Communication method based on ai model, communication apparatus, and device

Abstract

The present application belongs to the technical field of communications. Disclosed are an AI model-based communication method, a communication apparatus, and a device. The communication method in the embodiments of the present application comprises: a first device acquiring input information; and the first device obtaining output information on the basis of an AI model and the input information, wherein the output information is used for adjusting transmission-related configuration parameters of a data link transmission layer.

Description

AI-based communication methods, communication devices and equipment

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411593978.3, filed on November 8, 2024, entitled "Communication Method, Communication Device and Equipment Based on AI Model", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of communication technology, specifically relating to a communication method, communication device, and equipment based on an artificial intelligence (AI) model. Background Technology

[0004] With the rapid development of streaming media services, new demands are being placed on the data link layer (L2 layer) of the wireless air interface. Currently, controlling L2 packet assembly and retransmission parameters requires consideration of many factors. Combined with dynamically changing Quality of Service (QoS) attributes, it is difficult to dynamically and adaptively adjust relevant configuration parameters to meet user service needs. Therefore, optimizing these configuration parameters is an urgent problem to be solved. Summary of the Invention

[0005] This application provides a communication method, communication device, and equipment based on an AI model, which can solve the problem of how to optimize relevant configuration parameters.

[0006] Firstly, a communication method based on intelligent algorithms is provided, which includes:

[0007] The first device acquires input information;

[0008] The first device obtains output information based on the AI ​​model and the input information, and the output information is used to adjust the transmission-related configuration parameters of the data link transport layer.

[0009] Secondly, a communication method based on intelligent algorithms is provided, which includes:

[0010] The second device sends model inference configuration information to the first device. The model inference configuration information is used to indicate the input and output information of the AI ​​model deployed on the first device. The output information is used to adjust the transmission-related configuration parameters of the data link transport layer.

[0011] Thirdly, a communication device based on intelligent algorithms is provided, comprising:

[0012] The processing module is used to acquire input information;

[0013] The processing module is also used to obtain output information based on the AI ​​model and the input information, and the output information is used to adjust the transmission-related configuration parameters of the data link transport layer.

[0014] Fourthly, a communication device based on intelligent algorithms is provided, comprising:

[0015] The sending module is used to send model inference configuration information to the first device. The model inference configuration information is used to indicate the input and output information of the AI ​​model deployed on the first device. The output information is used to adjust the transmission-related configuration parameters of the data link transmission layer.

[0016] Fifthly, a communication device is provided, the device being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0017] In a sixth aspect, a communication device is provided, comprising a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method described in the first aspect.

[0018] In a seventh aspect, a communication device is provided, including a processor, wherein the processor is configured to acquire input information;

[0019] Based on the AI ​​model and the input information, output information is obtained, which is used to adjust the transmission-related configuration parameters of the data link transport layer.

[0020] Eighthly, a communication device is provided, the communication device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the second aspect.

[0021] In a ninth aspect, a communication device is provided, including a processor and a communication interface, wherein the communication interface is used to send model inference configuration information to a first device, the model inference configuration information being used to indicate the input and output information of an AI model deployed on the first device; the output information being used to adjust transmission-related configuration parameters of the data link transport layer.

[0022] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the second aspect.

[0023] Eleventhly, a wireless communication system is provided, comprising: a terminal and a network-side device, wherein the terminal can be used to perform the steps of the method as described in the first aspect, and the network-side device can be used to perform the steps of the method as described in the second aspect.

[0024] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run programs or instructions to implement the method as described in the first aspect, or to implement the method as described in the second aspect.

[0025] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium and executed by at least one processor to implement the steps of the two methods as described in the first aspect.

[0026] In this embodiment, output information is obtained by reasoning based on input information using an AI model, and the transmission-related configuration parameters of the data link transport layer are adjusted based on the output information. The AI ​​model is advantageous for dynamically and adaptively adjusting the transmission-related configuration parameters of the data link transport layer by considering multiple factors, which is beneficial for meeting the user's business needs. Attached Figure Description

[0027] Figure 1 is a block diagram of a wireless communication system applicable to an embodiment of this application;

[0028] Figure 2 is a schematic diagram of the 5G user plane protocol stack;

[0029] Figure 3A is a schematic diagram of the uplink (UL) protocol stack structure;

[0030] Figure 3B is a schematic diagram of the downlink (DL) protocol stack structure;

[0031] Figure 4 is a schematic diagram of QoS flow;

[0032] Figure 5A shows the data processing flow of the Radio Link Control (RLC) entity in Unacknowledged Mode (UM).

[0033] Figure 5B shows the data processing flow of RLC entities in Acknowledged Mode (AM).

[0034] Figure 6 is a schematic diagram of the operating framework of the AI ​​model;

[0035] Figure 7 is a schematic diagram of a communication method based on an artificial intelligence (AI) model according to an embodiment of this application;

[0036] Figure 8 is a schematic diagram of another communication method based on an artificial intelligence (AI) model according to an embodiment of this application;

[0037] Figure 9 is a schematic block diagram of a communication device according to an embodiment of this application;

[0038] Figure 10 is a schematic block diagram of another communication device according to an embodiment of this application;

[0039] Figure 11 is a schematic diagram of the structure of the communication device provided in an embodiment of this application;

[0040] Figure 12 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of this application;

[0041] Figure 13 is a schematic diagram of the hardware structure of a network-side device that implements an embodiment of this application. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0043] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0044] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0045] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0046] Figure 1 shows a block diagram of a wireless communication system applicable to an embodiment of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM, or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (APs), or Wireless Fidelity (WiFi) nodes, etc.The term "base station" can be referred to as Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical terminology. It should be noted that this application embodiment only uses a base station in an NR system as an example for description and does not limit the specific type of base station.

[0047] Core network equipment, also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), and Binding Support. The core network functions include: BSF (Block Network Function), Application Function (AF), Location Management Function (LMF), Gateway Mobile Location Centre (GMLC), and Network Data Analytics Function (NWDAF). It should be noted that this application embodiment only uses core network equipment in the NR system as an example and does not limit the specific type of core network equipment. If the name of the core network equipment mentioned in this application embodiment changes in subsequent protocol versions (e.g., 6G), it will still be within the scope of protection of this application.

[0048] Optionally, the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that the aforementioned functional modules can be network elements in hardware devices, software functional modules running on dedicated hardware, or virtualized functional modules instantiated on a platform (e.g., a cloud platform).

[0049] To facilitate understanding of the application embodiments, the following explains the relevant knowledge of 5G user plane.

[0050] The 5G user plane protocol stack, as shown in Figure 2, mainly includes Service Data Adaptation Protocol (SDAP), Packet Data Convergence Protocol (PDCP), Radio Link Control (RLC), Medium Access Control (MAC), and Physical Layer (PHY).

[0051] The SDAP layer is primarily responsible for mapping between Quality of Service (QoS) and Data Radio Bearer (DRB). Data is carried based on DRBs, and the SDAP layer needs to map QoS stream data to different DRBs according to the network-configured mapping rules. The PDCP layer is mainly responsible for data encryption / decryption, integrity protection, header compression, sequencing, and data reliability assurance in handover and traffic splitting scenarios. The RLC layer is mainly responsible for data segmentation, Automatic Repeat-reQuest (ARQ), and error handling to ensure data transmission reliability. The MAC layer is responsible for multiplexing and concatenation of different Logical Channels (LCHs) and the same LCH, random access, Discontinuous Reception (DRX), and data scheduling selection processes, and implements the underlying retransmission of Hybrid Automatic Repeat-reQuest (HARQ) multi-process. The PHY is the lowest layer of the 5G user plane protocol stack, responsible for the physical transmission and reception of data, signal modulation, demodulation, encoding, and decoding.

[0052] The protocol stack includes an uplink (UL) protocol stack and a downlink (DL) protocol stack. The UL protocol stack structure is shown in Figure 3A. The SDAP layer performs QoS flow handling, mapping QoS flows to corresponding Resource Blocks (RBs). The PDCP layer performs data compression and security protection on the data from each RB and transmits it to the RLC channel. The RLC layer performs data segmentation and automatic repeat (Segm.ARQ) and transmits it to the LCH. The MAC layer schedules and multiplexes the data in the LCH and transmits it to the Transport Channel using HARQ.

[0053] The DL protocol stack structure is shown in Figure 3B. The SDAP layer performs QoS flow handling, mapping the QoS flow to the corresponding RB. The PDCP layer performs robust header compression (ROHC) and security protection on the data from each RB and passes it to the RLC channel. The RLC layer performs data segmentation and automatic repeat (Segm.ARQ) and passes it to the LCH. The MAC performs scheduling / priority handling and multiplexing on the data in the LCH for different UEs, such as UE1…UE2. n It is transmitted to the transport channel using the HARQ method. Here, LCHs represents multiple LCHs, and RBs represents multiple RBs.

[0054] Figure 4 illustrates a schematic diagram of a QoS flow. As shown in Figure 4, a QoS flow includes multiple IP packets. After reaching the RAN, the QoS flow is mapped to the SDAP layer. The SDAP layer packages the received IP packets into SDAP Service Data Units (SDUs) and passes the SDAP SDUs to the PDCP layer. In the PDCP layer, a header is added to an SDU to form a PDCP Protocol Data Unit (PDU), which is then sent to the RLC. The RLC numbers, adds headers to, and segments a PDCP PDU to form an RLC PDU, which is then sent to the MAC for multiplexing and concatenation of the LCH, or for multiplexing and concatenation with other LCHs to form a MAC PDU Transport Block. Here, H represents the header, n, n+1, m represent the numbers of different IP packets, and RB represents the header number.x and RB y Indicates different RBs.

[0055] The RLC layer is divided into three different modes based on different services: Acknowledged Mode (AM), Unacknowledged Mode (UM), and Transparent Mode (TM).

[0056] UM mode provides unreliable data transmission services and does not guarantee retransmission or ordered arrival of data packets. UM mode generally carries real-time services and has a certain tolerance for packet loss, such as voice, supporting segmentation, sorting, and in-order delivery. Figure 5A illustrates the data processing flow of the RLC entity in UM mode. Device A (e.g., UE / GNB / UE) and device B (GNB / UE / UE) transmit data through the radio interface Uu / PC5. Device A's transmitting UM-RLC entity acquires data packets from the UM RLC channel, sequentially generates an RLC header and stores it in the transmission buffer, segments and modifies the RLC header, and adds an RLC header. Optionally, data packets are transmitted to the receiving UM-RLC entity via Dedicated Traffic Channel (DTCH), Sidelink Transport Channel (STCH), Sidelink Control Channel (SCCH), Multicast Control Channel (MCCH), or Multicast Traffic Channel (MTCH), and then sequentially enter the reception buffer, have their RLC header removed, and undergo SDU reassembly before entering the UM-RLC channel.

[0057] AM mode provides reliable data transmission services, including data retransmission and order fulfillment guarantees. AM mode is suitable for most internet services, such as video, web browsing, and games, and supports key functions such as segmentation, resegmentation, retransmission, control, and reordering. Figure 5B illustrates the data processing flow of the RLC entity in AM mode. Specifically, the transmitting AM-RLC entity receives data packets from the AM-RLC channel, sequentially generates an RLC header and stores it in the transmission buffer, segments and modifies the RLC header, adds an RLC header, and then transmits it via DTCH / DCCH / STCH / SCCH. Optionally, after adding the RLC header, the data packets can enter the retransmission buffer for resegmentation and modification of the RLC header or addition of a new RLC header. The receiving AM-RLC entity receives data packets through routing, sequentially entering the receive buffer, removing the RLC header, reassembling the SDU, and then entering the UM-RLC channel. Optionally, the routed data packets can also enter the RCL control channel.

[0058] TM mode does not perform any error handling or data retransmission.

[0059] To facilitate understanding of the application embodiments, the polling mechanism of the AM-RLC at the transmitting end is explained below.

[0060] The sending end determines whether to set P=1 in the RLC PDU header and update the status variable POLL_SN based on the following statistical analysis:

[0061] 1) The amount of newly transmitted data (bits, bytes) exceeds the network configuration threshold;

[0062] 2) The number of newly transmitted data PDUs exceeds the network configuration threshold;

[0063] 3) When both the new transfer and retransmission windows are empty;

[0064] 4) No new transmission can be sent because the sending window is blocked.

[0065] When this RLC PDU is sent to the underlying layer for scheduled transmission, the t-PollRetransmit polling retransmission timer is started. If a status report corresponding to POLL_SN is received before the timer expires, the timer is stopped. Upon timer expiration, a poll bit is set in the latest data packet. If there are no pending new or retransmitted data packets, packets that have not received an acknowledgment (ACK) can be blindly retransmitted.

[0066] To facilitate understanding of the application embodiments, the status report mechanism of the AM-RLC receiver is explained below.

[0067] The receiving end controls the sending of status reports through the status variable RX_Highest_Status. Only data packets with a sequence number (SN) less than this variable are considered lost, and a corresponding negative acknowledgment (NACK) is sent.

[0068] When a data packet with SN=X is received and the P field is set to 1, determine whether x is true.<RX_Highest_Status or x> =RX_Next + AM_Window_Size. If a status report can be triggered within this range, otherwise it is necessary to wait for X to be less than RX_Highest_Status.

[0069] The RX_Highest_Status variable is the highest SN PDU that can send status reports, and it is updated by continuously receiving new data packets and waiting for the RX_Next_Status_Trigger, which is controlled by a t-reassembly wait timer.

[0070] After the receiving end sends a status report, it will also start a t-status prohibit timer to control the frequent sending of status reports.

[0071] To facilitate understanding of the application embodiments, the UM-RLC mechanism of the receiving end is described below.

[0072] In UM mode, the receiver RLC maintains a reassembly window through some states. This reassembly window is used by the receiver to wait for out-of-order UM RLC PDUs to arrive in order to recover the PDCP PDU.

[0073] RX_Next_Highest represents the highest SN of the currently received SDU, and RX_Next_Highest–UM_Window_Size represents the receive window. New UM-RLC packets received that are smaller than this window need to be deleted.

[0074] RX_Next_Reassembly is used to represent the SDU with the smallest SN within the receive window that has not yet been received. The t-Reassembly timer is started for the SDU with the highest SN currently received, and the highest SN at the start time is assigned to the variable RX_Timer_Trigger. Data that has not been correctly received and whose SN is less than RX_Timer_Trigger after the timer expires are also deleted and no longer waited for.

[0075] To facilitate understanding of the application embodiments, the PDCP SN gap (GAP) report is described below.

[0076] 3GPP R18 uses a PDCP SN GAP reporting mechanism. When the UE transmitter deletes a numbered PDCP SDU that has not yet been sent to the underlying layer due to the PDCP discard feature, it needs to send a PDCP SN GAP report to notify the receiver which data packets have been deleted. The receiver does not need to wait anymore, saving reordering latency.

