An interference prediction method, a model training method, a communication device and a medium

Abstract

The embodiment of the application discloses a kind of interference prediction method, model training method, communication device and medium.The method of the application includes: obtaining first information and second information, the first information is associated with the position information of terminal device or network device, and the second information is the resource usage information corresponding to the first information;According to the first model based on hypergraph, the first information and the second information are processed to obtain the first distribution parameter, and the first distribution parameter is used to indicate the interference prediction result of terminal device or network device.In the embodiment of the application, since the first model is determined based on the first hypergraph, and the first hypergraph can effectively describe the interference relationship between multiple cells of a wireless communication system, therefore, the interference prediction by the first model can effectively capture the spatio-temporal dynamic characteristics, thereby improving the accuracy of interference prediction.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to an interference prediction method, a model training method, a communication device, and a medium. Background Technology

[0002] With the development of communication systems, wireless networks are transitioning from traditional cellular architectures to ultra-dense heterogeneous network deployments. However, increasing interference between base stations has become a major bottleneck limiting system performance and throughput. Interference not only affects network transmission quality but also directly restricts further improvements in network capacity. Modeling and predicting interference scenarios is a current hot research topic and a problem that needs to be solved.

[0003] One possible approach is to utilize large amounts of network data and advanced machine learning techniques. Data-driven models can extract implicit patterns from network topology, access control, and transmission protocols, such as radio maps. Another possible approach is based on a dynamic graph-driven interference coordination scheme. This scheme uses base stations and terminal devices in heterogeneous cellular networks as nodes, and constructs a real-time evolving network topology graph by periodically updating service edges (to characterize the connection strength between base stations and terminals) and dynamically triggered interference edges (to capture co-channel conflicts between pairs of terminals).

[0004] However, none of the above implementation methods can effectively capture spatiotemporal dynamics, which will affect the accuracy of interference prediction. Summary of the Invention

[0005] This application provides an interference prediction method, a model training method, a communication device, and a medium. By using a first model based on a hypergraph for interference prediction, the interference relationship between multiple cells in a wireless communication system can be effectively described, thereby improving the accuracy of interference prediction.

[0006] This application provides an interference prediction method. Optionally, the execution subject of this method can be a first 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 first 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. In this method, the first device acquires first information and second information. The first information can be information associated with the location of the terminal device or network device, or channel information of the terminal device or network device, which is not specifically limited here. The second information is transmission resource usage information, which corresponds to the first information. The first device processes the first information and the second information according to a first model based on a hypergraph to obtain a first distribution parameter, which is used to indicate the interference prediction result of the terminal device or network device.

[0007] Based on the first aspect of this application, since the first model is determined based on the first hypergraph, and the first hypergraph can effectively describe the interference relationship between multiple cells in a wireless communication system, interference prediction using the first model can effectively capture spatiotemporal dynamic characteristics, thereby improving the accuracy of interference prediction.

[0008] In some possible implementations, the first device may also schedule, allocate resources, coordinate interference, or pair users for terminal devices based on interference prediction results.

[0009] In some possible implementations, the first device can determine a first hypergraph based on first information and second information. The first hypergraph includes N nodes and K hyperedges. The N nodes indicate N network devices, which use K resources to communicate with U terminal devices. The K hyperedges indicate interference relationships between network devices and terminal devices in sharing transmission resources. The first hypergraph is used to determine a first model, where N is an integer greater than or equal to 2, and K and U are both positive integers. The first device can obtain first distribution parameters based on the first hypergraph.

[0010] In this embodiment, the first hypergraph can effectively describe the interference relationship between multiple cells in a wireless communication system, which facilitates interference modeling and prediction.

[0011] In some possible implementations, the first device may also determine a node feature matrix based on third and fourth information. The third information may be information associated with the locations of the N network devices, or it may be channel information of the N network devices; the specific details are not limited here. The fourth information is used to indicate the transmission resources occupied by the N network devices, and the node feature matrix is ​​used to indicate the characteristics of each of the N nodes.

[0012] In this embodiment, by determining the node feature matrix, the features corresponding to each node in the first hypergraph can be represented.

[0013] In some possible implementations, the first device may also determine the hyperedge feature matrix based on the fifth and sixth information. The fifth information may be information associated with the locations of the U terminal devices, or it may be the channel information of the U terminal devices; the specific details are not limited here. The sixth information is used to indicate the transmission resources occupied by the U terminal devices, and the hyperedge feature matrix is ​​used to indicate the characteristics of each of the K hyperedges.

[0014] In this embodiment, by determining the hyperedge feature matrix, the features corresponding to each hyperedge in the first hypergraph can be represented.

[0015] In some possible implementations, the first device may also determine the hyperedge weight matrix based on the transmission power on the K resources.

[0016] In this embodiment, by determining the hyperedge weight matrix, the signal transmission power on the transmission resource corresponding to each hyperedge in the first hypergraph can be represented.

[0017] In some possible implementations, the first device can determine a node feature matrix, a hyperedge feature matrix, and a hyperedge weight matrix based on a first hypergraph. The first device can also determine an attention matrix based on the node feature matrix, hyperedge feature matrix, and hyperedge weight matrix, the attention matrix being used to adjust the interference weights between each node and the hyperedge. The first device can then determine a first distribution parameter based on the attention matrix.

[0018] In this embodiment, by introducing a hyperedge attention mechanism, important interference sources in interference prediction can be dynamically adjusted, thereby enhancing the model's ability to capture spatial interference relationships.

[0019] In some possible implementations, the first device can update the node feature matrix through hypergraph convolution based on the attention matrix, and the updated node feature matrix is ​​used to determine the first interference feature. The first device can determine the first distribution parameter based on the multilayer perceptron and the first interference feature.

[0020] In this embodiment, spatiotemporal convolution helps the model capture the temporal correlation of disturbances, thereby improving the stability of disturbance prediction.

[0021] A second aspect of this application provides a model training method. Optionally, the execution entity of this method can be a first 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 first 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. In this method, the first device acquires first information and second information. The first information can be information associated with the location of the terminal device or network device, or channel information of the terminal device or network device; the specific details are not limited here. The second information is transmission resource usage information, which corresponds to the first information. The first device processes the first and second information according to a second model based on a hypergraph to obtain second distribution parameters, which are used to indicate the interference prediction results of the terminal device or network device. The first device updates the parameters of the second model according to the second distribution parameters to obtain a first model based on a hypergraph.

[0022] In some possible implementations, the first device can determine a second hypergraph based on first and second information. The second hypergraph includes N nodes and K hyperedges. The N nodes indicate N network devices, which use K resources to communicate with U terminal devices. The K hyperedges indicate interference relationships between network devices and terminal devices that share transmission resources. The second hypergraph is used to determine a second model, where N is an integer greater than or equal to 2, and K and U are both positive integers. The first device can obtain second distribution parameters based on the second hypergraph.

[0023] In some possible implementations, the first device may also determine a node feature matrix based on third and fourth information. The third information may be information associated with the locations of the N network devices, or it may be the channel information of the N network devices; the specific details are not limited here. The fourth information is used to indicate the resources occupied by the N network devices, and the node feature matrix is ​​used to indicate the characteristics of each of the N nodes.

