Method and device for determining processing delay requirement, terminal equipment and network equipment

Abstract

Provided in an embodiment of the present application are a method and device for determining a processing delay requirement, a terminal device, and a network device, the method comprising: a terminal device determining a CSI processing delay requirement corresponding to CSI reporting based on a first model, the CSI reporting being CSI reporting based on AI / ML, the first model being a model used by the CSI reporting; and the terminal device determines whether to carry out the CSI reporting and / or whether to update the CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

Description

Method and device for determining processing delay requirements, terminal equipment, and network equipment Technical Field

[0001] The embodiments of the present application relate to the field of mobile communication technology, and specifically to a method and apparatus for determining processing delay requirements, a terminal device, and a network device. Background Art

[0002] For semi-continuous or non-periodic channel state information (CSI) reporting, the network device can be triggered by downlink control information (DCI), but sufficient processing time must be reserved for the terminal device for the corresponding CSI measurement and preparation of the physical uplink shared channel (PUSCH) that carries the CSI. The delay requirement that this processing time needs to meet is the CSI processing delay requirement.

[0003] CSI reporting can be implemented based on artificial intelligence / machine learning (AI / ML) models, referred to as AI / ML-based CSI reporting or AI / ML-based CSI reporting. Currently, the design of CSI processing latency requirements does not consider the processing complexity and latency required for AI / ML-based CSI reporting. Furthermore, different AI / ML models have different inference complexities and require different processing times. Using a fixed CSI processing latency requirement makes it difficult to support flexible switching between AI / ML models.

[0004] Summary of the Invention

[0005] Embodiments of the present application provide a method and apparatus for determining processing delay requirements, a terminal device, a network device, a chip, a computer-readable storage medium, a computer program product, and a computer program.

[0006] In a first aspect, an embodiment of the present application provides a method for determining a processing latency requirement, the method comprising:

[0007] The terminal device determines, based on a first model, a CSI processing delay requirement corresponding to a CSI report, where the CSI report is an AI / ML-based CSI report and the first model is a model used for the CSI report;

[0008] The terminal device determines whether to perform the CSI reporting and / or whether to update the CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

[0009] In a second aspect, an embodiment of the present application provides a method for determining a processing latency requirement, the method comprising:

[0010] The network device determines, based on a first model, a CSI processing latency requirement corresponding to a CSI report, where the CSI report is an AI / ML-based CSI report and the first model is a model used for the CSI report;

[0011] The network device triggers the terminal device to perform the CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

[0012] In a third aspect, an embodiment of the present application provides a device for determining a processing delay requirement, which is applied to a terminal device, and includes:

[0013] a determination unit for determining, based on a first model, a CSI processing delay requirement corresponding to a channel state information (CSI) report, where the CSI report is an AI / ML-based CSI report and the first model is a model used for the CSI report; and determining, based on the CSI processing delay requirement corresponding to the CSI report, whether to perform the CSI report and / or whether to update the CSI report.

[0014] In a fourth aspect, an embodiment of the present application provides a device for determining a processing delay requirement, which is applied to a network device, and includes:

[0015] a determining unit, configured to determine, based on a first model, a CSI processing delay requirement corresponding to a CSI report, where the CSI report is an AI / ML-based CSI report, and the first model is a model used for the CSI report;

[0016] A triggering unit is used to trigger the terminal device to perform the CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

[0017] In a fifth aspect, an embodiment of the present application provides a terminal device comprising a processor and a memory. The memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory to perform the above-mentioned method for determining the processing delay requirement.

[0018] In a sixth aspect, an embodiment of the present application provides a network device comprising a processor and a memory. The memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory to perform the above-mentioned method for determining the processing delay requirement.

[0019] In a seventh aspect, an embodiment of the present application provides a chip, which includes: a processor for calling and running a computer program from a memory, so that a device equipped with the chip executes the above-mentioned method for determining the processing delay requirement.

[0020] In an eighth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by at least one processor, implements the above-mentioned method for determining the processing delay requirement.

[0021] In a ninth aspect, an embodiment of the present application provides a computer program product, which includes computer program instructions, and the computer program instructions enable a computer to execute the above-mentioned method for determining the processing delay requirement.

