Beam management channel state information report transmission method, device and storage medium

Abstract

The channel state information (CSI) report transmission method, device, and storage medium for beam management provided in this application, relating to the field of communication technology, involve obtaining priority relationship configuration instructions through a terminal device to configure the priority relationship between CSI reports related to AI models and those related to non-AI models used in beam management; generating CSI reports and adding a report category field to the CSI reports; determining priority parameters for the CSI reports based on the priority relationship configuration instructions, the report category field, and the configuration information of the CSI reports; adding the CSI reports to a task queue according to the priority parameters; and sending the CSI reports to network devices according to the task queue. This effectively resolves the conflict between CSI reports related to AI models and those related to non-AI models in beam management scenarios using AI models, meets the needs for timely processing and orderly management of diverse CSI reports, and improves resource utilization efficiency.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method, device and storage medium for transmitting channel state information reports in beam management. Background Technology

[0002] Channel State Information (CSI) report prioritization is used in communication systems to determine the processing order of different types of CSI reports. This concept is of great significance in today's complex communication environment, especially with the application of AI / ML (AI / ML) technology in beam management, leading to the emergence of various types of CSI reports, making the rational determination of their priorities increasingly crucial.

[0003] Traditional CSI report priority rules are determined based on specific priority parameters, which are related to time domain behavior, report content, serving cell index, and CSI report index.

[0004] However, with the introduction of AI / ML technology into beam management, the types and number of new CSI reports are constantly increasing, and the original priority rules are difficult to adapt to this change, which may result in some CSI reports failing to be sent successfully or in a timely manner. Summary of the Invention

[0005] This application provides a method, device, and storage medium for transmitting channel state information reports using beam management, which are applied in the field of communication technology.

[0006] In a first aspect, embodiments of this application propose a beam-managed Channel State Information (CSI) report transmission method, applied to a terminal device, the method comprising:

[0007] Obtain priority relationship configuration instructions, which are used to configure the priority relationship between CSI reports related to AI models and CSI reports related to non-AI models applied by beam management;

[0008] Generate a CSI report and add a report category field to the CSI report. The report category field is used to identify whether the CSI report is related to AI models or not related to AI models.

[0009] Based on the priority relationship configuration instructions, the report category field, and the CSI report configuration information, determine the priority parameters of the CSI report;

[0010] The CSI report is added to the task queue according to the priority parameter, and then sent to the network device according to the task queue.

[0011] Therefore, the channel state information report transmission method for beam management in this application can effectively resolve the conflict between CSI reports related to AI models and CSI reports related to non-AI models in beam management scenarios using AI models, meet the needs of timely processing and orderly management of diverse CSI reports in AI model beam management scenarios, and improve resource utilization efficiency.

[0012] In one possible implementation, the priority parameters of the CSI report are determined based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report, including:

[0013] Determine the configuration information for CSI reports, including: the maximum number of serving cells, the maximum number of CSI reports configured, the serving cell index, the CSI report index, the CSI report delivery method, and whether the CSI report includes network quality indicator information;

[0014] Based on priority relationship configuration instructions, report category fields, and CSI report configuration information, the priority parameters of CSI reports are determined using a preset priority formula.

[0015] In other words, for CSI reports based on AI / ML beam management, the priority parameters of the CSI report can be determined by combining the priority relationship configuration instructions and the report category field with the configuration information of the CSI report. This can clarify the priority order of different types of CSI reports in AI / ML beam management and avoid report conflicts.

[0016] In one possible implementation, the priority parameters of the CSI report are determined using a preset priority formula based on priority relationship configuration instructions, the report category field, and the CSI report configuration information, including:

[0017] The priority parameters of CSI reports are determined using the following preset priority formula. :

[0018]

[0019] in, To maximize the number of service communities, Configure the maximum number of CSI reports. Parameters characterizing the way CSI reports are carried, A parameter used to characterize whether a CSI report contains network quality metrics information. To serve the cell index, 'b' is the CSI report index, 'b' is a parameter representing the report category field, and 'a' is a parameter representing the priority relationship configuration instruction.

[0020] In the above formula, based on the traditional CSI report priority parameter calculation formula, a parameter b representing the report category field and a parameter a representing the priority relationship configuration instruction are added. This enables the formula to calculate the priority parameters of CSI reports related to AI models and those not related to AI models, thereby distinguishing the priority of CSI reports related to AI models and those not related to AI models. This effectively resolves the conflict between CSI reports related to AI models and those not related to AI models, which is conducive to timely processing and orderly management of CSI reports and improves resource utilization efficiency.

[0021] In one possible implementation, the method further includes:

[0022] If the CSI report is an AI model performance testing CSI report, then configure the parameter representing the report category field to 2; or

[0023] If the CSI report is a CSI report representing the results of AI model inference, then configure the parameter representing the report category field to 1; or

[0024] If the CSI report is not related to an AI model, then the parameter representing the report category field will be configured to 0.

[0025] In other words, by configuring different parameter b for different report category fields, the priority of different categories of CSI reports can be effectively reflected, thereby affecting the priority parameters of the final CSI report.

[0026] In one possible implementation, the method further includes:

[0027] If the priority relationship configuration instruction prioritizes AI model-related CSI reports over non-AI model-related CSI reports, then the parameter of the priority relationship configuration instruction for AI model-related CSI reports is configured to -1, and the parameter of the priority relationship configuration instruction for non-AI model-related CSI reports is configured to 1; or

[0028] If the priority relationship configuration instruction configures the priority of non-AI model-related CSI reports to be higher than that of AI model-related CSI reports, then the parameter of the representation priority relationship configuration instruction for AI model-related CSI reports will be configured to 1, and the parameter of the representation priority relationship configuration instruction for non-AI model-related CSI reports will be configured to -1.

[0029] In other words, when the priority relationship configuration instruction configures different priority relationships between AI model-related CSI reports and non-AI model-related CSI reports, configuring the parameter 'a' of the priority relationship configuration instruction representing AI model-related CSI reports and the priority relationship configuration 'a' of the non-AI model-related CSI reports respectively can effectively reflect the priority tendency of different categories of CSI reports under different priority relationships, thereby affecting the priority parameters of the final CSI reports.

[0030] In one possible implementation, CSI reports are added to a task queue based on a priority parameter, and then sent to the network device according to the task queue, including:

[0031] If the CSI report is an AI model performance detection CSI report, then the CSI report is added to the head of the task queue, and the AI ​​model performance detection CSI report at the head of the task queue is sent to the network device through the pre-configured first channel; or

[0032] If the CSI report is not a CSI report for AI model performance testing, the CSI report is added to the task queue according to the priority parameter, and the CSI reports in the task queue are sent to the network device through the second channel in ascending order of priority parameter.

[0033] In other words, the CSI report for AI model performance testing is added to the head of the task queue and sent directly to the network device through the pre-configured first channel without waiting for task queue scheduling, ensuring the priority transmission of the AI ​​model performance testing CSI report. Meanwhile, the CSI reports for AI model inference results and non-AI model-related CSI reports are added to the task queue according to priority parameters, sorted based on these parameters, and await the task queue's scheduling of the second channel for transmission. This ensures that the AI ​​model performance testing CSI report does not conflict with non-AI model performance testing CSI reports, effectively preventing the AI ​​model inference result CSI report from being discarded due to conflicts with the AI ​​model performance testing CSI report.

[0034] In one possible implementation, if the CSI report is not a CSI report for AI model performance testing, the CSI report is added to the task queue according to a priority parameter, and the CSI reports in the task queue are sent to the network device through a second channel in ascending order of priority parameter, including:

[0035] For CSI reports of AI model inference results whose priority parameters are located before a preset order in the task queue, they are sent to the network device through a pre-configured second channel based on the order of priority parameters from smallest to largest; or

[0036] For CSI reports that are not related to the AI ​​model or for CSI reports of AI model inference results that are not in the preset order in the task queue, they are sent to the network device through the remaining second channel in the second channel in ascending order of priority parameter.

[0037] In other words, by dividing the resources of the second channel into two parts, we can ensure the reporting of CSI reports for high-priority AI model inference results, while CSI reports related to non-AI models and CSI reports for AI model inference results that are not in the preset order will wait for the task queue to schedule the remaining second channel, thus achieving efficient resource allocation for the second channel.

[0038] In one possible implementation, for CSI reports that are not related to the AI ​​model or for CSI reports of AI model inference results that are not in a preset order in the task queue, they are sent to the network device through the remaining second channel in the second channel in ascending order of priority parameter, including:

[0039] For CSI reports that are not related to AI models or CSI reports that are not in the preset order of AI model inference results in the task queue, if there are not enough remaining second channels in the second channel, the CSI report with higher priority parameters will take over the remaining second channels occupied by the CSI report with lower priority parameters.