[0024] In some possible implementations, the first device may also determine the hyperedge feature matrix based on the fifth and sixth information. The fifth information may be information associated with the locations of the U terminal devices, or it may be the channel information of the U terminal devices; the specific information is not limited here. The sixth information is used to indicate the resources occupied by the U terminal devices, and the hyperedge feature matrix is ​​used to indicate the characteristics of each of the K hyperedges.

[0025] In some possible implementations, the first device may also determine the hyperedge weight matrix based on the transmission power on the K resources.

[0026] In some possible implementations, the first device can determine a node feature matrix, a hyperedge feature matrix, and a hyperedge weight matrix based on a first hypergraph. The first device can also determine an attention matrix based on the node feature matrix, hyperedge feature matrix, and hyperedge weight matrix, the attention matrix being used to adjust the interference weights between each node and the hyperedge. The first device can then determine a first distribution parameter based on the attention matrix.

[0027] In some possible implementations, the first device can update the node feature matrix through hypergraph convolution based on the attention matrix, and the updated node feature matrix is ​​used to determine the first interference feature. The first device can determine the first distribution parameter based on the multilayer perceptron and the first interference feature.

[0028] In some possible implementations, the first device can adjust the parameters of the second model based on the first loss value to obtain the first model. The first loss value is determined based on the deviation between the second distribution parameter and the third distribution parameter, which is used to indicate the actual interference result of the terminal device or network device.

[0029] A third aspect of this application provides a communication device, which may be the first device described above. The communication device includes modules or units for performing the methods described in the first aspect and any possible implementation thereof.

[0030] A fourth aspect of this application provides a communication device, which may be the first device described above. The communication device includes modules or units for performing the methods described in the second aspect and any possible implementation thereof.

[0031] A fifth aspect of this application provides a communication device. This communication device can be a first device, a component applied to the first 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. The communication device includes:

[0032] A processor for executing a program that causes the communication device to perform the method as described in the first or second aspect of the foregoing and any possible implementation thereof.

[0033] Optionally, the communication device further includes a memory, and the processor is coupled to the memory; the memory is used to store programs.

[0034] 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.

[0035] The communication interface in the chip can be an input / output interface, pins, or circuits.

[0036] 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.

[0037] The seventh aspect of this application provides a communication system, including communication means for performing the first aspect and any possible implementation thereof, and communication means for performing the second aspect and any possible implementation thereof.

[0038] 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.

[0039] 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

[0040] Figures 1a to 1f A schematic diagram of the communication system provided in this application;

[0041] Figures 2a to 2g This is a schematic diagram of the AI ​​processing involved in this application;

[0042] Figure 3 A schematic diagram of the interference prediction method provided in this application;

[0043] Figures 4a to 4b A schematic diagram illustrating the hypergraph construction and first model inference process provided in this application;

[0044] Figure 5 A schematic diagram of the model training method provided in this application;

[0045] Figures 6 to 9 A schematic diagram of the communication device provided in this application. Detailed Implementation

[0046] First, some terms used in the embodiments of this application will be explained to facilitate understanding by those skilled in the art.

[0047] (1) Terminal device: can be a wireless terminal device capable of receiving 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.

[0048] 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.

[0049] 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 detection.

[0050] 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.

[0051] 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, including but not limited to vehicles, cellular network terminals (integrating satellite terminal functions), drones, and Internet of Things (IoT) devices.

[0052] In this embodiment, the terminal device can also obtain AI services provided by the network device. Optionally, the terminal device can also have AI processing capabilities.

[0053] (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 (BS), 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.

[0054] 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).

[0055] 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 set up 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).

[0056] 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.

[0057] 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.

[0058] The correspondence between network elements and their achievable protocol layer functions in the ORAN system can be found in Table 1 below.

[0059] Table 1

[0060] ORAN network elements 3GPP protocol layer functions O-CU-CP RRC+PDCP-Control Plane (PDCP-C) O-CU-UP SDAP+PDCP - User Plane (PDCP-U) O-DU RLC+MAC+PHY-high O-RU PHY-low

[0061] 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.

[0062] 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 future communication networks.

[0063] 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).

[0064] 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.

[0065] (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 transmission resources based on these values ​​or information. Pre-configuration is similar to configuration; it can be parameter information or parameter values ​​negotiated in advance between the network device / server and the terminal device, or it can be parameter information or parameter values ​​used by the base station / network device or terminal device as specified in standard protocols, or it can be parameter information or parameter values ​​pre-stored in the base station / server or terminal device. This application does not limit this.

[0066] Furthermore, these values ​​and parameters can be changed or updated.

[0067] (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.

[0068] (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.

[0069] 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.

[0070] 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.

[0071] (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.

[0072] 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 in 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.

[0073] 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.

[0074] Please see Figure 1a This is a schematic diagram of the architecture of the communication system 1000 used in an embodiment of this application. Figure 1aAs shown, 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 (e.g., Figure 1a 110a and 110b, collectively referred to as 110, may also include at least one terminal (such as...). Figure 1a RAN100, denoted as RAN100, comprises RAN nodes 120a-120j, collectively referred to as RAN120. RAN100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 1a (Not shown in the image). Terminal 120 connects wirelessly to RAN node 110, and RAN node 110 connects wirelessly or via a wired connection to core network 200. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be independent physical devices, or they can be the same physical device integrating the logical functions of core network equipment and RAN nodes. Terminals can connect to each other, and RAN nodes can connect to each other, via wired or wireless connections.

[0075] by Figure 1a Taking the communication system shown as an example, in addition to performing communication-related services, different devices (including network devices and terminal devices, and / or terminal devices and terminal devices) may also perform AI-related services.

[0076] like Figure 1b As shown, taking a network device as a base station as an example, a 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.

[0077] like Figure 1c As shown, taking terminal devices including TVs and mobile phones as an example, TVs and mobile phones can also perform communication-related services and AI-related services.

[0078] The technical solution provided in this application can be applied to wireless communication systems (e.g.) Figure 1a , Figure 1b or Figure 1cThe system shown, for example, the communication system provided in this application, can incorporate AI network elements to implement 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, an 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 implement 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 a network element independently set up in the communication system. Optionally, the terminal or its built-in chip can also include an AI entity to implement AI-related functions.

[0079] For example, Figure 1d This is another schematic diagram of a communication system applicable to embodiments of this application. Compared to Figure 1b The communication system shown, Figure 1d The communication system shown includes at least one network device 110, at least one terminal device 120 and at least one terminal device 130, and also includes an AI node 140. The AI ​​node 140 is used to perform AI-related operations, such as building training datasets, training or inferring AI models, etc.

[0080] In one implementation, network device 110 can send data related to AI model training to AI node 140, whereby AI node 140 constructs a training dataset and trains the AI ​​model. As an example, the data related to AI model training may include data reported by terminal devices. AI node 140 can send the results of AI model-related operations to network device 110, which then forwards them to the terminal devices. For example, the results of AI model-related operations may include at least one of the following: a trained AI model, model evaluation results, or test results. Exemplarily, a portion of the trained AI model may be deployed on network device 110, and another portion on the terminal devices. Optionally, the trained AI model may be deployed on network device 110, or it may be deployed on the terminal devices.

