connection (e.g., remote UE, server, etc.).

[0162] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node in this application.

[0163] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node in this application.

[0164] As an example, the first request is generated in RRC 306.

[0165] As an example, the first result is generated in RRC 306.

[0166] As an example, the first request is generated at MAC 302 or MAC 352.

[0167] As an example, the first result is generated in MAC 302 or MAC 352.

[0168] As an example, the first request is generated in PHY 301 or PHY 351.

[0169] As an example, the first result is generated in the PHY 301 or PHY 351.

[0170] As an example, the higher layer mentioned in this application refers to the layer above the physical layer.

[0171] As an example, the higher layer described in this application includes the MAC layer.

[0172] As an example, the higher layer described in this application includes the RRC layer.

[0173] Example 4

[0174] Example 4 illustrates a schematic diagram of a first communication device and a second communication device according to an embodiment of this application, as shown in Figure 4. Figure 4 is a block diagram of a first communication device 410 and a second communication device 450 communicating with each other in an access network.

[0175] The first communication device 410 includes a controller / processor 475, a memory 476, a receiver processor 470, a transmitter processor 416, a multi-antenna receiver processor 472, a multi-antenna transmitter processor 471, a transmitter / receiver 418, and an antenna 420.

[0176] The second communication device 450 includes a controller / processor 459, a memory 460, a data source 467, a transmitting processor 468, a receiving processor 456, a multi-antenna transmitting processor 457, a multi-antenna receiving processor 458, a transmitter / receiver 454, and an antenna 452.

[0177] In the transmission from the first communication device 410 to the second communication device 450, at the first communication device 410, upper-layer data packets from the core network are provided to the controller / processor 475. The controller / processor 475 implements L2 functionality. In the DL, the controller / processor 475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the second communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for HARQ operation, retransmission of lost packets, and signaling to the second communication device 450. The transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for L1 (i.e., the physical layer). Transmit processor 416 performs encoding and interleaving to facilitate forward error correction (FEC) at the second communication device 450, and mapping of signal clusters based on various modulation schemes (e.g., Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK), M-PSK, and M-Quadrature Amplitude Modulation (M-QAM)). Multi-antenna transmit processor 471 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, generating one or more parallel streams. The transmit processor 416 then maps each parallel stream to a subcarrier, multiplexes the modulated symbols with a reference signal (e.g., a pilot) in the time and / or frequency domains, and then uses an inverse fast fourier transform (IFFT) to generate a physical channel carrying the time-domain multicarrier symbol stream. The multi-antenna transmit processor 471 then performs transmit analog precoding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 418 converts the baseband multicarrier symbol stream provided by the multi-antenna transmit processor 471 into an RF stream, which is then provided to a different antenna 420.

[0178] In the transmission from the first communication device 410 to the second communication device 450, at the second communication device 450, each receiver 454 receives a signal through its corresponding antenna 452. Each receiver 454 recovers the information modulated onto the radio frequency carrier and converts the radio frequency stream into a baseband multicarrier symbol stream, which is then provided to the receiver processor 456. The receiver processor 456 and the multi-antenna receiver processor 458 implement various L1 signal processing functions. The multi-antenna receiver processor 458 performs receive analog precoding / beamforming operations on the baseband multicarrier symbol stream from the receiver 454. The receiver processor 456 uses a Fast Fourier Transform (FFT) to convert the baseband multicarrier symbol stream after the receive analog precoding / beamforming operations from the time domain to the frequency domain. In the frequency domain, the physical layer data signal and the reference signal are demultiplexed by the receiver processor 456, where the reference signal is used for channel estimation, and the data signal is recovered in the multi-antenna receiver processor 458 after multi-antenna detection to recover any parallel stream destined for the second communication device 450. Symbols on each parallel stream are demodulated and recovered in the receive processor 456, generating soft decisions. The receive processor 456 then decodes and deinterleaves the soft decisions to recover the upper-layer data and control signals transmitted by the first communication device 410 over the physical channel. The upper-layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements L2 functionality. The controller / processor 459 may be associated with a memory 460 storing program code and data. The memory 460 may be referred to as computer-readable media. In the DL, the controller / processor 459 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover upper-layer packets from the core network. The upper-layer packets are then provided to all protocol layers above L2. Various control signals may also be provided to L3 for L3 processing. The controller / processor 459 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0179] In the transmission from the second communication device 450 to the first communication device 410, at the second communication device 450, a data source 467 is used to provide upper-layer data packets to the controller / processor 459. The data source 467 represents all protocol layers above L2. Similar to the transmission functions at the first communication device 410 described in the DL, the controller / processor 459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between logical and transport channels based on the radio resource allocation of the first communication device 410, implementing L2 functions for the user plane and control plane. The controller / processor 459 is also responsible for HARQ operations, retransmission of lost packets, and signaling to the first communication device 410. Transmit processor 468 performs modulation mapping and channel coding processing, while multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming processing. Subsequently, transmit processor 468 modulates the generated parallel stream into a multi-carrier / single-carrier symbol stream. After analog precoding / beamforming operations in multi-antenna transmit processor 457, the stream is provided to different antennas 452 via transmitter 454. Each transmitter 454 first converts the baseband symbol stream provided by multi-antenna transmit processor 457 into a radio frequency symbol stream before providing it to antenna 452.