[0022] In a tenth aspect, the computer program provided in the embodiment of the present application, when running on a computer, enables the computer to execute the above-mentioned method for determining the processing delay requirement.

[0023] The technical solution of the embodiment of the present application takes into account the processing complexity and processing delay required for CSI reporting based on the AI / ML model (referred to as the model), and the terminal device / network device determines the CSI processing delay requirement corresponding to the CSI reporting based on the first model. In this way, different CSI processing delay requirements can be determined for different models, thereby supporting flexible switching between different AI / ML models without exceeding the processing capability of the terminal device, thereby ensuring the accuracy of CSI feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0025] FIG1 is a schematic diagram of an application scenario of an embodiment of the present application;

[0026] FIG2 is a schematic diagram of CSI reporting methods with different periodicities;

[0027] FIG3 is a first schematic diagram of CSI processing latency requirements;

[0028] FIG4 is a second schematic diagram of CSI processing latency requirements;

[0029] FIG5 is a third schematic diagram of CSI processing latency requirements;

[0030] Figure 6 is a schematic diagram of an example of neuron structure;

[0031] FIG7 is a schematic diagram of an example of a neural network;

[0032] FIG8 is a schematic diagram of a neural network for CSI feedback;

[0033] FIG9 is a flowchart of a method for determining a processing delay requirement according to an embodiment of the present application;

[0034] FIG10 is a second flow chart of a method for determining a processing delay requirement according to an embodiment of the present application;

[0035] FIG11 is a flowchart of a method for determining a processing delay requirement according to an embodiment of the present application;

[0036] FIG12 is a schematic diagram of the first structure of a device for determining a processing delay requirement according to an embodiment of the present application;

[0037] FIG13 is a second schematic diagram of the structure of the apparatus for determining the processing delay requirement according to an embodiment of the present application;

[0038] FIG14 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0039] FIG15 is a schematic structural diagram of a chip according to an embodiment of the present application;

[0040] FIG16 is a schematic block diagram of a communication system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0042] FIG1 is a schematic diagram of an application scenario of an embodiment of the present application.

[0043] As shown in Figure 1, a communication system 100 may include a terminal device 110 and a network device 120. The network device 120 may communicate with the terminal device 110 via an air interface. The terminal device 110 and the network device 120 support multi-service transmission.

[0044] It should be understood that the embodiments of the present application are only illustrative of the communication system 100, but the embodiments of the present application are not limited thereto. That is, the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, LTE Time Division Duplex (TDD), Universal Mobile Telecommunication System (UMTS), Internet of Things (IoT) system, Narrow Band Internet of Things (NB-IoT) system, enhanced Machine-Type Communications (eMTC) system, 5G communication system (also known as New Radio (NR) communication system), or future communication systems.

[0045] In the communication system 100 shown in Figure 1, the network device 120 may be an access network device that communicates with the terminal device 110. The access network device may provide communication coverage for a specific geographical area and may communicate with the terminal device 110 (eg, UE) located within the coverage area.

[0046] The network device 120 may be an evolved Node B (eNB or eNodeB) in a Long Term Evolution (LTE) system, or a Next Generation Radio Access Network (NG RAN) device, or a base station (gNB) in an NR system, or a wireless controller in a Cloud Radio Access Network (CRAN), or the network device 120 may be a relay station, an access point, an in-vehicle device, a wearable device, a hub, a switch, a bridge, a router, or a network device in a future evolved Public Land Mobile Network (PLMN), etc.

[0047] The terminal device 110 may be any terminal device, including but not limited to a terminal device connected to the network device 120 or other terminal devices by wire or wireless connection.

[0048] For example, the terminal device 110 may refer to an access terminal, user equipment (UE), a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user apparatus. An access terminal may be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, an IoT device, a satellite handheld terminal, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in a 5G network, or a terminal device in a future evolution network, etc.

[0049] The terminal device 110 can be used for device-to-device (D2D) communication.