[0081] It should be understood that Figure 1dThis illustration only takes the direct connection between AI node 140 and network device 110 as an example. In other scenarios, AI node 140 can also be connected to a terminal device. Alternatively, AI node 140 can be connected to both network device 110 and a terminal device simultaneously. Alternatively, AI node 140 can also be connected to one or more of network device 110 and terminal devices through a third-party network element. This application embodiment does not limit the connection relationship between the AI ​​network element and other network elements.

[0082] Alternatively, in another implementation, the AI ​​node 140 can also be configured as a module in a network device and / or a terminal device, for example, in a network device 110, a terminal device 120, or a terminal device 130.

[0083] Figure 1e This is a schematic diagram of a possible application framework in a communication system. For example... Figure 1e As shown, network elements in a communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network elements, such as core network equipment, access network equipment (RAN nodes), terminals, or one or more devices in the operation administration and maintenance (OAM) system, are equipped with one or more AI modules. Access network equipment can be a single RAN node or can include multiple RAN devices, for example, CUs and DUs. The CUs and / or DUs can also be equipped with one or more AI modules. Optionally, a CU can be further divided into CU-CPs and CU-UPs. One or more AI models are configured in the CU-CPs and / or CU-UPs.

[0084] The AI ​​module is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0085] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0086] The network device can be a network device equipped with one or more AI modules. For example, the network device can be... Figure 1e The core network equipment, access network equipment, or one or more devices in the OAM are shown. The AI ​​module can be... Figure 1f The RAN intelligent controller (RIC) shown can be a near real-time RIC or a non-real-time RIC. For example, a near real-time RIC is set in a RAN node (e.g., in a CU or DU), while a non-real-time RIC is set in an OAM, cloud server, core network device, or other network device.

[0087] Figure 1f This is a schematic diagram of another possible application framework in a communication system. For example... Figure 1f As shown, the communication system includes a RIC. For example, the RIC could be... Figure 1a The AI ​​module in the RAN device shown is used to implement AI-related functions. RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (Non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency on the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency on the order of tens of milliseconds.

[0088] Near real-time RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. Near real-time RICs can obtain network-side and / or terminal-side information from RAN devices (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminal devices. This information can be used as training data or as data for inference.

[0089] Optionally, near real-time RIC can deliver inference results to RAN devices and / or terminal devices.

[0090] Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, near real-time RIC submits inference results to DU, and DU sends them to RU.

[0091] Non-real-time RICs are also used for model training and inference. For example, they can be used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN devices (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or as inference data, and the inference results can be delivered to RAN nodes and / or terminals.

[0092] Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, a non-real-time RIC can submit inference results to DU, which in turn can send them to RU.

[0093] Near real-time RICs and non-real-time RICs can also be configured as separate devices. Alternatively, near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be configured in RAN nodes (e.g., CU, DU), while non-real-time RICs can be configured in OAM, cloud servers, core network devices, or other devices.

[0094] Optionally, the AI ​​model can be implemented as hardware circuitry, software, or a combination of both, without limitation. Non-limiting examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application program, or software application, etc.

[0095] Air interface AI models can be divided into single-end models (e.g., single UE end model and single base station end model) and dual-end models.

[0096] A dual-end AI model typically consists of an encoder and a decoder. The encoder is responsible for converting input data (such as channel measurement results) into feature vectors, while the decoder is responsible for converting these feature vectors into the target output (such as reconstruction or prediction results). Depending on the task, the encoder and decoder are located on the terminal side and the network side, respectively. Usually, CSI (Content Sequence Indicator) is fed back from the terminal side to the network side, meaning the encoder is located on the terminal side, while the decoder is located on the network side.

[0097] 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.

[0098] 1. Enhanced CSI feedback:

[0099] 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.

[0100] 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.

[0101] 2. Enhanced beam management.

[0102] 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.

[0103] Beam management enhancements may include at least one sub-function, such as: beam scan matrix prediction and optimal (or better) beam prediction.

[0104] 3. Enhanced positioning accuracy:

[0105] 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.

[0106] 4. Network energy saving:

[0107] 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.

[0108] 5. Load balancing:

[0109] 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.

[0110] 6. Mobility Management:

[0111] 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.

[0112] 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.

[0113] 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.

[0114] For example, an AI function may include multiple AI sub-functions.

[0115] Optionally, AI application cases are also called AI application scenarios or AI functions.

[0116] 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.

[0117] The following is a brief introduction to the concepts that may be involved in this application.

[0118] 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).

[0119] Machine learning (ML) can include supervised learning, unsupervised learning, and reinforcement learning. Unsupervised learning can also be called learning without supervision.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] like Figure 2a The diagram shown is a schematic representation of a neuron structure. Assume the neuron's input 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.

[0126] 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.

[0127] 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).

[0128] Figure 2b This is a schematic diagram of a Free-Nearest Neural Network (FNN). A key characteristic of FNNs 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] The implementation process of the neural network will be described below with reference to the accompanying drawings.

[0134] 1. Fully connected neural network, also known as multilayer perceptron (MLP).

[0135] like Figure 2c As shown, 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.

[0136] Optionally, considering neurons in two adjacent layers, the output h of a neuron in the next layer 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:

[0137] h = f(wx + b).

[0138] Where w is the weight matrix, b is the bias vector, and f is the activation function.

[0139] Alternatively, the output of the neural network can be recursively expressed as:

[0140] y = f z (w z f z-1 (…)+b z ).

[0141] 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.

[0142] 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.

[0143] Optionally, the training method involves using a loss function to evaluate the output of the neural network.

[0144] like Figure 2d As shown, 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. Figure 2d The term "relative advantage (e.g., optimal advantage)" is used. This is understandable. Figure 2d The neural network parameters corresponding to the "better points (e.g., the best points)" in the data can be used as neural network parameters in the trained AI model information.

[0145] Alternatively, the gradient descent process can be represented as:

[0146]

[0147] 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.

[0148] Alternatively, the backpropagation process can utilize the chain rule for partial derivatives.

[0149] like Figure 2e As shown, 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:

[0150]

[0151] 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.

[0152] 2. Federated Learning (FL).

[0153] 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.

[0154] like Figure 2f As shown, the FL architecture is currently the most widely used training architecture in the FL field, and the FedAvg algorithm is the foundational algorithm of FL. The FedAvg algorithm flow is roughly as follows:

[0155] (1) Initialize the model to be trained at the center end. And broadcast it to all clients.

[0156] (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. Report it to the central node. Figure 2f In the example shown, the local training results sent by distributed nodes n, k, and m are denoted as G, respectively. n G k G m .

[0157] (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.

[0158] (4) Repeat steps (2) and (3) until the model finally converges or the number of training rounds reaches the upper limit.

[0159] 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.

[0160] 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.

[0161] 3. Decentralized learning.

[0162] like Figure 2g The diagram shows 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. i The 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:

[0163]

[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 (e.g.) Figure 1a or Figure 1b or Figure 1cIn a communication system (as shown in the diagram), communication nodes typically possess both signal transmission and reception capabilities and computational capabilities. Taking a network device with computational capabilities as an example, the network device's computational capabilities primarily provide computing power support for signal transmission and reception capabilities (e.g., processing signals for transmission and reception) to enable the network device to perform communication tasks with other communication nodes.