[0180] In the transmission from the second communication device 450 to the first communication device 410, the function at the first communication device 410 is similar to the receiving function at the second communication device 450 described in the transmission from the first communication device 410 to the second communication device 450. Each receiver 418 receives radio frequency signals through its corresponding antenna 420, converts the received radio frequency signals into baseband signals, and provides the baseband signals to the multi-antenna receiving processor 472 and the receiving processor 470. The receiving processor 470 and the multi-antenna receiving processor 472 jointly implement the L1 function. The controller / processor 475 implements the L2 function. The controller / processor 475 may be associated with a memory 476 storing program code and data. The memory 476 may be referred to as computer-readable media. The controller / processor 475 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover upper-layer data packets from the second communication device 450. The upper-layer data packets from the controller / processor 475 may be provided to the core network. The controller / processor 475 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0181] As one embodiment, the second communication device 450 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The second communication device 450 receives at least a first request; and in response to receiving the first request, generates a first result through a first model; the first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with a plurality of sub-identifiers, the plurality of sub-identifiers respectively indicating a plurality of data; the plurality of data includes at least one of channel quality information data, codebook data, and location assistance information data.

[0182] As one embodiment, the second communication device 450 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: receiving a first request; and, in response to receiving the first request, generating a first result through a first model.

[0183] As one embodiment, the first communication device 410 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The first communication device 410 at least sends a first request; the recipient of the first request, in response to receiving the first request, generates a first result through a first model; the first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, the multiple sub-identifiers respectively indicating multiple data; the multiple data includes at least one of channel quality information data, codebook data, and location assistance information data.

[0184] As one embodiment, the first communication device 410 includes: a memory storing a computer-readable instruction program that produces an action when executed by at least one processor, the action including: sending a first request.

[0185] As an example, the first node in this application includes the second communication device 450.

[0186] As an example, the second node in this application includes the first communication device 410.

[0187] As an example, at least one of {the antenna 420, the transmitter 418, the transmitter processor 416, the multi-antenna transmitter processor 471, the controller / processor 475, and the memory 476} is used to send a first request; at least one of {the antenna 452, the receiver 454, the receiver processor 456, the multi-antenna receiver processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first request.

[0188] As an example, at least one of {the antenna 420, the transmitter 418, the transmission processor 416, the multi-antenna transmission processor 471, the controller / processor 475, and the memory 476} is used to transmit the first result; at least one of {the antenna 452, the receiver 454, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first result.

[0189] Example 5

[0190] Example 5 illustrates a first flowchart of transmission between a first node and a second node according to an embodiment of this application, as shown in Figure 5. In Figure 5, the steps in block F51 are optional. It should be noted that the order in this embodiment does not limit the signal transmission order or the order of implementation in this application.

[0191] For the first node U1, a first request is received in step S510; in step S511, as a response to receiving the first request, a first result is generated through the first model; and in step S512, the first result is sent.

[0192] For the second node N2, a first request is sent in step S520; a first result is received in step S521.

[0193] In embodiment 5, the first model is used for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

[0194] Typically, at least one of the plurality of sub-identifiers is associated with a set of cells, any cell in the set of cells being able to use the data indicated by the at least one sub-identifier.

[0195] As an example, the cell set includes at least one cell.

[0196] As one example, the cell set includes multiple cells.

[0197] As an example, a terminal in any cell of the cell set can use the data indicated by the at least one sub-identifier.

[0198] As an example, the gNB corresponding to any cell in the cell set can use the data indicated by the at least one sub-identifier.

[0199] As an example, the cell set depends on at least one of the plurality of sub-identifiers.

[0200] As an example, at least one of the plurality of sub-identifiers is used to identify a set of cells.

[0201] As an example, the data indicated by the at least one sub-identifier is shared among cells in the cell set.

[0202] Typically, at least one of the plurality of sub-identifiers is associated with a second identifier, the second identifier identifying a second model, which is used for at least one of training or inference, and the second model is different from the first model.

[0203] As an example, the second model includes an AI model.

[0204] As an example, the second model includes an ML model.

[0205] As an example, the second model is for AI.

[0206] As an example, the second model is for ML.