[0077] To facilitate understanding of the application embodiments, the following describes air interface transmission based on an AI model.

[0078] AI models can be implemented in various ways, including but not limited to: neural networks, decision trees, support vector machines, Bayesian classifiers, etc. AI can also be represented as machine learning (ML).

[0079] Figure 6 is a schematic diagram of the operation framework of an AI model. As shown in Figure 6, the lifecycle management of an AI model includes multiple functional modules: data collection, model training, model management, model inference, and model storage.

[0080] The data collection module is used to collect training data, supervision data, and inference data required for model training, model supervision, and model inference.

[0081] The model training module performs AI model training, validation, and testing, and can generate model performance metrics that can be used as part of the model testing process. If necessary, the model training module is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) of the training data provided by the data collection module.

[0082] The model training module also performs model updates, transferring trained, validated, and tested AI models to the model storage function, or transferring updated versions of the model to the model storage module, which stores multiple versions of the AI ​​model.

[0083] The model management module supervises the AI ​​model, distributes AI function-related information, and provides feedback on model monitoring performance. This module is also responsible for making decisions based on data received from the data collection and inference modules to ensure correct inference operations.

[0084] The model management module sends AI function-related information to the model inference module through management commands. This AI function-related information includes selecting / activating / switching models or using AI-based functions, and reverting to non-AI operations (i.e., not relying on the inference process).

[0085] The model management module requests the required AI model from the model storage module via a model transfer request. The model management module also inputs necessary information into the model training module via a performance feedback request or a retraining request, such as the purpose of retraining or updating the model.

[0086] The model inference module is used to provide the AI ​​model's output using the inference data provided by the data collection module as input. If necessary, this module is also responsible for data preparation of the inference data provided by the data collection module (e.g., data preprocessing and cleaning, formatting and transformation).

[0087] The relevant solutions include the following four AI use cases in air interface AI:

[0088] Use Case 1: Beam Prediction. This includes spatial beam prediction and temporal beam prediction. Spatial beam prediction uses partial beam measurements to predict the signal quality of other parts of the beam. Temporal beam prediction uses beam measurements at the current time to predict the beam signal quality at time +n.

[0089] Use Case 2: Location Prediction. Similar to the location measurement prediction in this section, this involves using the location measurement results as a reference or directly predicting the location result.

[0090] Use Case 3: Channel State Information (CSI) Prediction. Predict the CSI reported by the UE to reduce the number of UE reports.

[0091] Use Case 4: Mobility Prediction. Prediction of mobility measurement results in the time domain, frequency domain, and spatial domain.

[0092] To facilitate understanding of the embodiments of this application, the technical problems to be solved by the embodiments of this application are described below.

[0093] Since the 3G system, the user plane has remained largely unchanged in 3GPP. However, in recent years, with the rapid development of streaming media services and the continuous evolution of service encoding and transmission technologies, such as the enhancements in encoding and transmission technologies like HTTP3, H.266 / VCC, and FEC, new demands have been placed on the data link layer (L2 layer) of the wireless air interface. For example, the L2 layer requires faster and more adaptive ARQ retransmissions over the air interface, dynamic adjustments to the L2 transmission mechanism based on application layer encoding / decoding measurements and air interface status, and accurate control of PDUs to ensure performance while reducing air interface overhead. Currently, controlling the parameters for L2 packet assembly and retransmission requires consideration of many factors, and combined with dynamically changing service QoS attributes, it is difficult to dynamically and adaptively meet user service needs by adjusting relevant configuration parameters. Therefore, optimizing relevant configuration parameters is an urgent problem to be solved.

[0094] The AI ​​model-based communication method provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0095] Figure 7 shows a schematic diagram of a communication method based on an artificial intelligence (AI) model according to an embodiment of this application. As shown in Figure 7, the method 700 includes:

[0096] 710, The first device acquires input information.

[0097] 720. The first device obtains output information based on the AI ​​model and input information. The output information is used to adjust the transmission-related configuration parameters of the data link transmission layer.

[0098] In this embodiment, the first device obtaining output information based on the AI ​​model and input information can also be described as follows: the first device inputs the input information into the AI ​​model and obtains the output information; or, the AI ​​model obtains the output information based on the input information. The input information serves as the input to the AI ​​model, and the AI ​​model performs reasoning based on the input information to obtain the output information. This output information is used to adjust the transmission-related configuration parameters of the data link transport layer. For example, this output information can be used to adjust the transmission-related configuration parameters of the data link transport layer of at least one of the terminal and network devices.

[0099] Optionally, AI models can also be called AI algorithms, without limitation.

[0100] Therefore, the embodiments of this application obtain output information based on the input information through the AI ​​model, and then adjust the transmission-related configuration parameters of the data link transport layer according to the output information. The AI ​​model is beneficial to dynamically and adaptively adjust the transmission-related configuration parameters of the data link transport layer by considering multiple factors, which is beneficial to meeting the user's business needs.

[0101] It should be understood that Figure 7 illustrates the steps or operations of the communication method, but these steps or operations are merely examples, and other operations or variations of the operations in Figure 7 may also be performed in this application.

[0102] In this embodiment, the execution entity for model inference is a first device, which can be a terminal or a network-side device in the system shown in Figure 1. For example, the network-side device can be a base station, a TRP (Telematics Retrieval System), or a core network device (such as a core network device specifically used for model training). The base station can be the base station of the cell where the terminal is currently camped, the base station of the cell the terminal is currently accessing, the base station of the target cell after the terminal's handover, the base station of the target cell after the terminal's reselection, the base station of the Pcell the terminal is currently accessing, or the base station of the Scell ​​the terminal is currently accessing, etc.

[0103] The AI ​​model can be trained by the first device itself, or it can be trained by the second device and sent to the first device, where the second device serves as the training device for the AI ​​model. Optionally, the second device can transmit the AI ​​model to the first device, such as transmitting the AI ​​model's parameters or identifiers. When the first device is a terminal, the second device can be another terminal or a network-side device; when the first device is a network-side device, the second device can be a terminal.

[0104] In the embodiments of this application, the AI ​​model may also be referred to as an AI unit, AI structure, etc., or the AI ​​model may refer to a processing unit that can implement specific algorithms, formulas, processing flows, capabilities, etc. related to AI, or the AI ​​model may be a processing method, algorithm, function, module or unit for a specific dataset, or the AI ​​model may be a processing method, algorithm, function, module or unit running on AI-related hardware such as a Graphics Processing Unit (GPU), Neural Network Processing Unit (NPU), Tensor Processing Unit (TPU), Application Specific Integrated Circuit (ASIC), etc. This application does not make specific limitations in this regard.

[0105] The identifier (i.e., ID) of the AI ​​model in this application embodiment may be a model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific dataset associated with the AI ​​model, or an identifier of a specific scene, environment, channel characteristics, or device related to AI, or an identifier of an AI-related function, characteristic, capability, or module. This application does not make any specific limitations on this.

[0106] In this embodiment, the AI ​​model's ID (or index) can be represented in various ways, such as the model's functional ID or model ID, physical ID, logical ID, global ID, or local ID. It is understood that an AI model may have multiple functions, and correspondingly, it can have multiple functional IDs. The global ID can be a unique, global ID defined by the AI ​​model across all networks or models provided by all model providers, uniquely identifying a model. The local ID is used to identify a model within a specific network or model provided by a specific model provider.

[0107] In some embodiments, the data link transport layer, or L2 layer, can correspond to the user plane protocol stack, mainly including protocol layers such as SDAP, PDCP, RLC, MAC, and PHY, used for the control and transmission of data blocks. Specifically, each protocol layer can be referred to in the relevant descriptions of Figures 2, 3A, 3B, 4, 5A, and 5B above.

[0108] Optionally, the data link transport layer can also be called the data link layer, link layer, L2 layer, etc., without limitation.

[0109] In some embodiments, the output information includes at least one of the following:

[0110] Automatic retransmission request (ARQ) retransmission related configuration parameters;

[0111] Configuration parameters related to Radio Link Control (RLC) layer status reporting;

[0112] Configuration parameters related to Media Access Control (MAC) packages;

[0113] The sending end transmits PDCP-related configuration parameters.

[0114] The receiving end transmits PDCP-related configuration parameters.

[0115] In one implementation, the output information is used to adjust at least one of the following:

[0116] Automatic retransmission request (ARQ) retransmission related configuration parameters;

[0117] Configuration parameters related to Radio Link Control (RLC) layer status reporting;

[0118] Configuration parameters related to Media Access Control (MAC) packages;

[0119] The sending end transmits PDCP-related configuration parameters.

[0120] The receiving end transmits PDCP-related configuration parameters.

[0121] In one implementation, ARQ retransmission related configuration parameters can be used to optimize the configuration of ARQ retransmission parameters, RLC layer status report related configuration parameters can be used to optimize the timing and / or content of status report transmission, MAC packet assembly related configuration parameters can be used to optimize the configuration of L2 packet assembly, sender PDCP transmission related configuration parameters can be used to optimize the configuration of sender PDCP transmission parameters, and receiver PDCP transmission related configuration parameters can optimize the configuration of receiver PDCP transmission parameters.

[0122] Therefore, this application embodiment can optimize and adjust the data link transport layer transmission-related configuration parameters by dynamically and adaptively adjusting at least one of the ARQ retransmission-related configuration parameters, RLC layer status report-related configuration parameters, MAC packet assembly-related configuration parameters, sender PDCP transmission-related configuration parameters, and receiver PDCP transmission-related configuration parameters based on an AI model, thereby meeting user service requirements.

[0123] Among them, MAC packet assembly can refer to the MAC layer assembling data packets from higher layers, such as RLC and MAC packet assembly, or PDCP, RLC and MAC packet assembly, etc., without limitation.

[0124] In some embodiments, the ARQ retransmission related configuration parameters include at least one of the following:

[0125] Maximum number of retransmissions;

[0126] The retransmission time point is used to indicate the time interval since the last initial transmission or retransmission.

[0127] New data volume;

[0128] Poll the relevant parameters.

[0129] The maximum number of retransmissions can be understood as the maximum number of retransmissions allowed before abandoning a retransmission. Limiting the maximum number of retransmissions helps avoid excessive retransmissions of data packets, which can lead to resource waste. Optionally, when the maximum number of retransmissions is 0, it can be understood as UM mode, i.e., no retransmissions.

[0130] The time interval since the last initial transmission or retransmission can include the time interval since the new transmission or blind retransmission with feedback, or the time interval of blind retransmission. Blind retransmission has no feedback.

[0131] Optionally, the amount of newly transmitted data includes at least one of the following:

[0132] The number of bits, bytes, and Protocol Data Units (PDUs) of the newly transmitted data must be at least one of the following:

[0133] The ratio of newly transmitted data bits to retransmitted data bits;

[0134] The ratio of newly transmitted data bytes to retransmitted data bytes;

[0135] The ratio of the number of PDUs for newly transmitted data to the number of PDUs for retransmitted data.

[0136] The number of bits, bytes, or PDUs in the newly transmitted data directly represents the amount of newly transmitted data. The ratio of the number of bits, bytes, or PDUs in the newly transmitted data to the number of retransmitted data indicates the amount of newly transmitted data relative to the amount of retransmitted data.

[0137] Optionally, the polling-related parameters include at least one of the following:

[0138] The number of bytes that triggered the polling;

[0139] The number of PDUs that triggered the polling;

[0140] Polling retransmission timer.

[0141] For example, the number of bytes that triggers polling can be represented as pollByte, the number of PDUs that trigger polling can be represented as pollPDU, and the polling retransmission timer can be represented as t-PollRetransmit.

[0142] Optionally, when the output information includes ARQ retransmission related configuration parameters, the input information may include at least one of the following:

[0143] Current RLC transmitter configuration parameters;

[0144] Current sending status;

[0145] Packet loss rate is the ratio of lost data packets to the total number of data packets sent.

[0146] Retransmission rate is the ratio of the number of retransmitted data packets to the number of newly transmitted data packets.

[0147] Average number of retransmissions;

[0148] Current transmission rate;

[0149] Average RLC PDU length;

[0150] The average amount of RLC PDU data transmitted per transmission interval;

[0151] Quality of Service (QoS) requirements;

[0152] Transmission Time Interval (TTI) length;

[0153] HARQ maximum retransmission count;

[0154] HARQ accuracy of Hybrid Automatic Repeat Requests;

[0155] HARQ ACK / NACK error rate;

[0156] Open port status.

[0157] For example, the packet loss rate can be the packet loss rate statistically calculated by the RLC layer or PDCP layer, such as the ratio of the number of NACKs received for all transmitted data packets (including initial transmissions and / or retransmissions) to the total number of transmitted data packets within a statistical period.

[0158] For example, the retransmission rate is the retransmission rate statistically calculated by the RLC layer, such as the ratio of the number of retransmitted data packets to the number of newly transmitted data packets within a statistical period.

[0159] For example, the average retransmission count is the average number of retransmissions of each data packet in the RLC within the statistical period. Optionally, if there are no retransmissions, the average retransmission count is 0.

[0160] For example, the current transmission rate is the transmission rate counted by the RLC layer or PDCP layer, and the unit can be bps.

[0161] For example, the average RLC PDU length can be the length of the RLC PDU transmitted for each Transmission Time Interval (TTI), including the number of PDUs and the length of each PDU, such as the ratio of the sum of the lengths of each PDU to the number of PDUs. Optionally, the average RLC PDU length can include the average number of RLC PDU bytes.

[0162] For example, the RLC PDU data volume can be the number of PDUs or the number of bytes.

[0163] Optionally, HARQ accuracy can be defined as the average number of HARQ retransmissions over a statistical period.

[0164] Optionally, the HARQ ACK / NACK error rate may include at least one of the error rate of treating ACK as NACK and the error rate of treating NACK as ACK.

[0165] Optionally, the current RLC transmitter configuration parameters include at least one of the following:

[0166] RLC mode;

[0167] SN length;

[0168] The number of PDUs that triggered the polling;

[0169] The number of bytes that triggered the polling;

[0170] Polling retransmission timer;

[0171] Maximum number of retransmissions.

[0172] Optionally, the RLC mode may include TM mode, UM mode, or AM mode.

[0173] For example, the current RLC transmitter configuration parameters may include polling-related parameters, such as the number of PDUs that trigger polling, the number of bits that trigger polling, and the polling retransmission timer.

[0174] Optionally, the current transmission status includes at least one of the following:

[0175] The number of data packets sent;

[0176] The time the data packet was sent;

[0177] Average data transmission rate as statistically analyzed by the RLC layer;

[0178] The number of retransmitted data packets;

[0179] The retransmission data packet sending time and the number of retransmissions must be at least one of the following:

[0180] Send window size;

[0181] The latency of data waiting to be transmitted while it is in the cache;

[0182] The latency from when data arrives at the buffer to when it is successfully received.

