Communication method and communication device

Abstract

The invention provides a communication method and a communication device, when a plurality of prediction tasks based on AI are executed by a terminal device, the terminal device obtains a prediction result based on the plurality of prediction tasks, and the prediction result is obtained by executing a certain prediction task in the plurality of prediction tasks. And if the prediction results of the other prediction tasks can be represented, the terminal equipment can report one prediction result for the plurality of prediction tasks, and meanwhile, the prediction result is associated with the other prediction tasks, so that one prediction result is reported by the plurality of prediction tasks, and the air interface overhead of sending a CSI report by the terminal equipment can be reduced.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and more specifically, to a communication method and a communication device. Background Technology

[0002] The application of beam management based on artificial intelligence (AI) mainly focuses on two aspects: spatial prediction and temporal prediction. In spatial prediction, the AI ​​model's input is the beam information of a specific pattern scanned at a given time, typically the reference signal received power (RSRP). The AI ​​model predicts information for all beams and selects K beams from this pool, along with their associated information, to report to the network. In temporal prediction, a sliding time window collects the AI ​​model's input information. The AI ​​model processes this input and outputs either the prediction results for all beams within the future time window (e.g., a regression model) or the identifiers of K beams from this pool (e.g., a classification model). Finally, it selects K beams and their associated information to report to the network, where K is a positive integer.

[0003] When multiple prediction tasks are performed simultaneously, the network side typically configures reference signal resources for terminal devices to independently execute these two prediction tasks. The two prediction tasks do not interfere with each other, and ultimately, the prediction results of each task are reported. However, the current mechanism for reporting prediction results incurs significant air interface overhead. Summary of the Invention

[0004] This application provides a communication method and a communication device that helps reduce air interface overhead.

[0005] In a first aspect, a communication method is provided, to be executed by a communication device or a module for the communication device (e.g., a processor, chip, circuit, AI entity, etc., or a logic module, hardware and / or software, etc., capable of implementing all or part of the functions of the communication device), the communication device corresponding to the network device in the method embodiment. The method includes: determining a first prediction result based on a first prediction task and a second prediction task, wherein the first prediction result is obtained based on the first prediction task and is associated with the second prediction task; or, the first prediction result is obtained based on the second prediction task and is associated with the first prediction task; and sending a Channel State Information (CSI) report, the CSI report containing the first prediction result.

[0006] In the technical solution of this application, when multiple prediction tasks are executed by a terminal device, the terminal device determines a prediction result to be reported based on these multiple prediction tasks. This prediction result is obtained by executing one of the multiple prediction tasks, but it can represent the prediction results of the other prediction tasks, thus associating the prediction result with the other prediction tasks. Therefore, when the terminal device sends a CSI report, it can report a single prediction result for multiple prediction tasks. Compared to each prediction task reporting its own prediction result separately, this reduces the air interface overhead of the terminal device sending the CSI report.

[0007] The multiple prediction tasks can be two or more prediction tasks.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, determining the first prediction result based on the first prediction task and the second prediction task includes: obtaining the second prediction result based on the first prediction task; obtaining the third prediction result based on the second prediction task; and obtaining the first prediction result based on the second prediction result and the third prediction result.

[0009] In this implementation, the terminal device obtains the prediction results of two prediction tasks respectively, and determines a prediction result to be reported based on the prediction results of these two prediction tasks.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the first prediction task corresponds to the first prediction period, and the second prediction task corresponds to the observation time window and the prediction time window; the first prediction result is the prediction result that is closer to the observation time window between the second prediction result and the third prediction result; the second prediction result is the prediction result of the first prediction task corresponding to the first prediction period; the third prediction result is the prediction result of the second prediction task corresponding to the second prediction period within the prediction time window; the prediction time window includes multiple prediction periods, and the second prediction period is one of the multiple prediction periods.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining the similarity between the second prediction result and the third prediction result when the length of the prediction time window is less than or equal to a set threshold.

[0012] In this implementation, considering that the longer the prediction time window of the time-domain prediction task (corresponding to the second prediction task) is, the lower the probability that the prediction result of the time-domain prediction task is the same or similar to the prediction result of the spatial-domain prediction task (corresponding to the first prediction task), the greater the probability that it is not suitable for merging and reporting (or deduplication or redundancy removal reporting, etc.), because at this time, it cannot be guaranteed that the accuracy of the merged prediction result can be used to represent the prediction results of these multiple prediction tasks. Therefore, by limiting the length of the prediction time window of the second prediction task to less than or equal to a threshold, unnecessary similarity judgments for the prediction results of the two prediction tasks can be reduced. Therefore, even after similarity judgment, the two prediction results are more likely to be dissimilar, and they cannot be merged and reported. By reducing unnecessary similarity judgments, the computational load related to similarity judgments of the terminal device can be reduced.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the first prediction result is the second prediction result obtained by the first prediction task in the first prediction period, and the third prediction result obtained by the second prediction task in the second prediction period is discarded; or, the first prediction result is the third prediction result obtained by the second prediction task in the second prediction period, and the second prediction result obtained by the first prediction task in the first prediction period is discarded.

[0014] In this implementation, when the first prediction task is a second prediction result obtained based on the first prediction task, it means that between the second prediction result obtained based on the first prediction task and the third prediction result obtained based on the second prediction task, the second prediction result is retained as the reported prediction result, and the third prediction result is discarded; otherwise, the third prediction result is retained as the reported prediction result, and the second prediction result is discarded, thereby reducing the reporting air interface overhead and reducing the waste of air interface resources.

[0015] Secondly, a communication method is provided, which can be executed by a communication device or a module for the communication device (e.g., a processor, chip, circuit, AI entity, etc., or a logic module, hardware, and / or software that can implement all or part of the functions of the communication device), wherein the communication device can correspond to the terminal device in the method embodiment. The method includes: receiving a Channel State Information (CSI) report, the CSI report containing a first prediction result, the first prediction result being obtained based on a first prediction task and associated with a second prediction task; or, the first prediction result being obtained based on a second prediction task and associated with the first prediction task.

[0016] The second aspect is the network-side method, which corresponds to the first aspect. The beneficial technical effects can be found in the explanation of the first aspect, and will not be elaborated here.

[0017] Based on the technical solution of this application, when a network device receives a CSI report containing a first prediction result for a first prediction task, and the first prediction result is associated with a second prediction task, the network device can obtain the prediction results of both the first and second prediction tasks, which is the first prediction result. This is because, although the first prediction result is obtained based on a certain prediction task, since it is associated with another prediction task, it indicates that the prediction result can characterize the prediction result of the associated prediction task. Therefore, when the network device receives one prediction result, it is equivalent to obtaining the prediction results of two prediction tasks.

[0018] In some implementations of the first or second aspect, the first prediction task corresponds to a first prediction period, and the second prediction task corresponds to an observation time window and a prediction time window; the first prediction result is the prediction result that is closer to the observation time window between the second and third prediction results, the second prediction result is the prediction result of the first prediction task corresponding to the first prediction period, and the third prediction result is the prediction result of the second prediction task corresponding to the second prediction period within the prediction time window, the prediction time window includes multiple prediction periods, and the second prediction period is one of the multiple prediction periods.

[0019] In this implementation, the first prediction task can be spatial prediction, and the second prediction task can be temporal prediction. When determining the first prediction result to be reported based on the prediction results of the two prediction tasks, the terminal device can select the prediction result that is closer to the observation time window of the temporal prediction task from the prediction results of each of the two prediction tasks. This saves air interface overhead while ensuring the accuracy of the reported prediction results.

[0020] In some implementations of the first or second aspect, the first prediction result is associated with the second prediction task, including: the first prediction result is used to characterize the prediction result of the second prediction task.

[0021] In the embodiments of this application, the first prediction result is associated with a prediction task and can be represented by one of the following: the first prediction result can be used to characterize the prediction result of the associated prediction task; the prediction result of the first prediction result is the same as the prediction result of the second prediction task, or the similarity between the prediction result of the first prediction result and the prediction result of the second prediction task is less than the similarity threshold.

[0022] In some implementations of the first or second aspect, the first prediction task and the second prediction task satisfy set conditions, which include: the time interval between the start times of the first prediction task and the second prediction task is less than or equal to a threshold; and the similarity between the second prediction result and the third prediction result is less than or equal to a similarity threshold.

[0023] In this implementation, prediction tasks whose prediction results can be merged and reported should meet certain conditions. Only by reporting the prediction results of multiple prediction tasks that meet these conditions using the "merged reporting" method provided in this application can the accuracy of the reported prediction results be guaranteed while minimizing overhead.

[0024] Furthermore, if the start times of two prediction tasks are the same, for example, if the threshold is 0, the execution instructions for the two prediction tasks can be issued simultaneously, and the reference signal used for beam scanning (or reference signal measurement) can be the same, thereby saving signaling overhead and reference signal resources.

[0025] In some implementations of the first or second aspect, the CSI report also includes forecast results for the remaining forecast periods within the forecast window, excluding the second forecast period.