[0166] With the development of communication systems, wireless networks are transforming from traditional cellular architectures to ultra-dense heterogeneous network deployments. Ultra-dense heterogeneous networks primarily increase network density by densely deploying cells, thereby supporting better operation of cellular networks. It organizes various ultra-dense network devices into a cohesive system. These network devices may include macro base stations, micro base stations, pico base stations, and other types, which are densely deployed in specific areas with varying coverage and backhaul capabilities, collectively forming a complex network structure.

[0167] However, increased inter-base station interference has become a major bottleneck limiting system performance and throughput. Interference not only affects network transmission quality but also directly restricts further improvements in network capacity. Modeling and predicting interference is a current hot research topic and a problem that needs to be solved.

[0168] One possible approach is to leverage massive amounts of network data and advanced machine learning techniques. Data-driven models can extract implicit patterns from network topology, access control, and transmission protocols, such as radio maps. Radio maps encode environmental parameters like terrain elevation and base station locations into 2D raster inputs, extract multi-scale features through an encoder-decoder structure, and output the predicted reference signal receiving power (RSRP) for each pixel within the region in parallel. This method optimizes network parameters through offline training.

[0169] However, radio maps only implicitly represent interference at the pixel level, resulting in predictions that cannot characterize the covariance matrix structure of the real interference field (such as the directional nature of distance attenuation). Furthermore, they only support scenarios with fixed base stations and fixed environmental parameters, failing to handle dynamic changes in the location of terminal devices. In other words, radio maps fail to consider the spatiotemporal correlation of interference when modeling it, especially in multi-cell communication environments, neglecting the higher-order dependencies of interference between base stations and terminals, thus affecting the accuracy of interference prediction.

[0170] Another possible implementation is a dynamic graph-driven interference coordination scheme. This scheme uses base stations and terminal devices in a heterogeneous cellular network as nodes. It constructs a real-time evolving network topology by periodically updating service edges (representing the connection strength between base stations and terminals) and dynamically triggered interference edges (capturing co-frequency conflicts between pairs of terminals). A dual-channel graph attention network processes service and interference information separately. The service channel calculates attention weights based on channel quality and service requirements, while the interference channel aggregates conflict signals based on frequency overlap and spatial proximity. Finally, a joint optimization layer synchronously outputs a resource block allocation probability matrix and transmit power adjustment, forming a closed-loop control command that is sent to the base station.

[0171] However, this scheme lacks the ability to model complex network relationships. Specifically, the binary edge architecture forcibly decomposes the cooperative interference of multiple terminals and resource blocks into independent pairwise relationships, leading to increased prediction errors of cooperative interference in dense scenarios. Furthermore, the discretized "node-edge" modeling severs the continuous physical field characteristics of signal propagation (such as path loss gradient and multipath phase superposition). The dynamic update mechanism relies on global adjacency matrix reconstruction and full attribute synchronization, which is difficult to adapt to the requirements of ultra-low latency scenarios. At the same time, the simplified assumption of decoupling from the physical layer (ignoring multipath delay spread and Doppler shift) further exacerbates the scheduling mismatch in high-speed mobile scenarios.

[0172] Based on this, an embodiment of this application provides a method. Please refer to [link / reference]. Figure 3 , Figure 3 This is a schematic diagram of the interference prediction method provided in the embodiments of this application. Figure 3 The method shown is executed interactively by the first device and the second device.

[0173] The first device can 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 capable of implementing all or part of the functions of the terminal device. Alternatively, the first 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 capable of implementing all or part of the functions of the network device (such as a CU, DU, or RU).

[0174] The second device can be a terminal device, 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. Alternatively, the second device can be a network device, a component or device applied to a network 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 network device (such as a CU, DU, or RU).

[0175] The first device and the second device are of different types; for example, the first device may be a terminal device and the second device may be a network device, or the first device may be a network device and the second device may be a terminal device. The specific type is not limited here. The method includes:

[0176] 301. The first device acquires first information and second information.

[0177] The first piece of information is associated with the location information of the terminal device or network device. Specifically, the first piece of information can be information associated with the location of the terminal device or network device, or it can be the channel information of the terminal device or network device; the specifics are not limited here. The second piece of information is the resource usage information corresponding to the first piece of information.

[0178] Specifically, the first information can be used to indicate the location of network devices, terminal devices, or a specific area. For example, the first information may include the coordinates of the network device. The first information can also be used to indicate channel information between the network device and the terminal device, such as the CSI, channel impulse response, and channel frequency domain response between the network device and the terminal device, etc., without being limited here.

[0179] Optionally, this first information can be historical information.

[0180] The second information corresponds to the first information; that is, the second information is the resource usage information of the network device, terminal device, or specific area indicated by the first information. The second information may include resource usage information exchanged between base stations in adjacent cells. For example, the second information includes base station resource usage information [r] n1 ,...,r nK [r] and resource usage information of terminal devices u1 ,...,r uK ].

[0181] It should be noted that resources include two dimensions: time-domain resources and / or frequency-domain resources. The unit of time-domain resources is a time-domain unit, and the unit of frequency-domain resources is a frequency-domain unit.

[0182] Time-domain units can be symbols, orthogonal frequency division multiplexing (OFDM) symbols, slots, mini-slots, partial slots, sub-frames, frames, radio frames, etc.

[0183] Frequency domain units can be resource elements (REs), resource blocks (RBs), RB sets, channels, subchannels, control channel elements (CCEs), interlaces, combs, resource pools, bandwidth parts (BWPs), carriers, bands, etc.

[0184] The time-domain and frequency-domain units mentioned above can be combined arbitrarily. For example, a resource can be a time-frequency unit with symbols in the time domain and REs in the frequency domain. Another example is that a resource can be a time-frequency unit with time slots in the time domain and RBs in the frequency domain.

[0185] Optionally, the second piece of information can be historical information.

[0186] In one possible implementation, the first information and the second information can be obtained by the first device through calculation or measurement.

[0187] In another possible implementation, the first and second information can be obtained by the first device receiving messages from other devices. For example, if the first device is a terminal device and the second device is a network device, then the first device can receive the first and second information from the second device. As another example, if the first device is a network device, then the first device can receive the first and second information from a core network device; the specific implementation is not limited here.

[0188] 302. The first device processes the first information and the second information according to the first model based on the hypergraph to obtain the first distribution parameters.

[0189] Specifically, the first distribution parameter is used to indicate the interference prediction result of the terminal device or network device. Alternatively, the first device inputs the first information and the second information into a first model based on a hypergraph, and the output result is the first distribution parameter. This first model can also be referred to as the interference prediction model.

[0190] A hypergraph is an extension of the concept in graph theory, offering greater generality than a traditional graph. In a traditional graph, an edge can connect only two vertices, while in a hypergraph, an edge (called a hyperedge) can connect any number of vertices. This flexibility allows hypergraphs to express more complex relationships and structures.

[0191] In the instantiation process of a hypergraph model, nodes represent participants in a design pattern, and directed arcs between nodes represent relationships between classes (objects).