[0183] For example, the current transmission status can be obtained from the transmission status of the sender within a statistical period, such as the number of data packets sent within the statistical period, the transmission time of each data packet, the number of retransmitted data packets, the transmission time of retransmitted data packets, the average data transmission rate statistically analyzed by the RLC layer, the number of retransmissions of retransmitted data packets, the actual transmission window size, the latency of data packets waiting for transmission in the buffer, or the latency from data reaching the buffer to successful acceptance, etc. For example, the actual transmission window size can be represented as TX_Next_Ack to TX_Next.

[0184] Optionally, the service QoS requirements include at least one of the following:

[0185] The Aggregate Maximum Bit Rate (AMBR) describes the maximum rate at which a terminal can receive or send data within a specific time period.

[0186] Prioritized Bit Rate (PBR) is a parameter used to describe the maximum priority rate at which a terminal's logical channel can receive or transmit data within a specific time period.

[0187] Priority Level;

[0188] Packet Delay Budget is used to define the upper limit of the time from when a data packet arrives at the PDCP layer to when the air interface transmission is completed;

[0189] Packet error rate refers to the probability that a data packet cannot be received normally during transmission.

[0190] The 5G QoS Identifier (5QI) is used to identify different QoS flows;

[0191] Low latency requirement (Delay Critical) indicates a high requirement for real-time data transmission, where the latency budget is below a certain preset threshold.

[0192] Maximum Data Burst Volume refers to the maximum amount of data that the access network needs to transmit within one cycle of the access network.

[0193] Extended Packet Delay Budget indicates the maximum delay extension that a data packet can tolerate during transmission;

[0194] The PDU Set Packet Delay Budget is used to indicate that the time from the arrival of the first packet in the PDU set to the completion of the transmission of the last packet does not exceed a predetermined threshold.

[0195] PDU Set Error Rate is the proportion of PDU sets that have been successfully sent but not correctly received by the receiver.

[0196] PDU Set Integrated Handling Information refers to information that manages, schedules, or deletes individual data packets within a PDU set. For example, when this indication is set to True, if one data packet in the PDU set is deleted, the other data packets should also be deleted.

[0197] Optionally, the air interface status includes at least one of the following:

[0198] Channel State Information Reference Signal (CSI-RS);

[0199] Synchronization Signal Block (SSB) Reference Signal Receiving Power (RSRP);

[0200] Reference Signal Receiving Quality (RSRQ);

[0201] Signal to Interference plus Noise Ratio (SINR).

[0202] Optionally, CSI-RS, SSB RSRP, RSRQ, and SINR can be instantaneous values ​​or filtered values ​​over a period of time, without limitation.

[0203] In some embodiments, the output information includes Automatic Repeat Request (ARQ) retransmission configuration parameters, and the input information of the AI ​​model corresponding to the output information is a use case of the AI ​​model.

[0204] For example, in this use case, by inputting at least one of the following into the AI ​​model: the relevant configuration parameters of the RLC transmitter, the current transmission status, packet loss rate, retransmission rate, average number of retransmissions, current transmission rate, average RLC PDU length, average amount of RLC PDU data sent per transmission interval, service QoS requirements, HARQ accuracy, HARQ ACK / NACK error rate, and air interface status, the ARQ retransmission-related configuration parameters can be predicted.

[0205] Therefore, this application embodiment, by reasoning about ARQ retransmission related configuration parameters based on AI model and input information, can realize the required ARQ retransmission related configuration parameters adaptively obtained based on the actual transmission status and service QoS attributes and current status of different scenarios, thus meeting the requirements of wireless air interface L2.

[0206] In some embodiments, the RLC layer status reporting configuration parameters include at least one of the following:

[0207] The timing and / or content of sending a status report, wherein the timing indicates the time interval since the last status report was sent, and the content is the maximum sequence number (SN) of the feedback data packet; that is, whether the data packets below SN were received correctly needs to be reported.

[0208] The time to terminate retransmission is used to indicate when the receiving end should give up receiving the data packet; that is, the time interval between the operation of replying to the sending end with ACK even if it is not received correctly and the last time the NACK status report was sent for the data packet.

[0209] The delay reordering parameter is used to indicate the duration of the timer that triggers the sending status report timer, i.e., the T-reassembly timer;

[0210] PDCP reordering time, also known as T-reordering timer.

[0211] The timing and / or content of sending status reports may include the time interval from identifying the SN GAP to triggering the status report, which may vary for each GAP. The content of the status report includes the maximum SN of the returned data packets, i.e., the correct acceptance status of data packets with SNs smaller than that needs to be reported.

[0212] For example, the timing of sending status reports can include a status report prohibition (t-StatusProhibit) timer, used to control the prohibition of sending status reports for a certain period of time. For instance, the t-StatusProhibit timer is started when the receiver receives a status report request or when other triggering conditions are met. During the timer's operation, the receiver will not send new status reports, even if it receives more PDUs. This helps reduce the frequency of status report transmission, thereby alleviating network load.

[0213] The retransmission termination time is the time at which the receiving end gives up receiving a certain data packet. Specifically, the retransmission termination time can be the time when the receiving end replies with an ACK to the sending end even if it has not received the packet correctly, or the time interval between sending the ACK and the last time the packet received a NACK status report.

[0214] For example, the delay reordering parameter can be the duration of a reassembly timer (t-Reassembly), used to control the reassembly process of the RLC receiver after receiving an AM-mode RLC PDU. For instance, if t-Reassembly times out, the RLC receiver entity will update the corresponding status variables and restart t-Reassembly if necessary. Furthermore, the timeout of t-Reassembly triggers the generation of a status report to inform the sender about the PDU reception status. t-Reassembly can also determine the timing of sending the status report content based on existing status variables.

[0215] The PDCP reordering time, or t-re-ordering parameter, can be a timer in the PDCP layer used for packet reordering to ensure that data is delivered to the upper layer in the correct order.

[0216] Optionally, when the output information includes configuration parameters related to the RLC layer status report, the input information may include at least one of the following:

[0217] Current RLC receiver configuration parameters;

[0218] Data packet reception status;

[0219] Status report sent status;

[0220] Retransmission rate;

[0221] Average waiting time;

[0222] Open port status;

[0223] Service QoS requirements;

[0224] TTI length;

[0225] HARQ maximum retransmission count;

[0226] HARQ accuracy;

[0227] HARQ ACK / NACK error rate.

[0228] Optionally, the current RLC receiver configuration parameters include at least one of the t-Reassembly timer duration and the t-StatusProhibit timer duration.

[0229] Optionally, the data packet reception status includes at least one of the following:

[0230] The number of data packets received within a statistical period;

[0231] Data packet reception time;

[0232] Status report of the sent data packets;

[0233] The number of NACKs corresponding to data packets;

[0234] The ratio of the number of data packets waiting to be received in the receive window to the window size.

[0235] The number of NACK counts for a data packet can be 1 or more, without limitation.

[0236] For example, the window size of the receiving window can be represented as (RX_Next~RX_Next_Highest).

[0237] Optionally, the status report sending status includes the average sending frequency of status reports within a statistical period.

[0238] Optionally, the retransmission rate includes the ratio of data packets retransmitted N times to all data packets, where N is a positive integer.

[0239] For example, the retransmission rate may include the ratio of a retransmitted data packet to all data packets, or the ratio of a retransmitted data packet to all data packets, or the ratio of a retransmitted data packet to all data packets, etc., without limitation.

[0240] For example, the retransmission rate can be the ratio of NACKs sent to ACKs sent within a statistical period, or the average number of NACKs sent for a specific data packet.

[0241] Optionally, the average waiting time includes at least one of the following:

[0242] SN gap average waiting time; refers to the time interval from the occurrence of an SN GAP to the correct reception of the corresponding data packet;

[0243] The ratio of the number of times the reconfiguration timer is reset to the number of times the reconfiguration timer expires. The number of times the reconfiguration timer expires can also be referred to as the number of times the reconfiguration timer is started.

[0244] For details regarding air interface status, service QoS requirements, HARQ accuracy, and HARQ ACK / NACK error rate, please refer to the relevant descriptions above.

[0245] In some embodiments, the output information includes configuration parameters related to the RLC layer status report, and the input information of the AI ​​model corresponding to the output information is another use case of the AI ​​model.

[0246] For example, in this use case, at least one of the following can be input into the AI ​​model: relevant configuration parameters of the RLC receiver, packet reception status, status report sending status, retransmission rate, average waiting latency, air interface status, service QoS requirements, HARQ accuracy, and HARQ ACK / NACK error rate, to predict the relevant configuration parameters of the RLC layer status report.

[0247] Therefore, this application embodiment, by reasoning from the AI ​​model and input information, obtains the configuration parameters related to the RLC layer status report. It can achieve the adaptive acquisition of the required RLC layer status report configuration parameters based on the actual transmission status and service QoS attributes and current status of different scenarios, thus meeting the requirements of wireless air interface L2.

[0248] In some embodiments, the configuration parameters of the MAC packet include at least one of the following:

[0249] Selected logical channel (LCH);

[0250] The amount of data selected for each logical channel (LCH);

[0251] The priority order of at least two of the following: LCH PDU, RLC new transmission PDU, RLC retransmission PDU, RLC control PDU, and PDCP control PDU;

[0252] At least two PDCP PDU priority orders;

[0253] Priority order of at least two RLC PDUs;

[0254] At least two MAC addresses control the priority order of PDUs;

[0255] The length of SN;

[0256] Prioritized Bit Rate (PBR) parameters for each logical channel;

[0257] Priority of each logical channel.

[0258] The selected LCH is the one used for packet assembly at the PDCP, RLC, and MAC layers. The number of selected LCHs can be one, two, or more, without limitation. Furthermore, the data volume of each LCH is also not limited; it can be one, two, or more.

[0259] When the PDUs that need to be packaged include MAC PDU, RLC new transmission PDU, RLC retransmission PDU, RLC control PDU, PDCP control PDU, and MAC control unit, the relevant configuration parameters may also include the priority order of at least two of the following: MAC PDU, MAC control unit, RLC new transmission PDU, RLC retransmission PDU, RLC control PDU, and PDCP control PDU.

[0260] When at least two PDCP PDUs are included, the relevant configuration parameters may also include the priority order of the at least two PDCP PDUs. When at least two RLC PDUs are included, the relevant configuration parameters may also include the priority order of the at least two RLC PDUs. When at least two MAC control PDUs are included, the relevant configuration parameters may also include the priority order of the at least two MAC control PDUs.

[0261] Therefore, when performing MAC packet assembly, PDUs can be selected sequentially according to the configured priority order.

[0262] The PBR parameter of each selected logical channel is the priority rate configured for each logical channel, which is the transmission rate that the corresponding logical channel is given priority to guarantee within a specific time period. This helps to ensure that high-priority logical channels can obtain more resources during data transmission to meet transmission requirements.

[0263] The priority of each selected logical channel, i.e., the priority of data packet transmission within the logical channel, allows for the sequential assembly and transmission of corresponding data packets according to their logical channel priority. For example, the logical channel priority values ​​range from 1 to 16, with smaller values ​​indicating higher priority.

[0264] Optionally, when the output information includes configuration parameters related to MAC packet assembly, the input information may include at least one of the following:

[0265] Service QoS requirements;

[0266] The current logical channel priority processing LCP-related configuration parameters;

[0267] The amount of business data to be transmitted;

[0268] Current LCP and service transmission status;

[0269] Open port status;

[0270] Cell load status.

[0271] Among them, the configuration parameters related to Logical Channel Prioritization (LCP) are used to determine which logical channel's data should be processed first when multiple logical channels have data to be sent.

[0272] Optionally, the current LCP-related configuration parameters include at least one of the following:

[0273] At least one of the following parameters must be used: logical channel priority, priority bit rate (PBR), token bucket duration (BSD), and LCP restriction.

[0274] Among them, the token bucket duration (BSD) represents the length of time that tokens accumulate in the token bucket algorithm.

[0275] The LCP limiting parameters can be used to manage or limit the priority processing of logical channels. Optionally, the LCP limiting parameters include at least one of the following:

[0276] Allowed serving cell;

[0277] Allowable subcarrier spacing (SCS);

[0278] Maximum uplink shared channel (PUSCH) duration;

[0279] The configured grant type 1 is allowed.

[0280] Allowed PHY-PriorityIndex;

[0281] Allowed HARQ mode.

[0282] Optionally, the amount of service data to be transmitted includes at least one of the following:

[0283] The amount of new data to be transmitted;

[0284] The amount of data to be retransmitted;

[0285] At least one of the PDCP data volume and priority to be transmitted;

[0286] At least one of the following must be present: the amount of RLC data to be transmitted and its priority.

[0287] The amount of MAC control data to be transmitted and its priority must be at least one of the following:

[0288] Optionally, the current LCP and service transmission status includes at least one of the following:

[0289] LCH Bj satisfaction rate is used to represent the proportion of Bj that is satisfied in each scheduling within a statistical period; where Bj is used to represent the amount of data guaranteed by the token bucket.

[0290] The duration that LCH Bj cannot satisfy;

[0291] LCH transmission average delay;

[0292] Statistical analysis of packet loss rate at the RLC layer or MAC layer;

[0293] TTI length;

[0294] HARQ maximum retransmission count;

[0295] ARQ or HARQ retransmission rate;

[0296] The transmission rate counted by the RLC layer or PHY layer;

[0297] The number or proportion of packets deleted due to latency at the PDCP layer.

[0298] The cell load status can include the cell load level or percentage, without limitation.

[0299] In some embodiments, the output parameters include relevant configuration parameters of the MAC group, and the input information of the AI ​​model corresponding to the output information is another use case of the AI ​​model.

[0300] For example, in this use case, by taking at least one of the following input values—service QoS requirements, current LCP-related configuration parameters, the amount of service data to be transmitted, current LCP and service transmission status, air interface status, cell load status, etc.—as an AI model, the relevant configuration parameters for MAC packet assembly are predicted.

[0301] Therefore, this application embodiment, by reasoning the relevant configuration parameters of MAC packets based on the AI ​​model and input information, can realize the adaptive acquisition of the required MAC packet configuration parameters based on the actual transmission status and service QoS attributes and current status of different scenarios, thereby meeting the requirements of wireless air interface L2.

[0302] In some embodiments, the PDCP transmission-related configuration parameters of the transmitting end include at least one of the following:

[0303] Whether to enable PDCP duplication;

[0304] Enable integrity protection;

[0305] Partial data packets that are protected for integrity;

[0306] Number of PDCP SDUs cascaded;

[0307] Whether to enable SDU discard based on PDCP timer;

[0308] SDUs based on PDCP timers discard the corresponding suggested timer values;

[0309] Whether to enable header compression algorithm;

[0310] Enable header compression algorithm selection;

[0311] Whether to enable Uplink Data Compression (UDC) and the corresponding algorithm.

[0312] PDCP duplication refers to sending the same PDCP PDU through multiple RLC entities, thereby increasing the probability of data being received correctly and enhancing transmission reliability.