[0026] In this implementation, the prediction results that can be merged and reported can be for the same or adjacent prediction time periods of two prediction tasks. That is, if a prediction task is a time-domain prediction task, the prediction results of that time-domain prediction task may be multiple prediction results output within the prediction time window, and only one or part of the prediction results may overlap with the prediction time period of another prediction task (e.g., another spatial domain prediction task), or be different but adjacent. Therefore, the terminal device merges and reports the prediction results of the two prediction tasks for the overlapping or adjacent prediction time periods, but reports the prediction results of the two prediction tasks for other prediction time periods outside the overlapping or adjacent prediction time periods separately.

[0027] In some implementations of the first or second aspect, the first prediction task and the second prediction task satisfy set conditions, which include: the start time of the first prediction task is after the start time of the second prediction task and before the end time of the second prediction task; and the prediction time window includes the first prediction period.

[0028] In this implementation, the first prediction task and the second prediction task are asynchronous and parallel. The first prediction task is triggered after the start of the beam scanning phase of the second prediction task and before the end of the prediction phase. In this case, the merged reporting mechanism provided in this application can be applied.

[0029] In some implementations of the first or second aspect, the first prediction result is the prediction result of the second prediction task corresponding to the first prediction period.

[0030] In some implementations of the first or second aspect, the first prediction task and the second prediction task each correspond to an observation time window and a prediction time window. The first prediction task and the second prediction task satisfy set conditions, which include: the first prediction task and the second prediction task correspond to the same one or more prediction periods; in any one of the one or more prediction periods, the second prediction result corresponding to the first prediction task and the third prediction result corresponding to the second prediction task are the same; the first prediction result is the prediction result closer to the first observation time window selected from the second prediction result and the third prediction result; and the first observation time window is the later observation time window in time among the observation time windows corresponding to the first prediction task and the second prediction task.

[0031] In this implementation, both prediction tasks can correspond to time-domain prediction tasks. The prediction periods of the two time-domain prediction tasks may overlap. Therefore, during the overlapping prediction periods, a single prediction result can be reported for both tasks, reducing air interface overhead. Furthermore, during the overlapping prediction periods, the terminal device can execute only one prediction task, while the other can be omitted, obtaining a single prediction result for both tasks and thus saving air interface resources.

[0032] In some implementations of the first or second aspect, the first prediction task and the second prediction task are periodic, or the first prediction task and the second prediction task are aperiodic.

[0033] In some implementations of the first or second aspect, one or more prediction time periods are determined based on information from the observation time windows and prediction time windows corresponding to the first and second prediction tasks, respectively.

[0034] In this implementation, when both prediction tasks are executed periodically, the prediction time periods of the two prediction tasks can be determined by calculating the length of the observation time window and the prediction time window of each of the two prediction tasks.

[0035] In some implementations of the first or second aspect, the CSI report includes the prediction results of the first prediction task for other prediction periods in the corresponding first prediction time window besides the one or more prediction periods mentioned above; or, the CSI report includes the prediction results of the second prediction task for other prediction periods in the corresponding second prediction time window besides the one or more prediction periods mentioned above.

[0036] In this implementation, if both prediction tasks are time-domain prediction tasks, the prediction results for other prediction periods besides the overlapping prediction periods also need to be reported.

[0037] Thirdly, a communication device is provided, which has the function of implementing the method in the first aspect or any possible implementation of the first aspect. The function can be implemented by hardware, by software, or by hardware executing corresponding software. The hardware or software includes one or more units corresponding to the above-described function.

[0038] Fourthly, a communication device is provided, the communication device having the function of implementing the method in the second aspect or any possible implementation of the second aspect. The function can be implemented by hardware, or by software, or by hardware executing corresponding software. The hardware or software includes one or more units corresponding to the above-described function.

[0039] Fifthly, a communication device is provided, comprising at least one processor configured to cause the communication device to execute a method of the first aspect or any possible implementation thereof; or execute a method of the second aspect or any possible implementation thereof; or execute a method of the third aspect or any possible implementation thereof. Optionally, the at least one processor is coupled to at least one memory for storing a computer program or instructions, and the at least one processor is configured to call and execute the computer program or instructions from the at least one memory, causing the communication device to execute a method of the first aspect or any possible implementation thereof; or execute a method of the second aspect or any possible implementation thereof. Optionally, the at least one processor may be included in the communication device or may be configured externally to the communication device. Optionally, the communication device further includes the at least one memory. Optionally, the communication device further includes a communication interface.

[0040] A sixth aspect provides a communication device, including a communication interface and a circuit. The communication interface is used to receive a signal to be processed and transmit the signal to the circuit. The circuit is used to process the signal to perform a method as described in the first aspect or any possible implementation thereof; or to perform a method as described in the second aspect or any possible implementation thereof. Optionally, the communication interface is also used to output the signal processed by the circuit. As an example, the communication interface may be a transceiver, hardware circuit, bus, module, pin, or other type of communication interface. The signal includes information and / or data. Optionally, the communication device may be a chip.

[0041] A seventh aspect provides a computer-readable storage medium storing computer program code or instructions that, when executed on a computer, cause the method of the first aspect or any possible implementation thereof to be implemented; or the method of the second aspect or any possible implementation thereof to be implemented.

[0042] Eighthly, a computer program product is provided, the computer program product comprising computer program code or instructions, which, when executed on a computer, cause the method in the first aspect or any possible implementation thereof to be implemented; or, as in the second aspect or any possible implementation thereof, the method to be implemented.

[0043] A ninth aspect provides a wireless communication system, including a communication device as described in the third aspect and a communication device as described in the fourth aspect. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of a communication system applicable to embodiments of this application.

[0045] Figure 2 This is another schematic diagram of a communication system applicable to embodiments of this application.

[0046] Figure 3 This is a schematic diagram of a possible application framework in a communication system.

[0047] Figure 4 This is a schematic diagram of another possible application framework in a communication system.

[0048] Figure 5 This is a schematic diagram of the prediction process for BM case 1.

[0049] Figure 6 This is a schematic diagram of the prediction process for BM case 2.

[0050] Figure 7 A schematic flowchart of the communication method 700 provided in this application.

[0051] Figure 8 This is a schematic diagram illustrating an application scenario applicable to an embodiment of this application.

[0052] Figure 9 An example of the communication method provided in this application.

[0053] Figure 10 This is a schematic diagram illustrating another application scenario applicable to embodiments of this application.

[0054] Figure 11Another example of the communication method provided in this application.

[0055] Figure 12 This is a schematic diagram illustrating another application scenario applicable to the embodiments of this application.

[0056] Figure 13 Another example of the communication method provided in this application.

[0057] Figure 14 A schematic block diagram of the communication device 1000 provided in this application.

[0058] Figure 15 A schematic block diagram of another communication device 1100 provided in this application.

[0059] Figure 16 A schematic structural diagram of the chip provided in this application.

[0060] Figure 17 A schematic diagram of the system architecture of the chip provided in this application. Detailed Implementation

[0061] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0062] The technical solutions provided in this application can be applied to various communication systems, such as 5th generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, and satellite communication systems. Furthermore, they can be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), as well as Internet of Things (IoT) communication systems, future communication systems, or integrated systems of multiple systems.

[0063] In a communication system, a network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. A network element can also be replaced by an entity, network entity, device, communication equipment, communication module, node, or communication node; this embodiment uses a network element as an example. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device.

[0064] Figure 1 This is a schematic diagram of a communication system applicable to embodiments of this application. For example... Figure 1 As shown, the communication system 100 may include at least one network device, such as... Figure 1 The network device 110 shown; the communication system 100 may also include at least one terminal device, such as Figure 1 The terminal devices 120 and 130 are shown. Network device 110 can communicate with the terminal devices (such as terminal devices 120 and 130) via a wireless link. Communication devices in this communication system, for example, network device 110 and terminal device 120, can communicate via multi-antenna technology.

[0065] Optionally, the communication system may also include at least one AI node.

[0066] Figure 2 This is another schematic diagram of a communication system applicable to embodiments of this application. Compared to Figure 1 Regarding the communication system 100 shown, Figure 2 The communication system 200 shown also includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building training datasets, training AI models, or performing inference on AI models.

[0067] In one implementation, network device 110 can send data related to AI model training to AI network element 140, which then 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 network element 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.

[0068] It should be understood that Figure 2 This explanation only uses the direct connection between AI network element 140 and network device 110 as an example. In other scenarios, AI network element 140 can also be connected to a terminal device. Alternatively, AI network element 140 can be connected to both network device 110 and a terminal device simultaneously. Alternatively, AI network element 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 AI network element and other network elements.

[0069] Alternatively, in another implementation, the AI ​​network element 140 can also be configured as a module in network devices and / or terminal devices, for example, configured in... Figure 1 In the network device 110 or terminal device shown.

[0070] It should be noted that, Figure 1 and Figure 2 This is a diagram for ease of understanding only. The communication system may also include other devices, such as wireless repeaters and / or wireless backhaul devices. Figure 1 and Figure 2 The figures are not shown. Furthermore, in practical applications, a communication system may include multiple network devices or multiple terminal devices. This application does not limit the number of network devices and terminal devices.