[0207] As an example, the second model includes an ML entity.

[0208] As an example, the second model includes an MnS (Management Service) Producer.

[0209] As an example, the second model is used for training.

[0210] As an example, the second model is used for reasoning.

[0211] As an example, the second model is used for both training and inference.

[0212] As an example, the second identifier is a non-negative integer.

[0213] As an example, the second identifier is a positive integer.

[0214] As an example, the second identifier is an Identity.

[0215] As one example, the second identifier is an Identifier.

[0216] As an example, the second identifier is an index.

[0217] As an example, the data indicated by at least one of the plurality of sub-identifiers can be used by both the first model and the second model simultaneously.

[0218] Typically, the training of the first model and the training of any one of the multiple data corresponding to the multiple sub-identifiers are independent.

[0219] As an example, the training of the first model does not depend on the training of any one of the multiple data corresponding to the multiple sub-identifiers.

[0220] As an example, the training of the first model depends on at least one of the multiple data corresponding to the multiple sub-identifiers.

[0221] As an example, the training of any one of the multiple data corresponding to the multiple sub-identifiers does not depend on the training of the first model.

[0222] Typically, the channel quality information data includes CSI.

[0223] As an example, the channel quality information data is based on statistics.

[0224] As an example, the channel quality information data is periodic.

[0225] As an example, the channel quality information data corresponds to a statistical time window.

[0226] As an example, the channel quality information data corresponds to an effective time window.

[0227] As an example, the CSI includes CQI (Channel Quality Indicator).

[0228] As an example, the CSI includes PMI (Precoding Matrix Indicator).

[0229] As one example, the CSI includes CRI (CSI-RS resource indicator, Channel State Information Reference Signal Resource Indicator).

[0230] As an example, the CSI includes SSBRI (SS / PBCH Block Resource indicator).

[0231] As an example, the CSI includes LI (layer indicator).

[0232] As an example, the CSI includes RI (rank indicator).

[0233] As an example, the CSI includes L1-RSRP (Layer 1 Reference Signal Received Power).

[0234] As an example, the channel quality information data includes the CSI generated by the first node within a given time window.

[0235] As one embodiment, the sub-identifier corresponding to the channel quality information data is associated with a first cell set, and the channel quality information data includes the CSI reported by the cells included in the first cell set.

[0236] Typically, the codebook data is a statistical result of the codebook used by the first node within a given time window.

[0237] As an example, the codebook data is based on statistics.

[0238] As an example, the codebook data is periodic.

[0239] As an example, the codebook data corresponds to a statistical time window.

[0240] As an example, the codebook data corresponds to an effective time window.

[0241] As one example, the codebook data includes the codebook used by the first node within a given time window.

[0242] As one embodiment, the sub-identifier corresponding to the codebook data is associated with a second cell set, and the codebook data includes the codebooks used by terminals in the cells included in the second cell set.

[0243] Typically, the location assistance information data includes at least one of positioning data or mobility data.

[0244] As an example, the location assistance information data is based on statistics.

[0245] As an example, the location assistance information data is periodic.

[0246] As one example, the location assistance information data corresponds to a statistical time window.

[0247] As one example, the location assistance information data corresponds to an effective time window.

[0248] As one embodiment, the location assistance information data includes the location assistance information of the first node within a given time window.

[0249] As one embodiment, the sub-identifier corresponding to the location assistance information data is associated with a third cell set, and the location assistance information data includes the location assistance information of terminals in the cells included in the third cell set.

[0250] As one example, the positioning data includes the terminal's accuracy and latitude.

[0251] As one example, the location data includes the cell where the terminal is camped.

[0252] As one example, the location data includes base stations that provide services to the terminal.

[0253] As one embodiment, the positioning data includes spatial transmission parameters or spatial reception parameters used by the terminal.

[0254] As one example, the positioning data includes the UEPositioningAssistanceInfo message.

[0255] As one example, the location data includes the location information of the terminal obtained by the location server.

[0256] As one example, the mobility data includes the terminal's movement trajectory.

[0257] As one example, the mobility data includes a list of cells where the terminal is camped.

[0258] As one example, the mobility data includes a list of base stations that provide services to the terminal.

[0259] As one example, the plurality of data includes the UE variable VarLogMeasConfig.

[0260] As one example, the plurality of data includes the UE variable VarLogMeasReport.

[0261] As one example, the plurality of data includes the UE variable VarAppLayerIdleConfig.

[0262] As one example, the plurality of data includes the UE variable VarAppLayerPLMN-ListConfig.

[0263] As one example, the plurality of data includes the UE variable VarConditionalReconfig.

[0264] As one example, the plurality of data includes the UE variable VarConnEstFailReport.

[0265] As one example, the plurality of data includes the UE variable VarConnEstFailReportList.