[0192] The first model is determined based on the first hypergraph. The first hypergraph includes N nodes and K hyperedges. The N nodes are used to indicate N network devices. The N network devices use K resources to communicate with U terminal devices. The K hyperedges are used to indicate the interference relationship of shared resources between network devices and terminal devices. N is an integer greater than or equal to 2, and K and U are both positive integers.

[0193] For example, Figure 4a This diagram illustrates one possible implementation of the first hypergraph. The first hypergraph includes three nodes, corresponding to three base stations: BS1, BS2, and BS3. BS1 and BS3 use the same resource block RB1, while BS1, BS2, and BS3 use the same resource blocks RB2 and RB3. RB0 is used only by BS1.

[0194] The first device can perform inference based on the first hypergraph and the first model to obtain the first distribution parameters. The specific inference process is as follows: Figure 4b As shown, the following explanation follows.

[0195] In the first hypergraph, node v n Corresponding to network device n, hyperedge e k Connecting multiple network devices with the same resources. Specifically, the first hypergraph represents the network devices in each cell of a wireless communication system consisting of N cells. (in Using resource K n ={1,2,…,K} serves U within time slot t n Terminal devices Where K represents the number of resources.

[0196] binary pointer δ n,u,k ∈{0,1} indicates whether network device n communicates with terminal device u on resource k. The signal power used for communication with terminal device u on resource k is denoted as P. n,u,k The channel gain from network device n to end-user device u on resource k is represented by H. n,u,k The beamforming vectors of network device n and terminal device u on resource k are represented as w. n,u,k The additive white noise (AWGN) received by terminal device u on resource k is denoted as... The signal expression received by terminal device u communicating with network device n on resource k is:

[0197]

[0198] Among them, s n,u,kThis represents the normalized modulation symbol transmitted from network device n and terminal device u on resource k. Specifically, the desired signal component of terminal device u on resource k is:

[0199]

[0200] The total interference power caused by signals from different network devices is expressed as:

[0201]

[0202] Since the correspondence between network devices, terminal devices, and resources is bound in the data, the embodiments of this application can use I. i Let represent the interference value of the i-th data.

[0203] The first device determines the vertex feature matrix, hyper-edge feature matrix, and hyper-edge weight matrix based on the first hypergraph. Alternatively, the first hypergraph can be represented by these three matrices. The vertex feature matrix indicates the characteristics of each of the N nodes, the hyper-edge feature matrix indicates the characteristics of each of the K hyperedges, and the hyper-edge weight matrix indicates the transmission power on the K resources.

[0204] Specifically, the first device determines the node feature matrix based on the third information and the fourth information. The third information is associated with the location information of N network devices, and the fourth information is used to indicate the resources occupied by the N network devices.

[0205] The first device determines the hyperedge feature matrix based on the fifth and sixth information. The fifth information is associated with the location information of the U terminal devices, and the sixth information is used to indicate the resources occupied by the U terminal devices.

[0206] The first device determines the hyperedge weight matrix based on the transmission power on the K resources.

[0207] The node feature matrix can be represented by X, and the features of node n (i.e., network device n) can be represented by X. n Among them, X n Satisfy the following formula:

[0208] X n =[Embed PE (x n ,d),Embed PE (y n ,d),r n1 ,...,r nK ]

[0209] coordinates (x) n ,y n ) represents the location of network device n; vector [r n1 ,...,r nK ] represents the resource block occupied by network device n. The expression for the position encoding function can be:

[0210]

[0211] The hyperedge feature matrix can be represented by E, and the feature of hyperedge k (i.e., the hyperscale corresponding to resource k) can be represented by E. k Among them, E k Satisfy the following formula:

[0212] E k =[Embed PE (x u ,d / N),Embed PE (y u ,d / N),…,r n1 ,...,r nK ]

[0213] coordinates (x) u ,y u ) represents the physical location of terminal device u; vector [r] u1 ,...,r uK ] indicates the resources used by the service terminal device u.

[0214] The hyperedge weight matrix can be used with W e It means that, among them, The hyperedge weight matrix is ​​a diagonal matrix, where w k,k Indicates the superedge e k The weight represents the transmission power of the resource.

[0215] Optionally, the first hypergraph can also be composed of the node-hyperedge incidence matrix J and the hyperedge degree matrix. and node degree matrix It indicates. Among them, The node-hyperedge incidence matrix represents the relationship between nodes and hyperedges, J n,k =1 indicates that network device n is related to resource k, J n,k =0 indicates no relation. Hyperboundary degree matrix It can be represented as:

[0216]

[0217] Node degree matrix It can be represented as:

[0218]

[0219] Hypermarginal matrix and node degree matrix These represent the degree of the hyperedge and the node, respectively, and are used to handle changes in the size of the hyperedge.

[0220] In this embodiment of the application, the interference relationship between multiple cells in a wireless communication system can be effectively described based on the first hypergraph, which facilitates interference modeling and prediction.

[0221] To dynamically adjust the impact of interference sources, the first device can calculate the attention score for each hyperedge. It can be represented as:

[0222]

[0223] Among them, W e This is the hyperedge weight matrix. The node feature matrix, Let A be the hyperedge feature matrix. In one possible implementation, the first device normalizes the attention score using the Softmax function to obtain the attention matrix A, which is used to adjust the interference weights between each base station and the hyperedge. The normalization method can be expressed as:

[0224]

[0225] In this embodiment, by introducing a hyperedge attention mechanism, important interference sources in interference prediction can be dynamically adjusted, thereby enhancing the model's ability to capture spatial interference relationships.

[0226] The first device updates the node feature matrix based on the attention matrix using hypergraph convolution. Hypergraph convolution is used to aggregate interference information between network devices. At layer r, the first device updates the node feature matrix X, and the calculation formula can be expressed as:

[0227]

[0228] Where A(r) is the attention matrix, W e Let be the hyperedge weight matrix, σ(·) be the activation function, and P(r) be the trainable feature transformation matrix. It is the hypermarginality matrix. This is the node degree matrix.

[0229] To accurately capture the spatiotemporal dynamics of interference propagation, the first device can perform interference modeling using data from historical and current time slots via spatiotemporal convolution. The spatiotemporal convolution formula is as follows:

[0230]

[0231] Where T is the time window, W t It is the spatiotemporal feature transformation matrix, and X(t′) is the disturbance feature at time t′, which can also be called the first disturbance feature.

[0232] In this embodiment, spatiotemporal convolution helps the model capture the temporal correlation of interference, thereby improving the stability of interference prediction.

[0233] The first device determines based on the multilayer sensor and the first interference feature. Predict the interference distribution p(I) for each user equipment i ), that is, the first distribution parameter, can be expressed as:

[0234]

[0235] This distribution can be expressed using a Gaussian function as follows:

[0236]

[0237] In this embodiment of the application, the first model based on a hypergraph is used for interference prediction, which can effectively capture spatiotemporal dynamic characteristics and thus improve the accuracy of interference prediction.

[0238] In one possible implementation, if the first device is a network device and the second device is a terminal device, the first device can schedule, allocate resources, coordinate interference, or pair users with the second device based on the interference prediction results, without being limited here.

[0239] Optional, Figure 3 The illustrated embodiment also includes step 303. Step 303 may be performed after step 302.