[0071] In the embodiments of this application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user apparatus. The terminal device can be a device that provides voice / data, such as a handheld device or vehicle-mounted device with wireless connectivity. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving vehicles, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0072] As an example and not a limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart 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 and smart jewelry for vital sign monitoring.

[0073] In this embodiment, the device used to implement the functions of the terminal device can be the terminal device itself, or any device capable of supporting the terminal device in implementing corresponding functions, such as a processor, circuit, or chip. This device can be configured in the terminal device or used in conjunction with the terminal device. In this embodiment, the terminal device is used as an example to illustrate the function of the terminal device, and this does not constitute a limitation on the solution of this embodiment.

[0074] The network device in this application embodiment can be a device for communicating with a terminal device, and can refer to a radio access network (RAN) node that connects the terminal device to the wireless network, such as a base station. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, a device that performs base station functions in D2D, V2X, and M2M communications, or a device that performs base station functions in future communication systems. A base station can support networks using the same or different access technologies. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technologies or equipment forms used in the network equipment.

[0075] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0076] In some deployments, the network devices mentioned in the embodiments of this application may be devices including CU, DU, or CU and DU, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes. For example, the network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0077] In some deployments, multiple RAN nodes collaborate to assist terminals 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, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0078] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0079] 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 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. 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.

[0080] In this embodiment, the device used to implement the functions of the network device can be a network device itself; it can also be a device capable of supporting the network device in implementing corresponding functions, such as a processor, circuit, or chip. This device can be configured within the network device or used in conjunction with the network device. In this embodiment, the network device is used as an example to illustrate the function of the network device, and this does not constitute a limitation on the solutions described in this embodiment.

[0081] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware or general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0082] Optionally, AI nodes can be deployed in one or more of the following locations within the communication system: access network devices, terminal devices, or core network devices, etc. Alternatively, AI nodes can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. AI nodes can communicate with other devices in the communication system, which can be, for example, one or more of the following: network devices, terminal devices, or core network elements, etc.

[0083] This application does not limit the number of AI nodes. For example, when there are multiple AI nodes, they can be divided based on function, such as different AI nodes being responsible for different functions.

[0084] Optionally, AI nodes can be independent devices, integrated into the same device to implement different functions, or they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the AI ​​nodes described above. AI nodes can also be called AI network elements or AI modules.

[0085] Figure 3 This is a schematic diagram of a possible application framework in a communication system. For example... Figure 3 As shown, network elements in a communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in the OAM, are equipped with one or more AI modules (for clarity, ...). Figure 3 (Only one is shown in the image). An access network node can be a single RAN node or can include multiple RAN nodes, such as a CU and a DU. The CU and / or DU can also be configured with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are configured in the CU-CP and / or CU-UP.

[0086] 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.

[0087] 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.

[0088] The network device can be a network device equipped with one or more AI modules. For example, the network device can be... Figure 3 The core network equipment, access network node (RAN node), or one or more devices in the OAM are shown. The AI ​​module can be... Figure 4 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, a cloud server, a core network device, or other network device.

[0089] Figure 4 This is a schematic diagram of another possible application framework in a communication system. For example... Figure 4 As shown, the communication system includes a RIC. For example, the RIC could be... Figure 1 The AI ​​module in the RAN node 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 in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0090] 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 nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or as data for inference.

[0091] Optionally, near real-time RIC can deliver inference results 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, near real-time RIC submits inference results to DU, and DU sends them to RU.

[0093] 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 nodes (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 the RAN nodes and / or terminals.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] To facilitate understanding of the embodiments of this application, the relevant technologies involved are described below.

[0098] To achieve beam management, methods such as layered scanning can be used to reduce beam scanning overhead. For example, a wide beam can be scanned first, followed by a narrow beam within the wide beam. Beam selection is primarily accomplished through reference signals and corresponding beam measurements. Reference signals mainly include the synchronization signal block (SSB) and the channel state information-reference signal (CSI-RS). The SSB is a cell broadcast signal, comprising the primary synchronization signal (PSS), secondary synchronization signal (SSS), physical broadcast channel (PBCH), and demodulation reference signal (DMRS). The SSB is transmitted periodically according to the cell configuration, and its function extends beyond beam management, also including initial access and time-frequency synchronization. Simply put, the SSB signal can be considered a wide-beam signal. Correspondingly, the CSI-RS signal is a UE-level signal; the network configures one or more CSI-RS signals for the UE based on actual conditions. Similarly, CSI-RS signals are not only used for beam management, but also for channel quality measurement, etc. CSI-RS signals can be understood as narrow-beam signals.

[0099] Traditional beam management systems perform a two-step beam scan during the serving beam selection phase: the first phase scans the SSB (i.e., scans wide beams), in which the UE measures and reports the reference signal received power (RSRP) of the SSB beam to the network side; the second phase involves the network side selecting the SSB beam with the largest RSRP based on the RSRP reported by the UE, and configuring the CSI-RS signal for the terminal device to scan the narrow beams covered by the SSB beam with the largest RSRP to determine the optimal beam.

[0100] In recent years, artificial intelligence (AI) technology has played a significant role in beam management, particularly in reducing beam scanning overhead. Typically, the AI ​​model takes the received power of a wide beam or a sparsely scanned narrow beam measured by the UE as input. The AI ​​model infers and outputs K candidate narrow beams, referred to as the Top-K candidate beams. For example, it can output the RSRP value or ID of the beam set. The network side performs a scan based on the Top-K candidate beams to ultimately determine the optimal beam, where K is a positive integer equal to or greater than 1. The AI ​​model can typically be deployed on either the UE side or the network side.

[0101] CSI-RS resource configuration and CSI report feedback both support three configuration modes: periodic, semi-static, and aperiodic. In periodic CSI-RS configuration, the network side configures the CSI transmission period (e.g., every n slots, where n is a positive integer) and offset (symbol offset within the period) and instructs the UE, then transmits according to the configured period and offset. In semi-static CSI-RS configuration, the network side configures the CSI transmission period and offset and instructs the UE, but whether or not transmission actually occurs is determined by the medium access control-control element (MAC CE). The MAC CE can activate or deactivate CSI-RS transmission and notify the UE. In aperiodic CSI-RS configuration, the network side notifies the UE of each CSI-RS transmission via downlink control information (DCI) signaling. Furthermore, aperiodic CSI-RS configuration also supports configuring the transmission of multiple CSI-RS resources at once.

[0102] Currently, AI beam management (BM) is mainly applied in two aspects: spatial prediction and temporal prediction, which can be referred to as BM case 1 and BM case 2, respectively.

[0103] Figure 5 This is a schematic diagram of the prediction process for BM case 1. The input to the AI ​​model is the beam information (usually RSRP value) of a specific pattern scanned at a certain time. The set of this beam information is called set B. After prediction by the AI ​​model, the complete set of output beams is called set A. The top-K beams and their related information are selected and reported to the network side.

[0104] Figure 6 This is a schematic diagram of the prediction process in BM case 2. A sliding time window is used to collect input information from the AI ​​model, such as... Figure 6The RSRP of the set B from time (t-N+1) to time (t) is shown. Time (t-N+1) to time (t) corresponds to the observation time window T1. The AI ​​model processes the input information and outputs the prediction result of the future time window. The future time window is as follows: Figure 6 The time interval from (t+1) to (t+M) shown is also represented as time window T2. If the AI ​​model is a regression model, the prediction result is set A; if the AI ​​model is a classification model, the prediction result is the IDs of the top-K beams. Accordingly, the terminal device ultimately selects the top-K beams and their related information, or selects the beam IDs of the top-K beams to report to the network side. top-K(t+1) represents the prediction result at time (t+1), which is the top-K beams output by the AI ​​model.

[0105] The current AI model supports two prediction tasks: BMcase1 and BMcase2. When multiple tasks are performed simultaneously, the gNB usually independently instructs the UE to perform predictions for BMcase1 and BMcase2 by configuring CSI-RS resources. The prediction tasks do not affect each other, and each task reports its prediction results.

[0106] As mentioned in the background section, when multiple cases are involved in prediction tasks in parallel, continuing to use the mechanism of reporting the prediction results of each prediction task separately will result in significant air interface overhead and waste of air interface resources.

[0107] This application addresses scenarios involving multiple parallel prediction tasks, such as BMcase1 and BMcase2 described above, and proposes a scheme for reducing air interface overhead by merging and reporting (or "deduplication" or "de-redundancy" reporting) for the UE-side AI model. In this embodiment, merged reporting refers to reporting only one prediction result from multiple identical or similar prediction results, rather than reporting all of them. Assuming the reported prediction result is obtained based on the first prediction task among multiple prediction tasks, this prediction result is associated with all other prediction tasks in the CSI report. For the network side, after receiving the CSI report, it retrieves the prediction result and its association with other prediction tasks, thus obtaining the prediction results of each of these multiple prediction tasks. In other words, this single prediction result represents the prediction results of all multiple prediction tasks. This achieves the reporting of a single prediction result for multiple prediction tasks, thereby reducing air interface overhead.