[0266] As one example, the plurality of data includes the UE variable VarLTM-Config.

[0267] As one example, the plurality of data includes the UE variable VarLTM-ServingCellNoResetID.

[0268] As one example, the plurality of data includes UE variable VarLTM-ServingCellUE-MeasuredTA-ID.

[0269] As one example, the plurality of data includes the UE variable VarMeasReportList.

[0270] As one example, the plurality of data includes statistics on terminal RLF (Radio Link Failure).

[0271] As one example, the plurality of data includes statistics on terminal BFR (Beam Failure Recovery).

[0272] As an example, the plurality of data includes data for RLF.

[0273] As one example, the plurality of data includes data for BFR.

[0274] As an example, the physical layer channel occupied by the first request includes PDCCH (Physical Downlink Control Channel).

[0275] As an example, the physical layer channel occupied by the first request includes PDSCH (Physical Downlink Shared Channel).

[0276] As an example, the physical layer channel occupied by the first result includes PUCCH (Physical Uplink Control Channel).

[0277] As an example, the physical layer channel occupied by the first result includes PUSCH (Physical Uplink Shared Channel).

[0278] Example 6

[0279] Example 6 illustrates a schematic diagram of a first model according to an embodiment of this application, as shown in Figure 6. In Figure 6, the first model is identified by a first identifier, and the first identifier is associated with a plurality of sub-identifiers, wherein sub-identifiers #1 to #K shown in the figure are the plurality of sub-identifiers, and sub-identifiers #1 to #K correspond to data #1 to data #K respectively; wherein K is a positive integer greater than 1.

[0280] As an example, any two of the plurality of sub-identifiers are different.

[0281] As an example, the data #1 to data #K correspond to the plurality of data in this application.

[0282] As an example, at least two of the data #1 to data #K come from different layers.

[0283] As an example, at least two of the data #1 to data #K are designed for different performance requirements.

[0284] As an example, the multiple data depend on the capabilities of the first node.

[0285] As an example, the multiple data items depend on the categories of the first node.

[0286] Example 7

[0287] Example 7 illustrates a second model schematic diagram according to an embodiment of this application, as shown in Figure 7. In Figure 7, first data is simultaneously associated with a first sub-identifier and a second sub-identifier, the first identifier corresponding to the first model is associated with the first sub-identifier, and the second identifier corresponding to the second model is associated with the second sub-identifier.

[0288] As an example, the first data can be used by both the first model and the second model.

[0289] As an example, the first model and the second model correspond to different training types.

[0290] As an example, the first model and the second model correspond to different inference types.

[0291] As an example, the first model and the second model correspond to different runtimes.

[0292] As an example, the first model and the second model correspond to different training contexts.

[0293] Example 8

[0294] Example 8 illustrates a schematic diagram of the deployment of a first model according to an embodiment of this application, as shown in Figure 8.

[0295] As an example, the deployment of the first model includes generating the first result through the first model.

[0296] As one example, the deployment includes obtaining an AI entity.

[0297] As one example, the deployment includes obtaining the AI ​​entity that generated the first result.

[0298] As one example, the deployment includes obtaining the AI ​​entity used to train the first model.

[0299] As one example, the deployment includes loading the first model.

[0300] As one example, the deployment includes making a request to load the first model.

[0301] As an example, the given node in Figure 8 is the first node, and the request in Figure 8 is the first request made by the first node to load the first model.

[0302] As an example, the response in Figure 8 is a response to the request made by the first node to load the first model.

[0303] As an example, the response in Figure 8 includes the first result.

[0304] As an example, the given node in Figure 8 is the second node, and the request in Figure 8 is the first request made by the second node to load the first model.

[0305] As an example, the response in Figure 8 is a response to the request made by the second node to load the first model.

[0306] As an example, the response in Figure 8 includes the first result.

[0307] As an example, the first model is obtained from the serving cell of the first node.

[0308] As an example, the first model is obtained from the sustaining base station of the serving cell of the first node.

[0309] As an example, the first model is obtained from the core network.

[0310] As an example, the first model is obtained by loading from a first producer.

[0311] As an example, the first producer provides the first result to the first node via the response shown in Figure 9.

[0312] As an example, the first producer is the first model.

[0313] As an example, the first producer is the first node.

[0314] As an example, the deployment is accomplished by an AI function.

[0315] As an example, the deployment is accomplished by AI functionality deployed on the first node.

[0316] As an example, the deployment is accomplished by an AI deployment function.

[0317] As an example, the deployment is accomplished by the AI ​​deployment function deployed on the first node.

[0318] As an example, the deployment is accomplished using AI inference functionality.

[0319] As an example, the deployment is accomplished by an AI inference function deployed on the first node.