[0040] In one possible implementation, the first channel is a physical uplink control channel; the second channel is a physical uplink shared channel. The first channel can ensure low latency and high reliability of CSI report submission for AI model performance testing; the second channel can be scheduled more flexibly.

[0041] In one possible implementation, the method further includes:

[0042] If the CSI report is a CSI report of AI model inference results, then configure the lifecycle of the CSI report of AI model inference results;

[0043] Before sending the CSI report of the AI ​​model inference results to the network device, determine whether the lifecycle of the CSI report of the AI ​​model inference results has ended;

[0044] If the CSI report for the AI ​​model inference results has not yet expired, then the CSI report for the AI ​​model inference results will be sent to the network device; or

[0045] If the CSI report for the AI ​​model inference results has reached the end of its lifecycle, then discard the CSI report for the AI ​​model inference results.

[0046] In other words, determining whether the lifecycle of the CSI report for AI model inference results has ended before sending it can avoid wasting resources by sending CSI reports for AI model inference results that have ended their lifecycle to network devices.

[0047] In one possible implementation, the method further includes:

[0048] If the CSI report is a CSI report of AI model inference results, then configure the lifecycle of the CSI report of AI model inference results;

[0049] Filter and clear CSI reports of AI model inference results whose lifecycles have ended in the task queue.

[0050] In other words, by continuously filtering out CSI reports of AI model inference results whose lifecycles have ended from the task queue, we can avoid wasting resources by sending CSI reports of AI model inference results whose lifecycles have ended to network devices. At the same time, we can also free up space in the task queue to facilitate the processing of subsequent CSI reports.

[0051] In one possible implementation, obtaining priority relationship configuration instructions includes:

[0052] Based on the terminal device capabilities and / or scenario, configure the priority relationship between CSI reports related to AI models and CSI reports related to non-AI models, and generate priority relationship configuration instructions; or

[0053] Receive priority relationship configuration instructions sent by network devices.

[0054] In one possible implementation, the method further includes:

[0055] Receive task queue configuration information sent by network devices, and configure the task queue according to the task queue configuration information.

[0056] In other words, the terminal device can receive the task queue configuration information sent by the network device, so that the task queue can send CSI reports to meet the terminal device's requirements for sending CSI reports and the network device's requirements for obtaining CSI reports. Furthermore, the network device can coordinate the behavior of multiple terminal devices in reporting CSI reports to avoid conflicts or waste of resources.

[0057] In one possible implementation, the task queue configuration information includes the capacity of the task queue.

[0058] In other words, network devices can configure the capacity of this task queue, which can optimize network performance, allocate resources reasonably, improve resource utilization, and ensure the timeliness of CSI reports, avoiding excessive accumulation of CSI reports that lead to outdated information.

[0059] Secondly, embodiments of this application provide a beam-managed channel state information (CSI) report transmission apparatus, comprising:

[0060] The acquisition module is used to acquire priority relationship configuration instructions, wherein the priority relationship configuration instructions are used to configure the priority relationship between CSI reports related to AI models and CSI reports related to non-AI models applied by beam management;

[0061] The generation module is used to generate CSI reports and add a report category field to the CSI report. The report category field is used to identify whether the CSI report is related to AI models or not related to AI models.

[0062] The priority determination module is used to determine the priority parameters of the CSI report based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report.

[0063] The sending module is used to add the CSI report to the task queue according to the priority parameter, and send the CSI report to the network device according to the task queue.

[0064] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory, wherein the memory is used to store computer execution instructions, and the processor is used to run the computer execution instructions stored in the memory to perform the method described in the first aspect or any possible implementation of the first aspect.

[0065] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program or instructions that, when executed on a computer, cause the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0066] Fifthly, embodiments of this application provide a computer program product including a computer program, which, when run, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0067] Sixthly, this application provides a chip or chip system including at least one processor and a communication interface. The communication interface and the at least one processor are interconnected via a circuit. The at least one processor is used to run computer programs or instructions to perform the methods described in the first aspect or any possible implementation of the first aspect. The communication interface in the chip can be an input / output interface, pins, or circuits, etc.

[0068] In one possible implementation, the chip or chip system described above in this application further includes at least one memory storing instructions. The memory can be an internal storage unit of the chip, such as a register or cache, or it can be a storage unit of the chip itself (e.g., read-only memory, random access memory, etc.).

[0069] It should be understood that the second to sixth aspects of this application correspond to the technical solutions of the first aspect of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be repeated here.

[0070] The channel state information (CSI) report transmission method, device, and storage medium for beam management provided in this application embodiment obtains a priority relationship configuration instruction through a terminal device. This instruction configures the priority relationship between CSI reports related to the AI ​​model and those not related to the AI ​​model used in beam management. A CSI report is generated, and a report category field is added to the report, indicating whether the CSI report is related to the AI ​​model or not. Based on the priority relationship configuration instruction, the report category field, and the CSI report configuration information, priority parameters for the CSI report are determined. The CSI report is added to a task queue according to the priority parameters, and then sent to the network device according to the task queue. In beam management scenarios using AI models, this effectively resolves the conflict between AI model-related and non-AI model-related CSI reports, meets the needs for timely processing and orderly management of diverse CSI reports in AI model beam management scenarios, and improves resource utilization efficiency. Attached Figure Description

[0071] Figure 1 This is a schematic diagram of a scenario provided for an embodiment of this application;

[0072] Figure 2 A flowchart illustrating the channel state information reporting and transmission method for beam management provided in this application embodiment. Figure 1 ;

[0073] Figure 3 A flowchart illustrating the channel state information reporting and transmission method for beam management provided in this application embodiment. Figure 2 ;

[0074] Figure 4 A schematic diagram illustrating a temporal conflict between the CSI report for AI model performance testing and the CSI report for AI model inference results provided in this application embodiment;

[0075] Figure 5 A schematic diagram of the structure of the beam-managed channel state information reporting transmission device provided in the embodiments of this application;

[0076] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0077] To facilitate a clear description of the technical solutions in the embodiments of this application, some terms and technologies involved in the embodiments of this application will be briefly introduced below:

[0078] 1. Electronic equipment:

[0079] The electronic devices in this application embodiment may include handheld devices with beam management functions, vehicle-mounted devices, etc. For example, some electronic devices include: mobile phones, tablets, PDAs, laptops, mobile internet devices (MIDs), virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, 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, in-vehicle devices, terminal devices in 5G networks, or terminal devices in future evolved public land mobile networks (PLMNs), etc., and the embodiments of this application are not limited to these.

[0080] By way of example and not limitation, in this embodiment, the electronic 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.

[0081] Furthermore, in this embodiment of the application, the electronic device can also be a terminal device in the Internet of Things (IoT) system. IoT is an important part of the future development of information technology. Its main technical feature is to connect objects to the network through communication technology, thereby realizing an intelligent network of human-machine interconnection and object-to-object interconnection.

[0082] The electronic devices in the embodiments of this application may also be referred to as: terminal equipment, user equipment (UE), mobile station (MS), mobile terminal (MT), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent, or user device, etc.

[0083] 2. Network equipment:

[0084] In this embodiment of the application, the network device can be any device with wireless transceiver capabilities. This equipment includes, but is not limited to: evolved Node B (eNB), Radio Network Controller (RNC), Node B (NB), Base Station Controller (BSC), Base Transceiver Station (BTS), Home base station (e.g., Home evolved Node B, or HomeNode B, HNB), Base Band Unit (BBU), Access Point (AP), Wireless Relay Node, Wireless Backhaul Node, Transmission Point (TP), or Transmission and Reception Point (TRP) in a Wireless Fidelity (WIFI) system. It can also be a gNB in ​​a 5G system, such as NR, or a transmission point (TRP or TP), one or a group of antenna panels (including multiple antenna panels) of a base station in a 5G system, or a network node constituting a gNB or transmission point, such as a Base Band Unit (BBU) or a Distributed Unit (DU).

[0085] In some deployments, a gNB may include a centralized unit (CU) and a distribution unit (DU). The gNB may also include an active antenna unit (AAU). The CU implements some of the gNB's functions, and the DU implements others. For example, the CU handles non-real-time protocols and services, implementing radio resource control (RRC) and packet data convergence protocol (PDCP) layer functions. The DU handles physical layer protocols and real-time services, implementing radio link control (RLC), media access control (MAC), and physical (PHY) layer functions. The AAU implements some physical layer processing functions, radio frequency processing, and active antenna-related functions. Since RRC layer information ultimately becomes PHY layer information, or is derived from PHY layer information, in this architecture, higher-layer signaling, such as RRC layer signaling, can be considered to be sent by the DU, or by the DU+AAU. It is understood that network devices can be devices that include one or more of the following: CU nodes, DU nodes, and AAU nodes. In addition, the CU can be classified as a network device in the radio access network (RAN) or as a network device in the core network (CN), and this application does not limit this.