[0108] Optionally, this application uses AI model-based prediction tasks as an example for illustration. In other AI-based training or inference tasks, if one network element needs to send information and / or data of multiple tasks to another network element, the information and / or data of multiple tasks can also be merged and sent based on the technical solution provided in this application. For example, information and / or data of one task can be sent and associated with other tasks, thereby realizing the transmission of multiple tasks in one go, so as to save air interface overhead.

[0109] In the embodiments of this application, the time period or time unit can be understood as any one or more of time slots, subframes, frames, and OFDM symbols, or a longer time period with one of these as the granularity. For example, the prediction time period corresponding to prediction task A can represent the time slot, subframe, frame, or OFDM symbol corresponding to prediction task A, or a time period with time slots, subframes, frames, or OFDM symbols as the granularity, such as two time slots or four time slots as a time period or time unit, etc., without limitation.

[0110] In this embodiment of the application, it is assumed that the input codebook (referred to as set B) and the output full codebook (referred to as set A) of the AI ​​model used for each prediction task are the same.

[0111] The technical solution provided in this application is described in detail below.

[0112] Figure 7 This is a schematic flowchart of the communication method 700 provided in this application. Method 700 relates to network devices and terminal devices. Optionally, the communication devices (e.g., network devices or terminal devices) involved in method 700 can also be replaced by means for these communication devices. For example, the network device can be replaced by a first means, which can be a chip, processor, circuit, or AI entity serving the network device applied to communication. The AI ​​entity can be deployed on the network device or outside the network device. As an example, the AI ​​entity can be an over-the-top (OTT) server or a cloud server. The terminal device can also be replaced by a corresponding means, which will not be described in detail here. The following embodiments use network devices and terminal devices as examples for description.

[0113] 710. The terminal device determines the first prediction result based on the first prediction task and the second prediction task.

[0114] The first prediction result is obtained based on the first prediction task and is associated with the second prediction task; or, the first prediction result is obtained based on the second prediction task and is associated with the first prediction task.

[0115] As mentioned above, this application mainly relates to the scenario of multiple prediction tasks, where the first prediction task and the second prediction task can refer to two different prediction tasks. Furthermore, this application uses only two prediction tasks as an example in its embodiments; based on the same concept, the solution in this application's embodiments is also applicable when there are more than two prediction tasks. The two prediction tasks can be two different prediction tasks of the same type, such as two different temporal domain prediction tasks, or two prediction tasks of different types, such as a spatial domain prediction task and a temporal domain prediction task.

[0116] In the embodiments of this application, a first prediction result is associated with a prediction task, indicating that the first prediction result can be used to characterize the prediction result of that prediction task. Furthermore, the first prediction result is obtained based on another prediction task. For example, if the first prediction result is obtained based on a first prediction task and is associated with a second prediction task, it means that the first prediction task is a prediction result obtained based on the first prediction task, and the first prediction task can be used to characterize the prediction result of the second prediction task. Alternatively, if the first prediction result is obtained based on a second prediction task and is associated with a first prediction task, it means that the first prediction task is a prediction result obtained based on the second prediction task, and the first prediction result can be used to characterize the prediction result of the first prediction task. In other words, one prediction result reflects the prediction results of two prediction tasks.

[0117] In one implementation, the terminal device obtains a second prediction result based on a first prediction task, and obtains a third prediction result based on the second prediction task. The terminal device then obtains the first prediction result based on the second and third prediction results. For example, the first prediction result can be one of the second and third prediction results. Whether the first prediction result is the second or the third prediction result depends on the specific circumstances of the first and second prediction tasks, which will be explained in detail below.

[0118] In another implementation, the terminal device can determine the first prediction result based on the result of a prediction task.

[0119] For example, the terminal device obtains a second prediction result based on a first prediction task. Based on relevant information about the first and second prediction tasks, such as their respective observation periods and prediction periods, the terminal device determines that the second prediction result can be used to characterize the prediction result of the second prediction task. In this case, the second prediction result is the first prediction result. As another example, the terminal device obtains a third prediction result based on a second prediction task. Based on relevant information about the first and second prediction tasks, the terminal device determines that the third prediction result can be used to characterize the prediction result of the first prediction task. In this case, the third prediction result is the first prediction result. In this implementation, the terminal device obtains the prediction result of one of the two prediction tasks as the first prediction result, without needing to obtain the prediction result of the other prediction task.

[0120] In summary, when the prediction result obtained based on one prediction task can characterize the prediction result of another prediction task, the prediction result is the first prediction result mentioned in the embodiments of this application.

[0121] Optionally, a prediction result (e.g., the first prediction result mentioned above) can be used to characterize the prediction result of a prediction task, and may include: a prediction result can be used to characterize the prediction result of a prediction task corresponding to one prediction time period, or to characterize the prediction result of a prediction task corresponding to multiple prediction time periods, without limitation. When the prediction result is used to characterize the prediction result of a prediction task corresponding to one prediction time period, the prediction result can be associated with the identifier of that prediction time period; when the prediction result is used to characterize the prediction result of a prediction task corresponding to multiple prediction time periods, the prediction result can be associated with the identifiers of multiple prediction time periods, to indicate that the prediction result of the prediction task corresponding to these multiple prediction time periods can all be characterized by this one prediction result.

[0122] 720. The terminal device sends a CSI report, which includes the first prediction result.

[0123] As explained in step 710, when a prediction result obtained from one prediction task can also be used to characterize the prediction result of another prediction task, the CSI report sent by the terminal device to the network side can include one prediction result, rather than including separate prediction results for each of the two prediction tasks. In other words, the first prediction result in the CSI report indicates that the first prediction result is the prediction result obtained by the terminal device performing a certain prediction task, and the first prediction result can also serve as (or characterize) the prediction result of another associated prediction task.

[0124] Based on the technical solution of this application, when multiple prediction tasks are executed by a terminal device, the terminal device may only report one prediction result based on these multiple prediction tasks. This single prediction result is obtained from executing one of the multiple prediction tasks, but it can reflect or characterize the prediction results of these multiple prediction tasks. Therefore, compared to each prediction task reporting its own prediction result separately, the air interface overhead of the terminal device sending CSI reports can be reduced.

[0125] For multiple prediction tasks to report a prediction result, these multiple prediction tasks need to meet certain conditions. Depending on the different prediction tasks, the conditions that these multiple prediction tasks need to meet will also be different. The following is a detailed explanation with examples.

[0126] As mentioned above, current applications of AI in beam management mainly involve spatial and temporal prediction. Therefore, the following embodiments use these two types of prediction as examples. When AI can be applied to more types of prediction in the future, the technical solutions in the embodiments of this application can also be applied to similar technical problems.

[0127] For the sake of brevity, the following embodiments will use spatial prediction as the first prediction task and temporal prediction as the second prediction task as examples.

[0128] Example 1

[0129] In scenarios involving the simultaneous issuance of the first and second prediction tasks, the following will be discussed in conjunction with... Figure 8 Please provide an explanation.

[0130] Figure 8 This is a schematic diagram illustrating an application scenario applicable to embodiments of this application. In this scenario, the network device simultaneously sends two prediction tasks to the terminal device. Although the prediction time periods corresponding to these two prediction tasks are not exactly the same, they are relatively close. This means that the two prediction tasks have a certain probability of outputting similar prediction results. Therefore, the method provided in this application can be considered for reporting prediction results to reduce the air interface overhead of reporting. For example... Figure 8 In the scenario, at a certain moment in time slot t, the UE receives instructions from the network device to execute prediction task 1 and prediction task 2. After receiving the instructions, the UE begins executing prediction task 1 and prediction task 2. Prediction task 1, after obtaining the input information from the AI ​​model, performs model prediction and outputs its prediction result. Prediction task 2, after an observation time window, performs model prediction and outputs its prediction result. It can be seen that the prediction time periods of prediction task 1 and prediction task 2 are not exactly the same. However, if the prediction time window of prediction task 2 is close to the prediction time period of prediction task 1, the two prediction tasks may output the same or similar prediction results.

[0131] Figure 9 An example of the communication method provided in this application.

[0132] 301. UE reporting capability information.

[0133] Capability information is used to indicate the types of prediction tasks supported by the AI ​​model deployed on the UE side. As an example, if the AI ​​model deployed on the UE side supports both spatial and temporal prediction, the capability information reported by the UE can indicate both types of prediction simultaneously.

[0134] Optionally, the UE can also send a request message. The request message indicates to the UE that it can begin executing the prediction task. Thus, the network device can issue prediction tasks supported by the AI ​​model on the UE side based on the UE's request message, for example, issuing multiple prediction tasks. These multiple prediction tasks can be issued synchronously or asynchronously.

[0135] Step 301 is an optional step. For example, when the UE has reported capability information to the network side, the network device saves the UE's capability information. Before subsequent AI-based prediction tasks are issued, the UE does not need to report its capability information every time. Unless the type of prediction task supported by the UE changes, the UE can indicate the changed capability information to the network device.

[0136] 302. The network device configures reference signal resources, executes instructions for the first prediction task and the second prediction task, and sets a similarity threshold between the prediction results of the first prediction task and the prediction results of the second prediction task.

[0137] Optionally, the configuration of the reference signal resources, the instructions for executing the prediction task, and the similarity determination threshold can be configured through one or more signaling instructions, without limitation. The instructions for executing the first and second prediction tasks can be one or two instructions, also without limitation.

