Communication method, communication apparatus and storage medium

Abstract

Disclosed in the embodiments of the present application are a communication method, a communication apparatus and a storage medium, which are applied to the technical field of communications, and are used for performing performance monitoring on an AI model for data transmission. The method in the embodiments of the present application comprises: acquiring configuration information, wherein the configuration information is used for indicating one or more of one or more AI models, ground truths of the one or more AI models, and performance computation indicators of the one or more AI models, and the one or more AI models comprise at least one AI model for data transmission; and on the basis of the configuration information, monitoring the performance of the one or more AI models. In the embodiments of the present application, by means of acquiring configuration information, a receiver-side apparatus can determine a mode of monitoring one or more AI models, such that the receiver-side apparatus can perform performance monitoring on at least one AI model for data transmission, thereby ensuring the reliability of an AI system.

Description

A communication method, communication device and storage medium

[0001] This application claims priority to Chinese Patent Application No. 202411943649.7, filed on December 24, 2024, entitled "A Communication Method, Communication Device and Storage Medium", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a communication method, communication device and storage medium. Background Technology

[0003] With the development of communication technology, communication performance can be improved by using artificial intelligence (AI) technology in the communication modules of communication systems. Generally, systems that include AI modules, such as communication systems, can also be called AI systems.

[0004] Given the generalization issues inherent in AI technology, AI performance monitoring is necessary to ensure the reliability of the entire communication system. AI performance monitoring refers to the continuous monitoring and testing of the performance metrics of an AI model or system during actual operation. This process aims to ensure that the AI ​​model or system consistently meets performance requirements and to take timely measures to optimize or repair it when problems arise.

[0005] However, in the above process, how to provide AI performance monitoring for data transmission is a technical problem that urgently needs to be solved. Summary of the Invention

[0006] This application provides a communication method, communication device, and storage medium for monitoring the performance of AI models applied to data transmission.

[0007] The first aspect of this application provides a communication method. Optionally, the executing entity of this method can be a receiving device, which can be a network device, a component or device applied to the network device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the network device (e.g., a central unit (CU), a distributed unit (DU), or a radio unit (RU)). The receiving device can also be a terminal device, a component or device applied to the terminal device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the terminal device. Taking the receiving device as a terminal device as an example, in this method, the receiving device acquires configuration information. The configuration information is used to indicate one or more of the following: one or more AI models, the truth value of the output data of one or more AI models, and the performance calculation indicators of one or more AI models. At least one AI model is included in the one or more AI models for data transmission. The receiving device monitors the performance of one or more AI models according to the configuration information.

[0008] Based on the first aspect, by acquiring configuration information, the receiving device can determine the method of monitoring one or more AI models, thereby enabling the receiving device to perform performance monitoring on at least one AI model used for data transmission, thus ensuring the reliability of the AI ​​system.

[0009] In some possible implementations, at least one AI model includes an AI model for channel estimation, an AI model for demodulation, or an AI model for decoding.

[0010] In this embodiment, since the AI ​​model can be deployed in the communication modules corresponding to channel estimation, demodulation, and decoding, the reliability of data transmission in the AI ​​system can be guaranteed by monitoring the performance of the AI ​​models corresponding to these communication modules.

[0011] In some possible implementations, the truth value of the output data of one or more AI models comes from the sending device, or the truth value of the output data of one or more AI models is generated by a random number generator.

[0012] In this embodiment, by clarifying the source of the truth value of the AI ​​model output data, the receiving device can obtain the expected truth value of one or more AI model outputs, thereby monitoring the actual output of the AI ​​model based on the expected truth value, and thus ensuring the reliability of the AI ​​system.

[0013] In some possible implementations, performance metrics for one or more AI models include multipath feature deviation, vector distance, statistical information deviation, constellation point distance, bit error rate, block error rate, symbol error rate, number of response messages, or proportion of response messages.

[0014] In this embodiment, by limiting the performance calculation indicators of the AI ​​model, the receiving device can obtain monitoring results based on different performance calculation indicators, thereby ensuring the reliability of the AI ​​system.

[0015] In some possible implementations, the configuration information also includes preset conditions. When the preset conditions are met, the receiving device monitors the performance of one or more AI models based on the configuration information.

[0016] In this embodiment of the application, by indicating preset conditions in the configuration information, the receiving device monitors the performance of one or more AI models only when the preset conditions are met, thereby reducing the waste of resources of the receiving device.

[0017] In some possible implementations, satisfying the preset conditions includes at least one of the following:

[0018] The performance of the communication system is below the first threshold.

[0019] The channel estimation performance is higher than the second threshold;

[0020] Channel estimation performance is below the third threshold;

[0021] Decoding performance is below the fourth threshold;

[0022] Demodulation performance is above the fifth threshold;

[0023] Demodulation performance is below the sixth threshold;

[0024] Decoding works in mode 1;

[0025] Demodulation is performed in the second mode;

[0026] Channel estimation operates in the third mode;

[0027] Reaching the preset duration; or

[0028] The preset cycle has been reached.

[0029] In some possible implementations, the configuration information may also include one or more of the following: a first threshold, a second threshold, a third threshold, a fourth threshold, a fifth threshold, a sixth threshold, a preset duration, or a preset period.

[0030] In some possible implementations, the receiving device receives a first signaling message, which includes configuration information.

[0031] In this embodiment of the application, the receiving device can receive first information from the transmitting device, thereby enabling the monitoring configuration of the receiving device to match the requirements of the transmitting device.

[0032] In some possible implementations, the receiving device sends capability information, which indicates whether it has monitoring capabilities and / or which AI model it has monitoring capabilities for.

[0033] In this embodiment of the application, the receiving device can send capability information to indicate whether the receiving device has monitoring capability and / or which AI model it has monitoring capability for, so that the sending device can determine the configuration information based on the capability information.

[0034] In some possible implementations, monitoring results are sent, which are obtained by monitoring the performance of at least one of one or more AI models.

[0035] In this embodiment of the application, the receiving device can send monitoring results to the sending device, enabling the sending device to determine subsequent actions based on the monitoring results, thereby ensuring the reliability of the AI ​​system.

[0036] The second aspect of this application provides a communication method. Optionally, the executing entity of this method can be a transmitting device, which can be a network device, a component or device applied to the network device (e.g., a processor, circuit, chip, or chip system), or a logic module or software (e.g., CU, DU, or RU) capable of implementing all or part of the functions of the network device. The transmitting device can also be a terminal device, a component or device applied to the terminal device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the terminal device. Taking a network device as an example, the transmitting device determines configuration information. The configuration information indicates one or more of the following: one or more AI models, the truth value of the output data of one or more AI models, and the performance calculation indicators of one or more AI models. At least one AI model is included in the one or more AI models for data transmission. The transmitting device then transmits the configuration information.

[0037] In some possible implementations, at least one AI model includes an AI model for channel estimation, an AI model for demodulation, or an AI model for decoding.

[0038] In some possible implementations, the truth value of the output data of one or more AI models comes from the sending device, or the truth value of the output data of one or more AI models is generated by a random number generator.

[0039] In some possible implementations, performance metrics for one or more AI models include multipath feature deviation, vector distance, statistical information deviation, constellation point distance, bit error rate, block error rate, symbol error rate, number of response messages, or proportion of response messages.

[0040] In some possible implementations, the configuration information also includes preset conditions, which are satisfied if the receiving device satisfies at least one of the following:

[0041] The performance of the communication system is below the first threshold.

[0042] The channel estimation performance is higher than the second threshold;

[0043] Channel estimation performance is below the third threshold;

[0044] Decoding performance is below the fourth threshold;

[0045] Demodulation performance is above the fifth threshold;

[0046] Demodulation performance is below the sixth threshold;

[0047] Decoding works in mode 1;

[0048] Demodulation is performed in the second mode;

[0049] Channel estimation operates in the third mode;

[0050] Reaching the preset duration; or

[0051] The preset cycle has been reached.

[0052] In some possible implementations, the configuration information may also include one or more of the following: a first threshold, a second threshold, a third threshold, a fourth threshold, a fifth threshold, a sixth threshold, a preset duration, or a preset period.

[0053] In some possible implementations, the transmitting device sends a first signaling message, which includes configuration information.

[0054] In some possible implementations, the transmitting device may also receive capability information, which indicates whether it has monitoring capability and / or which AI model it has monitoring capability for.

[0055] In some possible implementations, the transmitting device may also receive monitoring results obtained by monitoring the performance of at least one of one or more AI models.

[0056] A third aspect of this application provides a communication device, which may be the aforementioned receiving device. The communication device includes modules or units for performing the methods described in the first aspect and any possible implementation thereof.

[0057] A fourth aspect of this application provides a communication device, which may be the aforementioned transmitting end device. The communication device includes modules or units for performing the methods described in the second aspect and any possible implementation thereof.

[0058] A fifth aspect of this application provides a communication device, which may be a first device or a second device, or a component applied to the first device or the second device (e.g., a processor, circuit, chip, or chip system), or a logic module or software (e.g., CU, DU, or RU) capable of implementing all or part of the functions of the first device or the second device. The communication device includes:

[0059] A processor for executing a program that causes the communication device to perform the method as described in the first or second aspect and any possible implementation thereof.

[0060] Optionally, the communication device further includes a memory, and the processor is coupled to the memory; the memory is used to store programs.

[0061] The sixth aspect of this application provides a chip or chip system including at least one processor and a communication interface, the communication interface and at least one processor being interconnected via a line, the at least one processor being used to run computer programs or instructions to perform the communication method described in any of the possible implementations of the first or second aspect.

[0062] The communication interface in the chip can be an input / output interface, pins, or circuits.

[0063] In one possible implementation, the chip or chip system described above in this application further includes at least one memory storing instructions. The memory can be an internal storage unit of the chip, such as a register or cache, or it can be a storage unit of the chip itself, such as a read-only memory or random access memory.