[0086] Network equipment provides services to cells. Terminal devices communicate with cells through transmission resources (e.g., frequency domain resources, or spectrum resources) allocated by the network equipment. The cell can belong to a macro base station (e.g., macro eNB or macro gNB) or to a base station corresponding to a small cell. Small cells can include: metrocell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0087] 3. Beam Management: This is a technology that dynamically adjusts the direction and frequency of communication beams based on channel quality. It ensures reliable, high-quality communication by continuously monitoring and adjusting the beams. Beam management typically achieves dynamic optimization through the following steps: 1) Beam Scanning: Within the beam coverage area, the network device sends a set of beams (reference signals) at preset time intervals and directions to find the optimal beam transmission direction; 2) Beam Measurement: After receiving the beam, the UE evaluates the signal quality, such as RSRP (Reference Signal Received Power) and SINR (Signal-to-Interference-plus-Noise Ratio); 3) Beam Reporting and Selection: The UE reports the measurement results to the network device through Channel State Information (CSI), and the network device selects the optimal beam; 4) Beam Indication and Switching: The network device notifies the UE of the selected beam, and the UE performs a switch according to the notification.

[0088] 4. AI / ML-based Beam Management: Beam management based on Artificial Intelligence (AI) and Machine Learning (ML) aims to optimize beamforming and beam switching intelligently to improve network coverage, spectrum efficiency, and user experience. A typical AI / ML-based beam management process includes: 1) Data Collection and Model Training: Collecting historical data (such as reference signal measurement results, UE location, and movement trajectory); offline training of AI models (such as neural networks, Long Short-Term Memory networks (LSTM), etc.) to learn the mapping relationship between channels and beam pairs; 2) Beam Prediction: Spatial Domain Beam Prediction (SBP): Predicting the optimal beam pair for different spatial locations based on current measurement results; Temporal Domain Beam Prediction (TBP): Predicting the optimal beam pair for future time points, suitable for high-mobility scenarios; 3) Beam Selection and Verification: The AI ​​model outputs prediction results, network devices or UEs select beam pairs based on the predictions, and the accuracy of the predictions is verified through measurement; 4) Model Update and Management: Updating the AI ​​model online or offline to adapt to channel changes, involving model selection, activation / deactivation, and performance monitoring.

[0089] 5. Channel State Information (CSI) Report: Used by the UE to report channel quality information to the network equipment to support adaptive transmission, beam management, and resource scheduling. It can be categorized according to its triggering method:

[0090] Periodic CSI Reporting (P-CSI): Configured via RRC (Radio Resource Control) signaling, it will perform measurements and report according to a predetermined period after configuration.

[0091] Semi-persistent CSI reporting (SP-CSI): It is also configured via RRC signaling, but periodic measurement and reporting will only begin after the network device sends a trigger message;

[0092] Aperiodic CSI Reporting (A-CSI): Aperiodic CSI is a one-time measurement and reporting triggered by the MAC (Medium Access Control) layer when needed.

[0093] 6. Channel State Information (CSI) Report Priority: Priority management of Channel State Information (CSI) reports is crucial for resource allocation, scheduling efficiency, and system performance optimization. Traditional CSI report priority rules are determined based on specific priority values, which are related to time-domain behavior, CSI report content, serving cell index (ID), and CSI report index (ID). Each CSI report is assigned a unique priority value; the lower the priority value, the higher the priority. When transmission time-frequency resources are limited, the UE can discard lower-priority CSI reports. When computing resources (CPU) are limited, the UE can choose not to update low-priority CSI reports, i.e., not to perform calculations for low-priority CSI reports.

[0094] 7. Physical Uplink Control Channel (PUCCH): Primarily used for transmitting uplink control information.

[0095] 8. Physical Uplink Shared Channel (PUSCH): Primarily used for transmitting uplink user data, including voice, video, file transfer, and other service data.

[0096] 9. Other terms

[0097] In the embodiments of this application, terms such as "first" and "second" are used to distinguish identical or similar items with substantially the same function and purpose. For example, "first chip" and "second chip" are used only to distinguish different chips and do not limit their order of execution. Those skilled in the art will understand that terms such as "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply that they are different.

[0098] It should be noted that, in the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0099] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, a--c, bc, or abc, where a, b, and c can be single or multiple.

[0100] It should be noted that the phrase "at...time" in the embodiments of this application can refer to the instant at which a certain situation occurs, or to a period of time after the occurrence of a certain situation; the embodiments of this application do not specifically limit this. Furthermore, the display interface provided in the embodiments of this application is merely an example, and the display interface may include more or less content.

[0101] The following is combined with Figure 1 The use cases for the channel state information (CSI) report transmission method in beam management are explained. For example... Figure 1 As shown, the communication system includes a terminal device 110 and a network device 120. The network device 120 can send beams to the terminal device 110. The terminal device 110 can perform beam management based on AI / ML and send a beam management CSI report to the network device 120.

[0102] However, traditional CSI report priority rules are determined based on specific priority parameters, which are related to time-domain behavior, report content, serving cell index, and CSI report index. But in AI / ML-based beam management scenarios, new CSI report types and quantities are constantly increasing. In data collection scenarios, terminal devices need to measure and report CSI report information related to Set A (predicted beam set) / Set B (measured beam set); in inference scenarios, terminal devices generate reports about predicted beams through AI models; in performance monitoring scenarios, terminal devices generate CSI reports on AI model performance testing to evaluate model performance. The timing of these CSI reports and their importance to the network vary. For example, AI model performance testing CSI reports reflect whether the AI ​​model is working properly and its performance, and their timeliness is crucial for stable network operation; while training data collection reports are usually non-real-time and have relatively lower timeliness requirements.

[0103] However, traditional CSI report prioritization rules are ill-suited to the ever-increasing types and numbers of CSI reports and cannot effectively distinguish the priorities of these CSI reports. In some cases, this may lead to significant report processing delays and affect network performance, such as impacting the network equipment's accurate prediction of channel conditions and the rational allocation of resources.

[0104] In view of this, this application provides a method for transmitting Channel State Information (CSI) reports for beam management. In beam management scenarios using AI models, the priority relationship between CSI reports related to the AI ​​model and those not related to the AI ​​model is configured through a priority relationship configuration instruction. A report category field is added to the CSI report. Based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report, the priority parameters of the CSI report are determined. A task queue is introduced, and the CSI report is added to the task queue according to the priority parameters. The CSI report is then sent to the network device according to the task queue. This effectively resolves the conflict between CSI reports related to the AI ​​model and those not related to the AI ​​model, meets the needs of timely processing and orderly management of diverse CSI reports in AI model beam management scenarios, and improves resource utilization efficiency.

[0105] The methods provided in the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0106] It should be understood that the following description is for ease of understanding and explanation only, using the interaction between a terminal device and a network device as an example to illustrate the methods provided in the embodiments of this application. However, this should not constitute any limitation on the subject executing the methods provided in this application. For example, the terminal device shown in the embodiments below can be replaced by components (such as chips or circuits) configured in the terminal device. The network device shown in the embodiments below can also be replaced by components (such as chips or circuits) configured in the network device.

[0107] The embodiments shown below do not specifically limit the structure of the execution subject of the method provided in the embodiments of this application. As long as it is possible to communicate according to the method provided in the embodiments of this application by running a program that records the code of the method provided in the embodiments of this application, for example, the execution subject of the method provided in the embodiments of this application can be a terminal device, or a functional module in the terminal device that can call and execute the program.

[0108] Figure 2 This is a schematic flowchart illustrating the beam management channel state information (CSI) report transmission method provided in this application embodiment from the perspective of device interaction. Figure 2 As shown, the channel state information (CSI) report transmission method for beam management may include:

[0109] S201. The terminal device obtains a priority relationship configuration instruction, wherein the priority relationship configuration instruction is used to configure the priority relationship between CSI reports related to the AI ​​model and CSI reports related to the non-AI model used in beam management.

[0110] In this embodiment of the application, when performing beam management, the terminal device can send a CSI report to the network device. The types of CSI reports can include CSI reports related to the applied AI model and CSI reports not related to the AI ​​model. CSI reports related to the applied AI model include, but are not limited to, CSI reports on AI model performance detection, CSI reports on AI model inference results, and CSI reports related to AI model training. CSI reports not related to the AI ​​model are CSI reports that are unrelated to the AI ​​model, such as some conventional CSI reports, such as reports on feedback channel quality information.