[0313] Integrity protection ensures that data remains in its original state during transmission and is not subject to unauthorized modification, tampering, or destruction.

[0314] A PDCP SDU refers to a data unit processed at the PDCP layer. It typically refers to data received from the upper layer that undergoes header compression, integrity protection, and encryption at the PDCP layer before being sent to the lower layer for transmission. PDCP SDU concatenation refers to the ability of a single PDCP PDU to contain data from multiple SDUs. That is, when the PDCP layer encapsulates SDUs into a PDU, it may merge the data from multiple SDUs into a single PDU. Optionally, this includes transmitting multiple PDCP SDUs within a single TTI as multiple PDCP PDUs. PDCP SDU concatenation reduces the number of PDCP PDUs, thereby reducing transmission overhead and improving transmission efficiency.

[0315] SDU discarding based on PDCP timers: By monitoring the transmission status of PDCP SDUs and discarding outdated SDUs in a timely manner, space in the transmission buffer is freed up, ensuring timely data transmission.

[0316] Header compression algorithms can identify and eliminate redundant information in the packet header, thereby reducing the size of the header information and the amount of data transmitted. Optionally, header compression algorithms may include, but are not limited to, robust header compression (ROHC) algorithms.

[0317] Uplink data compression (UDC) reduces uplink data transmission volume and improves uplink air interface utilization and reliability by identifying and eliminating redundant information in the data. Optionally, the UDC algorithm may include, but is not limited to, Differential Pulse Code Modulation (DPCM), Adaptive Differential Pulse Code Modulation (ADPCM), and Huffman coding.

[0318] Optionally, when the output information includes configuration parameters related to PDCP transmission at the sending end, the input information may include at least one of the following:

[0319] Current PDCP layer configuration parameters;

[0320] Current data link transport layer transmission status;

[0321] Open port status;

[0322] Service QoS requirements;

[0323] Data link transport layer processing status;

[0324] The application (APP) layer processes information.

[0325] Optionally, the current PDCP layer configuration parameters include at least one of the following:

[0326] Delete the timer;

[0327] SN serial number length;

[0328] Header compression algorithm and parameters;

[0329] Integrity protection status;

[0330] Status reporting enabled or disabled;

[0331] Submit in sequence whether to open or not;

[0332] Multiple RLC mappings;

[0333] Reordering t-reordering timer duration;

[0334] Uplink data compression parameters;

[0335] The PDU set includes at least one of the processing switches and the encryption switch.

[0336] The discard timer in the PDCP layer, also known as a drop timer, controls when unsuccessfully transmitted data packets are discarded. During data transmission, when a data packet waits in the transmit buffer for longer than the set value of the discard timer, the PDCP layer will give up waiting and discard the data packet. For example, this discard timer can be the timer used in the SDU discarding mechanism based on the PDCP timer mentioned above.

[0337] Optionally, the current data link transport layer transmission status includes at least one of the following:

[0338] RLC retransmission rate, bit error rate, and average transmission delay at the PDCP layer.

[0339] RLC retransmission rate refers to the proportion of data packets that need to be retransmitted at the RLC layer due to transmission errors or loss. It can be obtained by comparing the number of retransmitted data packets to the total number of data packets sent within a statistical period. Symbol Error Rate (SER) represents the proportion of erroneous code blocks to the total number of code blocks during data transmission. It can be determined by comparing the number of erroneous bits to the total number of code blocks within a statistical period. Bit Error Rate (BER) represents the proportion of erroneous bits to the total number of bits transmitted. It can be calculated by comparing the number of erroneous bits to the total number of transmitted bits within a statistical period.

[0340] PDCP layer transmission delay refers to the average time from when the transmitting end of the PDCP receives a data packet from a higher layer to when the data packet is correctly sent to the other end. It includes the data packet processing time in the PDCP layer, the transmission time in the wireless channel, and possible retransmission time.

[0341] Optionally, the information processed by the application (APP) layer includes at least one of the following:

[0342] Whether forward error correction (FEC) is supported, FEC parameters, redundancy ratio, and ability to handle out-of-order packets.

[0343] FEC (Fault-Correcting Encoding) incorporates redundant error-correcting codes into the transmitted data, enabling the receiver to automatically correct any distortions or errors in the received signal using a decoding algorithm, thereby reducing the received signal's bit error rate (BER). Optionally, FEC parameters may include, but are not limited to, coding overhead, decision method, and codeword scheme. The redundancy ratio is the ratio of redundant information added during FEC encoding to correct potential transmission errors to the original data information.

[0344] Optionally, the data link transport layer processing includes at least one of processing latency and resource consumption.

[0345] Data link transport layer processing latency is the time required for data to be processed at the data link transport layer. Resource consumption can include computing resources, storage resources, bandwidth resources, etc. required during the data processing at the data link transport layer.

[0346] In some embodiments, the output information includes PDCP transmission-related configuration parameters of the sending end, and the input information of the AI ​​model corresponding to the output information is another use case of the AI ​​model.

[0347] For example, in this use case, at least one of the following can be input into the AI ​​model: current PDCP layer configuration parameters, current data link transport layer transmission status, air interface status, service QoS requirements, data link transport layer processing status, and application (APP) layer processing information, to predict the PDCP transmission-related configuration parameters of the sending end.

[0348] Therefore, this application embodiment, by reasoning from the AI ​​model and input information, obtains the PDCP transmission-related configuration parameters of the transmitting end, and can realize the adaptive acquisition of the required PDCP transmission-related configuration parameters of the transmitting end based on the actual transmission status and service QoS attributes and current status of different scenarios, thereby meeting the requirements of L2 wireless interface.

[0349] In some embodiments, the receiving end PDCP transmission related configuration parameters include at least one of the following:

[0350] Whether to enable out-of-order delivery;

[0351] Reordering time (t-re-ordering).

[0352] For example, in the out-of-order delivery mechanism, the PDCP layer assigns a serial number (SN) to each data packet to ensure that the receiver can identify the order of the packets. When a data packet arrives at the receiver, the PDCP layer reorders the packets according to the SN to restore the original order. The receiver can set a reordering timer to wait for out-of-order data packets. If the lost data packet is not received before the timer expires, the receiver can deliver the current data packet to a higher layer or request a retransmission. This timer is called the t-re-ordering timer.

[0353] Optionally, when the output information includes configuration parameters related to the receiver's PDCP transmission, the input information includes at least one of the following:

[0354] Service QoS requirements;

[0355] Service rate statistics at the RLC / PDCP layer;

[0356] Average PDCP latency at the receiver;

[0357] RLC configuration parameters;

[0358] Receiver RLC statistical parameters;

[0359] MAC HARQ configuration parameters.

[0360] The average waiting time of the receiver PDCP is the average time that a data packet waits to be processed in the receiver PDCP layer. It can be the average time from when the data packet arrives at the receiver PDCP buffer to when the data packet is passed to the higher layer.

[0361] RLC configuration parameters may include, but are not limited to, at least one of the following: maximum retransmission count and receive window size. Maximum retransmission count refers to the maximum number of retransmission attempts allowed by the sender for a data packet that has not been successfully received within the RLC layer. If an ACK is not received within this number, the data packet may be discarded or an error reported. Receive window size refers to the range of data packet numbers (SNs) that the receiver can process simultaneously. This window size determines the number of unacknowledged data packets that the receiver can receive and buffer.

[0362] Receiver RLC statistics can include the average wait time for RLC SN GAP. RLC SN GAP reflects the average wait time at the receiver when processing packets with discontinuous SNs, that is, the average time from detecting the presence of an SN GAP in the received packets to successfully receiving the packet that fills the GAP.

[0363] MAC HARQ configuration parameters may include, but are not limited to, at least one of the following: TTI, maximum number of retransmissions.

[0364] In MAC HARQ, the sender waits for ACK / NACK feedback from the receiver at the end of each TTI to decide whether to retransmit. The length and number of TTIs affect the timing and frequency of HARQ feedback. For example, the TTI length can be 1ms, or it can be a shorter TTI, such as a short TTI, to meet the needs of low-latency services.

[0365] In MAC HARQ, the maximum number of retransmissions defines the maximum number of times the sender is allowed to retransmit data after receiving a NACK from the receiver, thus preventing resource waste caused by unlimited retransmissions.

[0366] In some embodiments, the output information includes configuration parameters related to the receiving end PDCP transmission, and the input information of the AI ​​model corresponding to the output information is a use case of the AI ​​model.

[0367] For example, in this use case, by inputting at least one of the following into the AI ​​model: service QoS requirements, service rate statistics of RLC / PDCP layer, average waiting time of receiver PDCP, RLC configuration parameters, receiver RLC statistical parameters, MAC HARQ configuration parameters, etc., the receiver PDCP transmission-related configuration parameters can be predicted.

[0368] Therefore, this application embodiment, by reasoning about the receiving end PDCP transmission-related configuration parameters based on the AI ​​model and input information, can realize the required receiving end PDCP transmission-related configuration parameters adaptively obtained based on the actual transmission status and service QoS attributes and current status of different scenarios, thus meeting the requirements of wireless air interface L2.

[0369] In some embodiments, in the above communication method, the first device may also obtain the performance supervision configuration information of the AI ​​model and perform performance supervision on the AI ​​model according to the supervision configuration information.

[0370] For example, the performance supervision configuration information of the AI ​​model can be sent to the first device by the training device of the AI ​​model, or it can be sent to the first device by other devices (such as the second device). The first device can determine when and / or how to perform model supervision based on the performance supervision configuration information.

[0371] Understandably, when the inference environment of an AI model differs significantly from its training environment, the inference performance of the AI ​​model will become very poor, meaning the accuracy of the inferred information may be insufficient. Therefore, it is necessary to supervise the actual inference performance of AI models to ensure the reliability of their inference results.

[0372] Optionally, the performance monitoring configuration information may include at least one of the following:

[0373] Monitor parameters and / or reference values;

[0374] The threshold value that triggers the reporting.

[0375] Among them, the monitoring parameters and / or reference values ​​are used as indicators for evaluating the performance of the AI ​​model, i.e., the AI ​​model performance supervision and evaluation conditions. The threshold value that triggers reporting is used to indicate the reporting conditions for the performance of the AI ​​model.

[0376] Optionally, the performance monitoring configuration information includes at least one of the following:

[0377] Reporting threshold values ​​corresponding to transmission rates of different air interface signal qualities;

[0378] Reporting threshold values ​​for packet loss rates corresponding to different air interface signal qualities;

[0379] Reporting threshold values ​​for retransmission rates corresponding to different air interface signal qualities;

[0380] The reporting threshold for the proportion of data packets that are deleted or become delay-critical data;

[0381] The reporting threshold for the percentage of retransmissions that are abandoned;

[0382] Transmission delay reporting threshold

[0383] The reporting threshold for packet loss rate;

[0384] The reporting threshold value corresponding to the retransmission rate;

[0385] The reporting threshold for redundancy retransmission rate; that is, the ratio of unnecessary retransmissions to all retransmissions.

[0386] The reporting threshold for the PDCP packet deletion ratio.

[0387] For example, air interface signal quality may include, but is not limited to, CSI-RS, SSB RSRP, RSRQ, etc. Different transmission rate reporting thresholds may correspond to different ranges of air interface signal quality values. Different packet loss rate reporting thresholds may correspond to different ranges of air interface signal quality values. Different retransmission rate reporting thresholds may correspond to different ranges of air interface signal quality values.

[0388] The actual value corresponding to the air interface signal quality can include the actual value of the transmission rate, the actual value of the packet loss rate, or the actual value of the retransmission rate. When the actual value of the air interface signal quality exceeds (or falls below) the reporting threshold of the corresponding reference value, the first device can perform performance monitoring and reporting.

[0389] Data packets may be deleted or become delay critical data due to latency. This means that when the proportion of data packets that are deleted or become delay critical data exceeds the configured reporting threshold within a statistical period, the first device can perform performance monitoring and reporting.

[0390] Optionally, different reporting thresholds can be configured for different air interface conditions, such as the reporting threshold for the proportion of retransmissions that can be abandoned, the reporting threshold for transmission delay, the reporting threshold for packet loss rate, the reporting threshold for retransmission rate, the reporting threshold for redundant retransmission rate, and the reporting threshold for the proportion of PDCP packet deletion. The first device performs statistics for a period of time, and when the statistical value reaches the corresponding reporting threshold, it performs performance monitoring and reporting.

[0391] Therefore, in this embodiment of the application, the performance supervision configuration information of the AI ​​model is obtained by the first device, and the AI ​​model is supervised according to the performance supervision configuration information to determine whether the performance of the AI ​​model meets the requirements, which helps to ensure the reliability of the AI ​​model.

[0392] In some embodiments, the first device may receive first signaling from the second device, the first signaling including the performance monitoring configuration information. Correspondingly, the second device sends the first signaling, including the performance monitoring configuration information, to the first device.

[0393] For example, the first device can be a terminal, and the second device can be a network-side device. When the terminal deploys an AI model for model inference and model performance supervision, the network-side device can configure corresponding performance supervision configuration information for the AI ​​model. Optionally, the network-side device can configure corresponding performance supervision configuration information for each use case of the AI ​​model.

[0394] One possible implementation is that the first signaling can be Radio Resource Control (RRC) signaling. RRC signaling can be used to statically configure performance supervision information for the AI ​​model.

[0395] Another possible implementation is that the first signaling can be a MAC Control Element (MAC CE) or Downlink Control Information (DCI). MAC CE or DCI can be used to dynamically configure the performance supervision information of the AI ​​model.

[0396] For example, when a terminal acts as the transmitter, if the differences between its measured downlink and uplink signal quality are significant, the network-side device can use dynamic signaling, such as MAC CE or DCI, to notify the terminal of the performance supervision configuration information of the AI ​​model in real time. Optionally, the network-side device can also use dynamic downlink signaling, such as MAC CE or DCI, to notify the terminal of the performance supervision configuration information of the AI ​​model based on uplink air interface quality or congestion conditions.

[0397] Optionally, the first device can also compare the statistical value with the performance monitoring configuration information and send model monitoring feedback information to the second device when the trigger reporting threshold is met. Correspondingly, the second device can receive the model monitoring feedback information.

[0398] Specifically, the first device can compare actual statistical values ​​over a statistical period, such as transmission rates, packet loss rates, and retransmission rates exceeding reference values ​​for CSI-RS, SSB RSRP, and RSRQ, the proportion of data packets deleted or becoming latency-critical data, the proportion of abandoned retransmissions, transmission latency, and the proportion of PDCP data packet deletions, with the reporting threshold values ​​in the performance monitoring configuration information. If the reporting threshold is met, model monitoring feedback information is sent to the second device. The second device can then adjust the AI ​​model based on this feedback, such as updating or rolling back the model, thereby improving its reliability.