[0064] The seventh aspect of this application provides a communication system, including a communication device that performs the first aspect and any possible implementation thereof, and a communication device that performs the second aspect and any possible implementation thereof.

[0065] An eighth aspect of this application provides a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the method described in the first aspect above, or cause the computer to perform the method described in the second aspect above.

[0066] The ninth aspect of this application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the method described in the first aspect above, or cause the computer to perform the method described in the second aspect above. Attached Figure Description

[0067] Figures 1a to 1c are schematic diagrams of the communication system provided in this application;

[0068] Figures 2a to 2g are schematic diagrams of the AI ​​processing involved in this application;

[0069] Figure 3 is a schematic diagram of an embodiment of the communication method in this application;

[0070] Figures 4 to 7 are schematic diagrams of the communication device provided in this application. Detailed Implementation

[0071] First, some terms used in the embodiments of this application will be explained to facilitate understanding by those skilled in the art.

[0072] (1) Terminal device: can be a wireless terminal device that can receive network device scheduling and instruction information. The wireless terminal device can be a device that provides voice and / or data connectivity to the user, or a handheld device with wireless connection function, or other processing device connected to a wireless modem.

[0073] Terminal devices can communicate with one or more core networks or the Internet via a radio access network (RAN). Terminal devices can be mobile terminal devices, such as mobile phones (or "cellular" phones), computers, and data cards. For example, they can be portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile devices that exchange voice and / or data with the RAN. Examples include personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablets, and computers with wireless transceiver capabilities. Wireless terminal equipment can also be called subscriber unit, subscriber station, mobile station (MS), remote station, access point (AP), remote terminal, access terminal, user terminal, user agent, subscriber station (SS), customer premises equipment (CPE), terminal, user equipment (UE), mobile terminal (MT), etc.

[0074] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices or smart wearable devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets, smart helmets, and smart jewelry for vital sign monitoring.

[0075] Terminals can also be drones, robots, devices in device-to-device (D2D) communication, vehicles to everything (V2X) communication, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in telemedicine or telehealth services, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, etc.

[0076] Furthermore, terminal devices can also be terminal devices in future communication systems beyond the fifth generation (5G) (such as 5G Advanced communication systems) or in future evolved public land mobile networks (PLMNs). For example, 5G Advanced networks can further expand the form and function of 5G communication terminals; 5G Advanced terminals include, but are not limited to, vehicles, cellular network terminals (integrating satellite terminal functions), drones, and Internet of Things (IoT) devices.

[0077] (2) Network equipment: This can be equipment within a wireless network. For example, network equipment can be a RAN node (or device) that connects terminal devices to the wireless network, and can also be called a base station. Currently, some examples of RAN equipment include: base station, evolved NodeB (eNodeB), gNB (gNodeB) in 5G communication systems, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), home base station (e.g., home evolved Node B, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wi-Fi) access point (AP), etc. In addition, in a network architecture, network equipment can include central unit (CU) nodes, distributed unit (DU) nodes, or RAN equipment including both CU and DU nodes.

[0078] Optionally, RAN nodes can also be macro base stations, micro base stations, indoor stations, relay nodes, donor nodes, or radio controllers in cloud radio access network (CRAN) scenarios. RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU).

[0079] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CUs (control plane, CP), CUs (user plane, UP), or radio units (RUs). CUs and DUs can be configured separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio equipment or radio units, such as remote radio units (RRUs), active antenna units (AAUs), radio heads (RHs), or remote radio heads (RRHs).

[0080] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an open access network (open RAN, O-RAN, or ORAN) system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0081] Communication between access network devices and terminal devices follows a specific protocol layer structure. This protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: radio resource control (RRC) layer, packet data convergence protocol (PDCP) layer, radio link control (RLC) layer, media access control (MAC) layer, or physical (PHY) layer, etc. The user plane protocol layer may include at least one of the following: service data adaptation protocol (SDAP) layer, PDCP layer, RLC layer, MAC layer, or physical layer, etc.

[0082] The correspondence between network elements and their achievable protocol layer functions in the ORAN system can be found in Table 1 below.

[0083] Table 1

[0084] Network devices can be other devices that provide wireless communication functions for terminal devices. The embodiments of this application do not limit the specific technology or form of the network device. For ease of description, the embodiments of this application are not limited.

[0085] Network equipment may also include core network equipment, such as the Mobility Management Entity (MME), Home Subscriber Server (HSS), Serving Gateway (S-GW), Policy and Charging Rules Function (PCRF), and Public Data Network Gateway (PDN gateway or P-GW) in 4th generation (4G) networks; and access and mobility management function (AMF), user plane function (UPF), or session management function (SMF) in 5G networks. Furthermore, this core network equipment may also include other core network equipment in 5G networks and next-generation networks of 5G networks.

[0086] In this embodiment of the application, the network device may also have network nodes with AI capabilities, which can provide AI services to terminals or other network devices. For example, it may be an AI node, computing node, RAN node with AI capabilities, or core network element with AI capabilities on the network side (access network or core network).

[0087] In this application embodiment, the device for implementing the function of the network device can be the network device itself, or it can be a device capable of supporting the network device in implementing the function, such as a chip system. This device can be disposed within the network device. In the technical solutions provided in this application embodiment, the example of a network device being used to implement the function of the network device is used to describe the technical solutions provided in this application embodiment.

[0088] (3) Configuration and Pre-configuration: In this application, both configuration and pre-configuration are used. Configuration refers to the network device / server sending configuration information or parameter values ​​to the terminal via messages or signaling, so that the terminal can determine communication parameters or resources for transmission based on these values ​​or information. Pre-configuration is similar to configuration; it can be parameter information or parameter values ​​pre-negotiated between the network device / server and the terminal device, parameter information or parameter values ​​specified by standard protocols for use by the base station / network device or terminal device, or parameter information or parameter values ​​pre-stored in the base station / server or terminal device. This application does not limit this.

[0089] Furthermore, these values ​​and parameters can be changed or updated.

[0090] (4) The terms "system" and "network" in the embodiments of this application can be used interchangeably. "Multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. And, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of this application are used to distinguish multiple objects and are not used to limit the order, sequence, priority or importance of multiple objects.

[0091] (5) In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include sending directly through the air interface or sending indirectly through the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include receiving directly from YY through the air interface or receiving indirectly from YY through the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0092] In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via buses, wiring, or interfaces.

[0093] It is understandable that information may undergo necessary processing, such as encoding and modulation, between the source and destination, but the destination can understand the valid information from the source. Similar statements in this application can be interpreted in a similar way and will not be elaborated further.

[0094] (6) In the embodiments of this application, "instruction" may include direct instruction and indirect instruction, as well as explicit instruction and implicit instruction. The information indicated by a certain piece of information (as described below, the instruction information) is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is an association between the other information and the information to be instructed; or it can only indicate a part of the information to be instructed, while the other parts of the information to be instructed are known or pre-agreed upon. For example, the instruction can be implemented by using a pre-agreed (e.g., protocol predefined) arrangement order of various information, thereby reducing the instruction overhead to a certain extent. This application does not limit the specific method of instruction. It is understood that for the sender of the instruction information, the instruction information can be used to indicate the information to be instructed, and for the receiver of the instruction information, the instruction information can be used to determine the information to be instructed.

[0095] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, and the various methods / designs / implementations within each embodiment, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the various methods / designs / implementations within each embodiment are consistent and can be mutually referenced. The technical features in different embodiments and the various methods / designs / implementations within each embodiment can be combined to form new embodiments, methods, or implementations based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0096] This application can be applied to long-term evolution (LTE) systems, new radio (NR) systems, or future communication systems beyond 5G. These communication systems include at least one network device and / or at least one terminal device.

[0097] Please refer to Figure 1a, which is a schematic diagram of the architecture of the communication system 1000 used in the embodiments of this application. As shown in Figure 1a, the communication system may include a radio access network (RAN) 100. Optionally, the communication system 1000 may also include a core network 200 and an Internet 300. The RAN 100 includes at least one RAN node (110a and 110b in Figure 1a, collectively referred to as 110) and at least one terminal (120a-120j in Figure 1a, collectively referred to as 120). The RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1a). The terminal 120 is wirelessly connected to the RAN node 110, and the RAN node 110 is wirelessly or wiredly connected to the core network 200. The core network equipment in the core network 200 and the RAN node 110 in the RAN 100 may be independent and different physical devices, or they may be the same physical device integrating the logical functions of the core network equipment and the logical functions of the RAN node. Terminals can be connected to each other, as can RAN nodes, via wired or wireless means.

[0098] Taking the communication system shown in Figure 1a as an example, in addition to performing communication-related services, different devices (including network devices and network devices, network devices and terminal devices, and / or terminal devices and terminal devices) may also perform AI-related services.

[0099] As shown in Figure 1b, taking a network device as a base station as an example, the base station can perform communication-related services and AI-related services with one or more terminal devices, and different terminal devices can also perform communication-related services and AI-related services.

[0100] As shown in Figure 1c, taking terminal devices including televisions and mobile phones as an example, communication-related services and AI-related services can also be performed between televisions and mobile phones.

[0101] The technical solutions provided in this application can be applied to wireless communication systems (such as the systems shown in Figures 1a, 1b, or 1c). For example, AI network elements can be introduced into the communication system provided in this application to realize some or all AI-related operations. AI network elements can also be called AI nodes, AI devices, AI entities, AI modules, AI models, or AI units, etc. The AI ​​network element can be built into a network element within the communication system. For example, the AI ​​network element can be an AI module built into: access network equipment, core network equipment, cloud server, or operation, administration, and maintenance (OAM) to realize AI-related functions. The OAM can act as the network management system for the core network equipment and / or the access network equipment. Alternatively, the AI ​​network element can also be an independently set network element in the communication system. Optionally, the terminal or its built-in chip can also include an AI entity to realize AI-related functions.