[0138] It should be understood that the network device sets a similarity threshold to determine whether the prediction results of the first and second prediction tasks are similar or to what extent they are similar. The setting of this similarity threshold varies depending on the situation. For example, if the AI ​​model on the UE side is a classification model, it means that the AI ​​model outputs the top-K candidate beams. In this implementation, the network device sets a threshold M. If the overlap of the top-K beams predicted by the first and second prediction tasks is greater than M, then the prediction results of the first and second prediction tasks can be considered similar; otherwise, they are not similar. It should be understood that the number of the top-K candidate beams for each of the two prediction tasks can be equal or unequal. For example, both prediction tasks may have K optimal candidate beams. Another example is that K for the first prediction task is set to K1, and K for the second prediction task is set to K2, without limitation. As another example, if the AI ​​model on the UE side is a regression model, then the prediction result output by the AI ​​model is the RSRP value of the full codebook, i.e., setA. In this implementation, the network device sets a threshold H. The terminal device calculates the overall root mean squared error (RMSE) of the set A output by the first prediction task and the second prediction task. If it is less than the threshold H, the prediction results of the two prediction tasks can be determined to be similar; otherwise, they are not similar.

[0139] Considering that the observation window length of the second prediction task is configurable, while the first prediction task typically performs predictions at the task issuance time, the longer the observation window of the second prediction task, the farther the first output result (i.e., the first prediction result) within the second prediction task's prediction window is from the output time of the first prediction task (i.e., the time when the first prediction task outputs its prediction result). This reduces the likelihood of similarity between the two prediction tasks and simplifies the necessity of similarity assessment. To avoid unnecessary similarity checks, we can set the terminal device to not perform similarity assessments on the prediction results of the two prediction tasks when the observation window length of the second prediction task is equal to or greater than W, where W is an integer. For example, W equals 4.

[0140] It should be noted that the second prediction task is a time-domain prediction task, typically corresponding to an observation time window (also called a measurement time window or input time window) and a prediction time window (also called an output time window). The observation time window refers to the time interval during which the terminal device performs beam scanning to acquire input information for the AI ​​model. For example, within the observation time window, the UE measures the reference signal configured by the network device. This reference signal corresponds to a subset of all beams, hence a sparse beam. After completing the reference signal scan, the UE obtains measurement information corresponding to the sparse beam, such as the RSRP of the sparse beam. This measurement information serves as the input to the AI ​​model deployed on the UE side. Within the prediction time window, the AI ​​model outputs a prediction result based on the measurement information of the sparse beam. As an example, the observation time window can include one or more time periods (which can be called observation periods), and the prediction time window can include one or more time periods (which can be called prediction periods). These one or more observation periods and these one or more prediction periods can be in one-to-one correspondence. For example, according to the chronological order, the prediction result corresponding to the first prediction period within the prediction time window, or the first output result within the prediction time window, is obtained based on the input information obtained in the first observation period; the prediction result corresponding to the second prediction period is obtained based on the input information obtained in the second observation period, and so on.

[0141] 303. The network device sends reference signal resources for the UE to perform reference signal resource measurements.

[0142] Alternatively, the reference signal resource can also be called a beam, or beam resource. The process by which the UE measures the reference signal resource can also be called beam scanning.

[0143] 304. The UE performs beam scanning to obtain the first set of measurement information.

[0144] The first measurement information set consists of measurement information of the scanned beam obtained by the UE during the first observation period corresponding to the first prediction task, such as RSRP. It should be understood that in Example 1, the first and second prediction tasks start at the same time, and the first prediction task is a spatial prediction task while the second prediction task is a temporal prediction task. Therefore, the first observation period corresponding to the first prediction task is an observation period within the observation time window corresponding to the second prediction task. Thus, the measurement information in the first measurement information set is both the input information of the AI ​​model for the first prediction task and a part of the input information of the AI ​​model for the second prediction task.

[0145] 305. The UE obtains the prediction result corresponding to the first prediction task based on the AI ​​model and the first set of measurement information.

[0146] The UE uses the measurement information contained in the first measurement information set as input to the AI ​​model to make predictions and obtain the prediction result corresponding to the first prediction task. To distinguish it from the first prediction result mentioned above, it is referred to as the second prediction result.

[0147] 306. The UE performs beam scanning to obtain the second set of measurement information.

[0148] As described in step 304, the UE performs beam scanning during the first prediction period to obtain a portion of the input information for the AI ​​model of the second prediction task. In step 306, the UE performs beam scanning during the remaining time period within the first prediction period to obtain another portion of the input information for the AI ​​model of the second prediction task, namely the second measurement information set. Therefore, the sum of the first and second measurement information sets constitutes the input information for the AI ​​model of the second prediction task. Furthermore, the reference signal resources used for the first and second prediction tasks can be the same. The first prediction task measures the reference signal resources during the first observation period, and the second prediction task measures the reference signal resources during each observation period within the prediction time window.

[0149] 307. The UE obtains the prediction results for the second prediction task based on the AI ​​model, the first measurement information set, and the second measurement information set.

[0150] As mentioned above, the prediction time window of the second prediction task may include one or more prediction periods, and each prediction period outputs a prediction result, resulting in one or more prediction results. The following example illustrates how multiple prediction periods correspond one-to-one with multiple prediction results.

[0151] 308. The UE performs a similarity test on the prediction results of the first prediction task and the prediction results output by the second prediction task within the prediction time window.

[0152] As an example, the UE performs similarity determination on the second prediction result corresponding to the first prediction task and the multiple prediction results corresponding to the second prediction task one by one. If the second prediction result is similar to one of the multiple prediction results corresponding to the second prediction task, then the second prediction result and the aforementioned prediction result are deduplicated. Specifically, prediction results farther from the observation time window of the second prediction task are discarded, while prediction results closer to the observation time window of the second prediction task are retained. In addition, an association is established between the prediction tasks corresponding to the retained prediction results and the discarded prediction results. For example, a task identifier can be configured for each of the two prediction tasks, and the task identifiers corresponding to the retained prediction results and the discarded prediction results can be associated through the task identifiers. For example, if the second prediction result corresponding to the first prediction task is farther from the observation time window of the second prediction task, then the second prediction result corresponding to the first prediction task is discarded, while the third prediction result corresponding to the second prediction task, which is closer to the observation time window of the second prediction task, is retained, and the retained third prediction result is associated with the first prediction task. It should be understood that in this example, a prediction result of the second prediction task that is similar to the second prediction result is actually a prediction result corresponding to a certain prediction period within the prediction time window corresponding to the second prediction task. For ease of description, in this embodiment, the prediction result corresponding to a certain prediction period obtained based on the second prediction task, used for similarity determination with the second prediction result of the first prediction task, is called the third prediction result, and the prediction period corresponding to the third prediction result is called the second prediction period, to distinguish it from the first prediction period mentioned above. Thus, the terminal device performs a similarity determination on the second prediction result corresponding to the first prediction task and the third prediction result corresponding to the second prediction task. If they are similar, the prediction result closer to the prediction time window of the second prediction task is retained, while the other is discarded. Further, the retained prediction result is associated with the prediction task corresponding to the discarded prediction result. For example, if the second prediction result is retained, it is associated with the second prediction task; if the third prediction result is retained, it is associated with the first prediction task. The third prediction result is a prediction result obtained corresponding to any prediction period within the prediction time window corresponding to the second prediction task. As an example, suppose that the prediction time window corresponding to the second prediction task includes multiple prediction results, denoted as prediction result 1, prediction result 2, ..., prediction result M.If the second prediction result corresponding to the first prediction task is similar to a prediction result x corresponding to the second prediction task, and prediction result x is further away from the observation time window of the second prediction task, then prediction result x is discarded, while the second prediction result corresponding to the first prediction task is retained. Simultaneously, the second prediction result is associated with the second prediction task; for example, the second prediction result is associated with the second prediction task. A prediction period x can also be labeled to indicate that the second prediction result is associated with the prediction result x corresponding to the prediction period x of the second prediction task. In one example, the third prediction result can be the prediction result corresponding to the first prediction period within the prediction time window.

[0153] 309. Based on the similarity determination results of the prediction results of the first prediction task and the prediction results of the second prediction task, send a CSI report.

[0154] In one possible scenario, if the forecast result of the first forecast task is similar to a certain forecast result of the second forecast task, the CSI report will include the retained forecast result and its correlation with the other forecast task. Furthermore, forecast results for other forecast periods of the second forecast task will be reported.

[0155] In another possible scenario, if the prediction results of the first prediction task and the second prediction task are not similar, the UE shall report the prediction results of the first prediction task and the second prediction task separately.

[0156] In Example 1, by using similarity determination, if the prediction results of the first prediction task and the second prediction task are similar, a single prediction result report from the terminal device can correspond to two prediction tasks, reducing the air interface overhead caused by duplicate transmission of prediction results. Furthermore, if the network device instructs two prediction tasks with a single command, it can save the overhead of reference signals. In addition, the similarity determination mechanism for prediction results from different prediction tasks can also achieve a balance between efficiency and accuracy in prediction result reporting.