[0399] In some embodiments, the first device may also obtain model inference configuration information from the second device, the model inference configuration information being used to indicate the input information and the output information. Correspondingly, the second device sends the model inference configuration information to the first device.

[0400] For example, the first device can be a terminal, and the second device can be a network-side device. When the terminal deploys an AI model for model inference, the network-side device can configure corresponding model inference configuration information for the AI ​​model, that is, configure the corresponding input and output information. Optionally, the network-side device can configure corresponding model inference configuration information for each use case of the AI ​​model.

[0401] One possible implementation is that the second device can send RRC signaling to the first device, which includes model inference configuration information.

[0402] In some embodiments, the first device may also send capability reporting information to the second device. This capability reporting information indicates use cases supported by the AI ​​model, and the use cases include at least one of the input information and the output information. Correspondingly, the second device receives this capability reporting information.

[0403] For example, when the first device is a terminal and the second device is a network-side device, the terminal device can also send capability reporting information to the network-side device to indicate the use cases supported by the AI ​​model deployed on the terminal, thereby enabling the terminal to report the capabilities of the use cases supported by the AI ​​model. Optionally, the network-side device can configure corresponding model inference configuration information or performance supervision configuration information for the terminal based on the use cases supported by the terminal.

[0404] In some embodiments, the input information satisfies at least one of the following:

[0405] The input information is obtained based on the average of the statistical values ​​of at least one RLC entity, at least one PDCP entity, or at least one MAC entity on the terminal;

[0406] The input information is obtained based on the statistical values ​​of the RLC entities;

[0407] The input information is obtained based on the statistical values ​​of PDCP entities;

[0408] The input information is obtained based on the statistical values ​​of the MAC entity;

[0409] The input information is obtained based on the statistical values ​​of resource blocks (RBs).

[0410] When the input information is obtained based on the statistical values ​​of at least one RLC entity, at least one PDCP entity, or at least one MAC entity on the terminal, the inference of the AI ​​model is performed at the granularity of each terminal. For example, the input information may be the average of the statistical values ​​of at least one RLC entity, or the average of the statistical values ​​of at least one PDCP entity, or the average of the statistical values ​​of at least one MAC entity.

[0411] When the input information is obtained based on the statistical values ​​of RLC entities, the AI ​​model's inference is performed at the granularity of each RLC entity. That is, the statistical value of each RLC entity can be used as input information for model inference. For example, the statistical value of each RLC entity can be input into the AI ​​model to obtain ARQ retransmission-related configuration parameters or RLC layer status report-related configuration parameters.

[0412] When the input information is obtained based on the statistical values ​​of PDCP entities, the AI ​​model's inference is performed at the granularity of each PDCP entity. That is, the statistical value of each PDCP entity can be used as input information for model inference. For example, the statistical value of each PDCP entity can be input into the AI ​​model to obtain the relevant configuration parameters for MAC packet assembly, or the relevant configuration parameters for PDCP transmission at the sending end, or the relevant configuration parameters for PDCP transmission at the receiving end.

[0413] When the input information is obtained based on the statistical values ​​of MAC entities, the AI ​​model's inference is performed at the granularity of each MAC entity. That is, the statistical value of each MAC entity can be used as input information for model inference. For example, the statistical value of each MAC entity can be input into the AI ​​model to obtain the relevant configuration parameters of the MAC grouping.

[0414] When input information is obtained based on the statistical values ​​of Resource Blocks (RBs), the AI ​​model's inference is performed at the granularity of each RB. Specifically, at least one of the statistical values ​​of the RLC entity, the PDCP entity, and the MAC entity corresponding to each RB is used as input for model inference. Here, RBs are the basic units used for resource scheduling, carrying and transmitting data. For example, at least one of the statistical values ​​of the RLC entity, PDCP entity, and MAC entity corresponding to each RB can be input into the AI ​​model to obtain ARQ retransmission configuration parameters, or RLC layer status report configuration parameters, or MAC packet assembly configuration parameters, or sending-end PDCP transmission configuration parameters, or receiving-end PDCP transmission configuration parameters, etc.

[0415] Optionally, the output information satisfies at least one of the following:

[0416] The output information is at the terminal level;

[0417] The output information is at the RLC entity level;

[0418] The output information is at the PDCP entity level;

[0419] The output information is at the MAC entity level;

[0420] The output information is in RB granularity.

[0421] For example, when the input information is obtained based on the average of the statistical values ​​of at least one RLC entity, at least one PDCP entity, or at least one MAC entity on the terminal (i.e., the input information is at the terminal level), the output information can be at the terminal level. When the input information is obtained based on the statistical values ​​of an RLC entity (i.e., the input information is at the RLC entity level), the output information can be at the RLC entity level. When the input information is obtained based on the statistical values ​​of a PDCP entity (i.e., the input information is at the PDCP entity level), the output information can be at the PDCP entity level. When the input information is obtained based on the statistical values ​​of a MAC entity (i.e., the input information is at the MAC entity level), the output information is at the MAC entity level. When the input information is obtained based on the statistical values ​​of an RB (i.e., the input information is at the RB level), the output information is at the RB level.

[0422] In summary, this application embodiment, by reasoning output information based on input information using an AI model, can adaptively optimize the transmission-related configuration parameters of the data link transport layer by combining dynamically changing service QoS attributes and the actual transmission status of the data link transport layer, thereby meeting user service needs. For example, this application embodiment can dynamically optimize the configuration of ARQ retransmission-related parameters based on the AI ​​model algorithm, determine the optimal time to send status reports, perform optimal packet assembly at the data link transport layer, configure the PDCP parameters at both the sending and receiving ends, and satisfy the different configurations of each layer of the data link transport layer, such as the RLC layer, PDCP layer, and MAC layer, in different scenarios. Furthermore, it can quickly, accurately, and with low overhead adaptively adjust to a suitable configuration to improve the transmission efficiency of user plane data, increase data transmission rate, and ensure user experience.

[0423] Figure 8 illustrates a schematic diagram of another communication method based on an artificial intelligence (AI) model according to an embodiment of this application. It should be understood that Figure 8 illustrates the steps or operations of the communication method, but these steps or operations are merely examples, and other operations or variations of the operations shown in Figure 8 may also be performed in this application.

[0424] As shown in Figure 8, method 800 includes steps 810 to 880.

[0425] 810, data collection and model training are performed on the terminal or network side.

[0426] For example, data collection and model training for AI model training can be performed on either the terminal or the network side. For example, the data used for AI model training may include at least one of the input parameters and output parameters of the AI ​​model inference, i.e., parameters of the L2 layer, such as at least one of the various input and output information shown in Figure 7.

[0427] It should be understood that the model inference in Figure 8 is described using the terminal as an example. In other embodiments, the network side can also perform model inference, and this application does not limit this.

[0428] 820, AI model is transmitted from the network side to the terminal.

[0429] For example, after the network side collects data and trains the AI ​​model, it can transmit the trained model to the terminal, thereby enabling the deployment of the AI ​​model on the terminal. Optionally, the network side can send the AI ​​model's identifier, parameters, and network structure to the terminal, without limitation.

[0430] 830, the terminal reports its model use case capabilities to the network side.

[0431] For example, the terminal may send capability reporting information to the network side to indicate the use cases supported by the AI ​​model, wherein the use cases include at least one of the input information and the output information.

[0432] 840, The network side sends model inference configuration information to the terminal.

[0433] The model inference configuration information is used to indicate the input and output information of the AI ​​model deployed on the first device. Specifically, the input and output information of the AI ​​model are described in Figure 7.

[0434] 850, the network side sends performance monitoring configuration information to the terminal.

[0435] The performance supervision configuration information is used to supervise the performance of the AI ​​model, thereby helping to ensure the reliability of the AI ​​model. For details, please refer to the relevant description in Figure 7.

[0436] 860, the terminal performs model inference and model supervision.

[0437] Specifically, the terminal can perform model inference based on the model inference configuration information to obtain output information. The terminal can also supervise the AI ​​model based on the model's performance supervision configuration information.

[0438] 870, the terminal sends model monitoring feedback information to the network side.

[0439] Specifically, when the terminal compares the statistical values ​​with the model's performance supervision configuration information, it sends model monitoring feedback information to the network-side device when the trigger reporting threshold is met.

[0440] 880, The network side sends model update / rollback information to the terminal.

[0441] Specifically, the network side can determine whether to update or roll back the AI ​​model based on model monitoring feedback, and send the update / rollback information to the terminal. Correspondingly, the terminal can update or roll back the AI ​​model based on this information.

[0442] Therefore, the embodiments of this application obtain output information based on the input information through the AI ​​model, and then adjust the transmission-related configuration parameters of the data link transport layer according to the output information. The AI ​​model is beneficial to dynamically and adaptively adjust the transmission-related configuration parameters of the data link transport layer by considering multiple factors, which is beneficial to meeting the user's business needs.

[0443] The communication method based on intelligent algorithms provided in this application can be executed by a communication device. This application uses the execution of the intelligent algorithm-based communication method by a communication device as an example to illustrate the communication device provided in this application.

[0444] This application provides a communication device. As an example, the communication device may be a communication equipment or a component within a communication equipment, such as a chip. The communication equipment may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0445] The communication device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0446] Specifically, referring to Figure 9, the communication device 900 includes a processing module 901, used to acquire input information; and to obtain output information based on the AI ​​model and the input information, wherein the output information is used to adjust the transmission-related configuration parameters of the data link transmission layer.

[0447] Optionally, the output information includes at least one of the following:

[0448] Automatic retransmission request (ARQ) retransmission related configuration parameters;

[0449] Configuration parameters related to Radio Link Control (RLC) layer status reporting;

[0450] Configuration parameters related to Media Access Control (MAC) packages;

[0451] Sending end PDCP transmission related configuration parameters;

[0452] The receiving end transmits PDCP-related configuration parameters.

[0453] Optionally, the ARQ retransmission related configuration parameters include at least one of the following:

[0454] Maximum number of retransmissions;

[0455] The retransmission time point is used to indicate the time interval since the last initial transmission or retransmission.

[0456] New data volume;

[0457] Poll the relevant parameters.

[0458] Optionally, the amount of newly transmitted data includes at least one of the following:

[0459] The number of bits / bytes of newly transmitted data and the number of Protocol Data Units (PDUs) must be at least one of the following:

[0460] The ratio of newly transmitted data bits / bytes to retransmitted data bits / bytes;

[0461] The ratio of the number of PDUs for newly transmitted data to the number of PDUs for retransmitted data.

[0462] Optionally, the polling-related parameters include at least one of the following:

[0463] The number of bytes that triggered the polling;

[0464] The number of PDUs that triggered the polling;

[0465] Polling retransmission timer.

[0466] Optionally, the configuration parameters related to the RLC layer status report include at least one of the following:

[0467] The timing and / or content of sending a status report, wherein the timing is used to indicate the time interval since the last status report was sent, and the content is the maximum sequence number (SN) of the feedback data packet;

[0468] The time to terminate retransmission is used to indicate when the receiving end should give up receiving data packets;

[0469] The delay reordering parameter indicates the duration for triggering the timer to send the status report;

[0470] PDCP reordering time.

[0471] Optionally, the configuration parameters for the MAC packet include at least one of the following:

[0472] Selected logical channel (LCH);

[0473] The amount of data selected for each logical channel (LCH);

[0474] The priority order of at least two of the following: LCH PDU, RLC new transmission PDU, RLC retransmission PDU, RLC control PDU, and PDCP control PDU;

[0475] At least two PDCP PDU priority orders;

[0476] Priority order of at least two RLC PDUs;

[0477] At least two MAC addresses control the priority order of PDUs;

[0478] The length of SN;

[0479] Selected Priority Bit Rate (PBR) parameters for each logical channel;

[0480] The priority of each selected logical channel.

[0481] Optionally, the PDCP transmission-related configuration parameters of the sending end include at least one of the following:

[0482] Enable PDCP repeat;

[0483] Enable integrity protection;

[0484] Partial data packets that are protected for integrity;

[0485] Number of PDCP SDUs cascaded;

[0486] Whether to enable SDU discarding based on PDCP timer;

[0487] SDUs based on PDCP timers discard the corresponding timer suggestion values.

[0488] Enable header compression algorithm;

[0489] Enable header compression algorithm selection;

[0490] Whether to enable uplink data compression UDC and the corresponding algorithm.

[0491] Optionally, the receiving end PDCP transmission related configuration parameters include at least one of the following:

[0492] Enable out-of-order transmission;

[0493] t-re-ordering time.

[0494] Optionally, the input information includes at least one of the following:

[0495] Current RLC transmitter configuration parameters;

[0496] Current sending status;

[0497] Packet loss rate is the ratio of lost data packets to the total number of data packets sent.

[0498] Retransmission rate is the ratio of the number of retransmitted data packets to the number of newly transmitted data packets.

[0499] Average number of retransmissions;

[0500] Current transmission rate;

[0501] Average RLC PDU length;

[0502] The average amount of RLC PDU data transmitted per transmission interval;

[0503] Service Quality of Service (QoS) requirements;

[0504] Transmission Time Interval (TTI) length;

[0505] HARQ maximum retransmission count;

[0506] HARQ accuracy of Hybrid Automatic Repeat Requests;

[0507] HARQ ACK / NACK error rate;

[0508] Open port status.

[0509] Optionally, the current transmission status includes at least one of the following:

[0510] The number of data packets sent;

[0511] The time the data packet was sent;

[0512] Average data transmission rate as statistically analyzed by the RLC layer;

[0513] The number of retransmitted data packets;

[0514] The retransmission data packet sending time and the number of retransmissions must be at least one of the following:

[0515] Send window size;

[0516] The latency of data waiting to be transmitted while it is in the cache;

[0517] The latency from when data arrives at the buffer to when it is successfully received.

[0518] Optionally, the current RLC transmitter configuration parameters include at least one of the following:

[0519] RLC mode

[0520] SN length;

[0521] The number of PDUs that triggered the polling;

[0522] The number of bits that triggered the polling;

[0523] Polling retransmission timer;

[0524] Maximum number of retransmissions.

[0525] Optionally, the service QoS requirements include at least one of the following:

[0526] Aggregate maximum data rate (AMBR), priority bit rate (PBR), priority, packet latency budget, packet error rate, 5G QoS identifier, low latency requirement, maximum burst data volume, extended packet latency budget, PDU set latency budget, PDU set error rate, and PDU set joint processing information.

[0527] Optionally, the input information includes at least one of the following:

[0528] Current RLC receiver configuration parameters;

[0529] Data packet reception status;

[0530] Status report sent status;

[0531] Retransmission rate;

[0532] Average waiting time;

[0533] Open port status;

[0534] Service QoS requirements;

[0535] TTI length;

[0536] HARQ maximum retransmission count;

[0537] HARQ accuracy;

[0538] HARQ ACK / NACK error rate.

[0539] Optionally, the retransmission rate includes the ratio of data packets retransmitted N times to all data packets; N is a positive integer.