[0102] Optionally, in communication systems, AI application cases may include, but are not limited to: channel state information (CSI) feedback enhancement, beam management enhancement, positioning accuracy enhancement, network energy saving, load balancing, and mobility optimization. These will be explained below.

[0103] 1. Enhanced CSI feedback

[0104] Channel quality information (CSI) is the channel attribute of a communication link, reported by the terminal device to the network device. By reporting this information, the terminal device can select an appropriate modulation and coding scheme (MCS) to adapt to changing wireless channels. For example, the terminal device might perform channel estimation based on the received channel state information-reference signal (CSI-RS) and then feed back the CSI-RS to the network device. This information serves as input to the network device's model, enabling AI model training. Applying AI to CSI feedback enhancement can reduce overhead, improve accuracy, and enhance predictive capabilities.

[0105] CSI-RS feedback enhancement may include at least one sub-function, such as: CSI compression, CSI prediction, and CSI-RS configuration signaling reduction. CSI compression may further include CSI compression in at least one domain: spatial, time, and frequency.

[0106] 2. Enhanced Beam Management

[0107] Enhanced beam management primarily aims to discover the strongest transmit / receive beam pairs. AI-based sparse beam prediction can improve accuracy. This can be achieved through both network-side and terminal-side AI sparse beam prediction, based on AI training and inference. Taking terminal-side AI sparse beam prediction as an example, the pre-trained AI model on the terminal device can be provided by the network or pre-stored on the terminal device. During training, the network device scans all possible beams and then reports the transmit beam pattern to the terminal device. Once training is complete, the network device only needs to scan a small subset of beams, and the terminal device then feeds back the inference results. AI-based beam management can achieve beam prediction in, for example, the temporal and / or spatial domains, reducing overhead and latency and improving beam selection accuracy.

[0108] Beam management enhancements may include at least one sub-function, such as: beam scan matrix prediction and optimal beam prediction.

[0109] 3. Enhanced positioning accuracy

[0110] In line-of-sight (LOS) or non-line-of-sight (NLOS) scenarios, AI-based positioning can improve positioning accuracy with a smaller number of TRP antennas. Positioning enhancement can include at least one sub-function, such as: positioning enhancement based on access network devices, positioning enhancement based on positioning management function network elements, and positioning enhancement based on terminal devices.

[0111] 4. Network energy saving

[0112] Network energy conservation can be achieved through cell activation / deactivation, load reduction, coverage improvement, or other RAN setting adjustments. AI technology can be used to optimize energy-saving decisions by leveraging data collected within the RAN network. AI algorithms can predict energy efficiency and load status for the next cycle, which can be used to assist in cell activation / deactivation decisions to save energy. Based on the predicted load, the system can dynamically configure energy-saving strategies to maintain a balance between system performance and energy efficiency, and reduce energy consumption.

[0113] 5. Load balancing

[0114] Load balancing can distribute the load evenly between cells and across different areas within a cell, or transfer some traffic from congested cells, or offload users across a single cell, carrier, or access standard, thereby improving network performance. Using AI models to enhance load balancing performance—such as inputting various measurements and feedback from terminal devices and network nodes, as well as historical data—can provide a higher quality user experience and increase system capacity.

[0115] 6. Mobility Management

[0116] Mobility management is a solution that ensures service continuity for mobile devices by minimizing dropped calls, radio link failures (RLFs), unnecessary handovers, and ping-pong effects. AI can enhance mobility management by, for example, reducing the probability of unexpected events, predicting device location / mobility / performance, and routing traffic.

[0117] It should be understood that the definitions of the above technical terms are merely illustrative. For example, as technology continues to develop, the scope of the above definitions may also change, and the embodiments of this application are not intended to limit the scope.

[0118] It should be understood that the definitions of the above technical terms are merely illustrative. For example, as technology continues to develop, the scope of the above definitions may also change, and the embodiments of this application are not intended to limit the scope.

[0119] For example, an AI function may include multiple AI sub-functions.

[0120] Optionally, AI application cases are also called AI application scenarios or AI functions.

[0121] As described above regarding AI application examples, AI can be widely used to improve network performance in areas such as CSI feedback enhancement, beam management, positioning accuracy enhancement, energy saving, mobility enhancement, and load balancing. AI models can typically be deployed on the network side and / or the terminal device side. The training of AI models relies on the collection of training data, which can come from measurements and feedback from the terminal devices.

[0122] The following is a brief introduction to the concepts that may be involved in this application.

[0123] AI can endow machines with human-like intelligence, for example, allowing them to use computer hardware and software to simulate certain intelligent human behaviors. To achieve artificial intelligence, machine learning methods can be employed. In machine learning, machines learn (or train) a model using training data. This model represents the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result).

[0124] Machine learning (ML) can include supervised learning, unsupervised learning, and reinforcement learning. Unsupervised learning can also be called learning without supervision.

[0125] Supervised learning, based on collected sample values ​​and labels, uses machine learning algorithms to learn the mapping relationship between sample values ​​and labels, and then expresses this learned mapping relationship using an AI model. The process of training the machine learning model is the process of learning this mapping relationship. During training, sample values ​​are input into the model to obtain the model's predicted values, and the model parameters are optimized by calculating the error between the model's predicted values ​​and the sample labels (ideal values). After the mapping relationship is learned, it can be used to predict new sample labels. The mapping relationship learned in supervised learning can include linear or non-linear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0126] Unsupervised learning relies on collected sample values ​​to discover inherent patterns within the samples themselves. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals, meaning the model learns the mapping relationship from sample to sample; this is called self-supervised learning. During training, model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used for signal compression and decompression recovery applications; common algorithms include autoencoders and generative adversarial networks.

[0127] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have explicit "correct" action labels. The algorithm needs to interact with the environment to obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each user based on the total system throughput feedback from the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and a better (e.g., optimal) decision action. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action." Reinforcement learning training is achieved through iterative interaction with the environment.

[0128] Neural networks (NNs) are a specific model in machine learning techniques. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems rely on extensive expert knowledge to design communication modules, while deep learning communication systems based on neural networks can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0129] The idea behind neural networks comes from the neuronal structure of the brain. For example, each neuron performs a weighted summation of its input values ​​and outputs the result through an activation function.

[0130] Figure 2a shows a schematic diagram of a neuron structure. Assume the input to the neuron is x = [x0, x1, ..., x...]. n The weights corresponding to each input are w = [w0, w1, ..., w] n ], where n is a positive integer, w i and x i It can be any possible type, such as a decimal, an integer (e.g., 0, a positive integer, or a negative integer), or a complex number. i As x i The weights are used to assign weights to x. i Weighting is applied. The bias for the weighted sum of the input values ​​is, for example, b. Activation functions can take many forms. Suppose the activation function of a neuron is: y = f(z) = max(0, z), then the output of that neuron is: For example, if the activation function of a neuron is y = f(z) = z, then the output of that neuron is: Here, b can be any possible type, such as a decimal, an integer (e.g., 0, a positive integer, or a negative integer), or a complex number. The activation functions of different neurons in a neural network can be the same or different.

[0131] Furthermore, neural networks generally consist of multiple layers, each of which may include one or more neurons. Increasing the depth and / or width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can refer to the number of layers it includes, and the number of neurons in each layer can be called the width of that layer. In one implementation, a neural network includes an input layer and an output layer. The input layer processes the received input information through neurons and passes the processing result to the output layer, which then obtains the output of the neural network. In another implementation, a neural network includes an input layer, hidden layers, and an output layer. The input layer processes the received input information through neurons and passes the processing result to the hidden layer. The hidden layer calculates the received processing result and passes the calculation result to the output layer or the next adjacent hidden layer, ultimately obtaining the output of the neural network. A neural network may include one hidden layer or multiple sequentially connected hidden layers, without limitation.

[0132] Neural networks, for example, are deep neural networks (DNNs). Depending on how the network is constructed, DNNs can include feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs).

[0133] Figure 2b is a schematic diagram of an FNN network. A characteristic of FNN networks is that neurons in adjacent layers are completely connected pairwise. This characteristic makes FNNs typically require a large amount of storage space, leading to high computational complexity.

[0134] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time-series data (e.g., discrete sampling along a time axis) and image data (e.g., two-dimensional discrete sampling) can both be considered grid-like data. CNNs do not use all the input information at once for computation; instead, they use a fixed-size window to extract a portion of the information for convolution operations, which significantly reduces the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (e.g., people and objects in an image represent different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0135] Recurrent Neural Networks (RNNs) are a type of neural network that utilizes feedback time-series information. The input to an RNN includes the current input value and its own output value from the previous time step. RNNs are suitable for acquiring temporally correlated sequence features, and are applicable to applications such as speech recognition and channel coding / decoding.

[0136] In the model training process described above, a loss function can be defined. The loss function describes the difference between the model's output value and the ideal target value. The loss function can be expressed in various forms, and there are no restrictions on its specific form. The model training process can be viewed as follows: by adjusting some or all of the model's parameters, the value of the loss function is made to be less than a threshold or to meet the target requirement.

[0137] A model can also be called an AI model, a rule, or other names. An AI model can be considered a specific method for implementing AI functions. An AI model represents the mapping relationship or function between the model's input and output. AI functions can include one or more of the following: data collection, model training (or model learning), model information dissemination, model inference (or model reasoning, inference, or prediction, etc.), model monitoring or model validation, or inference result publication, etc. AI functions can also be called AI (related) operations or AI-related functions.

[0138] The implementation process of the neural network will be described below with reference to the accompanying drawings.

[0139] 1. Fully connected neural network, also known as multilayer perceptron (MLP).

[0140] As shown in Figure 2c, an MLP consists of an input layer (left side), an output layer (right side), and multiple hidden layers (middle). Each layer of an MLP contains several nodes, called neurons. Neurons in adjacent layers are connected pairwise.

[0141] Optionally, considering neurons in two adjacent layers, the output h of the next layer's neurons is the weighted sum of all neurons x in the previous layer connected to it, processed by an activation function, and can be expressed as: h = f(wx + b).