[0320] As an example, the deployment is performed by an AI entity.

[0321] As an example, the deployment is performed by an AI entity deployed on the first node.

[0322] As an example, the deployment is performed by an AI entity with a deployment function.

[0323] As an example, the deployment is performed by an AI entity with deployment capabilities deployed on the first node.

[0324] As an example, the deployment is accomplished by an AI entity with an inference function.

[0325] As an example, the deployment is performed by an AI entity with inference capabilities deployed on the first node.

[0326] As one embodiment, the deployment includes obtaining the first result from a first producer.

[0327] As one example, the deployment includes requesting a first producer to load the first model.

[0328] As one example, the deployment includes loading the first model from the first producer.

[0329] As an example, the first producer generates and provides AI entities.

[0330] As an example, the first producer generates and provides AI functionality.

[0331] As an example, the first producer is the producer of the first result.

[0332] As one example, the first producer includes an AI entity producer.

[0333] As one example, the first producer includes an AI function producer.

[0334] As one example, the first producer includes an AI deployment producer.

[0335] As one example, the first producer includes an AI loading producer.

[0336] As one example, the first producer includes an AI-trained producer.

[0337] As an example, the first producer includes an AI inference producer.

[0338] As an example, the first producer includes the producer of the AI ​​entity deployment.

[0339] As one example, the first producer includes the producer that loads the AI ​​entity.

[0340] As an example, the first producer includes an MnS (Management Service) producer.

[0341] As an example, the training of the first model is performed by the first producer.

[0342] As an example, the executor used to obtain the training of the first model is different from the first producer.

[0343] Example 9

[0344] Example 9 illustrates a schematic diagram of the ML / AI structure according to an embodiment of this application, as shown in Figure 9. In Figure 9, the ML MnS Consumer and the ML MnS Producer are connected via MnS, and the ML MnS Producer is connected to a database.

[0345] As an example, the ML MnS Consumer corresponds to the second node in this application.

[0346] As an example, the ML MnS Producer corresponds to the first node in this application.

[0347] As an example, the ML MnS Producer includes the first model in this application.

[0348] As an example, the ML MnS Producer corresponds to the first model deployed in the first node of this application.

[0349] As an example, the ML MnS Consumer sends the first request and receives the first data.

[0350] As an example, the ML MnS Producer receives the first request and sends the first data.

[0351] As an example, the database in Figure 9 corresponds to multiple data in this application.

[0352] As an example, the ML MnS Consumer corresponds to the entity in the first node of this application that requests the first result, and the ML MnS Producer corresponds to the entity in the first node of this application that generates the first result.

[0353] As an example, the first model implements the generation of the first result.

[0354] As an example, the first model generates the first result based on the maximum likelihood criterion.

[0355] As an example, the first model generates the first result based on the maximum probability criterion.

[0356] As an example, the first model generates the first result on its own.

[0357] As an example, the first model generates the first result based on the training results.

[0358] As an example, the first model generates the first result by combining the training results of the multiple data in this application with prediction.

[0359] As one embodiment, the first result includes first data and a first confidence level, the first confidence level being used to indicate the accuracy of the prediction of the first data.

[0360] As one embodiment, the first result includes first data and a first confidence interval, wherein the first confidence level is used to indicate the accuracy of the prediction of the first data.

[0361] Example 10

[0362] Example 10 illustrates a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application; as shown in Figure 10. Figure 10 includes processor A, processor B, processor C, and processor D. In Example 10, processor A sends a first dataset to processor B and a second dataset to processor C; processor B generates a target first type parameter set based on the first dataset, and sends the generated target first type parameter set to processor C; processor C processes the second dataset using the target first type parameter set to obtain a first type output, and processor C sends the first type output to processor D. In Figure 10, the first type of feedback and the second type of feedback are optional.

[0363] As one embodiment, the processor A includes a data collection module and a model training module.

[0364] As one embodiment, the processor B includes a data collection module and a model training module.

[0365] As an example, the processor A generates the first result.

[0366] As an example, the processor B generates the first result.

[0367] As an example, the processor C generates the first result.

[0368] As an example, processor C sends a first type of feedback to processor B, which is used to trigger a recalculation or update of the target first type of parameter group.

[0369] As one embodiment, the processor D sends a second type of feedback to the processor A, the second type of feedback being used to generate the first dataset or the second dataset, or the second type of feedback being used to trigger the sending of the first dataset or the sending of the second dataset.

[0370] As one embodiment, processor C belongs to the first node, and processor D belongs to the second node.

[0371] As an example, the second dataset includes the plurality of data described in this application.

[0372] As an example, the first dataset includes the plurality of data described in this application.

[0373] As an example, the first dataset includes training data.

[0374] As an example, the processor B is the producer of operation A.