[0540] Optionally, the current RLC receiver configuration parameters include at least one of the reassembly timer duration and the status report disable timer duration.

[0541] Optionally, the data packet reception status includes at least one of the following:

[0542] The number of data packets received within a statistical period;

[0543] Data packet reception time;

[0544] Status report of the sent data packets;

[0545] The number of NACKs corresponding to data packets;

[0546] The ratio of the number of data packets waiting to be received in the receive window to the window size.

[0547] Optionally, the status report sending status includes the average sending frequency of status reports within a statistical period.

[0548] Optionally, the average latency includes at least one of the following:

[0549] The average waiting delay between SN intervals and the ratio of the number of times the recombination timer is reset to the number of times the recombination timer expires.

[0550] Optionally, the input information includes at least one of the following:

[0551] Service QoS requirements;

[0552] The current logical channel priority processing LCP-related configuration parameters;

[0553] The amount of business data to be transmitted;

[0554] Current LCP and service transmission status;

[0555] Open port status;

[0556] Cell load status.

[0557] Optionally, the current logical channel priority processing LCP-related configuration parameters include at least one of the following:

[0558] At least one of the following parameters must be used: logical channel priority, priority bit rate (PBR), token bucket duration, and LCP limit.

[0559] Optionally, the LCP limiting parameters include at least one of the following:

[0560] Permitted service areas;

[0561] Permissible subcarrier spacing (SCS);

[0562] Maximum uplink physical shared channel (PUSCH) duration;

[0563] The configured authorization type 1 is allowed;

[0564] Allowed physical layer priority indexes;

[0565] Allowed HARQ modes.

[0566] Optionally, the amount of service data to be transmitted includes at least one of the following:

[0567] The amount of new data to be transmitted;

[0568] The amount of data to be retransmitted;

[0569] At least one of the PDCP data volume and priority to be transmitted;

[0570] At least one of the following must be present: the amount of RLC data to be transmitted and its priority.

[0571] The amount of MAC control data to be transmitted and its priority must be at least one of the following:

[0572] Optionally, the current LCP and service transmission status includes at least one of the following: LCH Bj satisfaction rate, which represents the proportion of each scheduled Bj that is satisfied within a statistical period;

[0573] The duration that LCH Bj cannot satisfy;

[0574] Average LCH transmission delay;

[0575] Statistical analysis of packet loss rate at the RLC layer or MAC layer;

[0576] TTI length;

[0577] HARQ maximum retransmission count;

[0578] ARQ or HARQ retransmission rate;

[0579] The transmission rate counted by the RLC layer or PHY layer;

[0580] The number or proportion of packets deleted due to latency at the PDCP layer.

[0581] Optionally, the input information includes at least one of the following:

[0582] Current PDCP layer configuration parameters;

[0583] Current data link transport layer transmission status;

[0584] Open port status;

[0585] Service QoS requirements;

[0586] Data link transport layer processing status;

[0587] The application (APP) layer processes information.

[0588] Optionally, the current PDCP layer configuration parameters include at least one of the following:

[0589] Delete the timer;

[0590] SN serial number length;

[0591] Header compression algorithm and parameters;

[0592] Integrity protection status;

[0593] Status reporting enabled or disabled;

[0594] Submit in sequence whether to open or not;

[0595] Multiple RLC mappings;

[0596] Reordering t-reordering timer duration;

[0597] Uplink data compression parameters;

[0598] The PDU set includes at least one of the processing switches and the encryption switch.

[0599] Optionally, the data link transport layer processing status includes at least one of processing latency and resource consumption. Optionally, the current data link transport layer transmission status includes at least one of the following: RLC retransmission rate, bit error rate, bit error rate, and PDCP layer average transmission latency.

[0600] Optionally, the information processed by the application (APP) layer includes at least one of the following:

[0601] Whether forward error correction (FEC) is supported, FEC parameters, redundancy ratio, and the ability to handle out-of-order packets. Optionally, the air interface status includes at least one of the following:

[0602] Channel State Information Reference Signal (CSI-RS);

[0603] Synchronization signal block reference signal received power SSB RSRP;

[0604] Reference signal reception quality (RSRQ);

[0605] Signal-to-interference-plus-noise ratio (SINR)

[0606] Optionally, the input information includes at least one of the following:

[0607] Service QoS requirements;

[0608] Service rate statistics at the RLC / PDCP layer;

[0609] Average PDCP latency at the receiver;

[0610] RLC configuration parameters;

[0611] Receiver RLC statistical parameters;

[0612] MAC HARQ configuration parameters.

[0613] Optionally, the processing module 901 is also used for:

[0614] Obtain the performance supervision configuration information of the AI ​​model;

[0615] The AI ​​model is subjected to performance supervision based on the supervision configuration information.

[0616] Optionally, the performance monitoring configuration information includes at least one of the following:

[0617] Reporting threshold values ​​corresponding to transmission rates of different air interface signal qualities;

[0618] Reporting threshold values ​​for packet loss rates corresponding to different air interface signal qualities;

[0619] Reporting threshold values ​​for retransmission rates corresponding to different air interface signal qualities;

[0620] The reporting threshold for the proportion of data packets that are deleted or become latency-critical data;

[0621] The reporting threshold for the percentage of retransmissions that are abandoned;

[0622] Transmission delay reporting threshold

[0623] The reporting threshold for packet loss rate;

[0624] The reporting threshold value corresponding to the retransmission rate;

[0625] The reporting threshold for redundancy retransmission rate;

[0626] The reporting threshold for the PDCP packet deletion ratio.

[0627] Optionally, the communication device 900 further includes a receiving module for:

[0628] Obtain first signaling from the second device, the first signaling including the performance monitoring configuration information.

[0629] Optionally, the communication device 900 further includes a transmitting module for:

[0630] Based on the comparison between the statistical values ​​and the performance supervision configuration information, model monitoring feedback information is sent to the second device when the trigger reporting threshold is met.

[0631] Optionally, the receiving module is also used for:

[0632] Obtain model inference configuration information from a second device, the model inference configuration information being used to indicate the input information and the output information.

[0633] Optionally, the sending module is also used for:

[0634] The capability reporting information is sent to the second device, the capability reporting information being used to indicate the use cases supported by the AI ​​model, the use cases including at least one of the input information and the output information.

[0635] Optionally, the input information must satisfy at least one of the following:

[0636] The input information is obtained based on the average of the statistical values ​​of at least one RLC entity, at least one PDCP entity, or at least one MAC entity on the terminal;

[0637] The input information is obtained based on the statistical values ​​of the RLC entities;

[0638] The input information is obtained based on the statistical values ​​of PDCP entities;

[0639] The input information is obtained based on the statistical values ​​of the MAC entity;

[0640] The input information is obtained based on the statistical values ​​of resource blocks (RBs).

[0641] Optionally, the output information satisfies at least one of the following:

[0642] The output information is at the terminal level;

[0643] The output information is at the RLC entity level;

[0644] The output information is at the PDCP entity level;

[0645] The output information is at the MAC entity level;

[0646] The output information is in RB granularity.

[0647] In this embodiment, output information is obtained by reasoning based on input information using an AI model, and the transmission-related configuration parameters of the data link transport layer are adjusted based on the output information. The AI ​​model is advantageous for dynamically and adaptively adjusting the transmission-related configuration parameters of the data link transport layer by considering multiple factors, which is beneficial for meeting the user's business needs.

[0648] The communication device provided in this application embodiment can implement the various processes of the first device implemented in the method embodiments of FIG7 to FIG8 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0649] Referring to Figure 10, the communication device 1000 includes a sending module 1001, which is used to send model inference configuration information to a first device. The model inference configuration information is used to indicate the input and output information of the AI ​​model deployed on the first device. The output information is used to adjust the transmission-related configuration parameters of the data link transmission layer.

[0650] Optionally, the output information includes at least one of the following:

[0651] Automatic retransmission request (ARQ) retransmission related configuration parameters;

[0652] Configuration parameters related to Radio Link Control (RLC) layer status reporting;

[0653] Configuration parameters related to Media Access Control (MAC) packages;

[0654] Sending end PDCP transmission related configuration parameters;

[0655] The receiving end transmits PDCP-related configuration parameters.

[0656] Optionally, the ARQ retransmission related configuration parameters include at least one of the following:

[0657] Maximum number of retransmissions;

[0658] The retransmission time point is used to indicate the time interval since the last initial transmission or retransmission.

[0659] New data volume;

[0660] Poll the relevant parameters.

[0661] Optionally, the amount of newly transmitted data includes at least one of the following:

[0662] The number of bits / bytes of newly transmitted data and the number of Protocol Data Units (PDUs) must be at least one of the following:

[0663] The ratio of newly transmitted data bits / bytes to retransmitted data bits / bytes;

[0664] The ratio of the number of PDUs for newly transmitted data to the number of PDUs for retransmitted data.

[0665] Optionally, the polling-related parameters include at least one of the following:

[0666] The number of bytes that triggered the polling;

[0667] The number of PDUs that triggered the polling;

[0668] Polling retransmission timer.

[0669] Optionally, the configuration parameters related to the RLC layer status report include at least one of the following:

[0670] The timing and / or content of sending a status report, wherein the timing is used to indicate the time interval since the last status report was sent, and the content is the maximum sequence number (SN) of the feedback data packet;

[0671] The time to terminate retransmission is used to indicate when the receiving end should give up receiving data packets;

[0672] The delay reordering parameter indicates the duration for triggering the timer to send the status report;

[0673] PDCP reordering time.

[0674] Optionally, the configuration parameters for the MAC packet include at least one of the following:

[0675] Selected logical channel (LCH);

[0676] The amount of data selected for each logical channel (LCH);

[0677] The priority order of at least two of the following: LCH PDU, RLC new transmission PDU, RLC retransmission PDU, RLC control PDU, and PDCP control PDU;

[0678] At least two PDCP PDU priority orders;

[0679] Priority order of at least two RLC PDUs;

[0680] At least two MAC addresses control the priority order of PDUs;

[0681] The length of SN;

[0682] Selected Priority Bit Rate (PBR) parameters for each logical channel;

[0683] The priority of each selected logical channel.

[0684] Optionally, the PDCP transmission-related configuration parameters of the sending end include at least one of the following:

[0685] Enable PDCP repeat;

[0686] Enable integrity protection;

[0687] Partial data packets that are protected for integrity;

[0688] Number of PDCP SDUs cascaded;

[0689] Whether to enable SDU discarding based on PDCP timer;

[0690] SDUs based on PDCP timers discard the corresponding timer suggestion values.

[0691] Enable header compression algorithm;

[0692] Enable header compression algorithm selection;

[0693] Whether to enable uplink data compression UDC and the corresponding algorithm.

[0694] Optionally, the receiving end PDCP transmission related configuration parameters include at least one of the following:

[0695] Enable out-of-order transmission;

[0696] t-re-ordering time.

[0697] Optionally, the input information includes at least one of the following:

[0698] Current RLC transmitter configuration parameters;

[0699] Current sending status;

[0700] Packet loss rate is the ratio of lost data packets to the total number of data packets sent.

[0701] Retransmission rate is the ratio of the number of retransmitted data packets to the number of newly transmitted data packets.

[0702] Average number of retransmissions;

[0703] Current transmission rate;

[0704] Average RLC PDU length;

[0705] The average amount of RLC PDU data transmitted per transmission interval;

[0706] Service Quality of Service (QoS) requirements;

[0707] Transmission Time Interval (TTI) length;

[0708] HARQ maximum retransmission count;

[0709] HARQ accuracy of Hybrid Automatic Repeat Requests;

[0710] HARQ ACK / NACK error rate;

[0711] Open port status.

[0712] Optionally, the current transmission status includes at least one of the following:

[0713] The number of data packets sent;

[0714] The time the data packet was sent;

[0715] Average data transmission rate as statistically analyzed by the RLC layer;

[0716] The number of retransmitted data packets;

[0717] The retransmission data packet sending time and the number of retransmissions must be at least one of the following:

[0718] Send window size;

[0719] The latency of data waiting to be transmitted while it is in the cache;

[0720] The latency from when data arrives at the buffer to when it is successfully received.

[0721] Optionally, the current RLC transmitter configuration parameters include at least one of the following:

[0722] RLC mode

[0723] SN length;

[0724] The number of PDUs that triggered the polling;

[0725] The number of bits that triggered the polling;

[0726] Polling retransmission timer;

[0727] Maximum number of retransmissions.

[0728] Optionally, the service QoS requirements include at least one of the following:

[0729] Aggregate maximum data rate (AMBR), priority bit rate (PBR), priority, packet latency budget, packet error rate, 5G QoS identifier, low latency requirement, maximum burst data volume, extended packet latency budget, PDU set latency budget, PDU set error rate, and PDU set joint processing information.

[0730] Optionally, the input information includes at least one of the following:

[0731] Current RLC receiver configuration parameters;

[0732] Data packet reception status;

[0733] Status report sent status;

[0734] Retransmission rate;

[0735] Average waiting time;

[0736] Open port status;

[0737] Service QoS requirements;

[0738] TTI length;

[0739] HARQ maximum retransmission count;

[0740] HARQ accuracy;

[0741] HARQ ACK / NACK error rate.

[0742] Optionally, the retransmission rate includes the ratio of data packets retransmitted N times to all data packets; N is a positive integer.

[0743] Optionally, the current RLC receiver configuration parameters include at least one of the reassembly timer duration and the status report disable timer duration.

[0744] Optionally, the data packet reception status includes at least one of the following:

[0745] The number of data packets received within a statistical period;

[0746] Data packet reception time;

[0747] Status report of the sent data packets;

[0748] The number of NACKs corresponding to data packets;

[0749] The ratio of the number of data packets waiting to be received in the receive window to the window size.

[0750] Optionally, the status report sending status includes the average sending frequency of status reports within a statistical period.

[0751] Optionally, the average latency includes at least one of the following:

[0752] The average waiting delay between SN intervals and the ratio of the number of times the recombination timer is reset to the number of times the recombination timer expires.

[0753] Optionally, the input information includes at least one of the following:

[0754] Service QoS requirements;

[0755] The current logical channel priority processing LCP-related configuration parameters;

[0756] The amount of business data to be transmitted;

[0757] Current LCP and service transmission status;

[0758] Open port status;

[0759] Cell load status.

[0760] Optionally, the current logical channel priority processing LCP-related configuration parameters include at least one of the following:

[0761] At least one of the following parameters must be used: logical channel priority, priority bit rate (PBR), token bucket duration, and LCP limit.

[0762] Optionally, the LCP limiting parameters include at least one of the following:

[0763] Permitted service areas;

[0764] Permissible subcarrier spacing (SCS);

[0765] Maximum uplink physical shared channel (PUSCH) duration;

[0766] The configured authorization type 1 is allowed;

[0767] Allowed physical layer priority indexes;

[0768] Allowed HARQ modes.