[0142] Where w is the weight matrix, b is the bias vector, and f is the activation function.

[0143] Alternatively, the output of the neural network can be recursively expressed as: y = f z (w z f z-1 (…)+b z ).

[0144] Where z is the index of the neural network layer, z is greater than or equal to 1 and z is less than or equal to Z, where Z is the total number of layers in the neural network.

[0145] In other words, a neural network can be understood as a mapping from an input data set to an output data set. Neural networks are typically initialized randomly; the process of obtaining this mapping from random values ​​w and b using existing data is called training the neural network.

[0146] Optionally, the training method involves using a loss function to evaluate the output of the neural network.

[0147] As shown in Figure 2d, the error can be backpropagated, and the neural network parameters (including w and b) can be iteratively optimized using gradient descent until the output of the loss function reaches its minimum value, which is the "better point (e.g., the optimal point)" in Figure 2d. It can be understood that the neural network parameters corresponding to the "better point (e.g., the optimal point)" in Figure 2d can be used as the neural network parameters in the trained AI model information.

[0148] Alternatively, the gradient descent process can be represented as:

[0149] Where θ represents the parameters to be optimized (including w and b), L is the loss function, and η is the learning rate, controlling the step size of gradient descent. This represents the differentiation operation. This indicates taking the derivative of θ with respect to L.

[0150] Alternatively, the backpropagation process can utilize the chain rule for partial derivatives.

[0151] As shown in Figure 2e, the gradient of the parameters in the previous layer can be recursively calculated from the gradient of the parameters in the next layer, and can be expressed as:

[0152] Among them, w ij Let s be the weight of the connection between node j and node i. i The weighted sum of the inputs at node i.

[0153] 2. Federated Learning (FL).

[0154] The concept of federated learning effectively addresses the current challenges in the development of artificial intelligence. While fully protecting user data privacy and security, it enables various edge devices and central servers to collaborate efficiently to complete the model's learning task.

[0155] As shown in Figure 2f, the FL architecture is the most widely used training architecture in the current FL field, and the FedAvg algorithm is the basic algorithm of FL. The FedAvg algorithm flow is roughly as follows:

[0156] (1) Initialize the model to be trained at the center end. And broadcast it to all clients.

[0157] (2) In the t∈[1,T] round, the client k∈[1,K] is based on the local dataset. For the received global model Perform E epochs of training to obtain the local training results. This is then reported to the central node. In the example shown in Figure 2f, the local training results sent by distributed nodes n, k, and m are denoted as G, respectively. n G k G m .

[0158] (3) The central node collects local training results from all (or some) clients. Assume the set of clients uploading local models in round t is... The central server will use the number of samples from the corresponding client as weights to calculate the new global model. The specific update rule is as follows: Then the central end will send the latest version of the global model. The broadcast is sent to all clients for a new round of training.

[0159] (4) Repeat steps (2) and (3) until the model finally converges or the number of training rounds reaches the upper limit.

[0160] Optionally, in addition to reporting the local model, the client can also... It can also train local gradients The central node averages the local gradients reported by all clients and updates the global model based on this average gradient.

[0161] As can be seen in the FL framework, the dataset resides on distributed nodes (such as clients). These distributed nodes collect their local datasets, perform local training, and report the local results (model or gradients) to the central node. The central node itself may not have a dataset; it can be responsible for fusing the training results from the distributed nodes to obtain a global model, which is then distributed back to the distributed nodes.

[0162] 3. Decentralized learning.

[0163] Figure 2g illustrates a fully distributed system without a central node. The design goal f(x) of a decentralized learning system is generally the goal f of each node. iThe mean of (x), i.e. Where n is the number of distributed nodes, and x is the parameter to be optimized; in machine learning, x is the parameter of the machine learning model (such as a neural network). Each node utilizes local data and its local target f. i (x) Calculate the local gradient Then it is sent to its communicatively reachable neighboring nodes. Upon receiving the gradient information from its neighbor, any node can update the parameters x of its local model according to the following formula:

[0164] in, This represents the parameters of the local model after the (k+1)th update (k is a natural number) in the i-th node. This represents the parameters of the local model for the i-th node after the k-th update (if k is 0, then it represents...). (where α is the parameter of the local model of the i-th node that is not involved in the update) k N represents the tuning coefficient. i It is the set of neighboring nodes of node i, |N i | represents the number of elements in the set of neighboring nodes of node i, that is, the number of neighboring nodes of node i. Through information interaction between nodes, the decentralized learning system will eventually learn a unified model.

[0165] The technical solution provided in this application can be applied to communication systems (such as the systems shown in Figure 1a, 1b, or 1c). In a communication system, communication nodes generally possess signal transmission and reception capabilities as well as computing capabilities. Taking a network device with computing capabilities as an example, the computing capabilities of the network device mainly provide computational support for the signal transmission and reception capabilities (e.g., processing the transmission and reception of signals) to realize the communication tasks between the network device and other communication nodes.

[0166] With the development of communication technology, communication equipment in communication systems can now perform not only traditional communication services but also new types of services, such as AI services. Generally, a system capable of handling AI services, such as a communication system, can also be called an AI system. Considering the generalization issues inherent in AI / ML technologies, AI / ML performance monitoring is necessary to ensure the reliability and trustworthiness of the entire communication system.

[0167] In one possible implementation, the performance of AI / ML implementations for modules or functions such as CSI, beam management, and positioning can be monitored to ensure the reliability of the AI ​​system. However, there is no corresponding monitoring method for data transmission at the wireless physical layer, such as the AI / ML implementation of modules or functions like demodulation reference signal (DMRS), channel estimation, demodulation, and encoding / decoding.

[0168] Please refer to Figure 3, which is a schematic diagram of a communication method provided in an embodiment of this application. The method shown in Figure 3 is executed interactively by a transmitting device and a receiving device. The transmitting device can be a network device, or a component or device applied to a network device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of a network device (e.g., a central unit (CU), a distributed unit (DU), or a radio unit (RU)). The transmitting device can also be a terminal device, or a component or device applied to a terminal device (e.g., a processor, circuit, chip, or chip system), or a circuit or chip in the terminal device responsible for communication functions (e.g., a modem chip, also known as a baseband chip, or a system-on-a-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip). The receiving end device can be a network device, or a component or device applied to a network device (such as a processor, circuit, chip, or chip system), or a logic module or software (such as a CU, DU, or RU) that can implement all or part of the functions of the network device. The receiving end device can also be a terminal device, or a component or device applied to a terminal device (such as a processor, circuit, chip, or chip system), or a logic module or software that can implement all or part of the functions of the terminal device.

[0169] It should be noted that the sending and receiving devices can be of the same type, for example, both the sending and receiving devices can be network devices, or both the sending and receiving devices can be terminal devices. Alternatively, the sending and receiving devices can be of different types, for example, the sending device can be a network device and the receiving device can be a terminal device; or, for example, the sending device can be a terminal device and the receiving device can be a network device. The specific type is not limited here.

[0170] In this embodiment of the application, a communication method includes:

[0171] 301. The receiving device obtains configuration information.

[0172] The configuration information is used to indicate one or more of the following: one or more AI models, the truth values ​​of one or more AI models, and the performance calculation metrics of one or more AI models, including at least one AI model used for data transmission.

[0173] In this embodiment of the application, the AI ​​model used for data transmission can be an AI model for channel estimation, an AI model for demodulation, or an AI model for decoding; the specific model is not limited here.

[0174] DMRS, or Demodulation Reference Signal, is used for channel estimation and correlation demodulation of the physical channel. It typically occupies a portion of time-domain, frequency-domain, spatial-domain, or code-domain transmission resources and is transmitted to the receiver along with the data. Upon receiving the DMRS, the receiver can use it for channel estimation to demodulate the data. DMRS and channel estimation are correlated; the transmitter sends the DMRS, and the receiver receives it and uses it for channel estimation. For example, in the communication module for DMRS and channel estimation, AI applications include three possible scenarios: using AI in the design of DMRS while still using non-AI channel estimation techniques, aiming to reduce the DMRS's occupation of time-domain, frequency-domain, spatial-domain, or code-domain transmission resources, or to achieve better channel estimation at the receiver; using AI in channel estimation while still using the existing DMRS, aiming to achieve more accurate channel estimation at the receiver, or to reduce latency and energy consumption in channel estimation at the receiver; and using AI simultaneously in both DMRS design and channel estimation, expected to achieve the above benefits simultaneously.

[0175] Modulation is the process of superimposing the desired signal onto one or more periodic carrier waves, commonly used in radio propagation, wired communication, and wireless communication. Modulation can be divided into digital modulation and analog modulation. Demodulation is the inverse process of modulation, used to extract the original signal. For example, using AI in a demodulation communication module includes three possible scenarios: using AI for modulation to achieve better transmission performance; using AI for demodulation to achieve better signal reception performance or reduce terminal demodulation latency and power consumption; and using AI for both modulation and demodulation to achieve the above benefits simultaneously.

[0176] Encoding and decoding are crucial components of communication systems and can be categorized into three schemes: channel coding and decoding, used to protect data from errors during transmission and to recover data in case of errors; source coding and decoding, used to reduce or eliminate redundancy in source data, reduce the amount of source data, and improve communication efficiency; and joint source-channel coding and decoding, which refers to jointly or simultaneously performing source coding and channel coding, and channel decoding and source decoding to achieve the objectives of both encoding and decoding methods. For example, the application of AI in decoding communication modules includes three possible scenarios: using AI for encoding to achieve better transmission performance; using AI for demodulation to achieve better data reception performance or reduce terminal decoding latency and energy consumption; and using AI simultaneously for encoding and decoding to achieve the aforementioned benefits simultaneously.