[0157] Compared to the method where the UE reports the prediction results separately when the network simultaneously issues the first and second prediction tasks, the technical solution of this application adds a similarity determination mechanism for the prediction results after completing the AI ​​model-based prediction, judging potentially similar prediction results. Similar prediction results are then merged and reported, thereby reducing air interface transmission overhead.

[0158] Example 2

[0159] The scenario involving the asynchronous parallelism of the first and second prediction tasks will be explained in conjunction with section 10 below.

[0160] Figure 10This is a schematic diagram illustrating another application scenario applicable to embodiments of this application. For example... Figure 10 When the UE executes the second prediction task, it receives the first prediction task from the network device. In this scenario, the prediction time periods of the two prediction tasks may be the same. If the UE detects the first prediction time period corresponding to the first prediction task within the prediction time window corresponding to the second prediction task, it will retain one of the two prediction results obtained in the same prediction time period and discard the other when configuring the CSI report, based on the similarity determination result. The UE will then indicate the association between the retained prediction result and the other prediction task to the network device.

[0161] Figure 11 Another example of the communication method provided in this application.

[0162] 501. UE reporting capability information.

[0163] Please refer to the explanation of step 301, which will not be repeated here.

[0164] 502. Configure the network device with the second prediction task and its corresponding reference signal resources, denoted as reference signal resource 2.

[0165] The configuration of the second prediction task by the network device may include the network device issuing an instruction to the UE to execute the second prediction task, as well as relevant information about the second prediction task.

[0166] 503. The network device sends reference channel resource 2 for the UE to perform beam scanning corresponding to the second prediction task.

[0167] 504. The UE performs beam scanning (i.e., measurement reference signal resource 2) during each observation period of the observation time window corresponding to the second prediction task to obtain the first measurement information set.

[0168] The first set of measurement information is the measurement information of the scanned beam obtained during beam scanning within the observation time window corresponding to the second prediction task, such as the RSRP of the scanned beam. See step 304 for further details.

[0169] 505. The UE enters the prediction phase of the second prediction task.

[0170] Step 505 indicates that after the UE obtains the input information of the AI ​​model, it moves from the beam scanning phase to the prediction phase. In other words, the prediction phase begins.

[0171] 506. Configure the network device with the first prediction task and its corresponding reference signal resources, denoted as reference signal resource 1.

[0172] 507. Network device transmits reference signal resource 1.

[0173] The UE performs a measurement of reference signal resource 1 and outputs the prediction result of the first prediction task during the first prediction period. The first prediction period of the first prediction task is denoted as period (t).

[0174] It is evident that the triggering instruction for the first prediction task (i.e., the instruction instructing the UE to execute the first prediction task) is given after the start of the prediction phase of the second prediction task and before its end.

[0175] 508. The UE records the first prediction period corresponding to the first prediction task, in order to Figure 10 For example, the prediction time period corresponding to the first prediction task corresponds to time period (t). The UE retrieves the timestamp information of the prediction results of the second prediction task. If it contains time period (t), then the prediction results obtained by the first prediction task in time period (t) and the prediction results of the second prediction task corresponding to time period (t) that are further away from the observation time window of the second prediction task are discarded, while the prediction results that are closer to the observation time window of the second prediction task are retained. In addition, the retained prediction results are associated with another prediction task. Here, the other prediction task refers to the prediction task corresponding to the discarded prediction results. It should be understood that retrieving the timestamp information of the prediction results of the second prediction task is equivalent to retrieving whether the prediction time window of the second prediction task contains the first prediction time period, because each prediction result of the second prediction task corresponds to a timestamp information indicating the prediction time period of that prediction result.

[0176] As an example, after obtaining the prediction results of the first prediction task and the second prediction task, the UE can compare them and discard prediction results that are further away from the observation time window of the second prediction task. As another example, during the execution of the prediction phase of the second prediction task, if the UE receives an instruction to execute the first prediction task, and retrieves the timestamp information of the prediction results of the second prediction task, and finds a prediction time period corresponding to the first prediction time period of the first prediction task, such as the second prediction time period, it can also skip executing the first prediction task and directly retain the prediction results of the second prediction task corresponding to the second prediction time period, while associating the retained prediction results with the first prediction task.

[0177] As can be seen, in this embodiment, the triggering timing of the first prediction task needs to be after the start of the scanning phase of the second prediction task and before the end of the prediction phase of the second prediction task, so that it is possible to correspond to the same time period. In step 508, if a prediction result for time period (t) is found in the second prediction task, the UE does not execute the first prediction task, which can further reduce additional overhead.

[0178] 509. The second prediction task is complete.

[0179] 510. The UE sends a CSI report, which includes the retained prediction results and the correlation between the retained and discarded prediction results and the corresponding prediction tasks.

[0180] In this embodiment, when the prediction time period is the same, the reporting of one prediction result corresponds to two prediction tasks, reducing the air interface overhead caused by repeatedly transmitting prediction results. In addition, the first prediction task omits the AI ​​model-based prediction process when it detects the same time corresponding to the second prediction task, further saving additional overhead.

[0181] Example 3

[0182] Scenarios involving the simultaneous execution of two second prediction tasks (whether they are deployed simultaneously or not) are discussed below. Figure 12 Please provide an explanation.

[0183] Figure 12 This is a schematic diagram illustrating another application scenario applicable to the embodiments of this application. For example... Figure 12 In one possible scenario, if both second prediction tasks are based on periodic or semi-persistent reference signals, such as periodic / semi-persistent CSI RS, and are triggered and executed periodically, then if the observation time windows and prediction task windows of the two second prediction tasks differ in length, the two second prediction tasks may have overlapping prediction periods. Figure 12 For example, the observation and prediction time windows of the second prediction task 1 are each one time unit, such as one time slot, and they are performed alternately; while the observation and prediction time windows of the second prediction task 2 are each two time units, such as two time slots. The terminal device can calculate that the prediction results of the two second prediction tasks will overlap every four time units. In another possible scenario, if both second prediction tasks are triggered by aperiodic CSI RS, for example, the method described in Example 2 above can be used to determine whether deduplication and reporting are permissible after detecting the repetition period.

[0184] Figure 13 Another example of the communication method provided in this application.

[0185] 601. UE reporting capability information.

[0186] Refer to step 301, which will not be repeated here.

[0187] 602. Configure the network device with the second prediction task 1 and its corresponding reference signal resources, denoted as reference signal resource 1.

[0188] 603. Network device transmits reference signal resource 1.

[0189] 604. The UE scans reference signal resource 1 within the observation time window of the second prediction task 1 to obtain the measurement information of reference signal resource 1 for each observation period, such as RSRP. The measurement information of reference signal resource 1 is also the input information of the AI ​​model of the second prediction task 1. The ellipsis after step 604 indicates that the observation phase includes the scanning of reference signal resource 1 for multiple observation periods.

[0190] 605. The UE enters the prediction phase of the second prediction task 1.

[0191] 606. Configure the network device with the second prediction task 2 and its corresponding reference signal resources, denoted as reference signal resource 2.

[0192] 607. Network device transmits reference signal resource 2.

[0193] 608. The UE scans reference signal resource 2 within the observation time window of the second prediction task 2 to obtain the measurement information of reference signal resource 2 for each observation period of the second prediction task 2. The measurement information of reference signal resource 2 is also the input information of the AI ​​model of the second prediction task 2.

[0194] 609. The UE enters the prediction phase of the second prediction task 2.

[0195] 610. The UE calculates the overlapping prediction period of the two second prediction tasks based on the observation time window information and prediction time window information of each task. There may be one or more overlapping prediction periods.

[0196] It should be understood that when both second prediction tasks are executed periodically, the overlapping prediction period occurs once every period T. For example, in... Figure 12 In this context, the overlap period T is 4 time units. The calculation period T is limited to the case where two second prediction tasks are executed periodically. If at least one second prediction task is not executed periodically, the method of retrieving overlapping prediction periods (or retrieving the timestamp information of the prediction results) in Example 2 is still used to query whether there are overlapping prediction periods between the two second prediction tasks, so as to deduplicate the prediction results of the two second prediction tasks during the overlapping prediction time.

[0197] 611. During the overlapping prediction period, the UE performs a similarity determination on the prediction results of the two prediction tasks. If the determination result is similar, the prediction results that are further away from the first prediction time window are discarded, while the prediction results that are closer to the first observation time window are retained. Here, the first prediction time window is the later observation time window in time among the observation time windows corresponding to the two second prediction tasks.

[0198] It should be understood that, in this example, since both prediction tasks are time-domain predictions, each second prediction task may correspond to a set of prediction results, containing one or more prediction results, during the overlapping period. Therefore, compared to the other embodiments described above, in this embodiment, what is discarded (or retained) is the set of prediction results corresponding to one of the second prediction tasks during the overlapping period.

[0199] 612. The UE completes the prediction task, that is, it completes two second prediction tasks.