[0375] As one embodiment, the processor B includes an AI training producer.

[0376] As one embodiment, the processor B includes an AI training function.

[0377] As an example, the processor B is used for model training, and the trained model is used to generate the first result.

[0378] As an example, the processor B belongs to the first node.

[0379] The above embodiments avoid transmitting the multiple data to the second node.

[0380] As an example, processor B belongs to the second node.

[0381] The above embodiments support joint training and optimize system performance.

[0382] As an example, processor B belongs to the core network.

[0383] The above embodiments support network-wide joint training, further optimizing system performance.

[0384] As one example, the plurality of data includes inference data.

[0385] As one embodiment, the processor C includes an AI inference producer.

[0386] As one embodiment, the processor C includes an AI inference function.

[0387] As an example, the processor C belongs to the first node.

[0388] As an example, the processor C constructs a model based on the plurality of data, and then inputs the plurality of data into the constructed model to obtain the first result.

[0389] As an example, the processor C generates a recovery dataset based on the first type of output, and the error between the recovery dataset and the second dataset is used to generate the first type of feedback.

[0390] As a sub-example of the above embodiment, the generation of the recovery dataset adopts a method similar to operation B.

[0391] As an example, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the processor B will recalculate the target first type of parameter set.

[0392] As an example, when the error is too large or the update has not been performed for too long, the performance of the trained model is considered to be unsatisfactory.

[0393] As an example, the target first type of parameter group includes one or more of the following: convolution kernel size, number of convolution layers, convolution stride, pooling kernel size, pooling kernel stride, pooling function, activation function, or number of feature maps.

[0394] As an example, the target first type of parameter group includes one or more of the following: convolution kernel, pooling kernel, pooling function, activation function, parameters of pooling function, or parameters of activation function.

[0395] As an example, the first model in this application includes a processor A.

[0396] As an example, the first model in this application includes a processor B.

[0397] As an example, the first model in this application includes a processor C.

[0398] As an example, the first model in this application includes a processor D.

[0399] Example 11

[0400] Example 11 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application; as shown in Figure 11. Figure 11 includes operations A, B, C, D, and E. In Example 11, operations A and B belong to the first stage, operation C belongs to the second stage, operation D belongs to the third stage, and operation E belongs to the fourth stage. In Figure 11, the lines with arrows indicate the sequence of processes.

[0401] As an example, operation A includes AI training, operation B includes AI testing, operation C includes AI emulation, operation D includes AI entity loading, and operation E includes AI inference.

[0402] As an example, the first stage includes a training phase, the second stage includes an emulation phase, the third stage includes a deployment phase, and the fourth stage includes an emulation phase.

[0403] As an example, the first stage includes AI model training.

[0404] As an example, the first stage includes AI model training and AI testing.

[0405] As an example, the AI ​​model training includes initial training and re-training of one or a group of AI entities.

[0406] As an example, the training of the AI ​​model depends on training data.

[0407] As an example, the AI ​​model training includes AI entity validation.

[0408] As an example, the AI ​​entity verification is used to evaluate the performance of the AI ​​entity.

[0409] As an example, the AI ​​entity verification relies on verification data.

[0410] As an example, if the AI ​​entity verification results do not meet expectations, the AI ​​model will be retrained.

[0411] As an example, the AI ​​testing includes testing the validated AI entity to estimate the performance of the trained AI model.

[0412] As an example, if the AI ​​test results meet expectations, the AI ​​entity proceeds to the next stage; otherwise, the AI ​​model will be retrained.

[0413] As an example, the AI ​​test relies on test data.

[0414] As an example, the second stage includes AI simulation, which performs inference of AI entities in a simulation environment.

[0415] As an example, the AI ​​simulation estimates the performance of AI entity inference in a simulation environment before using the AI ​​entity.

[0416] As one embodiment, the second stage is optional.

[0417] As an example, the third stage includes AI entity loading, which is to obtain trained AI entities to obtain the desired AI inference capabilities.

[0418] As an example, the third stage is optional.

[0419] As an example, the third stage is no longer needed when the training and inference functions are co-located.

[0420] As an example, the fourth stage includes AI inference.

[0421] As an example, operation E includes operation A.

[0422] As an example, operation E includes operation B.

[0423] Example 12

[0424] Example 12 illustrates a structural block diagram of a processing apparatus for a first node according to an embodiment of this application, as shown in Figure 12. In Figure 12, the processing apparatus 1200 in the first node includes a first receiver 1201 and a first transmitter 1202.

[0425] In embodiment 12, the first receiver 1201 receives a first request; and in response to receiving the first request, generates a first result through a first model; the first transmitter 1202 sends the first result.