[0050] The wireless communication system 100 may further include a core network device 130 for communicating with the base station. The core network device 130 may be a 5G core network (5G Core, 5GC) device, such as an Access and Mobility Management Function (AMF), an Authentication Server Function (AUSF), a User Plane Function (UPF), or a Session Management Function (SMF). Optionally, the core network device 130 may also be an Evolved Packet Core (EPC) device of an LTE network, such as a Session Management Function + Core Packet Gateway (SMF+PGW-C) device. It should be understood that SMF+PGW-C can simultaneously implement the functions that can be implemented by SMF and PGW-C. During the network evolution process, the above-mentioned core network device may also be called other names, or a new network entity may be formed by dividing the functions of the core network, which is not limited in the embodiments of the present application.

[0051] The functional units in the communication system 100 may also establish connections and implement communication via next generation (NG) network interfaces.

[0052] For example, the terminal device establishes an air interface connection with the access network device through the NR interface for transmitting user plane data and control plane signaling; the terminal device can establish a control plane signaling connection with the AMF through the NG interface 1 (referred to as N1); the access network device, such as the next generation wireless access base station (gNB), can establish a user plane data connection with the UPF through the NG interface 3 (referred to as N3); the access network device can establish a control plane signaling connection with the AMF through the NG interface 2 (referred to as N2); the UPF can establish a control plane signaling connection with the SMF through the NG interface 4 (referred to as N4); the UPF can exchange user plane data with the data network through the NG interface 6 (referred to as N6); the AMF can establish a control plane signaling connection with the SMF through the NG interface 11 (referred to as N11); the SMF can establish a control plane signaling connection with the PCF through the NG interface 7 (referred to as N7).

[0053] Figure 1 exemplarily shows a base station, a core network device and two terminal devices. Optionally, the wireless communication system 100 may include multiple base station devices and each base station may include other numbers of terminal devices within its coverage area, which is not limited in this embodiment of the present application.

[0054] It should be noted that Figure 1 is merely an example of a system applicable to this application. Of course, the methods described in the embodiments of this application can also be applied to other systems. Furthermore, the terms "system" and "network" are often used interchangeably herein. The term "and / or" herein simply describes an association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates that the associated objects are in an "or" relationship. It should also be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association relationship. For example, "A indicates B" can mean that A directly indicates B, for example, B can obtain information through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can obtain information through C; or it can mean that A and B have an association relationship. It should also be understood that the "correspondence" mentioned in the embodiments of this application can mean that there is a direct or indirect correspondence between two objects, or that there is an association relationship between the two objects, or a relationship between an indicator and the indicated, a configuration and the configured, and so on. It should also be understood that the “predefined” or “predefined rules” mentioned in the embodiments of the present application can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including a terminal device and a network device), and the present application does not limit its specific implementation method. For example, predefined can refer to a definition in a protocol. It should also be understood that in the embodiments of the present application, the “protocol” can refer to a standard protocol in the field of communications, such as an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.

[0055] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following relevant technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the protection scope of the embodiments of the present application.

[0056] 1. Downlink CSI feedback

[0057] In order for the network equipment to perform reasonable scheduling, the terminal equipment needs to feedback downlink CSI so that the network equipment can determine the scheduling information of the terminal equipment such as the number of transmission layers, precoding matrix, transmit beam, modulation and coding method. The terminal equipment feedbacks downlink CSI, which can also be understood as the terminal equipment performing CSI reporting. Specifically, the terminal equipment performs CSI reporting based on the CSI reporting configuration indicated by the network equipment. The uplink resources used by the terminal equipment for CSI reporting and the downlink reference signal used for CSI measurement are both indicated by the CSI reporting configuration. Each CSI reporting configuration corresponds to a CSI report, and each CSI report can include CSI-RS Resource Indicator (CRI), Rank Indicator (RI), Precoding Matrix Indicator (PMI), Channel Quality Indicator (CQI), Layer Indicator (LI), Reference Signal Receiving Power (RSRP) and other information. The information included in the CSI report is indicated by the report quantity information in the CSI reporting configuration. For example, Table 1 below shows the report quantities that can be indicated by the report quantity information. For example, if the report quantity is "cri-RI-PMI-CQI," the CSI report must include information such as CRI, RI, PMI, and CQI.