[0177] Since the configuration information is used by the receiving device for model monitoring, the one or more AI models indicated by the configuration information are also referred to as monitoring targets. The truth value of the output data of the one or more AI models indicated by the configuration information can be a specific data truth value or a method of obtaining the data truth value. The performance of the one or more AI models indicated by the configuration information can be understood as the performance calculation indicators and / or performance thresholds of the one or more AI models.

[0178] It should be understood that the true value (or grand truth) usually refers to the actual value of a data point in the dataset, which is the target that the model attempts to predict or estimate. The predicted value (also known as the estimated value) is the value calculated by the model based on the input data, used to compare with the true value to evaluate the accuracy of the model.

[0179] The configuration information varies depending on the AI ​​model. The following sections provide a detailed description of the configuration information for each different AI model.

[0180] I. AI Models for Channel Estimation

[0181] The configuration information may include use case indicators, which can be used to indicate use cases for channel estimation. For example, the use case indicator may be the number of the AI ​​model used for channel estimation, or the channel estimation function corresponding to the AI ​​model; the specifics are not limited here.

[0182] It should be noted that the AI ​​model deployed on the receiving device is an AI model for channel estimation, while the AI ​​model deployed on the transmitting device is an AI model for DMRS design. Specifically, the transmitting device transmits the designed DMRS to the receiving device through the channel based on the AI ​​model used for DMRS design, and the receiving device performs channel estimation based on the DMRS.

[0183] One possible implementation is to monitor the AI ​​model used for channel estimation, or to monitor the AI ​​model used for DMRS design and / or the AI ​​model used for channel estimation.

[0184] For AI models used for channel estimation, or AI models used for DMRS design and AI models used for channel estimation, the truth value can be obtained by configuring a higher density reference signal and traditional channel estimation methods. The specific method is not limited here.

[0185] For example, the performance metrics of the AI ​​model used for channel estimation included in the configuration information can be multipath feature bias, channel / feature vector distance, or statistical information bias. These are explained below:

[0186] 1) Multipath characteristic deviation:

[0187] Multipath feature bias refers to the multipath information extracted by the receiving device from the channel information obtained by the channel estimation algorithm, such as the number of paths, path loss, delay, frequency shift, and angle information. This multipath information is compared with the multipath information extracted from the true channel information to obtain the bias. This bias can be, for example, the difference in the number of paths, the difference in path loss of each path, the difference in delay, the difference in frequency shift, etc.

[0188] The performance threshold can be a threshold for deviation. For example, if M paths are extracted from the true channel information and N paths are extracted from the channel information output by the channel estimation model, the difference in the number of paths is |NM|. Assuming the threshold is T, if |NM| > T, then the threshold condition is considered met. For path loss, delay, frequency shift, and angle indicators of multiple paths, one can consider comparing the average difference between the multiple paths with the threshold, or whether the number of paths that meet the threshold condition (assumed to be threshold 1) meets the quantity threshold (assumed to be threshold 2), etc.

[0189] Optionally, some processing can be performed before or after multipath extraction, such as Fourier transform, normalization, etc., but the specifics are not limited here.

[0190] 2) Distance between channel and eigenvector:

[0191] Channel information is usually a matrix or tensor, which can be converted into a vector by methods such as expansion, dimensional slicing (row-by-row slicing, column-by-column slicing), and solving for eigenvectors. The distance between the vector of channel information output by the channel estimation model and the vector of truth information can be calculated, which can be used to measure the performance of the channel information output by the channel estimation model.

[0192] Methods for measuring the distance between two vectors can include, but are not limited to: calculating cosine similarity (CS) and its variations, such as cosine similarity, generalized cosine similarity, and squared generalized cosine similarity; calculating Minkowski distance and its variations, such as Minkowski distance (i.e., Manhattan distance, Euclidean distance, etc.), normalized Minkowski distance, and standardized Euclidean distance. In practical applications, other methods can also be used to measure the distance between two vectors, which are not limited here.

[0193] If the receiving device obtains a distance indicator, it can directly compare it with the distance threshold; if it obtains multiple indicators, it can compare and judge them by methods such as whether the number of distances that meet the threshold condition (threshold 1) meets the quantity threshold (threshold 2).

[0194] Optionally, some processing can be performed before or after multipath extraction, such as Fourier transform, normalization, etc., but the specifics are not limited here.

[0195] 3) Statistical information bias:

[0196] Statistical information bias refers to the process by which the receiving device statistically analyzes channel information and compares the collected statistical data. Statistical information may include (but is not limited to): mean, variance, maximum value, minimum value, percentile percentage, histogram percentage, etc.

[0197] Similarly, if the receiving device obtains one indicator, it can directly compare it with the threshold; if it obtains multiple indicators, it can compare and judge them by methods such as whether the number of distances that meet the threshold condition (threshold 1) meets the quantity threshold (threshold 2).

[0198] Optionally, the receiving device can perform statistics directly based on channel information, or it can convert the data into vectors for statistics.

[0199] Optionally, the receiving device may perform some processing before or after multipath extraction, such as Fourier transform, normalization, etc., which are not limited here.

[0200] It should be noted that the above performance calculation indicators or performance thresholds are only examples. In practical applications, configuration information can also be used to indicate other performance calculation indicators or performance thresholds, which are not limited here.

[0201] In practical applications, the configuration information also includes preset conditions. Specifically, if the preset conditions are met, the receiving device executes step 302. Meeting the preset conditions can be understood as meeting at least one of the following conditions:

[0202] The following conditions must be met: the communication system performance is below a first threshold; the channel estimation performance is below a third threshold; the decoding performance is below a fourth threshold; the demodulation performance is below a sixth threshold; the decoding operation of the receiving device is in the first mode; the demodulation operation of the receiving device is in the second mode; and a preset duration or preset period is met. Here, "decoding operation in the first mode" can be understood as decoding operation under a specific mode or configuration (e.g., non-AI mode). Similarly, "demodulation operation in the second mode" can be understood as demodulation operation under a specific mode or configuration, which is not specifically limited here.

[0203] Optionally, the configuration information includes a first threshold, a third threshold, a fourth threshold, a sixth threshold, a preset duration, or a preset period.

[0204] In this embodiment of the application, by defining the configuration information of the AI ​​model used for channel estimation, the receiving device can monitor the AI ​​model used for channel estimation according to the configuration information, thereby ensuring the reliability of the AI ​​system.

[0205] II. AI model used for demodulation.

[0206] The configuration information may include a use case indicator, which can be used to indicate the use case for demodulation. For example, the use case indicator may be the number of the AI ​​model used for demodulation, or it may be the demodulation function corresponding to the AI ​​model; the specifics are not limited here.

[0207] It should be noted that the AI ​​model deployed on the receiving device is a demodulation AI model, while the AI ​​model deployed on the transmitting device is a modulation AI model. Specifically, the transmitting device sends the modulated data to the receiving device according to the modulation AI model, and the receiving device demodulates the data according to the demodulation AI model.

[0208] One possible implementation is to monitor the AI ​​model used for demodulation, or to monitor the AI ​​model used for modulation and / or the AI ​​model used for demodulation.

[0209] For AI models used for demodulation, or AI models used for modulation and AI models used for demodulation, the receiving device can obtain the truth value in the following ways: the transmitting device sends the truth value to the receiving device; the transmitting and receiving devices can maintain a random number generator and synchronously generate the same truth value data; or the receiving device can re-encode the correctly received data after decoding to obtain the truth value. The specific method is not limited here.

[0210] Optionally, the sending and receiving devices can encode the data synchronously generated by the random number generator before using it as the true data value for monitoring.

[0211] The receiving device can calculate the deviation based on the demodulated data and the true data value, and determine the demodulation performance based on the deviation. For example, the AI ​​model performance calculation indicators for demodulation included in the configuration information can be constellation point distance, bit error rate (BER), or symbol error rate (SER).

[0212] The constellation distance refers to the distance between the data obtained by the demodulation algorithm (which can be soft values ​​or 0 / 1 values ​​after hard decision) and the ground truth value. This distance can include, but is not limited to: Error Vector Magnitude (EVM), cosine similarity and its variations, Minkowski Distance method and its variations, and cross entropy (CE).

[0213] BER (Bit Error Rate) refers to the probability of an error occurring in each bit during data transmission. Specifically, it is the ratio of the number of erroneous bits in a received digital signal within a given time period to the total number of bits received within the same time period. BER is a metric for measuring the accuracy of data transmission within a specified time, reflecting the performance of the data transmission system. A lower BER indicates higher data transmission accuracy and better system performance.

[0214] SER (Symptom Error Rate) refers to the proportion of symbol errors that occur at the receiver for a multi-level modulated signal. Specifically, it is the ratio of the number of erroneous symbols received within a certain time period to the total number of symbols received within the same time period. SER is an important indicator for measuring the accuracy of multi-level modulated signal transmission.

[0215] In practical applications, the configuration information also includes preset conditions. Specifically, if the preset conditions are met, the receiving device executes step 302. Meeting the preset conditions can be understood as meeting at least one of the following conditions:

[0216] The following conditions must be met for the communication system to meet the following criteria: performance below a first threshold, channel estimation performance above a second threshold, decoding performance below a fourth threshold, demodulation performance below a sixth threshold, decoding operation of the receiver in a first mode, channel estimation operation of the receiver in a third mode, and a preset duration or period must be met. Here, "decoding operation in the first mode" can be understood as decoding operation in a specific mode or configuration (e.g., non-AI mode). Similarly, "channel estimation operation in the third mode" can be understood as channel estimation operation in a specific mode or configuration (e.g., non-AI mode), but the specifics are not limited here.

[0217] Optionally, the configuration information includes a first threshold, a second threshold, a fourth threshold, a sixth threshold, a preset duration, or a preset period.

[0218] In this embodiment, by defining configuration information for the AI ​​model applied to demodulation, the receiving device can monitor the AI ​​model applied to demodulation according to the configuration information, thereby ensuring the reliability of the AI ​​system.