[0769] Optionally, the amount of service data to be transmitted includes at least one of the following:

[0770] The amount of new data to be transmitted;

[0771] The amount of data to be retransmitted;

[0772] At least one of the PDCP data volume and priority to be transmitted;

[0773] At least one of the following must be present: the amount of RLC data to be transmitted and its priority.

[0774] The amount of MAC control data to be transmitted and its priority must be at least one of the following:

[0775] Optionally, the current LCP and service transmission status includes at least one of the following:

[0776] LCH Bj satisfaction rate is used to represent the proportion of scheduling Bj that is satisfied in each time within a statistical period;

[0777] The duration that LCH Bj cannot satisfy;

[0778] Average LCH transmission delay;

[0779] Statistical analysis of packet loss rate at the RLC layer or MAC layer;

[0780] TTI length;

[0781] HARQ maximum retransmission count;

[0782] ARQ or HARQ retransmission rate;

[0783] The transmission rate counted by the RLC layer or PHY layer;

[0784] The number or proportion of packets deleted due to latency at the PDCP layer.

[0785] Optionally, the input information includes at least one of the following:

[0786] Current PDCP layer configuration parameters;

[0787] Current data link transport layer transmission status;

[0788] Open port status;

[0789] Service QoS requirements;

[0790] Data link transport layer processing status;

[0791] The application (APP) layer processes information.

[0792] Optionally, the current PDCP layer configuration parameters include at least one of the following:

[0793] Delete the timer;

[0794] SN serial number length;

[0795] Header compression algorithm and parameters;

[0796] Integrity protection status;

[0797] Status reporting enabled or disabled;

[0798] Submit in sequence whether to open or not;

[0799] Multiple RLC mappings;

[0800] Reordering t-reordering timer duration;

[0801] Uplink data compression parameters;

[0802] The PDU set includes at least one of the processing switches and the encryption switch.

[0803] Optionally, the data link transport layer processing includes at least one of processing latency and resource consumption.

[0804] Optionally, the current data link transport layer transmission status includes at least one of the following:

[0805] RLC retransmission rate, bit error rate, and average transmission delay at the PDCP layer.

[0806] Optionally, the information processed by the application (APP) layer includes at least one of the following:

[0807] Whether it supports Forward Error Correction (FEC), FEC parameters, redundancy ratio, and ability to handle out-of-order data packets.

[0808] Optionally, the air interface status includes at least one of the following:

[0809] Channel State Information Reference Signal (CSI-RS);

[0810] Synchronization signal block reference signal received power SSB RSRP;

[0811] Reference signal reception quality (RSRQ);

[0812] Signal-to-interference-plus-noise ratio (SINR)

[0813] Optionally, the input information includes at least one of the following:

[0814] Service QoS requirements;

[0815] Service rate statistics at the RLC / PDCP layer;

[0816] Average PDCP latency at the receiver;

[0817] RLC configuration parameters;

[0818] Receiver RLC statistical parameters;

[0819] MAC HARQ configuration parameters.

[0820] Optionally, the processing module 901 is also used for:

[0821] Obtain the performance supervision configuration information of the AI ​​model;

[0822] The AI ​​model is subjected to performance supervision based on the supervision configuration information.

[0823] Optionally, the performance monitoring configuration information includes at least one of the following:

[0824] Reporting threshold values ​​corresponding to transmission rates of different air interface signal qualities;

[0825] Reporting threshold values ​​for packet loss rates corresponding to different air interface signal qualities;

[0826] Reporting threshold values ​​for retransmission rates corresponding to different air interface signal qualities;

[0827] The reporting threshold for the proportion of data packets that are deleted or become latency-critical data;

[0828] The reporting threshold for the percentage of retransmissions that are abandoned;

[0829] Transmission delay reporting threshold

[0830] The reporting threshold for packet loss rate;

[0831] The reporting threshold value corresponding to the retransmission rate;

[0832] The reporting threshold for redundancy retransmission rate;

[0833] The reporting threshold for the PDCP packet deletion ratio.

[0834] Optionally, the sending module 1001 is further configured to:

[0835] A first signaling message is sent to the first device, the first signaling message including supervision configuration information; the supervision configuration information is used to supervise the performance of the AI ​​model.

[0836] Optionally, the performance monitoring configuration information includes at least one of the following:

[0837] Reporting threshold values ​​corresponding to transmission rates of different air interface signal qualities;

[0838] Reporting threshold values ​​for packet loss rates corresponding to different air interface signal qualities;

[0839] Reporting threshold values ​​for retransmission rates corresponding to different air interface signal qualities;

[0840] The reporting threshold for the proportion of data packets that are deleted or become latency-critical data;

[0841] The reporting threshold for the percentage of retransmissions that are abandoned;

[0842] Transmission delay reporting threshold

[0843] The reporting threshold for packet loss rate;

[0844] The reporting threshold value corresponding to the retransmission rate;

[0845] The reporting threshold for redundancy retransmission rate;

[0846] The reporting threshold for the PDCP packet deletion ratio.

[0847] Optionally, the device 1000 further includes a receiving module for acquiring model monitoring feedback information from the first device. The model monitoring feedback information is sent after a reporting threshold is met by comparing statistical values ​​with the performance supervision configuration information.

[0848] Optionally, the sending module 1001 is further configured to:

[0849] Obtain capability reporting information from the first device, the capability reporting information being used to indicate use cases supported by the AI ​​model, the use cases including at least one of the input information and the output information.

[0850] In this embodiment, output information is obtained by reasoning based on input information using an AI model, and the transmission-related configuration parameters of the data link transport layer are adjusted based on the output information. The AI ​​model is advantageous for dynamically and adaptively adjusting the transmission-related configuration parameters of the data link transport layer by considering multiple factors, which is beneficial for meeting the user's business needs.

[0851] The communication device provided in this application embodiment can implement the various processes of the second device implemented in the method embodiments of FIG7 to FIG8 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0852] As shown in Figure 11, this application embodiment also provides a communication device 1100, including a processor 1101 and a memory 1102. The memory 1102 stores a program or instructions that can run on the processor 1101. For example, when the communication device 1100 is a first device, the program or instructions executed by the processor 1101 implement the various steps of the first device in the above-described communication method embodiment, and achieve the same technical effect. When the communication device 1100 is a second device, the program or instructions executed by the processor 1101 implement the various steps of the second device in the above-described communication method embodiment, and achieve the same technical effect. To avoid repetition, this will not be described again here.

[0853] This application also provides a terminal, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps executed by the first device in the method embodiment shown in FIG7 or FIG8. This terminal embodiment corresponds to the first device in the above method embodiment, and all implementation processes and methods of the above method embodiments can be applied to this terminal embodiment and can achieve the same technical effect. The terminal can be the communication device shown in FIG9. Specifically, FIG12 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of this application.

[0854] The terminal 1200 includes, but is not limited to, at least some of the following components: radio frequency unit 1201, network module 1202, audio output unit 1203, input unit 1204, sensor 1205, display unit 1206, user input unit 1207, interface unit 1208, memory 1209, and processor 1210.

[0855] Those skilled in the art will understand that terminal 1200 may also include a power supply (such as a battery) for powering various components. The power supply can be logically connected to processor 1210 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The terminal structure shown in Figure 12 does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0856] It should be understood that, in this embodiment, the input unit 1204 may include a graphics processor 12041 and a microphone 12042. The graphics processor 12041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1206 may include a display panel 12061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1207 includes a touch panel 12071 and at least one of other input devices 12072. The touch panel 12071 is also called a touch screen. The touch panel 12071 may include a touch detection device and a touch controller. Other input devices 12072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0857] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 1201 can transmit it to the processor 1210 for processing; in addition, the radio frequency unit 1201 can send uplink data to the network-side device. Typically, the radio frequency unit 1201 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0858] The memory 1209 can be used to store software programs or instructions, as well as various data. The memory 1209 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1209 may include volatile memory or non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1109 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0859] Processor 1210 may include one or more processing units; optionally, processor 1210 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 1210.

[0860] The processor 1210 is used to acquire input information and, based on the AI ​​model and the input information, obtain output information, the output information being used to adjust transmission-related configuration parameters of the data link transport layer.

[0861] In this embodiment, output information is obtained by reasoning based on input information using an AI model, and the transmission-related configuration parameters of the data link transport layer are adjusted based on the output information. The AI ​​model is advantageous for dynamically and adaptively adjusting the transmission-related configuration parameters of the data link transport layer by considering multiple factors, which is beneficial for meeting the user's business needs.

[0862] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the first device in the method embodiment and achieve the same or corresponding technical effects. To avoid repetition, it will not be described again here.

[0863] This application also provides a network-side device, including a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the first device step or the second device step in the method embodiment shown in FIG7. This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[0864] Specifically, this application embodiment also provides a network-side device, which may be the communication device shown in FIG9 or the communication device shown in FIG10. As shown in FIG13, the network-side device 1300 includes: an antenna 131, a radio frequency device 132, a baseband device 133, a processor 134, and a memory 135. The antenna 131 is connected to the radio frequency device 132. In the uplink direction, the radio frequency device 132 receives information through the antenna 131 and sends the received information to the baseband device 133 for processing. In the downlink direction, the baseband device 133 processes the information to be transmitted and sends it to the radio frequency device 132. The radio frequency device 132 processes the received information and transmits it through the antenna 131.

[0865] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 133, which includes a baseband processor.

[0866] The baseband device 133 may include at least one baseband board, on which multiple chips are disposed, as shown in FIG13. One of the chips is, for example, a baseband processor, which is connected to the memory 135 via a bus interface to call the program in the memory 135 and execute the network device operation shown in the above method embodiment.

[0867] The network-side device may also include a network interface 136, such as a Common Public Radio Interface (CPRI).

[0868] Specifically, the network-side device 1300 in this application embodiment further includes: instructions or programs stored in memory 135 and executable on processor 134. Processor 134 calls the instructions or programs in memory 135 to execute the methods executed by the modules shown in FIG9 or FIG10 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0869] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described communication method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0870] The processor mentioned above is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[0871] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described communication method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0872] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0873] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described communication method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0874] This application also provides a communication system, including: a terminal and a network-side device, wherein the terminal can be used to perform the steps of the first device in the communication method described above, and the network-side device can be used to perform the steps of the second device in the communication method described above.

[0875] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0876] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0877] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. A communication method based on intelligent algorithms, wherein, include: The first device acquires input information; The first device obtains output information based on the artificial intelligence (AI) model and the input information, and the output information is used to adjust the transmission-related configuration parameters of the data link transport layer.

2. The method according to claim 1, wherein, The output information includes at least one of the following: Automatic retransmission request (ARQ) retransmission related configuration parameters; Configuration parameters related to Radio Link Control (RLC) layer status reporting; Configuration parameters related to Media Access Control (MAC) packages; Configuration parameters related to the transmission of Packet Data Convergence Protocol (PDCP) at the sending end; The receiving end transmits PDCP-related configuration parameters.

3. The method according to claim 2, wherein, The ARQ retransmission related configuration parameters include at least one of the following: Maximum number of retransmissions; The retransmission time point is used to indicate the time interval since the last initial transmission or retransmission. New data volume; Poll the relevant parameters.

4. The method according to claim 3, wherein, The amount of newly transmitted data includes at least one of the following: At least one of the number of bits / bytes of newly transmitted data and the number of Protocol Data Units (PDUs); The ratio of newly transmitted data bits / bytes to retransmitted data bits / bytes; The ratio of the number of PDUs for newly transmitted data to the number of PDUs for retransmitted data.

5. The method according to claim 3, wherein, The polling-related parameters include at least one of the following: The number of bytes that triggered the polling; The number of PDUs that triggered the polling; Polling retransmission timer.

6. The method according to claim 2, wherein, The configuration parameters related to the RLC layer status report include at least one of the following: The timing and / or content of sending a status report, wherein the timing is used to indicate the time interval since the last status report was sent, and the content is the maximum sequence number (SN) of the feedback data packet; The time to terminate retransmission is used to indicate when the receiving end should give up receiving data packets; The delay reordering parameter indicates the duration for triggering the timer to send the status report; PDCP reordering time.

7. The method according to claim 2, wherein, The configuration parameters for the MAC packet include at least one of the following: Selected logical channel (LCH); The amount of data selected for each logical channel (LCH); The priority order of at least two of the selected LCH PDU, RLC new transmission PDU, RLC retransmission PDU, RLC control PDU, and PDCP control PDU; At least two PDCP PDU priority orders; Priority order of at least two RLC PDUs; At least two MAC addresses control the priority order of PDUs; The length of SN; Selected Priority Bit Rate (PBR) parameters for each logical channel; The priority of each selected logical channel.

8. The method according to claim 2, wherein, The PDCP transmission-related configuration parameters of the transmitting end include information indicating at least one of the following: Enable PDCP repeat; Enable integrity protection; Partial data packets that are protected for integrity; Number of cascaded PDCP service data units (SDUs); Whether to enable SDU discarding based on PDCP timer; SDUs based on PDCP timers discard the corresponding timer suggestion values. Enable header compression algorithm; Enable header compression algorithm selection; Whether to enable uplink data compression UDC and the corresponding algorithm.

9. The method according to claim 2, wherein, The receiving end PDCP transmission related configuration parameters include at least one of the following: Enable out-of-order transmission; Reordering time.

10. The method according to any one of claims 3-5, wherein, The input information includes at least one of the following: Current RLC transmitter configuration parameters; Current sending status; Packet loss rate is the ratio of lost data packets to the total number of data packets sent. Retransmission rate is the ratio of the number of retransmitted data packets to the number of newly transmitted data packets. Average number of retransmissions; Current transmission rate; Average RLC PDU length; The average amount of RLC PDU data transmitted per transmission interval; Service Quality of Service (QoS) requirements; Transmission Time Interval (TTI) length; Maximum number of retransmissions for HARQ (Hybrid Automatic Repeat Request); HARQ accuracy of Hybrid Automatic Repeat Requests; HARQ ACK / NACK error rate; Open port status.

11. The method according to claim 10, wherein, The current transmission status includes at least one of the following: The number of data packets sent; The time the data packet was sent; Average data transmission rate as statistically analyzed by the RLC layer; The number of retransmitted data packets; The retransmission data packet sending time and the number of retransmissions must be at least one of the following: Send window size; The latency of data waiting to be transmitted while it is in the cache; The latency from when data arrives at the buffer to when it is successfully received.

12. The method according to claim 10, wherein, The current RLC transmitter configuration parameters include at least one of the following: RLC mode SN length; The number of PDUs that triggered the polling; The number of bits that triggered the polling; Polling retransmission timer; Maximum number of retransmissions.

13. The method according to claim 10, wherein, The service QoS requirements include at least one of the following: Aggregate maximum data rate (AMBR), priority bit rate (PBR), priority, packet latency budget, packet error rate, 5G QoS identifier, low latency requirement, maximum burst data volume, extended packet latency budget, PDU set latency budget, PDU set error rate, and PDU set joint processing information.