[0058] Table 1

[0059] The CRI is used to determine the CSI-RS resource currently used for channel measurement and the Interference Measurement Resource (IMR) currently used for interference measurement from multiple Channel State Information–Reference Signal (CSI-RS) resources. The RI is used to report the recommended number of transmission layers. The PMI is used to determine the recommended precoding matrix from a predefined codebook. The CQI is used to report the current channel quality and can be determined based on the Signal to Interference plus Noise Ratio (SINR) estimated by the terminal device. The channel portion of the SINR is determined based on the non-zero-power CSI-RS configured by the network for channel measurement, and the interference portion is determined based on the Channel State Information–Interference Measurement Resource (CSI-IM) or non-zero-power CSI-RS configured by the network device for interference measurement. The CQI is calculated based on the reported RI and PMI. The RSRP is used to report the RSRP of the CSI-RS or SSB corresponding to the reported index, which is used by the network device to determine the beam used for downlink transmission. LI is used to report the index of the transport layer associated with PTRS.

[0060] Terminal devices can report CSI in three ways: periodic CSI reporting, semi-persistent CSI reporting, and aperiodic CSI reporting. As shown in Figure 2, for periodic CSI reporting, CSI reporting is transmitted on the Physical Uplink Control Channel (PUCCH), and its CSI reporting configuration is configured by RRC signaling. After receiving the RRC signaling for configuring CSI reporting, the terminal device periodically reports CSI. For semi-persistent CSI reporting, CSI reporting can be transmitted on the PUCCH or PUSCH. The CSI reporting configuration corresponding to the CSI reporting transmitted on the PUCCH is pre-configured by RRC signaling and activated or deactivated by Media Access Control (MAC) layer signaling (such as MAC CE). The CSI reporting configuration corresponding to the CSI reporting transmitted on the PUSCH is dynamically indicated (activated or deactivated) via the DCI. After receiving the activation signaling configured by the network device, the terminal device periodically reports CSI on the PUCCH or PUSCH until it receives the deactivation signaling and stops reporting. The CSI reporting configuration corresponding to aperiodic CSI reporting is also pre-configured via RRC signaling. Some of the configurations can be activated via MAC layer signaling (such as MAC CE), and the CSI reporting configuration used for CSI reporting is then indicated by CSI trigger signaling in the DCI. After receiving the CSI trigger signaling, the terminal device performs the corresponding CSI reporting on the scheduled PUSCH once according to the indicated CSI reporting configuration.

[0061] When a CSI carries a large number of bits, in order to give priority to the transmission of important information, a CSI can be divided into two parts (part), namely CSI part 1 and CSI part 2. Exemplarily, for different types of codebooks, the information contained in CSI part 1 and CSI part 2 is shown in Table 2 below. The number of bits in CSI part 1 is fixed and is used to carry a small amount of important information such as RI and CQI; the number of bits in CSI part 2 is determined according to CSI part 1 and is used to carry information with a larger number of bits such as PMI. When the code rate of the PUSCH / PUCCH carrying CSI exceeds a certain value, the terminal device needs to discard some information in CSI part 2 to ensure the transmission performance of PUSCH / PUCCH, that is, the code rate cannot exceed the reference value configured by the network device. Specifically, the information in CSI part 1 will not be discarded, and the information in CSI part 2 will discard the lower priority information first according to the priority of CSI reporting. The priority of CSI reporting is determined based on the periodicity of the CSI report (periodic CSI reporting, semi-persistent CSI reporting, or aperiodic CSI reporting), the content of the CSI report (such as whether RSRP is included), the carrier corresponding to the CSI report (i.e., carrier index), and the CSI reporting configuration ID corresponding to the CSI report. If a CSI report has a lower priority and the information in CSI Part 2 needs to be discarded, the information corresponding to odd subbands is discarded first, followed by the information corresponding to even subbands, and finally the wideband information, until the bit rate meets the requirement.

[0062] Table 2

[0063] 2. CSI processing delay

[0064] For semi-persistent or aperiodic CSI reporting, as shown in Figure 2, network devices can trigger it via DCI. However, sufficient processing time must be reserved for the terminal device to perform the corresponding CSI measurement and prepare the PUSCH carrying the CSI. Because different CSI types require different CSI processing times, to ensure that the terminal device has sufficient time to prepare the CSI, the protocol defines different CSI processing delay requirements, expressed as Z / Z'.