[0111] The CSI report priority configuration command is used to configure the priority relationship between AI model-related CSI reports and non-AI model-related CSI reports when the terminal device sends beam management CSI reports to the network device. For example, AI model-related CSI reports take precedence over non-AI model-related CSI reports, or vice versa. It should be noted that this CSI report priority configuration command only declares the overall priority relationship between AI model-related and non-AI model-related CSI reports. It can reflect the preference for prioritizing AI model-related CSI reports over non-AI model-related CSI reports, but it cannot directly determine the priority of a specific CSI report based on this priority relationship. Further calculation of the priority parameters for each CSI report is needed to determine the final priority.

[0112] Optionally, when the terminal device obtains the priority relationship configuration instruction, the priority relationship configuration instruction can come from the terminal device itself or from the network device.

[0113] Among them, the terminal device can configure the priority relationship between CSI reports related to AI models and CSI reports related to non-AI models according to the terminal device's capabilities and / or scenario, and generate priority relationship configuration instructions.

[0114] Optionally, terminal device capabilities can consider one or more capabilities such as CPU (CSI process units) resources, network conditions, and AI model performance. Different priority relationships can be configured when terminal device capabilities differ. For example, when some terminal devices have insufficient capabilities, the terminal device can be configured to prioritize CSI reports related to non-AI models over CSI reports related to AI models. Different priority relationships can also be configured for different scenarios. For example, in MRDC (Multi-Radio Dual Connectivity) scenarios, for the primary carrier, the terminal device can be configured to prioritize CSI reports related to AI models over CSI reports related to non-AI models, while for the secondary carrier, the terminal device can be configured to prioritize CSI reports related to non-AI models over CSI reports related to AI models. As another example, in AI training scenarios, the terminal device can be configured to prioritize CSI reports related to AI models over CSI reports related to non-AI models.

[0115] Specifically, network devices can send priority relationship configuration commands to terminal devices. That is, the network device determines the priority relationship between AI model-related CSI reports and non-AI model-related CSI reports on the terminal device.

[0116] Optionally, in some scenarios, such as during peak AI training periods, where multiple terminal devices are simultaneously performing AI training, network devices can send priority relationship configuration instructions to multiple terminal devices, forcing CSI reports related to AI models to take precedence over CSI reports related to non-AI models. This enables global resource control and avoids network-level efficiency degradation caused by terminal devices operating independently.

[0117] Optionally, the terminal device can also send a terminal device capability report to the network device. This report may include one or more capability information such as the terminal device's CPU (CSI process units) resources, network status, AI model-related capability information, and CSI report-related capability information. AI model-related capability information includes, but is not limited to, beam prediction capability and the ability to predict parameters related to CSI reports. CSI report-related capability information includes, but is not limited to, whether the device has the ability to process AI model-related CSI reports and whether it has the ability to calculate priority parameters. Furthermore, the network device can send priority relationship configuration instructions to the terminal device based on the terminal device capability report, determining different priority relationships according to different terminal device capabilities. Additionally, if the network device does not support AI model-based beam prediction capability, it can issue task instructions for non-AI model-related CSI reports to the terminal device; or if the network device lacks the ability to calculate priority parameters, it can issue instructions to the terminal device using default priority rules.

[0118] It should be noted that, in this embodiment, the priority relationship configuration instruction can use an instruction of a first preset length, such as a 1-bit instruction. The 1-bit instruction can be 0 or 1, where 0 indicates that CSI reports related to the AI ​​model take precedence over CSI reports related to the non-AI model, and 1 indicates that CSI reports related to the non-AI model take precedence over CSI reports related to the AI ​​model. This is merely an example and should not be construed as limiting this application in any way.

[0119] S202. The terminal device generates a CSI report and adds a report category field to the CSI report. The report category field is used to indicate whether the CSI report is related to AI model or not related to AI model.

[0120] In this embodiment, the terminal device generates a CSI report when performing beam management. Since there are various types of generated CSI reports, a report type field can be added to the CSI report for easy identification. This field is used to characterize the specific category of the CSI report, that is, to characterize whether the CSI report is related to an AI model or not. It can also characterize which type of AI model-related CSI report or which category of non-AI model-related CSI report. Compared with traditional CSI reports that only contain measurement data such as RSRP / SINR, the CSI report with the added report type field can be easily identified directly, which is convenient for subsequent calculation of priority parameters and for network device identification.

[0121] Optionally, the report type field can use a field of a second preset length, such as a 2-bit field. The 2-bit field can take values ​​of 01, 10, and 11, where 01 represents a CSI report for AI model inference results, 10 represents a CSI report for AI model performance testing, and 11 represents a CSI report unrelated to AI models, etc. This is merely an example and should not be construed as limiting the scope of this application.

[0122] S203. The terminal device determines the priority parameters of the CSI report based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report.

[0123] In this embodiment, the priority parameters of traditional beam management CSI reports are usually determined based on the CSI report configuration information, such as time domain behavior, CSI report content, serving cell index (ID), and CSI report index (ID). However, the traditional method of determining the priority of CSI reports is not applicable to CSI reports based on AI / ML beam management. Therefore, in this embodiment, for CSI reports based on AI / ML beam management, the priority parameters of CSI reports can be determined based on the configuration information of the CSI report, combined with priority relationship configuration instructions and report category fields. This clarifies the priority order of different types of CSI reports in AI / ML beam management and avoids report conflicts.

[0124] Optionally, the terminal device can determine the configuration information of the CSI report. This configuration information includes, but is not limited to, the maximum number of serving cells, the maximum number of CSI reports configured, the serving cell index, the index of the CSI report, the CSI report carrying method, and whether the CSI report includes network quality indicator information. The CSI report carrying method can be using PUSCH to carry non-periodic CSI reports, or using PUSCH to carry semi-periodic CSI reports, or using PUCCH to carry semi-periodic CSI reports, or using PUCCH to carry periodic CSI reports, etc. Whether the CSI report includes network quality indicator information indicates whether the information carried in the CSI report includes RSRP and SINR information.

[0125] Furthermore, based on the aforementioned configuration information of the CSI report, and combined with the priority relationship configuration instruction and the report category field, the priority parameters of the CSI report are determined. This breaks through the limitation of traditional priority parameter determination rules that are based solely on fixed configuration information, and can adapt to different types of CSI reports in AI / ML beam management. It should be understood that in this embodiment, when determining the priority parameters, it is sufficient to comprehensively consider the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report; the specific determination method is not limited in this embodiment.

[0126] S204. The terminal device adds the CSI report to the task queue according to the priority parameter, and sends the CSI report to the network device according to the task queue.

[0127] In this embodiment, in a beam management scenario, the terminal device can configure a task queue, add CSI reports to the task queue according to priority parameters, sort the CSI reports in the task queue according to priority parameters, and further send the CSI reports in the task queue to the network device according to the sending rules of the task queue. By reasonably allocating resources through the task queue, the transmission of CSI reports is guaranteed.

[0128] Optionally, when configuring the task queue, the terminal device can first obtain the task queue configuration information, and then configure the task queue according to the task queue configuration information to meet the terminal device's requirements for sending CSI reports and the network device's requirements for obtaining CSI reports. The task queue configuration information includes, but is not limited to, the capacity of the task queue, the channel resources used by the task queue to send CSI reports, and the CSI report sending rules.

[0129] Optionally, the task queue configuration information can be configured by the terminal device and / or by the network device. That is, the terminal device receives the task queue configuration information sent by the network device, ensuring that the task queue's transmission of CSI reports meets both the terminal device's need to send CSI reports and the network device's need to acquire CSI reports. Furthermore, the network device can coordinate the CSI report reporting behavior of multiple terminal devices to avoid conflicts or resource waste. The task queue configuration information configured by the network device can include the capacity of the task queue, which can optimize network performance, rationally allocate resources, improve resource utilization, and ensure the timeliness of CSI reports, preventing excessive backlog of CSI reports that could lead to outdated information.

[0130] When the terminal device sends CSI reports to the network device according to the task queue, they can be sorted in order of priority to ensure that high-priority CSI reports are reported first, especially CSI reports for AI model performance detection, to ensure network status feedback; low-priority CSI reports wait for scheduling in the queue and can be reported in sequence when channel resources exist. Of course, CSI reports can be discarded if they time out and are not scheduled.

[0131] The Channel State Information (CSI) report transmission method for beam management provided in this application embodiment obtains a priority relationship configuration instruction through a terminal device. This instruction configures the priority relationship between CSI reports related to the AI ​​model and those not related to the AI ​​model used in beam management. A CSI report is generated, and a report category field is added to the report. This report category field indicates whether the CSI report is related to the AI ​​model or not. Based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report, priority parameters for the CSI report are determined. The CSI report is added to a task queue according to the priority parameters, and then sent to the network device according to the task queue. In beam management scenarios using AI models, this method effectively resolves the conflict between AI model-related and non-AI model-related CSI reports, meets the needs for timely processing and orderly management of diverse CSI reports in AI model beam management scenarios, and improves resource utilization efficiency.