14. The method according to claim 6, wherein, The input information includes at least one of the following: Current RLC receiver configuration parameters; Data packet reception status; Status report sent status; Retransmission rate; Average waiting time; Open port status; Service QoS requirements; TTI length; HARQ maximum retransmission count; HARQ accuracy; HARQ ACK / NACK error rate.

15. The method according to claim 14, wherein, The retransmission rate is the ratio of data packets that are retransmitted N times to all data packets; N is a positive integer.

16. The method of claim 14, wherein, The current RLC receiver configuration parameters include at least one of the reassembly timer duration and the status report disable timer duration.

17. The method of claim 14, wherein, The data packet reception status includes at least one of the following: The number of data packets received within a statistical period; Data packet reception time; Status report of the sent data packets; The number of unacknowledged NACK packets; The ratio of the number of data packets waiting to be received in the receive window to the window size.

18. The method according to claim 14, wherein, The status report sending status includes the average sending frequency of status reports within a statistical period.

19. The method of claim 14, wherein, The average waiting time includes at least one of the following: Average waiting time between SN intervals; The ratio of the number of times the reorganization timer is reset to the number of times the reorganization timer expires.

20. The method according to claim 7, wherein, The input information includes at least one of the following: Service QoS requirements; The current logical channel priority processing LCP-related configuration parameters; The amount of business data to be transmitted; Current LCP and service transmission status; Open port status; Cell load status.

21. The method according to claim 20, wherein, The current logical channel priority processing LCP-related configuration parameters include at least one of the following: At least one of the following parameters must be used: logical channel priority, priority bit rate (PBR), token bucket duration, and LCP limit.

22. The method according to claim 21, wherein, The LCP limiting parameters include at least one of the following: Permitted service areas; Permissible subcarrier spacing (SCS); Maximum uplink physical shared channel (PUSCH) duration; The configured authorization type 1 is allowed; Allowed physical layer priority indexes; Allowed HARQ modes.

23. The method of claim 20, wherein, The amount of service data to be transmitted includes at least one of the following: The amount of new data to be transmitted; The amount of data to be retransmitted; At least one of the PDCP data volume and priority to be transmitted; At least one of the following must be present: the amount of RLC data to be transmitted and its priority. The amount of MAC control data to be transmitted and its priority must be at least one of the following:

24. The method of claim 20, wherein, The current LCP and service transmission status includes at least one of the following: LCH Bj satisfaction rate is used to represent the proportion of scheduling Bj that is satisfied in each time within a statistical period; The duration that LCH Bj cannot satisfy; Average LCH transmission delay; Statistical analysis of packet loss rate at the RLC layer or MAC layer; TTI length; HARQ maximum retransmission count; ARQ or HARQ retransmission rate; The transmission rate as measured by the RLC layer or physical layer; The number or proportion of packets deleted due to latency at the PDCP layer.

25. The method according to claim 8, wherein, The input information includes at least one of the following: Current PDCP layer configuration parameters; Current data link transport layer transmission status; Open port status; Service QoS requirements; Data link transport layer processing status; The application (APP) layer processes information.

26. The method of claim 25, wherein, The current PDCP layer configuration parameters include at least one of the following: Delete the timer; SN serial number length; Header compression algorithm and parameters; Integrity protection status; Status reporting enabled or disabled; Submit in sequence whether to open or not; Multiple RLC mappings; Reorder timer duration; Uplink data compression parameters; The PDU set includes at least one of the processing switches and the encryption switch.

27. The method according to claim 25, wherein, The data link transport layer processing includes at least one of processing latency and resource consumption.

28. The method according to claim 25, wherein, The current data link transport layer transmission status includes at least one of the following: RLC retransmission rate, bit error rate, and average transmission delay at the PDCP layer.

29. The method according to claim 25, wherein, The information processed by the application (APP) layer includes at least one of the following: Whether it supports Forward Error Correction (FEC), FEC parameters, redundancy ratio, and ability to handle out-of-order data packets.

30. The method according to any one of claims 10-29, wherein, The air interface status includes at least one of the following: Channel State Information Reference Signal (CSI-RS); Synchronization signal block reference signal received power SSB RSRP; Reference signal reception quality (RSRQ); Signal-to-interference-plus-noise ratio (SINR) 31. The method according to claim 9, wherein, The input information includes at least one of the following: Service QoS requirements; Service rate statistics at the RLC / PDCP layer; Average PDCP latency at the receiver; RLC configuration parameters; Receiver RLC statistical parameters; MAC HARQ configuration parameters.

32. The method according to any one of claims 1-31, wherein, Also includes: The first device acquires the performance supervision configuration information of the AI ​​model; The first device performs performance supervision on the AI ​​model based on the supervision configuration information.

33. The method according to claim 32, wherein, The performance monitoring configuration information includes at least one of the following: Reporting threshold values ​​corresponding to transmission rates of different air interface signal qualities; Reporting threshold values ​​for packet loss rates corresponding to different air interface signal qualities; Reporting threshold values ​​for retransmission rates corresponding to different air interface signal qualities; The reporting threshold for the proportion of data packets that are deleted or become latency-critical data; The reporting threshold for the percentage of retransmissions that are abandoned; Transmission delay reporting threshold The reporting threshold for packet loss rate; The reporting threshold value corresponding to the retransmission rate; The reporting threshold for redundancy retransmission rate; The reporting threshold for the PDCP packet deletion ratio.

34. The method according to claim 32 or 33, wherein, The first device obtains the performance supervision configuration information of the AI ​​model, including: The first device receives a first signaling message from the second device, the first signaling message including the performance monitoring configuration information.

35. The method according to any one of claims 32-34, wherein, Also includes: The first device compares the statistical value with the performance monitoring configuration information and sends model monitoring feedback information to the second device when the trigger reporting threshold is met.

36. The method according to any one of claims 1-35, wherein, Also includes: The first device acquires model inference configuration information from the second device, the model inference configuration information being used to indicate the input information and the output information.

37. The method according to any one of claims 1-35, wherein, Also includes: The first device sends capability reporting information to the second device. The capability reporting information is used to indicate the use cases supported by the AI ​​model. The use cases include at least one of the input information and the output information.

38. The method according to any one of claims 1-37, wherein, The input information satisfies at least one of the following: The input information is obtained based on the average of the statistical values ​​of at least one RLC entity, at least one PDCP entity, or at least one MAC entity on the terminal; The input information is obtained based on the statistical values ​​of the RLC entities; The input information is obtained based on the statistical values ​​of PDCP entities; The input information is obtained based on the statistical values ​​of the MAC entity; The input information is obtained based on the statistical values ​​of resource blocks (RBs).

39. The method according to any one of claims 1-38, wherein, The output information satisfies at least one of the following: The output information is at the terminal level; The output information is at the RLC entity level; The output information is at the PDCP entity level; The output information is at the MAC entity level; The output information is in RB granularity.

40. A communication method based on intelligent algorithms, wherein, include: The second device sends model inference configuration information to the first device. The model inference configuration information is used to indicate the input and output information of the AI ​​model deployed on the first device. The output information is used to adjust the transmission-related configuration parameters of the data link transport layer.

41. The method according to claim 40, wherein, Also includes: The second device sends a first signaling message to the first device, the first signaling message including supervision configuration information; the supervision configuration information is used to supervise the performance of the AI ​​model.

42. The method according to claim 41, wherein, Also includes: The second device obtains model monitoring feedback information from the first device. The model monitoring feedback information is sent after the reporting threshold is met by comparing the statistical value with the performance supervision configuration information.

43. The method according to any one of claims 40 to 42, wherein, Also includes: The second device acquires capability reporting information from the first device, the capability reporting information being used to indicate the use cases supported by the AI ​​model, the use cases including at least one of the input information and the output information.

44. A communication device based on an intelligent algorithm, wherein, include: The processing module is used to acquire input information; The processing module is also used to obtain output information based on the artificial intelligence (AI) model and the input information, and the output information is used to adjust the transmission-related configuration parameters of the data link transmission layer.

45. The apparatus according to claim 44, wherein, The output information includes at least one of the following: Automatic retransmission request (ARQ) retransmission related configuration parameters; Configuration parameters related to Radio Link Control (RLC) layer status reporting; Configuration parameters related to Media Access Control (MAC) packages; Sending end PDCP transmission related configuration parameters; The receiving end transmits PDCP-related configuration parameters.

46. ​​The apparatus according to claim 45, wherein, The ARQ retransmission related configuration parameters include at least one of the following: Maximum number of retransmissions; The retransmission time point is used to indicate the time interval since the last initial transmission or retransmission. New data volume; Poll the relevant parameters.

47. The apparatus according to claim 45, wherein, The configuration parameters related to the RLC layer status report include at least one of the following: The timing and / or content of sending a status report, wherein the timing is used to indicate the time interval since the last status report was sent, and the content is the maximum sequence number (SN) of the feedback data packet; The time to terminate retransmission is used to indicate when the receiving end should give up receiving data packets; The delay reordering parameter indicates the duration for triggering the timer to send the status report; PDCP reordering time.

48. The apparatus according to claim 45, wherein, The configuration parameters for the MAC packet include at least one of the following: Selected logical channel (LCH); The amount of data selected for each logical channel (LCH); The priority order of at least two of the following: LCH PDU, RLC new transmission PDU, RLC retransmission PDU, RLC control PDU, and PDCP control PDU; At least two PDCP PDU priority orders; Priority order of at least two RLC PDUs; At least two MAC addresses control the priority order of PDUs; The length of SN; Priority Bit Rate (PBR) parameters for each logical channel; Priority of each logical channel.

49. The apparatus according to claim 45, wherein, The PDCP transmission-related configuration parameters of the transmitting end include at least one of the following: Enable PDCP repeat; Enable integrity protection; Partial data packets that are protected for integrity; Number of PDCP SDUs cascaded; Whether to enable SDU discarding based on PDCP timer; SDUs based on PDCP timers discard the corresponding timer suggestion values. Enable header compression algorithm; Enable header compression algorithm selection; Whether to enable uplink data compression UDC and the corresponding algorithm.

50. The apparatus according to claim 45, wherein, The receiving end PDCP transmission related configuration parameters include at least one of the following: Enable out-of-order transmission; Reordering time.

51. The apparatus according to claim 46, wherein, The input information includes at least one of the following: Current RLC transmitter configuration parameters; Current sending status; Packet loss rate is the ratio of lost data packets to the total number of data packets sent. Retransmission rate is the ratio of the number of retransmitted data packets to the number of newly transmitted data packets. Average number of retransmissions; Current transmission rate; Average RLC PDU length; The average amount of RLC PDU data transmitted per transmission interval; Service Quality of Service (QoS) requirements; Transmission Time Interval (TTI) length; HARQ maximum retransmission count; HARQ accuracy of Hybrid Automatic Repeat Requests; HARQ ACK / NACK error rate; Open port status.

52. The apparatus according to claim 47, wherein, The input information includes at least one of the following: Current RLC receiver configuration parameters; Data packet reception status; Status report sent status; Retransmission rate; Average waiting time; Open port status; Service QoS requirements; TTI length; HARQ maximum retransmission count; HARQ accuracy; HARQ ACK / NACK error rate.

53. The apparatus according to claim 48, wherein, The input information includes at least one of the following: Service QoS requirements; The current logical channel priority processing LCP-related configuration parameters; The amount of business data to be transmitted; Current LCP and service transmission status; Open port status; Cell load status.

54. The apparatus according to claim 49, wherein, The input information includes at least one of the following: Current PDCP layer configuration parameters; Current data link transport layer transmission status; Open port status; Service QoS requirements; Data link transport layer processing status; The application (APP) layer processes information.

55. The apparatus according to claim 50, wherein, The input information includes at least one of the following: Service QoS requirements; Service rate statistics at the RLC / PDCP layer; Average PDCP latency at the receiver; RLC configuration parameters; Receiver RLC statistical parameters; MAC HARQ configuration parameters.

56. The apparatus according to any one of claims 44-55, wherein, The processing module is also used to: obtain the performance supervision configuration information of the AI ​​model; The processing module is also used to perform performance supervision on the AI ​​model based on the supervision configuration information.

57. The apparatus according to claim 56, wherein, The performance monitoring configuration information includes at least one of the following: Reporting threshold values ​​corresponding to transmission rates of different air interface signal qualities; Reporting threshold values ​​for packet loss rates corresponding to different air interface signal qualities; Reporting threshold values ​​for retransmission rates corresponding to different air interface signal qualities; The reporting threshold for the proportion of data packets that are deleted or become latency-critical data; The reporting threshold for the percentage of retransmissions that are abandoned; Transmission delay reporting threshold The reporting threshold for packet loss rate; The reporting threshold value corresponding to the retransmission rate; The reporting threshold for redundancy retransmission rate; The reporting threshold for the PDCP packet deletion ratio.

58. The apparatus according to any one of claims 56-57, wherein, Also includes: The sending module is used to compare the statistical value with the performance supervision configuration information and send model monitoring feedback information to the second device when the trigger reporting threshold is met.

59. The apparatus according to any one of claims 44-58, wherein, Also includes: A receiving module is used to acquire model inference configuration information from a second device, wherein the model inference configuration information is used to indicate the input information and the output information.

60. The apparatus according to any one of claims 44-58, wherein, Also includes: A sending module is used to send capability reporting information to a second device. The capability reporting information is used to indicate the use cases supported by the AI ​​model. The use cases include at least one of the input information and the output information.

61. A communication device based on an intelligent algorithm, wherein, include: The sending module is used to send model inference configuration information to the first device. The model inference configuration information is used to indicate the input and output information of the artificial intelligence AI model deployed on the first device. The output information is used to adjust the transmission-related configuration parameters of the data link transmission layer.

62. The apparatus according to claim 61, wherein, The sending module is also used for: A first signaling message is sent to the first device, the first signaling message including supervision configuration information; the supervision configuration information is used to supervise the performance of the AI ​​model.

63. The apparatus according to claim 62, wherein, Also includes: The receiving module is used to obtain model monitoring feedback information from the first device. The model monitoring feedback information is sent after the reporting threshold is met by comparing the statistical value with the performance supervision configuration information.

64. The apparatus according to any one of claims 61 to 63, wherein, The sending module is also used for: Obtain capability reporting information from the first device, the capability reporting information being used to indicate use cases supported by the AI ​​model, the use cases including at least one of the input information and the output information.

65. A communication device, wherein, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the communication method as described in any one of claims 1 to 39.

66. A communication device, wherein, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the communication method as described in any one of claims 40 to 43.

67. A readable storage medium, wherein, The readable storage medium stores a program or instructions that, when executed by a processor, implement the communication method as described in any one of claims 1-39, or implement the steps of the communication method as described in any one of claims 40-43.

Images