[0240] 303. The first device sends a first distribution parameter to the second device. Correspondingly, the second device receives a distribution parameter from the first device.

[0241] The first device can send the prediction result, i.e. the first distribution parameter, to the second device so that the second device can perform subsequent operations based on the first distribution parameter.

[0242] For example, if the first device is a terminal device and the second device is a network device, the second device can schedule, allocate resources, coordinate interference, or pair users with the first device based on the first distribution parameters sent by the first device. The specifics are not limited here.

[0243] The construction of the first hypergraph and the inference process of the first model have been explained above. The training process of the first model will now be explained using the first device as the model training side as an example. It should be noted that the first device can be a terminal device or a network device; no specific limitation is made here. Please refer to [link / reference]. Figure 5 An embodiment of this application includes a model training method comprising:

[0244] 501. The first device acquires first information and second information.

[0245] The first device can acquire first information associated with location information and second information corresponding to the first information through calculation or measurement, and use these as inputs to the second model. The second model is a hypergraph-based interference prediction model. When the first device is a terminal device, the second model can be obtained from a network device or a third-party server.

[0246] 502. The first device determines the second hypergraph based on the first information and the second information.

[0247] 503. The first device determines the node feature matrix, the hyperedge feature matrix, and the hyperedge weight matrix based on the second hypergraph.

[0248] 504. The first device determines the attention matrix based on the node feature matrix, the hyperedge feature matrix, and the hyperedge weight matrix.

[0249] 505. The first device updates the node feature matrix through hypergraph convolution based on the attention matrix.

[0250] 506. The first device determines the second distribution parameter based on the multilayer sensor and the second interference characteristics.

[0251] Steps 502 to 506 in this embodiment are similar to the method of determining the first distribution parameter in the aforementioned first model inference process, and will not be described in detail here.

[0252] 507. The first device adjusts the parameters of the second model based on the first loss value.

[0253] The first device uses the deviation between the second and third distribution parameters as the first loss value, and updates the parameters of the second model through gradient backpropagation to obtain the first model based on the hypergraph.

[0254] In one possible implementation, the first device uses the Kullback-Leibler divergence (KL divergence) as a loss function to calculate the difference between the model's output and the true disturbance distribution. This loss function can be expressed as:

[0255]

[0256] The interference prediction method and model training method in the embodiments of this application have been described above. The communication device in the embodiments of this application will be described below.

[0257] Please see Figure 6 The communication device 600 can be used to perform Figure 3 The process executed by the first device in the illustrated embodiment can be specifically described in the relevant descriptions of the foregoing method embodiments. The communication device 600 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. Alternatively, the communication device 600 can 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.

[0258] The communication device 600 includes an interface module 601 and a processing module 602.

[0259] The processing module 602 is used for data processing. The interface module 601 can implement corresponding communication functions. The interface module 601 can also be called a communication interface or a communication module.

[0260] Optionally, the communication device 600 may further include a storage module, which can be used to store program code, program instructions and / or data. The processing module 602 can read the instructions and / or data in the storage module so that the communication device 600 can implement the aforementioned method embodiments.

[0261] The communication device 600 can be used to perform the actions performed by the first device in the above method embodiments. For example, it can be the first device, a communication module within the first device, or a circuit or chip in the first device responsible for communication functions. The communication device 600 can be the first device or a component configurable within the first device. The processing module 602 is used to perform processing-related operations on the first device side in the above method embodiments. The interface module 601 is used to perform receiving-related operations on the first device side in the above method embodiments.

[0262] Optionally, interface module 601 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.

[0263] It should be noted that the communication device 600 may include a transmitting module but not a receiving module. Alternatively, the communication device 600 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme performed by the communication device 600 includes both transmitting and receiving actions. For example, the communication device 600 is used to perform the above-described... Figure 3 The actions performed by the first device in the illustrated embodiment are shown above. For details, please refer to the above. Figure 3 The relevant descriptions in the illustrated embodiments will not be elaborated here.

[0264] For example, the communication device 600 is used to execute the following scheme:

[0265] Interface module 601 is used to obtain first information and second information. The first information is associated with the location information of the terminal device or network device, and the second information is the resource usage information corresponding to the first information.

[0266] The processing module 602 is used to process the first information and the second information according to the first model based on the hypergraph to obtain the first distribution parameter, which is used to indicate the interference prediction result of the terminal device or network device.

[0267] In one possible implementation, the processing module 602 is also used to schedule, allocate resources, coordinate interference, or pair users for terminal devices based on interference prediction results.

[0268] In another possible implementation, processing module 602 is used to process the first information and the second information according to the first model based on the hypergraph to obtain the first distribution parameters, including:

[0269] The processing module 602 is specifically used to determine a first hypergraph based on the first information and the second information. The first hypergraph includes N nodes and K hyperedges. The N nodes are used to indicate N network devices. The N network devices use K resources to communicate with U terminal devices. The K hyperedges are used to indicate the interference relationship between the network devices and the terminal devices in sharing transmission resources. The first hypergraph is used to determine a first model. N is an integer greater than or equal to 2, and K and U are both positive integers.

[0270] The processing module 602 is further used to obtain the first distribution parameters based on the first hypergraph.

[0271] In another possible implementation, the processing module 602 is further configured to determine a node feature matrix based on the third information and the fourth information. The third information is associated with the location information of N network devices, the fourth information is used to indicate the resources occupied by the N network devices, and the node feature matrix is ​​used to indicate the characteristics of each of the N nodes.

[0272] In another possible implementation, the processing module 602 is further configured to determine the hyperedge feature matrix based on the fifth information and the sixth information. The fifth information is associated with the location information of the U terminal devices, the sixth information is used to indicate the resources occupied by the U terminal devices, and the hyperedge feature matrix is ​​used to indicate the features of each hyperedge among the K hyperedges.

[0273] In another possible implementation, the processing module 602 is also used to determine the hyperedge weight matrix based on the transmission power on the K resources.

[0274] In another possible implementation, the processing module 602 is used to obtain the first distribution parameters based on the first hypergraph, including:

[0275] Processing module 602 is specifically used to determine the node feature matrix, hyperedge feature matrix, and hyperedge weight matrix based on the first hypergraph;

[0276] The processing module 602 is further used to determine the attention matrix based on the node feature matrix, the hyperedge feature matrix and the hyperedge weight matrix. The attention matrix is ​​used to adjust the interference weight between each node and the hyperedge.

[0277] The processing module 602 is further used to determine the first distribution parameters based on the attention matrix.

[0278] In another possible implementation, processing module 602 is used to determine the first distribution parameters based on the attention matrix, including:

[0279] Processing module 602 is specifically used to update the node feature matrix through hypergraph convolution based on the attention matrix, and the updated node feature matrix is ​​used to determine the first interference feature;

[0280] The processing module 602 is further configured to determine the first distribution parameters based on the multilayer perceptron and the first interference features.

[0281] 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.

[0282] Optionally, when the communication device 600 is a terminal device or a communication module within a terminal device, the processing module 602 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 601 can be implemented by a transceiver or transceiver-related circuitry. The interface module 601 may also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0283] Optionally, when the communication device 600 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 602 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 601 can be implemented by the interface circuit or data transceiver circuit on the aforementioned chip.