[0065] 1) For DCI-triggered CSI reporting, the interval T between the last orthogonal frequency division multiplexing (OFDM) symbol of the physical downlink control channel (PDCCH) carrying DCI and the first OFDM symbol of the PUSCH carrying CSI must be greater than or equal to T proc,CSI(Unit is OFDM symbol), otherwise the terminal device does not report CSI, as shown in Figure 3, symbol Z ref The interval between the last OFDM symbol of the PDCCH carrying DCI is T proc,CSI .

[0066] If PUSCH only contains CSI, then T proc,CSI =(Z)(2048+144)·κ2 -μ ·T c ; If CSI and data / HARQ-ACK are multiplexed in PUSCH, then T proc,CSI =(Z+d)·(2048+144)·κ2 -μ ·T c , for subcarrier spacing of 15 / 30 / 60 / 120kHz, the values ​​of d are {2,2,3,4} respectively.

[0067] Where Z = max m＝0,…,M-1 (Z(m)), where M is the number of CSI reports included in the CSI, and Z(m) is the CSI processing delay requirement corresponding to the m-th CSI report among the M CSI reports. Z can be called the first CSI processing delay requirement.

[0068] Wherein, μ is the subcarrier spacing parameter. For subcarrier spacing of 15 / 30 / 60 / 120 kHz, the values ​​of μ are {0, 1, 2, 3} respectively.

[0069] Where κ = T s / T c , T s and T c They are different time units and have fixed values.

[0070] If the above CSI processing delay requirement cannot be met (i.e. T<T proc,CSI ), and the semi-persistent or aperiodic CSI reporting is not multiplexed with HARQ-ACK / data, the terminal device ignores DCI and does not send PUSCH, that is, does not perform CSI reporting (such as not performing semi-persistent or aperiodic CSI reporting). If the above CSI processing delay requirement cannot be met (i.e., T<T proc,CSI ), and semi-continuous or non-periodic CSI reporting and HARQ-ACK / data are multiplexed, the terminal device sends PUSCH, which does not carry CSI but only HARQ-ACK / data.

[0071] 2) If aperiodic CSI reporting is based on aperiodic CSI-RS / CSI-IM measurements, the interval T between the last OFDM symbol in these CSI-RS / CSI-IM and the first OFDM symbol of the corresponding PUSCH carrying CSI must be greater than or equal to T' proc,CSI (Unit is OFDM symbol), otherwise the terminal device does not need to perform corresponding reporting and / or measurement, as shown in Figure 4, symbol Z' ref The interval between the last OFDM symbol in CSI-RS / CSI-IM is T' proc,CSI Here, CSI-RS / CSI-IM resources belong to CSI measurement resources. CSI-RS resources are used for channel measurement, and CSI-IM resources are used for interference measurement. proc,CSI =(Z′)(2048+144)·κ2 -μ ·T c

[0072] Where Z′=max m＝0,…,M-1 (Z′(m)), where M is the number of CSI reports included in the CSI, and Z′(m) is the CSI processing delay requirement corresponding to the mth CSI report among the M CSI reports. Z′ can be referred to as the second CSI processing delay requirement.

[0073] If the above CSI processing delay requirement cannot be met (ie T<T' proc,CSI ), and the DCI only triggers one CSI report, and the CSI report is not multiplexed with HARQ-ACK / data, the terminal device ignores the DCI and does not send PUSCH, that is, no CSI report is performed; for other cases, the terminal device does not need to update the CSI report that does not meet the above CSI processing delay requirements (but still performs CSI reporting).

[0074] 3) If non-periodic CSI reporting is based on periodic or semi-persistent CSI-RS / CSI-IM measurements, the interval T between the last OFDM symbol in these CSI-RS / CSI-IM and the first OFDM symbol of the corresponding PUSCH carrying CSI must be greater than or equal to Z' (in OFDM symbols), otherwise the terminal device does not need to perform measurements, as shown in Figure 5.

[0075] Here, Z' can be called the second CSI processing delay requirement.