[0132] Figure 3 This diagram illustrates the signaling interaction of another beam-managed Channel State Information (CSI) report transmission method in this embodiment of the application, from the perspective of device interaction. (Combined with...) Figure 3 The embodiments of this application will be described below.

[0133] S301. The terminal device sends a terminal device capability report to the network device.

[0134] The terminal device capability report may include one or more capability information such as the terminal device's CPU resources, network status, AI model-related capability information, and CSI report-related capability information. The AI ​​model-related capability information includes, but is not limited to, beam prediction capability and CSI report-related parameter prediction capability. The CSI report-related capability information includes, but is not limited to, whether it has the ability to process AI model-related CSI reports and whether it has the ability to calculate priority parameters.

[0135] S302. The network device sends a priority relationship configuration instruction to the terminal device, wherein the priority relationship configuration instruction is used to configure the priority relationship between CSI reports related to the AI ​​model and CSI reports related to the non-AI model used in beam management.

[0136] In other words, the network device determines the priority relationship between AI model-related CSI reports and non-AI model-related CSI reports from terminal devices. Optionally, in some scenarios, such as during peak AI training periods when multiple terminal devices are simultaneously performing AI training, the network device can send priority relationship configuration commands to multiple terminal devices, forcing AI model-related CSI reports to take precedence over non-AI model-related CSI reports. This enables global resource regulation and avoids network-level efficiency degradation caused by terminal devices operating independently.

[0137] S303. The terminal device generates a CSI report and adds a report category field to the CSI report. The report category field is used to indicate whether the CSI report is related to AI model or not related to AI model.

[0138] S304. The terminal device determines the priority parameters of the CSI report based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report.

[0139] S305. The terminal device adds the CSI report to the task queue according to the priority parameter, and sends the CSI report to the network device according to the task queue.

[0140] In this embodiment, the network device configures the priority relationship between AI model-related CSI reports and non-AI model-related CSI reports for beam management using priority relationship configuration instructions. The terminal device generates CSI reports, adding a report category field to each report. This report category field indicates whether the CSI report is related to the AI ​​model or not. Based on the priority relationship configuration instructions, the report category field, and the CSI report configuration information, the priority parameters of the CSI reports are determined. The CSI reports are added to a task queue according to the priority parameters, and then sent to the network device according to the task queue. In beam management scenarios using AI models, this effectively resolves the conflict between AI model-related and non-AI model-related CSI reports, meets the needs for timely processing and orderly management of diverse CSI reports in AI model beam management scenarios, and enables global resource control of network devices, improving resource utilization efficiency.

[0141] In some embodiments, when determining the priority parameters of CSI reports, the terminal device can determine the configuration information of CSI reports, including: the maximum number of serving cells, the maximum number of CSI reports configured, the serving cell index, the index of CSI reports, the CSI report carrying method, and whether the CSI reports include network quality indicator information; then, based on the priority relationship configuration instructions, the report category field, and the configuration information of CSI reports, the priority parameters of CSI reports are determined using a preset priority formula, thereby effectively resolving the priority conflict between CSI reports related to AI models and CSI reports related to non-AI models.

[0142] Optionally, the priority parameters of CSI reports can be determined using the following preset priority formula. :

[0143]

[0144] in, To maximize the number of service communities, Configure the maximum number of CSI reports. Parameters characterizing the way CSI reports are carried, A parameter used to characterize whether a CSI report contains network quality metrics information. To serve the cell index, 'b' is the CSI report index, 'b' is a parameter representing the report category field, and 'a' is a parameter representing the priority relationship configuration instruction.

[0145] In the above formula, based on the traditional CSI report priority parameter calculation formula, a parameter b representing the report category field and a parameter a representing the priority relationship configuration instruction are added. This enables the formula to calculate the priority parameters of CSI reports related to AI models and those not related to AI models, thereby distinguishing the priority of CSI reports related to AI models and those not related to AI models. This effectively resolves the conflict between CSI reports related to AI models and those not related to AI models, which is conducive to timely processing and orderly management of CSI reports and improves resource utilization efficiency.

[0146] Optionally, the parameter 'b' representing the report category field can be determined based on the report category field, mapping it to a specific value. Optionally, if the CSI report is an AI model performance detection CSI report, then parameter 'b' representing the report category field is configured to 2; if the CSI report is an AI model inference result CSI report, then parameter 'b' representing the report category field is configured to 1; if the CSI report is not related to an AI model, then parameter 'b' representing the report category field is configured to 0. By configuring different parameters 'b' for different report category fields, the priority of different categories of CSI reports can be effectively reflected, thus affecting the final priority parameter of the CSI report.

[0147] It should be understood that parameter b, which represents the report category field, can affect the priority parameter of the CSI report, but the value of parameter b corresponding to different report category fields can be adjusted according to actual needs, and is not limited to the example above.

[0148] Optionally, parameter 'a' representing the priority relationship configuration instruction can be configured according to the priority relationship between AI model-related CSI reports and non-AI model-related CSI reports in the priority relationship configuration instruction. Optionally, if the priority relationship configuration instruction configures the priority of AI model-related CSI reports to be higher than that of non-AI model-related CSI reports, then parameter 'a' representing the priority relationship configuration instruction for AI model-related CSI reports is configured to -1, and parameter 'a' representing the priority relationship configuration instruction for non-AI model-related CSI reports is configured to 1; if the priority relationship configuration instruction configures the priority of non-AI model-related CSI reports to be higher than that of AI model-related CSI reports, then parameter 'a' representing the priority relationship configuration instruction for AI model-related CSI reports is configured to 1, and parameter 'a' representing the priority relationship configuration instruction for non-AI model-related CSI reports is configured to -1. When different priority relationships are configured between AI model-related CSI reports and non-AI model-related CSI reports in the priority relationship configuration instruction, configuring parameter 'a' of the priority relationship configuration instruction for AI model-related CSI reports and parameter 'a' of the priority relationship configuration instruction for non-AI model-related CSI reports can effectively reflect the priority tendency of different categories of CSI reports under different priority relationships, thereby affecting the priority parameters of the final CSI reports.

[0149] In addition, parameters characterizing whether a CSI report contains network quality indicator information are defined as follows: y=0 indicates aperiodic CSI reports carried on the Physical Uplink Shared Channel (PUSCH); y=1 indicates semi-persistent CSI reports carried on the PUSCH; y=2 indicates semi-persistent CSI reports carried on the Physical Uplink Control Channel (PUCCH); and y=3 indicates periodic CSI reports carried on the PUCCH.

[0150] It should be noted that the coefficients involved in the above formula can also be adjusted according to actual needs. This application does not limit them, and the formula is only an example and should not constitute any limitation on this application.

[0151] As an example, the values ​​of some parameters involved in the above formula and the final CSI report priority parameters are shown in Table 1 below:

[0152] Table 1

[0153]

[0154] In the table above, the following resources are assumed to be... , , Same, and , , Resource ID 0: CSI report for AI model performance testing, y=0, k=0, a=-1, b=2; Resource ID 1: CSI report for periodic AI model inference results, y=1, k=0, a=-1, b=1; Resource ID 2: CSI report for non-AI periods, y=2, k=0, a=1, b=0.

[0155] It should be noted that in traditional CSI report prioritization, each CSI report is assigned a unique priority parameter value, meaning it is impossible for two different CSI reports to have the same priority parameter value. This embodiment also follows this requirement, ensuring that all CSI report priority parameter values ​​are unique and uniquely correspond to one CSI report. Unlike traditional CSI reports, the priority parameter values ​​in this embodiment may be negative, but this does not affect the comparison of CSI priority values. The principle of lower priority parameter values ​​indicating higher priority still applies; that is, a CSI report with a negative priority parameter value has a higher priority than a CSI report with a positive priority parameter value. Furthermore, since the priority parameter calculation formula in this embodiment is applicable to terminal devices with AI beam management-based CSI report processing functions, these terminal devices have the ability to process two CSI reports with negative priority values. The specific processing method is not required; for example, even when both priority values ​​are negative, the terminal device can still compare them, and the lower the priority parameter value, the higher the priority. The comparison method can be by comparing the absolute values ​​of the two priority parameter values.