[0219] III. AI Models Applied to Decoding

[0220] The configuration information may include use case indicators, which can be used to indicate the use cases for decoding. For example, the use case indicator may be the number of the AI ​​model applied to the decoding, or the AI ​​function corresponding to the decoding; the specifics are not limited here.

[0221] One possible implementation is to monitor the AI ​​model used for decoding, or to monitor the AI ​​model used for encoding and / or the AI ​​model used for decoding.

[0222] For AI models used in decoding, the truth value can be obtained by the sending device sending the truth value to the receiving device, or by the sending and receiving devices maintaining a random number generator to synchronously generate the same truth value data, or by the receiving device verifying the correctly received data after decoding as the truth value. The specific method is not limited here. Furthermore, the random number generator can also be replaced by a random content generator, which is also not limited here.

[0223] The receiving device can calculate the deviation based on the decoded output data and the true data value. The demodulation performance is then determined based on the deviation. For example, the configuration information may include performance metrics for the AI ​​model used in decoding, such as BER, block error rate (BLER), the number / proportion of acknowledgments (ACK) / negative acknowledgments (NACK), the distance between the soft value and the true value of the decoded output, or statistical distance statistics between the soft value and the true value of the decoded output.

[0224] It should be noted that the decoded output is a set of data, which can be converted into vector distances. Therefore, the distance between the soft value and the true value of the decoded output, or the distance statistics between the soft value and the true value of the decoded output, can be referred to the description of the vector distance and statistical information deviation in the above embodiment, and will not be repeated here.

[0225] BLER refers to the percentage of erroneous blocks out of all blocks sent.

[0226] In practical applications, the configuration information also includes preset conditions. Specifically, if the preset conditions are met, the receiving device executes step 302. Meeting the preset conditions can be understood as meeting at least one of the following conditions:

[0227] The following conditions must be met for the communication system to meet the following criteria: performance below a first threshold, channel estimation performance above a second threshold, decoding performance below a fourth threshold, demodulation performance above a fifth threshold, channel estimation at the receiving end device operating in a third mode, demodulation at the receiving end device operating in a second mode, and a preset duration or preset period must be met. Here, "channel estimation operating in the third mode" can be understood as channel estimation operating in a specific mode or configuration (e.g., non-AI mode). Similarly, "demodulation operating in the second mode" can be understood as demodulation operating in a specific mode or configuration, without further specific limitations here.

[0228] Optionally, the configuration information includes a first threshold, a second threshold, a fourth threshold, a fifth threshold, a preset duration, or a preset period.

[0229] It should be noted that the above preset conditions are only examples. In actual applications, the transmitting device can also be configured with other preset conditions, which are not limited here.

[0230] In this embodiment, by defining configuration information for the AI ​​model applied to decoding, the receiving device can monitor the AI ​​model applied to decoding based on the configuration information, thereby ensuring the reliability of the AI ​​system.

[0231] One possible implementation is that the configuration information is used to indicate multiple AI models, the truth values ​​of multiple AI models, or the performance of multiple AI models. Specifically, the multiple AI models can be at least two of the following: AI models applied to CSI, AI models applied to beam management, AI models applied to positioning, AI models applied to channel estimation, AI models applied to demodulation, or AI models applied to decoding; the specifics are not limited here. The configuration information can include combinations of the above-mentioned multiple truth value acquisition methods or combinations of the above-mentioned multiple performance calculation metrics. For example, the configuration information includes performance calculation metrics for the AI ​​model applied to CSI and performance calculation metrics for the AI ​​model applied to channel estimation. Another example is that the configuration information includes the truth values ​​of the AI ​​model applied to decoding and the truth values ​​of the AI ​​model applied to demodulation; the specifics are not limited here.

[0232] Optionally, the configuration information also includes operating modes. These modes include independent monitoring or sequential monitoring. Independent monitoring means the receiving device is configured to monitor multiple AI models, and the monitoring of each AI model is independent of the others. Sequential monitoring means the receiving device monitors the AI ​​model in the order of channel estimation, demodulation, and decoding. When the receiving device monitors one AI model, the communication modules corresponding to the other AI models need to be in a specific mode or configuration. For example, when the receiving device monitors the AI ​​model used for demodulation, the communication modules corresponding to the other AI models need to be in non-AI mode.

[0233] In one possible approach, the configuration information is also used to instruct the receiving device on the actions it needs to take when any AI model meets preset conditions. For example, when the AI ​​model used for channel estimation meets the preset conditions, the receiving device can cancel monitoring of the AI ​​model used for demodulation based on the configuration information. As another example, when the AI ​​model used for channel estimation does not meet the preset conditions, the receiving device can modify the configuration based on the configuration information and then monitor the AI ​​model used for demodulation again. Meeting the preset conditions can be understood as meeting at least one of the following conditions:

[0234] The communication system performance is below the first threshold, meets the preset duration, or meets the preset period.

[0235] In this embodiment, the reliability of the AI ​​system is improved by monitoring multiple AI models.

[0236] In one possible implementation, the receiving device obtains the configuration information by means of a configuration predefined in the protocol. For example, the protocol defines performance metrics for the AI ​​model used for demodulation, enabling the receiving device to determine these metrics.

[0237] In another possible implementation, the receiving device obtains the configuration information by receiving configuration information from the sending device. Correspondingly, the sending device sends the configuration information to the receiving device. For example, the sending device could be a network device, and the receiving device could be a terminal device. After determining the configuration information, the network device sends the configuration information to the terminal device, enabling the terminal device to monitor the AI ​​model based on the configuration information.

[0238] Optionally, network devices can directly indicate configuration information via RRC signaling. Network devices can also configure candidate schemes via RRC, using medium access control-control element (MAC-CE) and / or downlink control information (DCI) to indicate specific schemes to terminal devices.

[0239] It should be noted that network devices can indicate configuration information through one message or multiple messages; no specific limitation is made here.

[0240] In another possible implementation, the sending device can agree with the receiving device in advance, so that the receiving device can determine the configuration information.

[0241] In practical applications, the receiving device can also determine the configuration information in other ways, which are not limited here.

[0242] It should be understood that, in one possible implementation, the transmitting device is a core network device or a server device, and the receiving device is a terminal device. That is, the terminal device can communicate with the base station via AI technology, and the core network device or server device can issue monitoring configurations. The device configuring the AI ​​model for monitoring on the receiving device and the device receiving the monitoring results can be different devices; this is not specifically limited here.

[0243] 302. The receiving device monitors the performance of the AI ​​model.

[0244] The receiving device monitors the performance of the AI ​​model based on configuration information. For example, it can monitor the prediction accuracy of the AI ​​model to ensure the model can correctly identify and process input data and provide accurate prediction results. It can also monitor the response time of the AI ​​model or system to requests to ensure the model can complete the prediction task within the specified time, meeting real-time requirements. Furthermore, it can monitor the resource usage of the AI ​​model or system during operation, including the occupancy of CPU, memory, and disk resources, to ensure efficient resource utilization and avoid waste. Finally, it can monitor the stability of the AI ​​model or system to ensure that the model does not experience performance degradation or crashes during long-term operation. Specific details are not limited here.

[0245] Optionally, the embodiment shown in FIG3 further includes step 300a. Step 300a may be performed before step 301.

[0246] 300a. The transmitting device sends a capability request to the receiving device. Correspondingly, the receiving device receives the capability request from the transmitting device.

[0247] Optionally, the sending device may send a capability request to the receiving device, which requests the receiving device to report its monitoring capabilities. These monitoring capabilities may indicate the AI ​​models the receiving device can monitor, the monitoring methods it supports, or its computing power; specific details are not limited here.

[0248] Optionally, the transmitting device can also synchronize a random number generator and / or a random content generator with the receiving device. For example, for joint coding of the source and channel, the transmitting and receiving devices can produce content using a specific AI generator. In this case, the transmitting and receiving parties need to negotiate and determine the content to be generated (e.g., through content indication, category indication, service indication, or AI generator indication). The transmitting and receiving devices can also configure the seed number and / or output data distribution information (e.g., mean, variance, etc.) required by the AI ​​generator to ensure that the AI ​​generators at both ends can generate the same content data; specific details are not limited here.

[0249] Optionally, for AI models used for demodulation and AI models used for decoding, the transmitting and receiving devices may share the same random number generator or random content generator, or they may not share it; the specifics are not limited here.

[0250] Optionally, the embodiment shown in Figure 3 further includes step 300b. Step 300b may be performed before step 301.

[0251] 300b. The receiving device sends a capability response to the transmitting device, and the transmitting device receives the capability response from the receiving device accordingly.

[0252] In one possible implementation, the capability response is the response information to the capability request in step 300a. That is, the receiving device responds to the capability request from the sending device by reporting the monitoring capability to the sending device. This monitoring capability can be used to indicate the AI ​​models that the receiving device can monitor, the monitoring methods that the receiving device can support, or the computing power of the receiving device; the specifics are not limited here.

[0253] In another possible implementation, step 300a may be omitted. That is, the receiving device can proactively report its monitoring capabilities, thereby enabling the sending device to determine the configuration information based on the receiving device's monitoring capabilities.

[0254] Optionally, the embodiment shown in Figure 3 further includes step 303. Step 303 may be performed after step 302.

[0255] 303. The receiving device sends the monitoring results to the transmitting device. Correspondingly, the transmitting device receives the monitoring results from the receiving device.

[0256] After monitoring the AI ​​model, the receiving device obtains the monitoring results. The receiving device can then send the monitoring results to the sending device.

[0257] Specifically, the monitoring results can be the results of a single monitoring session, the results of multiple monitoring sessions, or the statistical results obtained by the receiving device based on the results of multiple monitoring sessions; no specific limitation is made here.

[0258] Optionally, the receiving device may also request the sending device to perform subsequent actions. For example, the receiving device may send an instruction to the sending device requesting the sending device to revert to non-AI mode. Another example is that the receiving device may send an instruction to the sending device requesting the sending device to perform data collection. Specific details are not limited here.