[0284] Please see Figure 7 The communication device 700 can be used to perform Figure 5 The process executed by the first device in the illustrated embodiment can be specifically described in the relevant descriptions of the foregoing method embodiments. The communication device 700 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. Alternatively, the communication device 700 can 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.

[0285] The communication device 700 includes an interface module 701. Optionally, a processing module 702.

[0286] The processing module 702 is used for data processing. The interface module 701 can implement corresponding communication functions. The interface module 701 can also be called a communication interface or a communication module.

[0287] Optionally, the communication device 700 may further include a storage module, which can be used to store program code, program instructions and / or data. The processing module 702 can read the instructions and / or data in the storage module so that the communication device 700 can implement the aforementioned method embodiments.

[0288] The communication device 700 can be used to perform the actions performed by the first device in the above method embodiments. For example, it can be the first device, a communication module within the first device, or a circuit or chip in the first device responsible for communication functions. The communication device 700 can be the first device or a component configurable within the first device. The processing module 702 is used to perform processing-related operations on the first device side in the above method embodiments. The interface module 701 is used to perform receiving-related operations on the first device side in the above method embodiments.

[0289] Optionally, interface module 701 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.

[0290] It should be noted that the communication device 700 may include a transmitting module but not a receiving module. Alternatively, the communication device 700 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme performed by the communication device 700 includes both transmitting and receiving actions. For example, the communication device 700 is used to perform the above-described... Figure 5 The actions performed by the first device in the illustrated embodiment are shown above. For details, please refer to the above. Figure 5 The relevant descriptions in the illustrated embodiments will not be elaborated here.

[0291] For example, the communication device 700 is used to execute the following scheme:

[0292] Interface module 701 is used to obtain first information and second information. The first information is associated with the location information of the terminal device or network device, and the second information is the resource usage information corresponding to the first information.

[0293] Processing module 702 is used to process the first information and the second information according to the second model based on the hypergraph to obtain the second distribution parameter, which is used to indicate the interference prediction result of the terminal device or network device.

[0294] The parameters of the second model are updated based on the second distribution parameters to obtain the first model based on the hypergraph.

[0295] In one possible implementation, the processing module 702 is configured to process the first information and the second information according to the second model based on the hypergraph to obtain the first distribution parameters, including:

[0296] The processing module 702 is specifically used to determine a second hypergraph based on the first information and the second information. The second hypergraph includes N nodes and K hyperedges. The N nodes are used to indicate N network devices. The N network devices use K resources to communicate with U terminal devices. The K hyperedges are used to indicate the interference relationship between the network devices and the terminal devices in sharing transmission resources. The second hypergraph is used to determine a second model. N is an integer greater than or equal to 2, and K and U are both positive integers.

[0297] The processing module 702 is also used to obtain the second distribution parameters based on the second hypergraph.

[0298] In another possible implementation, the processing module 702 is further configured to determine a node feature matrix based on the third information and the fourth information. The third information is associated with the location information of N network devices, the fourth information is used to indicate the resources occupied by the N network devices, and the node feature matrix is ​​used to indicate the characteristics of each of the N nodes.

[0299] In another possible implementation, the processing module 702 is further configured to determine the hyperedge feature matrix based on the fifth information and the sixth information. The fifth information is associated with the location information of the U terminal devices, the sixth information is used to indicate the resources occupied by the U terminal devices, and the hyperedge feature matrix is ​​used to indicate the features of each hyperedge among the K hyperedges.

[0300] In another possible implementation, the processing module 702 is also used to determine the hyperedge weight matrix based on the transmission power on the K resources.

[0301] In another possible implementation, the processing module 702 is further configured to obtain the first distribution parameters based on the first hypergraph, including:

[0302] Processing module 702 is specifically used to determine the node feature matrix, hyperedge feature matrix, and hyperedge weight matrix based on the first hypergraph;

[0303] The processing module 702 is further used to determine the attention matrix based on the node feature matrix, the hyperedge feature matrix, and the hyperedge weight matrix. The attention matrix is ​​used to adjust the interference weights between each node and the hyperedge.

[0304] The processing module 702 is also used to determine the first distribution parameter based on the attention matrix.

[0305] In another possible implementation, processing module 702 is used to determine the first distribution parameters based on the attention matrix, including:

[0306] Processing module 702 is specifically used to update the node feature matrix based on the attention matrix through hypergraph convolution, and the updated node feature matrix is ​​used to determine the first interference feature.

[0307] The processing module 702 is further used to determine the first distribution parameters based on the multilayer perceptron and the first interference features.

[0308] In another possible implementation, processing module 702 is further configured to update the parameters of the second model according to the second distribution parameters to obtain a first model based on the hypergraph, including:

[0309] The processing module 702 is specifically used to adjust the parameters of the second model according to the first loss value to obtain the first model. The first loss value is determined based on the deviation between the second distribution parameter and the third distribution parameter. The third distribution parameter is used to indicate the actual interference result of the terminal device or network device.

[0310] 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.

[0311] Optionally, when the communication device 700 is a terminal device or a communication module within a terminal device, the processing module 702 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 701 can be implemented by a transceiver or transceiver-related circuitry. The interface module 701 may also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0312] Optionally, when the communication device 700 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 702 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 701 can be implemented by the interface circuit or data transceiver circuit on the aforementioned chip.

[0313] The following describes a communication device provided in an embodiment of this application. Please refer to [link / reference]. Figure 8 , Figure 8 This is a schematic diagram of a communication device provided in an embodiment of this application. The communication device may be the first device or the second device in the above method embodiments, or it may be a chip, chip system, or processor that supports the first device or the second 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.

[0314] The communication device may include one or more processors 801, which are connected to a memory 802, an input / output unit 803, and a bus 804. The processor 801 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.

[0315] Optionally, the communication device may include one or more memories 802, which may store instructions that can be executed on the processor 801 to cause the communication device to perform the methods described in the above method embodiments. Optionally, the memories 802 may also store data. The processor 801 and the memories 802 may be configured separately or integrated together.

[0316] 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.

[0317] In another possible design, the processor 801 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 can be used for reading and writing code / data, or it can be used for transmitting or relaying signals.

[0318] In another possible design, the processor 801 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 801; in this case, the processor 801 may be implemented in hardware.

[0319] In another possible design, the communication device may include a circuit that can perform the transmitting or receiving or communication functions of the first or second 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.

[0320] The communication device described in the above embodiments may be a first device or a second 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 may vary. Figure 8 The communication device can be a standalone device or part of a larger device. For example, the communication device can be:

[0321] (1) Independent integrated circuit IC, or chip, or chip system or subsystem;

[0322] (2) A collection of one or more ICs, optionally including a storage component for storing data and instructions;

[0323] (3) ASIC, such as modem;

[0324] (4) Modules that can be embedded in other devices;

[0325] (5) Receivers, terminals, smart terminals, cellular phones, wireless devices, handheld devices, mobile units, vehicle-mounted devices, network devices, cloud devices, artificial intelligence devices, etc.

[0326] (6) Others, etc.