[0426] In embodiment 12, the first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, which respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

[0427] As an example, at least one of the plurality of sub-identifiers is associated with a set of cells, any cell in the set of cells being able to use the data indicated by the at least one sub-identifier.

[0428] As an example, at least one of the plurality of sub-identifiers is associated with a second identifier, the second identifier identifying a second model, the second model being for at least one of training or inference, and the second model being different from the first model.

[0429] As an example, the training of the first model and the training of any one of the multiple data corresponding to the multiple sub-identifiers are independent.

[0430] As an example, the channel quality information data includes CSI.

[0431] As an example, the codebook data is a statistical result of the codebook used by the first node within a given time window.

[0432] As one embodiment, the location assistance information data includes at least one of positioning data or mobility data.

[0433] As one example, the first node is a user equipment.

[0434] As an example, the first node is a relay node device.

[0435] As an example, the first receiver 1201 includes at least one of the following in embodiment 4: the antenna 452, the receiver 454, the receiver processor 456, the multi-antenna receiver processor 458, the controller / processor 459, the memory 460, and the data source 467.

[0436] As an example, the first transmitter 1202 includes at least one of the following in embodiment 4: the antenna 452, the transmitter 454, the transmission processor 468, the multi-antenna transmission processor 457, the controller / processor 459, the memory 460, and the data source 467.

[0437] Example 13

[0438] Example 13 illustrates a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application, as shown in Figure 13. In Figure 13, the processing apparatus 1300 in the second node includes a second transmitter 1301 and a second receiver 1302.

[0439] In embodiment 13, the second transmitter 1301 sends a first request; the second receiver 1302 receives a first result.

[0440] In embodiment 13, the recipient of the first request, as a response to receiving the first request, generates a first result through a first model; the first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

[0441] As an example, at least one of the plurality of sub-identifiers is associated with a set of cells, any cell in the set of cells being able to use the data indicated by the at least one sub-identifier.

[0442] As an example, at least one of the plurality of sub-identifiers is associated with a second identifier, the second identifier identifying a second model, the second model being for at least one of training or inference, and the second model being different from the first model.

[0443] As an example, the training of the first model and the training of any one of the multiple data corresponding to the multiple sub-identifiers are independent.

[0444] As an example, the channel quality information data includes CSI.

[0445] As an example, the codebook data is a statistical result of the codebook used by the first node within a given time window.

[0446] As one embodiment, the location assistance information data includes at least one of positioning data or mobility data.

[0447] As one example, the first node is a user equipment.

[0448] As an example, the first node is a relay node device.

[0449] In one embodiment, the second node is a base station device.

[0450] In one embodiment, the second node is a user equipment.

[0451] As an example, the second node is a TRP.

[0452] As an example, the second transmitter 1301 includes at least one of the following in embodiment 4: the antenna 420, the transmitter 418, the transmission processor 416, the multi-antenna transmission processor 471, the controller / processor 475, and the memory 476.

[0453] As one embodiment, the second receiver 1302 includes at least one of the following in embodiment 4: the antenna 420, the receiver 418, the receiver processor 470, the multi-antenna receiver processor 472, the controller / processor 475, and the memory 476.

[0454] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium, such as a read-only memory, hard disk, or optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Correspondingly, each module unit in the above embodiments can be implemented in hardware or in the form of software functional modules. This application is not limited to any specific combination of software and hardware. The user equipment, terminal, and UE in this application include, but are not limited to, drones, communication modules on drones, remote-controlled aircraft, aircraft, small aircraft, mobile phones, tablets, laptops, vehicle-mounted communication equipment, vehicles, RSUs, wireless sensors, internet cards, IoT terminals, RFID (Radio Frequency Identification) terminals, NB-IoT (Narrow Band Internet of Things) terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet cards, vehicle-mounted communication equipment, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base station or system equipment in this application includes, but is not limited to, macrocell base stations, microcell base stations, small cell base stations, home base stations, relay base stations, eNB (evolved Node B), gNB, TRP, GNSS (Global Navigation Satellite System), relay satellites, satellite base stations, airborne base stations, RSUs, unmanned aerial vehicles, and test equipment, such as transceivers or signaling testers that simulate some functions of a base station, and other wireless communication equipment.

[0455] Those skilled in the art will understand that the present invention can be practiced in other specified forms without departing from its core or essential characteristics. Therefore, the embodiments disclosed herein should in any way be considered descriptive rather than restrictive. The scope of the invention is defined by the appended claims rather than the foregoing description, and all modifications within their equivalent meaning and scope are considered to be included therein.

Claims

1. A first node for wireless communication, characterized in that, include: The first receiver receives the first request; In response to receiving the first request, a first result is generated using the first model; Wherein, the first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

2. The first node according to claim 1, characterized in that, At least one of the plurality of sub-identifiers is associated with a set of cells, any cell in the set of cells being able to use the data indicated by the at least one sub-identifier.