[0156] In some embodiments, based on the calculation method of the CSI report priority parameter provided in the above embodiments, it is possible to directly determine whether some CSI reports should be discarded or not updated according to the CSI report priority parameter. However, this may not be applicable in some AI beam management scenarios. For example, in AI model performance testing, the CSI report of AI model inference results and the CSI report of AI model performance testing compete for resources. According to the above formula, the priority of the CSI report of AI model performance testing is higher than that of the CSI report of AI model inference results, which leads to the CSI report of AI model inference results being discarded or not updated. However, the performance of the AI ​​model needs to be based on the content of the above two CSI reports. The network device may not be able to receive the CSI report of AI model inference results, so it is impossible to obtain the AI ​​model performance index value. Figure 4 This illustration demonstrates that when the CSI report for AI model performance detection and the CSI report for AI model inference results conflict in the time domain, and resources for CSI reporting are scarce, traditional CSI report processing rules will discard the CSI report for AI model inference results. To address the aforementioned technical problem, embodiments of this application can configure sending rules in the task queue to resolve the CSI report conflict issue.

[0157] Optionally, if the CSI report is an AI model performance detection CSI report, then the CSI report is added to the head of the task queue, and the AI ​​model performance detection CSI report at the head of the task queue is sent to the network device through a pre-configured first channel; if the CSI report is not an AI model performance detection CSI report, then the CSI report is added to the task queue according to the priority parameter, and the CSI reports of the task queue are sent to the network device through a second channel in ascending order of priority parameter.

[0158] In this embodiment, CSI reports for AI model performance testing and CSI reports for non-AI model performance testing are sent via different channels. The CSI reports for AI model performance testing are added to the head of the task queue and sent directly to the network device via a pre-configured first channel, without waiting for task queue scheduling, ensuring priority transmission of the AI ​​model performance testing CSI reports. Meanwhile, CSI reports for AI model inference results and CSI reports related to non-AI models are added to the task queue according to priority parameters, sorted based on priority parameters, and await task queue scheduling. The CSI reports for AI model performance testing are sent through a dedicated channel, ensuring that they do not conflict with those for non-AI model performance testing. This is especially important when AI model performance testing CSI reports, AI model inference result CSI reports, and non-AI model-related CSI reports coexist. AI model performance testing CSI reports always take priority, while AI model inference result CSI reports and non-AI model-related CSI reports are sorted according to priority parameters. Furthermore, non-AI model-related CSI reports are usually located at the end of the task queue, effectively preventing the AI ​​model inference result CSI reports from being discarded due to conflicts with AI model performance testing CSI reports.

[0159] The first channel can be the Physical Uplink Control Channel (PUCCH), ensuring low latency and high reliability of CSI reports for AI model performance testing. The second channel can be the Physical Uplink Shared Channel (PUSCH), allowing for more flexible scheduling. Optionally, the CSI reports for AI model performance testing can use L1 (physical layer) signaling and be sent to network devices through the first channel, ensuring low latency and high reliability.

[0160] Optionally, since both CSI reports of AI model inference results and CSI reports unrelated to AI models need to wait for the task queue to schedule the resources of the second channel, in order to ensure the reporting of CSI reports of AI model inference results, the resources of the second channel can be divided into two parts, including a pre-configured second channel and a remaining second channel. The pre-configured second channel can be dedicated to a portion of high-priority CSI reports of AI model inference results, while the remaining second channel is used for CSI reports of the remaining AI model inference results and CSI reports unrelated to AI models.

[0161] Specifically, a preset order can be configured in the task queue, such as the order at 30% of the task queue. For CSI reports of AI model inference results whose priority parameters are higher than the preset order in the task queue, they are sent to the network device through the pre-configured second channel in the second channel, based on the order of priority parameters from smallest to largest. For CSI reports of AI model inference results that are not related to AI models or are not higher than the preset order in the task queue, they are sent to the network device through the remaining second channel in the second channel, based on the order of priority parameters from smallest to largest. This ensures that high-priority CSI reports of AI model inference results are reported, while CSI reports of AI model inference results that are not related to AI models or are not higher than the preset order wait for the task queue to schedule the remaining second channel, achieving efficient resource allocation of the second channel.

[0162] Furthermore, for CSI reports that are not related to AI models or CSI reports that are not in the preset order of AI model inference results in the task queue, if there are not enough remaining second channels, resource preemption is required based on priority parameters. That is, CSI reports with higher priority parameters preempt the remaining second channels occupied by CSI reports with lower priority parameters, so as to ensure that higher priority CSI reports can be reported, while lower priority CSI reports can be discarded.

[0163] In some embodiments, CSI reports related to AI models have a lifecycle, as can be seen in [reference needed]. Figure 4AI model-related CSI reports are valid within their lifecycle, but become invalid after that time and do not need to be sent to network devices. Since AI model performance testing CSI reports are added to the head of the task queue, they are directly sent to network devices via the pre-configured first channel without waiting for task queue scheduling. Therefore, they are usually guaranteed to be sent to network devices within their lifecycle. However, AI model inference result CSI reports need to wait for the task queue to schedule resources for the second channel, and may exceed their lifecycle before being sent to network devices. Therefore, the lifecycle of CSI reports for AI model inference results in the task queue also needs to be considered.

[0164] Optionally, for CSI reports in the task queue, if the CSI report is an AI model inference result CSI report, then configure the lifecycle of the AI ​​model inference result CSI report; before sending the AI ​​model inference result CSI report to the network device, determine whether the lifecycle of the AI ​​model inference result CSI report has ended; if the lifecycle of the AI ​​model inference result CSI report has not ended, then send the AI ​​model inference result CSI report to the network device; if the lifecycle of the AI ​​model inference result CSI report has ended, then discard the AI ​​model inference result CSI report. Determining whether the lifecycle of the AI ​​model inference result CSI report has ended before sending it can avoid resource waste caused by sending AI model inference result CSI reports whose lifecycle has ended to the network device.

[0165] Optionally, for CSI reports in the task queue, if the CSI report is an AI model inference result CSI report, configure the lifecycle of the AI ​​model inference result CSI report; filter out AI model inference result CSI reports in the task queue whose lifecycle has ended, and clear them. By continuously filtering out AI model inference result CSI reports whose lifecycle has ended in the task queue, the resource waste caused by sending AI model inference result CSI reports whose lifecycle has ended to network devices can be avoided, and the space in the task queue can be freed up to process subsequent CSI reports.

[0166] In determining whether the lifecycle of the CSI report of the AI ​​model inference results has ended, the current time can be compared with the end time of the lifecycle of the CSI report of the AI ​​model inference results. Alternatively, the remaining time of the lifecycle can be determined by comparing the start time of the lifecycle of the CSI report of the AI ​​model inference results with the current time, and the lifecycle ends when the remaining time is reduced to 0.

[0167] Optionally, the order of CSI reports for AI model inference results in the task queue can be adjusted based on the remaining time in the lifecycle, so that CSI reports for AI model inference results with shorter remaining time can be sent first.

[0168] In some embodiments, the scheduling time of CSI reports can also be recorded, which helps in subsequent performance analysis and statistics, such as calculating the latency from report generation to scheduling. After the CSI report scheduling is completed, i.e., the CSI report is successfully sent to the network device or the CSI report is discarded, the CSI report entry needs to be removed from the task queue and the related cache space needs to be released to ensure efficient utilization of system resources. Temporary storage data associated with the CSI report should be cleared, such as temporary storage data of CSI reports for AI model inference results in the accelerated processing unit (XPU) of the terminal device. This can release the XPU's cache space to process subsequent CSI reports.

[0169] In some embodiments, when the terminal device has insufficient computing resources, such as insufficient CPU (CSI process units), the terminal device may not update low-priority CSI reports, but instead send historical CSI reports to the network device and send a signal indicating that the CSI report is invalid, so as to indicate to the network device that the CSI report is invalid and that the network device may discard or not update the CSI report.

[0170] In some embodiments, the beam-managed channel state information (CSI) report transmission method provided in this application can also be applied to scenarios such as AI CSI prediction and AI CSI compression. It can meet the needs of timely processing and orderly management of diverse CSI reports, avoiding the processing delays of important CSI reports caused by traditional CSI report priority rules, which affect the accurate prediction of channel states and the rational allocation of resources by network devices. This application embodiment can accurately and promptly report CSI reports, which is crucial for improving the performance of communication systems. By setting reasonable priorities, it can be ensured that critical CSI information can be processed and applied in a timely manner, thereby improving the accuracy of channel prediction and optimizing the quality and efficiency of data transmission. Timely processing of CSI reports reflecting rapid channel changes enables network devices to more accurately predict channel states, reduce data transmission errors and retransmissions, and improve system throughput and reliability. In high-speed mobile scenarios, fast and accurate CSI reports can help network devices adjust signal transmission strategies in a timely manner, ensuring the user's communication experience.