[0076] If the above CSI processing delay requirement cannot be met (ie, T<Z'), the terminal device still needs to perform CSI reporting, but does not need to update the CSI reporting.

[0077] In the above scheme, μ and Z / Z' can be determined according to the following method:

[0078] a)μ=min(μ PDCCH ,μ CSI-RS ,μ UL )

[0079] Among them, μ PDCCH Indicates the subcarrier spacing of the PDCCH where the DCI used to trigger CSI reporting is located; μ UL Indicates the subcarrier spacing of the PUSCH used to carry CSI reporting; μ CSI-RS Indicates the minimum subcarrier spacing in the aperiodic CSI-RS triggered by the DCI used to trigger CSI reporting.

[0080] b) The values ​​of Z / Z' can refer to the following Tables 3 and 4; Table 3 shows the values ​​of Z1 / Z1' under different subcarrier spacings, corresponding to CSI processing delay requirement 1 (CSI computation delay requirement 1); Table 4 shows the values ​​of Z1 / Z1', Z2 / Z2' and Z3 / Z3' under different subcarrier spacings, corresponding to CSI processing delay requirement 2 (CSI computation delay requirement 2), where X is the capability beam reporting time (beamReportTiming) reported by the terminal device, and KB is the capability beam switching time (beamSwitchTiming) reported by the terminal device.

[0081] Table 3

[0082] Table 4

[0083] The values ​​of Z / Z' given in Tables 3 and 4 above are used according to the following rules:

[0084] The values ​​of Z / Z' corresponding to fast CSI reporting are the values ​​of Z1 / Z1' in Table 3. Fast CSI reporting must meet all of the following conditions:

[0085] CSI reporting is aperiodic and not multiplexed with other information, and the CPU is not currently occupied.

[0086] The CSI report is a single wideband CSI report corresponding to a single CSI-RS resource (up to 4 ports, no CRI); and,

[0087] The RRC parameter configuration corresponding to CSI reporting is: codebookType = 'typeI-SinglePanel', reportQuantity = 'cri-RI-CQI'.

[0088] The Z / Z' values ​​for sub-fast CSI reporting are the same as the Z1 / Z1' values ​​in Table 4. Sub-fast CSI reporting must meet all of the following conditions:

[0089] The CSI report is a single wideband CSI report corresponding to a single CSI-RS resource (up to 4 ports, no CRI); and,

[0090] The RRC parameter configuration corresponding to CSI reporting is: codebookType = 'typeI-SinglePanel', reportQuantity = 'cri-RI-CQI'.

[0091] The values ​​of Z / Z' corresponding to the CSI report used for beam reporting are the values ​​of Z3 / Z3' in Table 3. The CSI report used for beam reporting must meet all of the following conditions:

[0092] The RRC parameter configuration corresponding to CSI reporting is: reportQuantity = 'cri-RSRP' or 'ssb-Index-RSRP'.

[0093] In addition to the above-mentioned fast CSI reporting, sub-fast CSI reporting and CSI reporting for beam reporting, the values ​​of Z / Z' corresponding to other CSI reporting are the values ​​of Z2 / Z2' in Table 3.

[0094] 3. Neural Networks for CSI

[0095] 1) Neuronal structure

[0096] A neural network is a computational model consisting of multiple interconnected neuron nodes. The connections between the nodes represent the weighted values ​​from the input signal to the output signal, which are called weights. Each node performs a weighted summation of different input signals and outputs them through a specific activation function. The neuron structure is shown in Figure 6, where a1, a2, ..., a n and 1 are the inputs of neurons, w1, w2, ..., w n and b represent weights, Sum represents the summation function, f represents the activation function, and t is the output result.

[0097] 2) Neural Networks

[0098] Figure 7 shows a simple neural network. This neural network consists of an input layer, a hidden layer, and an output layer. By connecting multiple neurons in different ways, combined with different weights and activation functions, different outputs can be generated, thereby fitting the mapping relationship from input to output. For example, each previous-level node can be connected to all of its next-level nodes, forming a fully connected model. This fully connected model can also be called a deep neural network (DNN).