[0200] 613. The UE sends a CSI report to the network device. The CSI report includes a set of prediction results for the overlapping period. This set of prediction results is based on one of two second prediction tasks, while a set of prediction results from the other prediction task during the overlapping period is discarded. The retained set of prediction results is associated with the second prediction task corresponding to the discarded set of prediction results. In addition, the CSI report also includes prediction results from these two second prediction tasks for other prediction periods outside the overlapping period.

[0201] In Example 3, when the prediction time periods corresponding to the prediction results overlap, the terminal device performs deduplication processing on the prediction results within the overlapping prediction time periods. Specifically, if the prediction results of two second prediction tasks are similar within the overlapping prediction time periods, the prediction result obtained by one of the second prediction tasks is discarded. Thus, within the overlapping prediction time periods, a prediction result is reported for both prediction tasks, reducing the air interface overhead caused by repeatedly transmitting the same or similar prediction results.

[0202] Alternatively, Example 3 uses the example of obtaining the prediction results of two prediction tasks separately and then deduplicating the prediction results. In another alternative, after obtaining the configuration information of the two second prediction tasks, the UE already has the information of the observation time window and prediction time window of each of the two second prediction tasks, and can thus determine the overlapping prediction periods through calculation. During the subsequent execution of the second prediction tasks, within each overlapping prediction period, the UE can omit the prediction process based on the AI ​​model corresponding to a certain prediction task. That is, in the overlapping prediction period, the UE only needs to perform the model inference process for one second prediction task, and the obtained prediction result is reported as the retained prediction result, while being associated with the other second prediction task that does not perform inference. In this way, additional overhead can be further saved. Introducing an overlapping period T in the scenario where prediction tasks are executed periodically makes deduplication reporting more convenient and efficient.

[0203] Furthermore, in the above embodiments or examples, the CSI report includes the combined prediction results of multiple prediction tasks. For other prediction results from these multiple prediction tasks that cannot be combined, the terminal device will also report them to the network device. As an example, for prediction results from each prediction task that cannot be combined, a separate CSI report can be sent for each prediction task. The CSI report for each prediction task can be configured by the network side.

[0204] The communication method provided in this application has been described in detail above. The corresponding communication device is described below.

[0205] Figure 14 A schematic block diagram of the communication device 1000 provided in this application. Figure 14 The communication device 1000 may include a processing module 1001 and a communication module 1002. The communication device 1000 may be a terminal device, or a communication device applied to or used in conjunction with a terminal device to achieve the corresponding functions of the terminal device, such as a processor, chip, circuit, or AI entity. Alternatively, the communication device 1000 may be a network device, or a communication device applied to or used in conjunction with a network device to achieve the corresponding functions of the network device, such as a processor, chip, circuit, or AI entity.

[0206] The communication module can also be called a transceiver module, transceiver, transceiver unit, or transceiver device. The processing module can also be called a processor, processing board, processing unit, or processing device. Optionally, the communication module is used to perform the sending and receiving operations on the terminal device side or network device side in the above method. The device in the communication module that implements the receiving function can be regarded as a receiving unit, and the device in the communication module that implements the sending function can be regarded as a sending unit. That is, the communication module includes a receiving unit and a sending unit.

[0207] When the communication device 1000 is applied to a terminal device, the processing module 1001 can be used to implement... Figures 7-13 The communication module 1002 can be used to implement the processing functions of the terminal device in each embodiment. Figures 7-10 The transmit and receive functions of the terminal device described in each embodiment.

[0208] For example, the processing module 1001 is configured to: determine a first prediction result based on a first prediction task and a second prediction task, wherein the first prediction result is obtained based on the first prediction task and is associated with the second prediction task; or, the first prediction result is obtained based on the second prediction task and is associated with the first prediction task; the communication module 1002 is configured to: send a Channel State Information (CSI) report, wherein the CSI report contains the first prediction result.

[0209] For example, the processing module 1001 is used to: obtain a second prediction result based on the first prediction task; obtain a third prediction result based on the second prediction task; and obtain the first prediction result based on the second prediction result and the third prediction result.

[0210] For example, the processing module 1001 is used to: determine the similarity between the second prediction result and the third prediction result when the length of the prediction time window is less than or equal to a set threshold. The prediction time window can be referred to the description in the foregoing method embodiments.

[0211] For example, the processing module 1001 is configured to: discard the third prediction result obtained by the second prediction task in the second prediction period when the first prediction result is the second prediction result obtained by the first prediction task in the first prediction period; or, discard the second prediction result obtained by the first prediction task in the first prediction period when the first prediction result is the third prediction result obtained by the second prediction task in the second prediction period.

[0212] When the communication device 1000 is applied to a network device, the processing module 1001 can be used to implement... Figures 7-13 In each embodiment, the network device's processing functions are described, and the communication module 1002 can be used to implement... Figures 7-13 The transmit and receive functions of the network device in each embodiment.

[0213] For example, the communication module 1002 is configured to: receive a Channel State Information (CSI) report, the CSI report containing a first prediction result, the first prediction result being obtained based on the first prediction task and associated with the second prediction task; or, the first prediction result being obtained based on the second prediction task and associated with the first prediction task.

[0214] For example, processing module 1001 determines the prediction results corresponding to the first prediction task and / or the second prediction task based on the CSI report.

[0215] Furthermore, it should be noted that the aforementioned communication module and / or processing module can be implemented through virtual modules. For example, the processing module can be implemented through software functional units or virtual devices, and the communication module can be implemented through software functions or virtual devices. Alternatively, the processing module or communication module can also be implemented through physical devices. For example, if the device is implemented using a chip / chip circuit, the communication module can be an input / output circuit and / or a communication interface, performing input operations (corresponding to the aforementioned receiving operation) and output operations (corresponding to the aforementioned sending operation); the processing module is an integrated processor, microprocessor, or integrated circuit.

[0216] The module division in this application is illustrative and represents only one logical functional division. In actual implementation, other division methods are possible. Furthermore, the functional modules in the various examples of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware, as software functional modules, or a combination of hardware and software.

[0217] Figure 15 A schematic block diagram of another communication device 1100 provided in this application. Optionally, the communication device 1100 may be a chip or a chip system. Optionally, in this application, the chip system may be composed of chips or may include chips and other discrete devices.

[0218] The communication device 1100 can be used to implement the functions of any of the network elements (e.g., network devices or terminal devices) described in the foregoing embodiments. The communication device 1100 may include at least one processor 1110. Optionally, the processor 1110 is coupled to a memory, which may be located within the communication device 1100, integrated with the processor, or located outside the communication device 1100. As an example, the communication device 1100 may also include at least one memory 1120. The memory 1120 stores the necessary computer programs (or computer instructions) and / or data for implementing the corresponding functions of any of the network elements in any of the above method embodiments; the processor 1110 may execute the computer programs stored in the memory 1120 to complete the methods implemented by any of the network elements in any of the above method embodiments.

[0219] The communication device 1100 may also include a communication interface 1130, through which the communication device 1100 can interact with other devices. For example, the communication interface 1130 may be a transceiver, circuit, bus, module, pin, or other type of communication interface. When the communication device 1100 is a chip-based device or circuit, the communication interface 1130 in the device 1100 may also be an input / output circuit, capable of inputting information (or receiving information) and outputting information (or sending information). The processor may be an integrated processor, a microprocessor, an integrated circuit, or a logic circuit, and the processor can determine the output information based on the input information.

[0220] The coupling in this application refers to indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, used for information exchange between devices, units, or modules. The processor 1110 may operate in conjunction with the memory 1120 and the communication interface 1130. This application does not limit the specific connection medium between the processor 1110, the memory 1120, and the communication interface 1130.

[0221] Optionally, such as Figure 12 As shown, the processor 1110, the memory 1120, and the communication interface 1130 are interconnected via a bus 1140. The bus 1140 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, Figure 12 The bus 1140 is represented by only one line, but this does not mean that there is only one bus or one type of bus.

[0222] In one implementation, the communication device 1100 can be applied to the network side, such as the network device in the embodiments of this application, or a host or cloud device in an OTT system. Specifically, the communication device 1100 can be a network device, or an apparatus capable of supporting the network device to implement the corresponding functions of the network device in any of the above method embodiments. The memory 1120 stores computer programs (or computer instructions) and / or data that implement the corresponding functions of the network device. The processor 1110 can execute the computer programs or instructions stored in the memory 1120 to complete the methods executed by the network device in any of the above method embodiments. The communication interface in the communication device 1100 can be used to interact with terminal devices, for example, to receive CSI reports from terminal devices.

[0223] In another implementation, the communication device 1100 can be applied to the terminal side. For example, the communication device 1100 can be a terminal device, or an apparatus capable of supporting the terminal device and implementing the corresponding functions of the terminal device in any of the above method embodiments. The memory 1120 stores computer programs (or computer instructions) and / or data that implement the corresponding functions of the terminal device in any of the above method embodiments. The processor 1110 can execute the computer program stored in the memory 1120 to complete the method executed by the terminal device in any of the above method embodiments. The communication interface in the communication device 1100 can be used to interact with network devices (e.g., base stations), send information to the network device or receive information from the network device, such as sending a CSI report to the network device.