[0259] The communication method in the embodiments of this application has been described above. The communication device in the embodiments of this application is described below. Referring to Figure 4, the communication device 400 can be used to execute the process performed by the receiving device in the embodiment shown in Figure 3. For details, please refer to the relevant descriptions in the foregoing method embodiments. The communication device 400 can be a network device, or a component or device applied to a network device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of a network device. The communication device can also be a terminal device, or a component or device applied to a terminal device (e.g., a processor, circuit, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of a terminal device.

[0260] The communication device 400 includes an interface module 401 and a processing module 402.

[0261] The processing module 402 is used for data processing. The interface module 401 can implement corresponding communication functions. The interface module 401 can also be called a communication interface or a communication module.

[0262] Optionally, the communication device 400 may further include a storage module, which can be used to store program code, program instructions and / or data. The processing module 402 can read the instructions and / or data in the storage module so that the communication device 400 can implement the aforementioned method embodiments.

[0263] The communication device 400 can be used to perform the actions performed by the receiving device in the above method embodiments. For example, it can be the receiving device itself, a communication module within the receiving device, or a circuit or chip within the receiving device responsible for communication functions. The communication device 400 can be the receiving device or a component configurable on the receiving device. The processing module 402 is used to perform processing-related operations on the receiving device side in the above method embodiments. The interface module 401 is used to perform reception-related operations on the receiving device side in the above method embodiments.

[0264] Optionally, interface module 401 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiments. The receiving module is used to perform the receiving operation in the above method embodiments.

[0265] It should be noted that the communication device 400 may include a transmitting module but not a receiving module. Alternatively, the communication device 400 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme executed by the communication device 400 includes both transmitting and receiving actions. For example, the communication device 400 is used to execute the actions performed by the receiving device in the embodiment shown in Figure 3. For details, please refer to the relevant descriptions in the embodiment shown in Figure 3; these will not be elaborated upon here.

[0266] For example, the communication device 400 is used to execute the following scheme:

[0267] Interface module 401 is used to obtain configuration information. The configuration information is used to indicate one or more of the following: one or more AI models, the truth value of the output data of one or more AI models, and the performance calculation indicators of one or more AI models. The one or more AI models include at least one AI model for data transmission.

[0268] Processing module 402 is used to monitor the performance of one or more AI models based on configuration information.

[0269] In one possible implementation, at least one AI model includes an AI model for channel estimation, an AI model for demodulation, or an AI model for decoding.

[0270] In another possible implementation, the truth value of the output data of one or more AI models comes from the sending device, or the truth value of the output data of one or more AI models is generated by a random number generator.

[0271] In another possible implementation, the performance metrics of one or more AI models include multipath feature deviation, vector distance, statistical information deviation, constellation point distance, bit error rate, block error rate, symbol error rate, number of response messages, or proportion of response messages.

[0272] In another possible implementation, the configuration information also includes preset conditions;

[0273] Processing module 402 is used to monitor the performance of one or more AI models based on configuration information, including:

[0274] The processing module 402 is specifically used to monitor the performance of one or more AI models according to the configuration information if preset conditions are met.

[0275] In another possible implementation, satisfying the preset conditions includes at least one of the following:

[0276] The performance of the communication system is below the first threshold.

[0277] The channel estimation performance is higher than the second threshold;

[0278] Channel estimation performance is below the third threshold;

[0279] Decoding performance is below the fourth threshold;

[0280] Demodulation performance is above the fifth threshold;

[0281] Demodulation performance is below the sixth threshold;

[0282] Decoding works in mode 1;

[0283] Demodulation is performed in the second mode;

[0284] Channel estimation operates in the third mode;

[0285] Reaching the preset duration; or

[0286] The preset cycle has been reached.

[0287] In another possible implementation, the configuration information may also include one or more of the following: a first threshold, a second threshold, a third threshold, a fourth threshold, a fifth threshold, a sixth threshold, a preset duration, or a preset period.

[0288] In another possible implementation, interface module 401 is used to obtain configuration information, including:

[0289] Interface module 401 is specifically used to receive the first signaling, which includes configuration information.

[0290] In another possible implementation, interface module 401 is also used to send capability information, which indicates whether it has monitoring capabilities and / or which AI model it has monitoring capabilities for.

[0291] In another possible implementation, interface module 401 is also used to send monitoring results, which are obtained by monitoring the performance of at least one of one or more AI models.

[0292] It should be understood that the specific procedures for each module to perform the above-mentioned corresponding processes have been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0293] Optionally, when the communication device 400 is a terminal device or a communication module within a terminal device, the processing module 402 in the above embodiments can be implemented by at least one processor or processor-related circuitry. Specifically, the processor may include a modem chip, or a system-on-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip. The interface module 401 can be implemented by a transceiver or transceiver-related circuitry. The interface module 401 may also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0294] Optionally, when the communication device 400 is a circuit or chip in a terminal device responsible for communication functions, such as a modem chip or a SoC chip or SIP chip containing a modem core, the function of the processing module 402 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processing cores. The function of the interface module 401 can be implemented by the interface circuit or data transceiver circuit on the aforementioned chip.

[0295] The following is another structural schematic diagram of the communication device according to an embodiment of this application. Referring to Figure 5, the communication device can be used to execute the process performed by the transmitting device in the embodiment shown in Figure 3. For details, please refer to the relevant description in the foregoing method embodiments.

[0296] The communication device 500 includes an interface module 501. Optionally, a processing module 502.

[0297] The processing module 502 is used for data processing. The interface module 501 can implement corresponding communication functions. The interface module 501 can also be called a communication interface or a communication module.

[0298] Optionally, the communication device 500 may further include a storage module, which can be used to store program code, program instructions and / or data. The processing module 502 can read the instructions and / or data in the storage module so that the communication device 500 can implement the aforementioned method embodiments.

[0299] The communication device 500 can be used to perform the actions performed by the transmitting device in the above method embodiments. For example, it can be the transmitting device itself, a communication module within the transmitting device, or a circuit or chip within the transmitting device responsible for communication functions. The communication device 500 can be the transmitting device or a component configurable on the transmitting device. The processing module 502 is used to perform processing-related operations on the transmitting device side in the above method embodiments. The interface module 501 is used to perform reception-related operations on the transmitting device side in the above method embodiments.

[0300] Optionally, interface module 501 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiments. The receiving module is used to perform the receiving operation in the above method embodiments.

[0301] It should be noted that the communication device 500 may include a transmitting module but not a receiving module. Alternatively, the communication device 500 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme executed by the communication device 500 includes both transmitting and receiving actions. For example, the communication device 500 is used to execute the actions performed by the transmitting device in the embodiment shown in Figure 3. For details, please refer to the relevant description in the embodiment shown in Figure 3; it will not be elaborated upon here.

[0302] For example, the communication device 500 is used to execute the following scheme:

[0303] Processing module 502 is used to determine configuration information, which is used to indicate one or more of the following: one or more AI models, the truth value of the output data of one or more AI models, and the performance calculation indicators of one or more AI models. The one or more AI models include at least one AI model for data transmission.

[0304] Interface module 501 is used to send configuration information.

[0305] In one possible implementation, at least one AI model includes an AI model for channel estimation, an AI model for demodulation, or an AI model for decoding.

[0306] In another possible implementation, the truth value of the output data of one or more AI models comes from the sending device, or the truth value of the output data of one or more AI models is generated by a random number generator.

[0307] In another possible implementation, the performance metrics of one or more AI models include multipath feature deviation, vector distance, statistical information deviation, constellation point distance, bit error rate, block error rate, symbol error rate, number of response messages, or proportion of response messages.

[0308] In another possible implementation, the configuration information also includes preset conditions, which are satisfied if the receiving device satisfies at least one of the following:

[0309] The performance of the communication system is below the first threshold.

[0310] The channel estimation performance is higher than the second threshold;

[0311] Channel estimation performance is below the third threshold;

[0312] Decoding performance is below the fourth threshold;

[0313] Demodulation performance is above the fifth threshold;

[0314] Demodulation performance is below the sixth threshold;

[0315] Decoding works in mode 1;

[0316] Demodulation is performed in the second mode;

[0317] Channel estimation operates in the third mode;

[0318] Reaching the preset duration; or

[0319] The preset cycle has been reached.

[0320] In another possible implementation, the configuration information may also include one or more of the following: a first threshold, a second threshold, a third threshold, a fourth threshold, a fifth threshold, a sixth threshold, a preset duration, or a preset period.

[0321] In another possible implementation, interface module 501 is used to send configuration information, including:

[0322] Interface module 501 is specifically used to send the first signaling, which includes configuration information.

[0323] In another possible implementation, interface module 501 is also used to receive capability information, which indicates whether there is a monitoring capability and / or which AI model has a monitoring capability.

[0324] In another possible implementation, interface module 501 is also used to receive monitoring results, which are obtained by monitoring the performance of at least one of one or more AI models.

[0325] It should be understood that the specific procedures for each module to perform the above-mentioned corresponding processes have been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0326] Optionally, when the communication device 500 is a terminal device or a communication module within a terminal device, the processing module 502 in the above embodiments can be implemented by at least one processor or processor-related circuitry. Specifically, the processor may include a modem chip, or a system-on-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip. The interface module 501 can be implemented by a transceiver or transceiver-related circuitry. The interface module 501 may also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0327] Optionally, when the communication device 500 is a circuit or chip in a terminal device responsible for communication functions, such as a modem chip or a SoC chip or SIP chip containing a modem core, the function of the processing module 502 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processing cores. The function of the interface module 501 can be implemented by the interface circuit or data transceiver circuit on the aforementioned chip.

[0328] The following describes a communication device provided in an embodiment of this application. Please refer to Figure 6, which is a schematic diagram of the structure of the communication device provided in an embodiment of this application. The communication device can be a receiving device or a transmitting device in the above method embodiments, or it can be a chip, chip system, or processor that supports the receiving device or transmitting device in implementing the above methods. This communication device can be used to implement the methods described in the above method embodiments, and for details, please refer to the description in the above method embodiments.