[0171] Figure 5 This is a schematic block diagram of a beam-managed channel state information (CSI) report transmission device 500 provided in an embodiment of this application. Figure 5As shown, the beam-managed channel state information (CSI) report transmission device 500 may include an acquisition module 501, a generation module 502, a priority determination module 503, and a transmission module 504.

[0172] The acquisition module 501 is used to acquire priority relationship configuration instructions, wherein the priority relationship configuration instructions are used to configure the priority relationship between CSI reports related to AI models and CSI reports related to non-AI models applied by beam management;

[0173] The generation module 502 is used to generate a CSI report and add a report category field to the CSI report, wherein the report category field is used to indicate whether the CSI report is an AI model-related CSI report or a non-AI model-related CSI report.

[0174] The priority determination module 503 is used to determine the priority parameters of the CSI report based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report.

[0175] The sending module 504 is used to add the CSI report to the task queue according to the priority parameter, and send the CSI report to the network device according to the task queue.

[0176] In some embodiments, when the priority determination module 503 determines the priority parameter of the CSI report based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report, it is used to:

[0177] Determine the configuration information for the CSI report, which includes: the maximum number of serving cells, the maximum number of CSI reports configured, the serving cell index, the index of the CSI report, the CSI report bearer method, and whether the CSI report includes network quality indicator information;

[0178] Based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report, the priority parameters of the CSI report are determined using a preset priority formula.

[0179] In some embodiments, when the priority determination module 503 determines the priority parameter of the CSI report using a preset priority formula based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report, it is used to:

[0180] The priority parameters of this CSI report are determined using the following preset priority formula. :

[0181]

[0182] in, To maximize the number of service communities, Configure the maximum number of CSI reports. Parameters characterizing the way CSI reports are carried, A parameter used to characterize whether a CSI report contains network quality metrics information. To serve the cell index, 'b' is the CSI report index, 'b' is a parameter representing the report category field, and 'a' is a parameter representing the priority relationship configuration instruction.

[0183] In some embodiments, the priority determination module 503 is further configured to:

[0184] If the CSI report is an AI model performance testing CSI report, then configure the parameter representing the report category field to 2; or

[0185] If the CSI report is a CSI report representing the results of an AI model inference, then the parameter representing the report category field should be set to 1; or

[0186] If the CSI report is not related to an AI model, then the parameter representing the report category field should be set to 0.

[0187] In some embodiments, the priority determination module 503 is further configured to:

[0188] If the priority relationship configuration instruction prioritizes AI model-related CSI reports over non-AI model-related CSI reports, then the parameter representing the priority relationship configuration instruction for AI model-related CSI reports is configured to -1, and the parameter representing the priority relationship configuration instruction for non-AI model-related CSI reports is configured to 1; or

[0189] If the priority relationship configuration instruction configures the priority of non-AI model-related CSI reports to be higher than that of AI model-related CSI reports, then the parameter of the priority relationship configuration instruction representing the AI ​​model-related CSI reports will be configured to 1, and the parameter of the priority relationship configuration instruction representing the non-AI model-related CSI reports will be configured to -1.

[0190] In some embodiments, when the sending module 504 adds the CSI report to a task queue according to a priority parameter and sends the CSI report to the network device according to the task queue, it is used to:

[0191] If the CSI report is an AI model performance detection CSI report, then add the CSI report to the head of the task queue, and send the AI ​​model performance detection CSI report at the head of the task queue to the network device through the pre-configured first channel; or

[0192] If the CSI report is not a CSI report for AI model performance testing, then the CSI report is added to the task queue according to the priority parameter, and the CSI reports of the task queue are sent to the network device through the second channel in ascending order of priority parameter.

[0193] In some embodiments, if the sending module 504 determines that the CSI report is not a CSI report for AI model performance detection, and adds the CSI report to the task queue according to the priority parameter, and sends the CSI reports of the task queue to the network device through the second channel in ascending order of the priority parameter, the module is used to:

[0194] For CSI reports of AI model inference results whose priority parameters are located before a preset order in the task queue, they are sent to the network device through a pre-configured second channel based on the order of priority parameters from smallest to largest; or

[0195] For CSI reports that are not related to the AI ​​model or CSI reports that are not in the preset order of AI model inference results in the task queue, they are sent to the network device through the remaining second channel in the second channel in ascending order of priority parameter.

[0196] In some embodiments, when the sending module 504 sends CSI reports that are not related to the AI ​​model or CSI reports of AI model inference results that are not located in the preset order to the network device through the remaining second channel in the second channel based on the priority parameter in ascending order, it is used to:

[0197] For CSI reports that are not related to AI models or CSI reports that are not in the preset order of AI model inference results in the task queue, if there are not enough remaining second channels in the second channel, the CSI report with higher priority parameters will take over the remaining second channels occupied by the CSI report with lower priority parameters.

[0198] In some embodiments, the first channel is a physical uplink control channel; the second channel is a physical uplink shared channel.

[0199] In some embodiments, the sending module 504 is further configured to:

[0200] If the CSI report is a CSI report of AI model inference results, then configure the lifecycle of the CSI report of AI model inference results;

[0201] Before sending the CSI report of the AI ​​model inference results to the network device, determine whether the lifecycle of the CSI report of the AI ​​model inference results has ended;

[0202] If the CSI report for the AI ​​model inference result has not yet expired, then the CSI report for the AI ​​model inference result is sent to the network device; or

[0203] If the CSI report for the AI ​​model inference results has reached the end of its lifecycle, then discard the CSI report for the AI ​​model inference results.

[0204] In some embodiments, the sending module 504 is further configured to:

[0205] If the CSI report is a CSI report of AI model inference results, then configure the lifecycle of the CSI report of AI model inference results;

[0206] Filter and clear CSI reports of AI model inference results that have ended their lifecycle in the task queue.

[0207] In some embodiments, when the acquisition module 501 acquires the priority relationship configuration instruction, it is used to:

[0208] Based on the terminal device capabilities and / or scenario, configure the priority relationship between CSI reports related to AI models and CSI reports related to non-AI models, and generate configuration instructions for this priority relationship; or

[0209] Receive the priority relationship configuration instruction sent by the network device.

[0210] In some embodiments, the acquisition module 501 is further configured to:

[0211] Receive the task queue configuration information sent by the network device, and configure the task queue according to the task queue configuration information.

[0212] In some embodiments, the task queue configuration information includes the capacity of the task queue.

[0213] It should be understood that the specific process of each module performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0214] It should be noted that the module names involved in the embodiments of this application can all be defined as other names, as long as they can achieve the function of each module, and no specific restrictions are placed on the module names.

[0215] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0216] The channel state information (CSI) report transmission method for beam management according to embodiments of this application has been described above. The apparatus for executing the above method provided in embodiments of this application is described below. Those skilled in the art will understand that the methods and apparatus can be combined with and referenced in relation to each other, and the related apparatus provided in embodiments of this application can execute the steps in the above method.

[0217] Figure 6 This is a schematic diagram of a possible structure of the electronic device 6000 provided in an embodiment of this application. The electronic device 6000 can be applied to, for example... Figure 1 In the system shown, the functions of the terminal device in the above method embodiments are executed. For example... Figure 6 As shown, the electronic device 6000 includes a processor 6010 and a transceiver 6020. Optionally, the electronic device 6000 also includes a memory 6030. The processor 6010, transceiver 6020, and memory 6030 can communicate with each other via internal connections to transmit control and / or data signals. The memory 6030 stores computer programs, and the processor 6010 retrieves and runs the computer programs from the memory 6030 to control the transceiver 6020 to transmit and receive signals. Optionally, the electronic device 6000 may also include an antenna 6040 for transmitting uplink data or uplink control signaling output by the transceiver 6020 via wireless signals.

[0218] The processor 6010 and the memory 6030 can be combined into a single processing device. The processor 6010 executes the program code stored in the memory 6030 to achieve the above functions. In specific implementations, the memory 6030 can be integrated into the processor 6010 or independent of the processor 6010.

[0219] The transceiver 6020 described above may include a receiver (or receiver circuit) and a transmitter (or transmitter circuit). The receiver is used to receive signals, and the transmitter is used to transmit signals.

[0220] It should be understood that Figure 6The electronic device 6000 shown can implement the various processes involving the terminal device in the above method embodiments. The operation and / or function of each module in the electronic device 6000 are respectively for implementing the corresponding processes in the above method embodiments. For details, please refer to the description in the above method embodiments; to avoid repetition, detailed descriptions are appropriately omitted here.

[0221] The processor 6010 described above can be used to execute the actions implemented internally by the terminal device as described in the preceding method embodiments, while the transceiver 6020 can be used to execute the actions described in the preceding method embodiments of sending data to or receiving data from the network device by the terminal device. For details, please refer to the descriptions in the preceding method embodiments; they will not be repeated here.