[0327] For cases where the communication device can be a chip or a chip system, please refer to [link / reference]. Figure 9 The diagram shows the structure of the chip. Figure 9 The chip 900 shown includes a processor 901 and an interface 902. Optionally, it may also include a memory 903. The number of processors 901 can be one or more, and the number of interfaces 902 can be multiple.

[0328] For cases where the chip is used to implement the functions of the first or second device in the embodiments of this application:

[0329] The interface 902 is used to receive or output signals;

[0330] The processor 901 is used to perform data processing operations of the first device or the second device.

[0331] It should be understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), graphics processing units (GPUs), neural network processing units (NPUs), artificial intelligence processors, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, any conventional processor, or one or more integrated circuits used to control the execution of a program for controlling the method provided in any of the above embodiments. The memory mentioned above can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM), etc. Some or all steps of the communication method in the embodiments of this application can be implemented by a GPU or NPU, or by a GPU or NPU in conjunction with other processors.

[0332] 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.

[0333] 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.

[0334] 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.

[0335] 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.

[0336] 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.

[0337] 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.

[0338] 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.

[0339] 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.

[0340] 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. An interference prediction method, characterized in that, The method includes: Obtain first information and second information, wherein the first information is associated with the location information of the terminal device or network device, and the second information is the resource usage information corresponding to the first information; The first information and the second information are processed according to the first model based on the hypergraph to obtain the first distribution parameter, which is used to indicate the interference prediction result of the terminal device or the network device.

2. The method according to claim 1, characterized in that, The method further includes: Based on the interference prediction results, the terminal devices are scheduled, resources are allocated, interference is coordinated, or users are paired.

3. The method according to claim 1 or 2, characterized in that, The step of processing the first information and the second information according to the first model based on the hypergraph to obtain the first distribution parameters includes: A first hypergraph is determined based on the first information and the second information. The first hypergraph includes N nodes and K hyperedges. The N nodes are used to indicate N network devices. The N network devices use K resources to communicate with U terminal devices. The K hyperedges are used to indicate the interference relationship between the network devices and the terminal devices in sharing transmission resources. The first hypergraph is used to determine the first model. N is an integer greater than or equal to 2, and K and U are both positive integers. The first distribution parameters are obtained based on the first hypergraph.

4. The method according to claim 3, characterized in that, The method further includes: The node feature matrix is ​​determined based on the third and fourth information, wherein the third information is associated with the location information of the N network devices, the fourth information is used to indicate the resources occupied by the N network devices, and the node feature matrix is ​​used to indicate the characteristics of each of the N nodes.

5. The method according to claim 3 or 4, characterized in that, The method further includes: The hyperedge feature matrix is ​​determined based on the fifth and sixth information. The fifth information is associated with the location information of the U terminal devices, the sixth information is used to indicate the resources occupied by the U terminal devices, and the hyperedge feature matrix is ​​used to indicate the features of each hyperedge among the K hyperedges.

6. The method according to any one of claims 3 to 5, characterized in that, The hyperedge weight matrix is ​​determined based on the transmission power on the K resources.

7. The method according to any one of claims 4 to 6, characterized in that, The step of obtaining the first distribution parameters based on the first hypergraph includes: The node feature matrix, the hyperedge feature matrix, and the hyperedge weight matrix are determined based on the first hypergraph; An attention matrix is ​​determined based on the node feature matrix, the hyperedge feature matrix, and the hyperedge weight matrix. The attention matrix is ​​used to adjust the interference weights between each node and the hyperedge. The first distribution parameter is determined based on the attention matrix.

8. The method according to claim 7, characterized in that, Determining the first distribution parameter based on the attention matrix includes: The node feature matrix is ​​updated by hypergraph convolution based on the attention matrix, and the updated node feature matrix is ​​used to determine the first interference feature. The first distribution parameter is determined based on the multilayer perceptron and the first interference feature.

9. A model training method, characterized in that, The method includes: Obtain first information and second information, wherein the first information is associated with the location information of the terminal device or network device, and the second information is the resource usage information corresponding to the first information; The first information and the second information are processed according to the second model based on the hypergraph to obtain the second distribution parameter, which is used to indicate the interference prediction result of the terminal device or the network device; The parameters of the second model are updated according to the second distribution parameters to obtain the first model based on the hypergraph.

10. The method according to claim 9, characterized in that, The step of processing the first information and the second information according to the second model based on the hypergraph to obtain the first distribution parameters includes: A second hypergraph is determined based on the first information and the second information. The second hypergraph includes N nodes and K hyperedges. The N nodes are used to indicate N network devices. The N network devices use K resources to communicate with U terminal devices. The K hyperedges are used to indicate the interference relationship between the network devices and the terminal devices in sharing transmission resources. The second hypergraph is used to determine the second model. N is an integer greater than or equal to 2, and K and U are both positive integers. The second distribution parameters are obtained based on the second hypergraph.

11. The method according to claim 10, characterized in that, The method further includes: The node feature matrix is ​​determined based on the third and fourth information, wherein the third information is associated with the location information of the N network devices, the fourth information is used to indicate the resources occupied by the N network devices, and the node feature matrix is ​​used to indicate the characteristics of each of the N nodes.

12. The method according to claim 10 or 11, characterized in that, The method further includes: The hyperedge feature matrix is ​​determined based on the fifth and sixth information. The fifth information is associated with the location information of the U terminal devices, the sixth information is used to indicate the resources occupied by the U terminal devices, and the hyperedge feature matrix is ​​used to indicate the features of each hyperedge among the K hyperedges.

13. The method according to any one of claims 10 to 12, characterized in that, The hyperedge weight matrix is ​​determined based on the transmission power on the K resources.

14. The method according to any one of claims 11 to 13, characterized in that, The step of obtaining the first distribution parameters based on the first hypergraph includes: The node feature matrix, the hyperedge feature matrix, and the hyperedge weight matrix are determined based on the first hypergraph; An attention matrix is ​​determined based on the node feature matrix, the hyperedge feature matrix, and the hyperedge weight matrix. The attention matrix is ​​used to adjust the interference weights between each node and the hyperedge. The first distribution parameter is determined based on the attention matrix.

15. The method according to claim 14, characterized in that, Determining the first distribution parameter based on the attention matrix includes: The node feature matrix is ​​updated by hypergraph convolution based on the attention matrix, and the updated node feature matrix is ​​used to determine the first interference feature. The first distribution parameter is determined based on the multilayer perceptron and the first interference feature.

16. The method according to any one of claims 9 to 15, characterized in that, The step of updating the parameters of the second model according to the second distribution parameters to obtain the first model based on the hypergraph includes: The parameters of the second model are adjusted according to the first loss value to obtain the first model. The first loss value is determined based on the deviation between the second distribution parameter and the third distribution parameter. The third distribution parameter is used to indicate the actual interference result of the terminal device or the network device.

17. A communication device, characterized in that, Includes modules or units for performing the method as described in any one of claims 1 to 8, or for performing the method as described in any one of claims 9 to 16.

18. 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 8, or causes the communication device to perform the method as described in any one of claims 9 to 16.

19. A computer-readable storage medium, characterized in that, Includes instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 8, or cause the computer to perform the method as described in any one of claims 9 to 16.

20. 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 8, or causes the computer to perform the method as described in any one of claims 9 to 16.

Images