[0329] The communication device may include one or more processors 601, which are connected to a memory 602, an input / output unit 603, and a bus 604. The processor 601 may be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control the communication device (e.g., base station, baseband chip, terminal, terminal chip, DU or CU, etc.), execute software programs, and process data from the software programs.

[0330] Optionally, the communication device may include one or more memories 602, which may store instructions that can be executed on the processor 601 to cause the communication device to perform the methods described in the above method embodiments. Optionally, the memories 602 may also store data. The processor 601 and the memories 602 may be provided separately or integrated together.

[0331] Optionally, the communication device may also include a transceiver and an antenna. A transceiver, also called a transceiver unit, transceiver, or transceiver circuit, is used to implement transmission and reception functions. A transceiver may include a receiver and a transmitter; the receiver, also called a receiver circuit, is used to implement the receiving function; the transmitter, also called a transmitter or transmitting circuit, is used to implement the transmitting function.

[0332] In another possible design, the processor 601 may include a transceiver for implementing receive and transmit functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing receive and transmit functions may be separate or integrated. The aforementioned transceiver circuit, interface, or interface circuit may be used for reading and writing code / data, or it may be used for transmitting or relaying signals.

[0333] In another possible design, the processor 601 may optionally store instructions that, when executed, cause the communication device to perform the methods described in the above method embodiments. The instructions may be stored in the processor 601; in this case, the processor 601 may be implemented in hardware.

[0334] In another possible design, the communication device may include circuitry that performs the transmitting or receiving or communication functions of the receiving or transmitting device in the aforementioned method embodiments. The processor and transceiver described in this application embodiment can be implemented on integrated circuits (ICs), analog ICs, radio frequency integrated circuits (RFICs), mixed-signal ICs, application-specific integrated circuits (ASICs), printed circuit boards (PCBs), electronic devices, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductors (CMOS), n-type metal-oxide-semiconductor (NMOS), p-type metal oxide semiconductors (PMOS), bipolar junction transistors (BJTs), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.

[0335] The communication device described in the above embodiments can be a receiving device or a transmitting device, but the scope of the communication device described in the embodiments of this application is not limited thereto, and the structure of the communication device is not limited to FIG. 6. The communication device can be a standalone device or part of a larger device. For example, the communication device can be:

[0336] (1) Independent integrated circuit IC, or chip, or chip system or subsystem;

[0337] (2) A collection of one or more ICs, optionally including a storage component for storing data and instructions;

[0338] (3) ASIC, such as modem;

[0339] (4) Modules that can be embedded in other devices;

[0340] (5) Receivers, terminals, smart terminals, cellular phones, wireless devices, handheld devices, mobile units, vehicle-mounted devices, network devices, cloud devices, artificial intelligence devices, etc.

[0341] (6) Others, etc.

[0342] For communication devices that can be chips or chip systems, please refer to the schematic diagram of the chip structure shown in Figure 7. The chip 700 shown in Figure 7 includes a processor 701 and an interface 702. Optionally, it may also include a memory 703. The number of processors 701 can be one or more, and the number of interfaces 702 can be multiple.

[0343] For cases where the chip is used to implement the functions of the receiving end device or the transmitting end device in the embodiments of this application:

[0344] The interface 702 is used to receive or output signals;

[0345] The processor 701 is used to perform data processing operations of the receiving device or the transmitting device.

[0346] In one possible implementation, the embodiments of this application can be applied to the baseband chip of a network device or terminal device. Transmitting / receiving can correspond to actions related to signal transmission or reception, and can be understood as transmitting / receiving radio frequency signals in the analog / intermediate frequency / radio frequency domain, or as initiating or controlling transmission / reception operations in the digital domain, or a combination of both. For example, when a device transmits or receives various signals, the processor in the device implements the transmission or reception by driving or controlling the radio frequency circuit. Therefore, during signal transmission and reception, the processor is the decision-maker or controller of the transmission and reception operation, while the radio frequency circuit is the specific executor of the transmission and reception; both, in conjunction with the antenna, can jointly realize the transmission and reception operation. The processor includes, but is not limited to, CPUs, DSPs, microprocessors, etc., and the radio frequency circuit includes, but is not limited to, radio frequency chips, radio frequency front-ends, PAs, LNAs, mixers, filters, duplexers, etc., and may also selectively include antennas integrated with the radio frequency circuit.

[0347] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the communication device given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0348] It should be understood that the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0349] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can 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. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAK are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0350] This application also provides a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the methods described in the foregoing embodiments. The computer-readable storage medium may be a non-volatile storage medium.

[0351] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the methods described in the foregoing embodiments.

[0352] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0353] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0354] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0355] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0356] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0357] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

Claims

1. A communication method, characterized in that, The method includes: Obtain configuration information, which is used to indicate one or more of the following: one or more AI models, the truth value of the output data of the one or more AI models, and the performance calculation indicators of the one or more AI models, wherein the one or more AI models include at least one AI model for data transmission; The performance of the one or more AI models is monitored based on the configuration information.

2. The method according to claim 1, characterized in that, The at least one AI model includes an AI model for channel estimation, an AI model for demodulation, or an AI model for decoding.

3. The method according to claim 1 or 2, characterized in that, The truth value of the output data of the one or more AI models comes from the sending device, or the truth value of the output data of the one or more AI models is generated by a random number generator.

4. The method according to any one of claims 1 to 3, characterized in that, The performance metrics of the one or more AI models include multipath feature deviation, vector distance, statistical information deviation, constellation point distance, bit error rate, block error rate, symbol error rate, number of response messages, or proportion of response messages.

5. The method according to any one of claims 1 to 4, characterized in that, The configuration information also includes preset conditions; The monitoring of the performance of the one or more AI models based on the configuration information includes: If the preset conditions are met, the performance of the one or more AI models will be monitored according to the configuration information.

6. The method according to claim 5, characterized in that, The preset conditions include at least one of the following: The performance of the communication system is below the first threshold. The channel estimation performance is higher than the second threshold; Channel estimation performance is below the third threshold; Decoding performance is below the fourth threshold; Demodulation performance is above the fifth threshold; Demodulation performance is below the sixth threshold; Decoding works in mode 1; Demodulation is performed in the second mode; Channel estimation operates in the third mode; Reaching the preset duration; or The preset cycle has been reached.

7. The method according to claim 6, characterized in that, The configuration information also includes one or more of the following: the first threshold, the second threshold, the third threshold, the fourth threshold, the fifth threshold, the sixth threshold, the preset duration, or the preset period.

8. The method according to any one of claims 1 to 7, characterized in that, The sending configuration information includes: Receive the first signaling, which includes the configuration information.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: Send capability information, which indicates whether monitoring capability is available.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: Send monitoring results, which are obtained by monitoring the performance of at least one of the one or more AI models.

11. A communication method, characterized in that, The method includes: The configuration information is determined, which is used to indicate one or more of the following: one or more AI models, the truth values ​​of the one or more AI models, and the performance calculation metrics of the one or more AI models, wherein at least one AI model is used for data transmission. Send the configuration information.

12. The method according to claim 11, characterized in that, The at least one AI model includes an AI model for channel estimation, an AI model for demodulation, or an AI model for decoding.

13. The method according to claim 11 or 12, characterized in that, The truth values ​​of the one or more AI models are derived from the sending device, or the truth values ​​of the one or more AI models are generated by a random number generator.

14. The method according to any one of claims 11 to 13, characterized in that, The performance metrics of the one or more AI models include multipath feature deviation, vector distance, statistical information deviation, constellation point distance, bit error rate, block error rate, symbol error rate, number of response messages, or proportion of response messages.

15. The method according to any one of claims 11 to 14, characterized in that, The configuration information also includes preset conditions. The preset conditions are satisfied if the receiving device meets at least one of the following: The performance of the communication system is below the first threshold. The channel estimation performance is higher than the second threshold; Channel estimation performance is below the third threshold; Decoding performance is below the fourth threshold; Demodulation performance is above the fifth threshold; Demodulation performance is below the sixth threshold; Decoding works in mode 1; Demodulation is performed in the second mode; Channel estimation operates in the third mode; Reaching the preset duration; or The preset cycle has been reached.

16. The method according to claim 15, characterized in that, The configuration information also includes one or more of the following: the first threshold, the second threshold, the third threshold, the fourth threshold, the fifth threshold, the sixth threshold, the preset duration, or the preset period.

17. The method according to any one of claims 11 to 16, characterized in that, The acquisition of configuration information includes: Send a first signaling message, which includes the configuration information.

18. The method according to any one of claims 11 to 17, characterized in that, The method further includes: Receive capability information, which is used to indicate whether monitoring capability is available.

19. The method according to any one of claims 11 to 18, characterized in that, The method further includes: Receive monitoring results, which are obtained by monitoring the performance of at least one of the one or more AI models.

20. A communication device, characterized in that, Includes modules or units for performing the method as described in any one of claims 1 to 10.

21. A communication device, characterized in that, Includes modules or units for performing the method as described in any one of claims 11 to 19.

22. A communication device, characterized in that, include: A processor for executing a program that causes the communication device to perform the method as described in any one of claims 1 to 10.

23. A communication device, characterized in that, include: A processor for executing a program that causes the communication device to perform the method as described in any one of claims 11 to 19.

24. A computer-readable storage medium, characterized in that, Includes instructions that, when executed on a computer, cause the computer to perform the method as claimed in any one of claims 1 to 10, or cause the computer to perform the method as claimed in any one of claims 11 to 19.

25. A computer program product containing instructions, characterized in that, When it is run on a computer, it causes the computer to perform the method as described in any one of claims 1 to 10, or causes the computer to perform the method as described in any one of claims 11 to 19.

Images