[0099] 5. Model acquisition

[0100] A neural network model can be trained through the processes of data set construction, training, verification and testing. In the embodiments of the present application, it is assumed that the neural network models have been trained in advance through offline training or online training. It should be noted that offline training and online training are not mutually exclusive. For example, the network can first obtain a static training result through offline training of the data set, and this process can be called offline training. During the use of the neural network model by the network or terminal device, as the terminal device further measures and / or reports, the neural network model can continue to collect more data and perform real-time online training to optimize the parameters of the neural network model, thereby achieving better inference and prediction results.

[0101] 6. CSI reporting based on artificial intelligence (AI) / machine learning (ML)

[0102] After obtaining the neural network model, the corresponding model output can be inferred by inputting the information obtained from the CSI measurement into the neural network model. For example, on the terminal device side, the channel information (such as eigenvectors, beam information, delay information, etc.) obtained from the CSI measurement is used as the input of the neural network model to infer the corresponding CSI quantization bits, which is called AI / ML-based CSI. On the network device side, there will be a neural network model corresponding to the terminal device side. The CSI quantization bits from the terminal device are used as the input of the neural network model to infer the corresponding channel information.

[0103] Figure 8 shows a typical neural network model for CSI feedback (or CSI reporting). A neural network model for encoding (encoder) (referred to as the encoding model) is deployed on the terminal device side, and a corresponding neural network model for decoding (decoder) (referred to as the decoding model) is deployed on the network side. Based on the encoding model, the terminal device outputs CSI quantized bits (such as PMI bits) and then feeds them back to the network device via an uplink channel (such as PUSCH / PUCCH). The network device uses the CSI quantized bits fed back by the terminal device as input to the decoding model, thereby outputting channel information corresponding to the terminal device input (such as eigenvectors, beam information, delay information, etc.) for downlink precoding. In addition, the terminal device can also monitor the performance of the encoding model. If the encoding model performance is poor, it can update the encoding model and report it to the network device, allowing the network device to synchronously update the decoding model. Here, since the neural network models on both the terminal device and the network device are matched, if a model update is required, both parties need to notify each other through signaling to achieve the purpose of synchronous model update.

[0104] In the embodiment of the present application, CSI reporting can be implemented based on the AI / ML model, which is referred to as AI / ML model-based CSI reporting or AI / ML-based CSI reporting. The current design of CSI processing latency requirements does not take into account the processing complexity and processing latency required for CSI reporting based on the AI / ML model. Moreover, the complexity of reasoning based on different AI / ML models varies, and the processing time required is also different. If a fixed CSI processing latency requirement is adopted, it is difficult to support flexible switching between AI / ML models. To this end, the following technical solutions of the embodiment of the present application are proposed.

[0105] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The above related technologies can be combined arbitrarily with the technical solutions of the embodiments of the present application as optional solutions, and all of them fall within the scope of protection of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0106] It should be noted that the “model” described in the embodiments of the present application can be called a neural network model or an AI / ML model, where the AI / ML model can be described as an AI model or an ML model.

[0107] It should be noted that the "model" described in the embodiments of the present application refers to the model on the terminal device side. The input information of the model on the terminal device side is the channel information obtained by the terminal device performing CSI measurement. For example, the channel information may include eigenvectors, channel covariance matrices, beam information, delay information, etc. The output information of the model on the terminal device side is the CSI quantization bit (or CSI feedback bit). For example, the CSI quantization bit may include RI bits, CRI bits, CQI bits, PMI bits, etc. The output information of the model on the terminal device side can be called AI / ML-based CSI, and the terminal device can report AI / ML-based CSI through PUSCH.

[0108] It should be noted that the "CSI reporting" described in the embodiments of the present application is an AI / ML-based CSI reporting, which is triggered by DCI and can be a semi-continuous CSI reporting or a non-periodic CSI reporting, with reference to Figure 2. In some embodiments, the AI / ML-based CSI reporting is a CSI reporting obtained by AI / ML-based CSI compression and / or a CSI reporting obtained by AI / ML-based CSI prediction. Here, CSI compression refers to compressing the measured channel information into CSI quantization bits. Here, CSI prediction refers to using the previously measured channel information to predict subsequent channel information. That is, the model on the terminal device side can achieve CSI compression and / or CSI prediction. In some embodiments, the AI / ML-based CSI reporting includes at least an AI / ML-based PMI, which can be understood as indication information for obtaining a precoding matrix. Optionally, it can also include an AI / ML-based CQI and / or an AI / ML-based RI.