[0224] Figure 16 This is a schematic structural diagram of the chip provided in this application. Chip 30 includes circuit 31 and communication interface 32. Circuit 31 can be a logic circuit, integrated circuit, etc., and communication interface 32 can also be called input / output circuit, input / output interface, interface circuit, etc., which can input information (or receive information) or output information (or send information). Chip 30 can execute the methods executed by network devices or terminal devices in the various embodiments of this application.

[0225] In this application, the processor can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0226] In this application, the memory can be non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), or it can be volatile memory, such as random-access memory (RAM). Memory is any other medium capable of carrying or storing desired program code in the form of instructions or data structures, and accessible by a computer, but is not limited to this. The memory in this application can also be a circuit or any other device capable of implementing storage functions for storing computer programs and / or data.

[0227] Figure 17 This is a schematic diagram of the system architecture of the chip provided in this application. Input / output control is used to manage the input and output signals of communication devices (such as network devices or terminal devices). For example, input / output control can take the form of a modem, keyboard, mouse, touchscreen, etc. Input / output control may also be part of the processor. The receiver / transmitter is used to communicate with other devices. The receiver / transmitter may include a modem for modulating information (transmitting device) or demodulating modulated information (receiving device). The antenna is used to transmit or receive signals. Storage can be used to store computer code, which can be executed by the processor to implement the corresponding functions of the communication device. The processor may include intelligent hardware devices, such as a general-purpose processor, digital signal processor (DSP), central processing unit (CPU), field-programmable gate array (FPGA), graphics processing unit (GPU), neural processing unit (NPU), etc. Figure 17 The chip provided can be used to implement the corresponding functions of the network device or terminal device in the embodiments of this application.

[0228] In addition, this application also provides a computer-readable storage medium storing computer instructions, which, when executed on a computer, cause operations and / or processes performed by a terminal device or network device in the various method embodiments of this application to be executed.

[0229] This application also provides a computer program product, which includes computer program code or instructions. When the computer program code or instructions are run on a computer, the operations and / or processes performed by a terminal device or network device in the various method embodiments of this application are executed.

[0230] This application also provides a chip including a processor, and a memory for storing a computer program, disposed independently of the chip. The processor executes the computer program stored in the memory, such that operations and / or processes performed by a terminal device or network device in any method embodiment are executed. Further, the chip may also include a communication interface. The communication interface may be an input / output interface or an interface circuit, etc. Further, the chip may also include a memory.

[0231] This application also provides a chip, which may include circuitry and an input / output interface. The circuitry may be logic circuitry, integrated circuits, etc., and exemplaryly, the circuitry may be one or more processors, or all or part of the circuitry in one or more processors used to implement one or more processing, control, or computing functions. The input / output interface may also be an input / output circuit, or an interface circuit, capable of inputting information (or receiving information) and / or outputting information (or sending information). The chip may include a chip system. Optionally, the chip system may be composed of chips or may include chips and other discrete devices. The chip can be used to execute the methods implemented by terminal devices or network devices in the various embodiments of this application. Optionally, the chip may be a baseband chip, also known as a modem.

[0232] Furthermore, this application provides a communication system, including the terminal device and network device in any embodiment of this application. This communication system can achieve... Figures 7-13 The communication method provided in any of the embodiments.

[0233] Those skilled in the art will 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.

[0234] The processor in this application embodiment has signal processing capabilities and can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in this application can be directly implemented by the hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above methods.

[0235] In the embodiments of this application, memory is any other medium capable of carrying or storing desired program code in the form of instructions or data structures, and accessible by a computer, but is not limited thereto. The memory in this application can also be a circuit or any other means capable of implementing a storage function for storing computer programs and / or data; or, it can also be a circuit or any other means capable of implementing a storage function for storing computer programs and / or data. As an example, memory can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. 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. Volatile memory can be random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM 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, the types described above or any other suitable types of memory.

[0236] The technical solutions provided in this application can be implemented in whole or in part through software, hardware, firmware, or any combination thereof. When implemented using software, they 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 program instructions are loaded and executed on a computer, all or part of the processes or functions described in this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a terminal device, an access network device, 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 website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access 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., digital video discs (DVDs)), or semiconductor media, etc.

[0237] In the embodiments of this application, "at least one" refers to one or more items. "More than one" means two or more items. "And / or" is used to describe the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0238] The term "comprising" and any variations thereof used in the embodiments of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0239] In this application, examples may reference each other without logical contradiction. For example, methods and / or terms between method embodiments may reference each other, functions and / or terms between device embodiments may reference each other, and functions and / or terms between device examples and method examples may reference each other.

[0240] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0241] 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 through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0242] 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.

[0243] In addition, 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.

[0244] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they 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 a portion 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.

[0245] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method characterized by comprising: The method comprises: determining a first prediction result based on a first prediction task and a second prediction task, the first prediction result being obtained based on the first prediction task and being associated with the second prediction task, or the first prediction result being obtained based on the second prediction task and being associated with the first prediction task; sending a channel state information (CSI) report, the CSI report comprising the first prediction result.

2. The method of claim 1, wherein, The determining of the first prediction result based on the first prediction task and the second prediction task comprises: obtaining a second prediction result based on the first prediction task; obtaining a third prediction result based on the second prediction task; obtaining the first prediction result based on the second prediction result and the third prediction result.

3. The method of claim 2, wherein, The first prediction task corresponds to a first prediction period, the second prediction task corresponds to an observation time window and a prediction time window, the first prediction result is a prediction result that is closer to the observation time window among the second prediction result and the third prediction result, the second prediction result is a prediction result corresponding to the first prediction period of the first prediction task, the third prediction result is a prediction result corresponding to a second prediction period within the prediction time window of the second prediction task, the prediction time window comprises a plurality of prediction periods, and the second prediction period is one of the plurality of prediction periods.

4. The method of claim 3, wherein, The first prediction task and the second prediction task satisfy a set condition, and the set condition comprises: a time interval between a start time of the first prediction task and a start time of the second prediction task is less than or equal to a threshold value; a similarity between the second prediction result and the third prediction result is less than or equal to a similarity threshold value.

5. The method according to claim 3 or 4, characterized in that, The CSI report further comprises prediction results corresponding to remaining prediction periods within the prediction time window except for the second prediction period.

6. The method according to any one of claims 3 to 5, characterized in that, The method further comprises: in a case where a length of the prediction time window is less than or equal to a set threshold value, determining the similarity between the second prediction result and the third prediction result.

7. The method according to any one of claims 1 to 3, characterized in that, The first prediction task and the second prediction task satisfy a set condition, and the set condition comprises: a start time of the first prediction task is located after a start time of the second prediction task and before an end time of the second prediction task; and the prediction time window comprises the first prediction period.

8. The method of claim 7, wherein, The first prediction result is a prediction result corresponding to the first prediction period of the second prediction task.

9. The method of claim 1, wherein, The first prediction task and the second prediction task each correspond to an observation time window and a prediction time window, and the first prediction task and the second prediction task satisfy a set condition, and the set condition comprises: The first prediction task and the second prediction task correspond to the same one or more prediction periods, at any one of the one or more prediction periods, a second prediction result corresponding to the first prediction task and a third prediction result corresponding to the second prediction task are the same, the first prediction result is a prediction result selected from the second prediction result and the third prediction result and closer to a first observation time window, and the first observation time window is a later observation time window in time among the observation time windows corresponding to the first prediction task and the second prediction task respectively.

10. The method of claim 9, wherein, The first prediction task and the second prediction task are periodic, or the first prediction task and the second prediction task are aperiodic.

11. The method according to claim 9 or 10, characterized in that, The one or more prediction periods are determined based on information of the observation time windows corresponding to the first prediction task and the second prediction task respectively and the prediction time window.

12. The method according to any one of claims 9 to 11, characterized in that, The CSI report includes prediction results of the first prediction task in other prediction periods in a corresponding first prediction time window except the one or more prediction periods, or the CSI report includes prediction results of the second prediction task in other prediction periods in a corresponding second prediction time window except the one or more prediction periods.

13. The method according to any one of claims 3 to 11, characterized in that, The method further includes: The first prediction result is the second prediction result obtained by the first prediction task in the first prediction period, and the third prediction result obtained by the second prediction task in the second prediction period is discarded; Or, The first prediction result is the third prediction result obtained by the second prediction task in the second prediction period, and the second prediction result obtained by the first prediction task in the first prediction period is discarded.

14. A communications device, characterized by The method comprises a module or a unit for implementing the method as claimed in any one of claims 1-13.

15. A communications device, characterized by The method comprises at least one processor for executing computer programs or instructions stored in a memory, so that the method as claimed in any one of claims 1-13 is executed.

16. A chip, characterized by The method comprises a circuit and a communication interface, the communication interface is used to receive a signal to be processed and send the signal to be processed to the circuit; the circuit is used to process the received signal, so that the method as claimed in any one of claims 1-13 is executed.

17. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer programs or instructions, when the computer programs or instructions run on the communication device, the communication device executes the method as claimed in any one of claims 1-13.

18. A computer program product, characterised in that, The computer program product comprises a module or a unit for executing the method as claimed in any one of claims 1-13. The computer program product comprises a module or a unit for executing the method as claimed in any one of claims 1-13.

Images