[0222] Optionally, the aforementioned electronic device 6000 may also include a power supply 6050 for providing power to various devices or circuits in the terminal device.

[0223] In addition, to make the terminal device more functional, the electronic device 6000 may also include one or more of the following: an input unit 6060, a display unit 6070, an audio circuit 6080, a camera 6090, and a sensor 6100. The audio circuit may also include a speaker 6110, a microphone 6120, etc.

[0224] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the technical solution executed by the terminal device or network device in the above communication method embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0225] In one possible implementation, a computer-readable storage medium may include random access memory (RAM), read-only memory (ROM), compact discread-only memory (CD-ROM) or other optical disc storage, disk storage or other magnetic storage devices, or any other medium targeted to carry or to store the required program code in the form of instructions or data structures, and accessible by a computer. Furthermore, any connection is appropriately referred to as a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. As used herein, disks and optical discs include optical discs, laser discs, optical discs, Digital Versatile Discs (DVDs), floppy disks, and Blu-ray discs, where disks typically reproduce data magnetically, while optical discs optically reproduce data using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0226] This application also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the technical solution executed by the terminal device or network device in the above communication method embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0227] This application also provides a chip or chip system, which includes at least one processor and a communication interface. The communication interface and the at least one processor are interconnected via a circuit. The at least one processor is used to run computer programs or instructions to execute the technical solution executed by the terminal device or network device in the above-described communication method embodiments. Its implementation principle and technical effects are similar and will not be repeated here. The communication interface in the chip can be an input / output interface, pins, or circuits, etc.

[0228] In one possible implementation, the chip or chip system described above in this application further includes at least one memory, in which instructions are stored. The memory can be an internal storage unit of the chip, such as a register or cache, or it can be a storage unit of the chip itself (e.g., read-only memory, random access memory, etc.).

[0229] In the specific implementation of the aforementioned terminal device or network device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules within the processor.

[0230] Those skilled in the art will understand that all or part of the steps in any of the above method embodiments can be implemented by hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium, and when the program is executed, all or part of the steps in the above method embodiments are performed.

[0231] If the technical solution of this application is implemented in software form and sold or used as a product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solution of this application can be embodied in the form of a software product, which is stored in a storage medium and includes a computer program or several instructions. This computer software product causes a computer device (which may be a personal computer, server, network device, or similar electronic device) to execute all or part of the steps of the method described in the embodiments of this application.

[0232] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0233] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0234] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0235] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0236] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0237] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 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 of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0238] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0239] The above specific embodiments further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. A beam-managed channel state information (CSI) report transmission method, characterized in that, Applied to a terminal device, the method includes: Obtain priority relationship configuration instructions, wherein the priority relationship configuration instructions are used to configure the priority relationship between CSI reports related to AI models and CSI reports related to non-AI models applied by beam management; Generate a CSI report, and add a report category field to the CSI report, wherein the report category field is used to characterize whether the CSI report is an AI model-related CSI report or a non-AI model-related CSI report; Based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report, the priority parameters of the CSI report are determined; The CSI report is added to the task queue according to the priority parameter, and then sent to the network device according to the task queue.

2. The method according to claim 1, characterized in that, The step of determining the priority parameters of the CSI report based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report includes: The configuration information of the CSI report is determined, including: the maximum number of serving cells, the maximum number of CSI reports configured, the serving cell index, the index of the CSI report, the CSI report carrying method, and whether the CSI report includes network quality indicator information; Based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report, the priority parameters of the CSI report are determined using a preset priority formula.

3. The method according to claim 2, characterized in that, The priority parameters of the CSI report are determined using a preset priority formula based on the priority relationship configuration instruction, the report category field, and the configuration information of the CSI report, including: The priority parameters of the CSI report are determined using the following preset priority formula. : in, To maximize the number of service communities, Configure the maximum number of CSI reports. Parameters characterizing the way CSI reports are carried, A parameter used to characterize whether a CSI report contains network quality metrics information. To serve the cell index, 'b' is the CSI report index, 'b' is a parameter representing the report category field, and 'a' is a parameter representing the priority relationship configuration instruction.

4. The method according to claim 3, characterized in that, The method further includes: If the CSI report is an AI model performance testing CSI report, then the parameter representing the report category field is configured to 2; or If the CSI report is a CSI report representing the inference results of an AI model, then the parameter representing the report category field is configured to 1; or If the CSI report is a non-AI model-related CSI report, then the parameter representing the report category field is configured to 0.

5. The method according to claim 3, characterized in that, The method further includes: If the priority relationship configuration instruction configures the priority of CSI reports related to AI models to be higher than that of CSI reports related to non-AI models, then the parameter representing the priority relationship configuration instruction for CSI reports related to AI models is configured to -1, and the parameter representing the priority relationship configuration instruction for CSI reports related to non-AI models is configured to 1; or If the priority relationship configuration instruction configures the priority of non-AI model-related CSI reports to be higher than that of AI model-related CSI reports, then the parameter representing the priority relationship configuration instruction for AI model-related CSI reports is configured to 1, and the parameter representing the priority relationship configuration instruction for non-AI model-related CSI reports is configured to -1.

6. The method according to any one of claims 1-5, characterized in that, The step of adding the CSI report to the task queue according to the priority parameter and sending the CSI report to the network device according to the task queue includes: If the CSI report is an AI model performance detection CSI report, then the CSI report is added to the head of the task queue, and the AI ​​model performance detection CSI report at the head of the task queue is sent to the network device through a pre-configured first channel; or If the CSI report is not a CSI report for AI model performance detection, then the CSI report is added to the task queue according to the priority parameter, and the CSI reports in the task queue are sent to the network device through the second channel in ascending order of priority parameter.

7. The method according to claim 6, characterized in that, If the CSI report is not a CSI report for AI model performance detection, then the CSI report is added to the task queue according to the priority parameter, and the CSI reports in the task queue are sent to the network device through the second channel in ascending order of the priority parameter, including: For CSI reports of AI model inference results whose priority parameters are located before a preset order in the task queue, they are sent to the network device through a pre-configured second channel in the second channel, based on the order of priority parameters from smallest to largest; or For CSI reports that are not related to the AI ​​model or CSI reports that are not in the preset order of AI model inference results in the task queue, they are sent to the network device through the remaining second channel in the second channel in ascending order of priority parameter.

8. The method according to claim 7, characterized in that, The CSI reports that are not related to the AI ​​model or are CSI reports of AI model inference results that are not in a preset order in the task queue are sent to the network device through the remaining second channel in the second channel in ascending order of priority parameter, including: For CSI reports that are not related to the AI ​​model or CSI reports that are not in the preset order of the task queue, if there are not enough remaining second channels in the second channel, the CSI report with higher priority parameters will preempt the remaining second channels occupied by the CSI report with lower priority parameters.

9. The method according to claim 6, characterized in that, The first channel is the physical uplink control channel; the second channel is the physical uplink shared channel.

10. The method according to claim 1, characterized in that, The method further includes: If the CSI report is a CSI report of AI model inference results, then configure the lifecycle of the CSI report of AI model inference results; Before sending the CSI report of the AI ​​model inference results to the network device, determine whether the lifecycle of the CSI report of the AI ​​model inference results has ended; If the CSI report of the AI ​​model inference result has not yet ended its lifecycle, then the CSI report of the AI ​​model inference result is sent to the network device; or If the CSI report for the AI ​​model inference results has reached the end of its lifecycle, then discard the CSI report for the AI ​​model inference results.

11. The method according to claim 1, characterized in that, The method further includes: If the CSI report is a CSI report of AI model inference results, then configure the lifecycle of the CSI report of AI model inference results; Filter and clear CSI reports of AI model inference results whose lifecycles have ended in the task queue.

12. The method according to claim 1, characterized in that, The instruction to obtain priority relationship configuration includes: Based on the terminal device capabilities and / or scenario, configure the priority relationship between CSI reports related to AI models and CSI reports related to non-AI models, and generate the priority relationship configuration instruction; or Receive the priority relationship configuration instruction sent by the network device.

13. The method according to claim 1, characterized in that, The method further includes: Receive task queue configuration information sent by the network device, and configure the task queue according to the task queue configuration information.

14. The method according to claim 13, characterized in that, The task queue configuration information includes the capacity of the task queue.

15. An electronic device, characterized in that, include: Processor and memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the electronic device to perform the method as described in any one of claims 1-14.

16. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-14.

17. A computer program product, characterized in that, Includes a computer program that, when run, causes a computer to perform the method as described in any one of claims 1-14.

Images