3. The first node according to claim 1 or 2, characterized in that, At least one of the plurality of sub-identifiers is associated with a second identifier, the second identifier identifying a second model, the second model being for at least one of training or inference, and the second model being different from the first model.

4. The first node according to any one of claims 1 to 3, characterized in that, The training of the first model and the training of any one of the multiple data corresponding to the multiple sub-identifiers are independent.

5. The first node according to any one of claims 1 to 4, characterized in that, The channel quality information data includes CSI.

6. The first node according to any one of claims 1 to 5, characterized in that, The codebook data is a statistical result of the codebook used by the first node within a given time window.

7. The first node according to any one of claims 1 to 6, characterized in that, The location assistance information data includes at least one of positioning data or mobility data.

8. The first node according to any one of claims 1 to 7, characterized in that... include: The first transmitter sends the first result.

9. A second node for use in wireless communication, characterized in that, include: The second transmitter sends the first request; Wherein, the recipient of the first request, as the responder to the first request, generates the first result through the first model; The first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

10. The second node according to claim 9, characterized in that, At least one of the plurality of sub-identifiers is associated with a set of cells, any cell in the set of cells being able to use the data indicated by the at least one sub-identifier.

11. The second node according to claim 9 or 10, characterized in that, At least one of the plurality of sub-identifiers is associated with a second identifier, the second identifier identifying a second model, the second model being for at least one of training or inference, and the second model being different from the first model.

12. The second node according to any one of claims 9 to 11, characterized in that, The training of the first model and the training of any one of the multiple data corresponding to the multiple sub-identifiers are independent.

13. The second node according to any one of claims 9 to 12, characterized in that, The channel quality information data includes CSI.

14. The second node according to any one of claims 9 to 13, characterized in that, The codebook data is a statistical result of the codebook used by the recipient of the first request within a given time window.

15. The second node according to any one of claims 9 to 14, characterized in that, The location assistance information data includes at least one of positioning data or mobility data.

16. The second node according to any one of claims 9 to 15, characterized in that, include: The second receiver receives the first result.

17. A method for use in a first node in wireless communication, characterized in that, include: Receive the first request; In response to receiving the first request, a first result is generated using the first model; Wherein, the first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

18. The method according to claim 17, characterized in that, At least one of the plurality of sub-identifiers is associated with a set of cells, any cell in the set of cells being able to use the data indicated by the at least one sub-identifier.

19. The method according to claim 17 or 18, characterized in that, At least one of the plurality of sub-identifiers is associated with a second identifier, the second identifier identifying a second model, the second model being for at least one of training or inference, and the second model being different from the first model.

20. The method according to any one of claims 17 to 19, characterized in that, The training of the first model and the training of any one of the multiple data corresponding to the multiple sub-identifiers are independent.

21. The method according to any one of claims 17 to 20, characterized in that, The channel quality information data includes CSI.

22. The method according to any one of claims 17 to 21, characterized in that, The codebook data is a statistical result of the codebook used by the first node within a given time window.

23. The method according to any one of claims 17 to 22, characterized in that, The location assistance information data includes at least one of positioning data or mobility data.

24. The method according to any one of claims 17 to 23, characterized in that, include: Send the first result.

25. A method for a second node in wireless communication, characterized in that, include: Send the first request; Wherein, the recipient of the first request, as the responder to the first request, generates the first result through the first model; The first model is for at least one of training or inference, and the first result is either a training result or an inference result; the identifier of the first model is a first identifier; the first identifier is associated with multiple sub-identifiers, and the multiple sub-identifiers respectively indicate multiple data; the multiple data include at least one of channel quality information data, codebook data, and location auxiliary information data.

26. The method according to claim 25, characterized in that, At least one of the plurality of sub-identifiers is associated with a set of cells, any cell in the set of cells being able to use the data indicated by the at least one sub-identifier.

27. The method according to claim 25 or 26, characterized in that, At least one of the plurality of sub-identifiers is associated with a second identifier, the second identifier identifying a second model, the second model being for at least one of training or inference, and the second model being different from the first model.

28. The method according to any one of claims 25 to 27, characterized in that, The training of the first model and the training of any one of the multiple data corresponding to the multiple sub-identifiers are independent.

29. The method according to any one of claims 25 to 28, characterized in that, The channel quality information data includes CSI.

30. The method according to any one of claims 25 to 29, characterized in that, The codebook data is a statistical result of the codebook used by the recipient of the first request within a given time window.

31. The method according to any one of claims 25 to 30, characterized in that, The location assistance information data includes at least one of positioning data or mobility data.

32. The method according to any one of claims 25 to 31, characterized in that, include: Receive the first result.

Images