[0109] Here, AI / ML-based CSI reporting can also be referred to as CSI reporting based on neural network inference, or CSI reporting based on compressed CSI based on a two-sides model, or CSI reporting based on AI training. It is different from traditional CSI reporting (i.e., CSI reporting not based on AI / ML). Traditional CSI reporting is CSI reporting based on a codebook or channel reciprocity.

[0110] It should be noted that the "CSI reporting" described in the embodiments of the present application can also be described as "CSI report" or "CSI" in some cases, that is, CSI reporting, CSI report and CSI can be replaced with each other.

[0111] It should be noted that the "CSI measurement resources" described in the embodiments of this application are used by a terminal device to perform CSI measurements. In some embodiments, the CSI measurement resources include CSI-RS / CSI-IM resources, where CSI-RS resources are used for channel measurement and CSI-IM resources are used for interference measurement.

[0112] It should be noted that the “CSI processing delay” described in the embodiments of the present application may also be described as “CSI computation time”.

[0113] FIG9 is a flowchart of a method for determining a processing delay requirement according to an embodiment of the present application. As shown in FIG9 , the method includes all or part of the following:

[0114] Step 901: The network device determines the CSI processing delay requirement corresponding to the CSI reporting based on the first model; the terminal device determines the CSI processing delay requirement corresponding to the CSI reporting based on the first model; the CSI reporting is an AI / ML-based CSI reporting, and the first model is the model used for the CSI reporting.

[0115] In some embodiments, the network device determines the CSI processing delay requirement corresponding to the CSI reporting based on the first model, which can be achieved in the following manner: the network device determines the CSI processing delay requirement corresponding to the CSI reporting based on the model information of the first model and a first corresponding relationship, where the first corresponding relationship is the corresponding relationship between the model information and the CSI processing delay requirement.

[0116] In some implementations, the network device receives indication information sent by the terminal device, where the indication information is used to indicate model information of the first model.

[0117] In some embodiments, the terminal device determines the CSI processing delay requirement corresponding to the CSI reporting based on the first model, which can be achieved in the following manner: the terminal device determines the CSI processing delay requirement corresponding to the CSI reporting based on the model information of the first model and a first corresponding relationship, where the first corresponding relationship is the corresponding relationship between the model information and the CSI processing delay requirement.

[0118] In some implementations, the model information of the first model may be indicated by the network device to the terminal device.

[0119] In some embodiments, the above-mentioned model information includes at least one of the following: the identification of the model, the function of the model, the model group to which the model belongs, the CSI measurement resource used to obtain the model input information (or the CSI measurement resource set to which the CSI measurement resource belongs), the output bit number of the model, the maximum output bit number of the model, and the output content of the model.

[0120] Exemplarily, the model information includes a model identifier, and the first corresponding relationship is a corresponding relationship between the model identifier (referred to as the model identifier or model ID) and the CSI processing delay requirement. The network device determines the CSI processing delay requirement corresponding to the CSI report based on the identifier of the first model used for the CSI report and the corresponding relationship between the model identifier (referred to as the model identifier) ​​and the CSI processing delay requirement. Here, the corresponding relationship between the model identifier and the CSI processing delay requirement can also be understood as the corresponding relationship between the model and the CSI processing delay requirement. Different model identifiers can have a corresponding relationship with different CSI processing delay requirements.

[0121] Exemplarily, the model information includes the functionality of the model, and the first correspondence is the correspondence between the functionality of the model and the CSI processing delay requirement. The network device determines the CSI processing delay requirement corresponding to the CSI report based on the functionality of the first model used for the CSI report and the correspondence between the functionality of the model and the CSI processing delay requirement. The functionality of the model is the function implemented by the AI / ML model, such as: PMI reporting, RI / PMI / CQI reporting, beam information reporting, RSRP reporting, CSI compression, CSI prediction, CSI prediction and compression, etc. The complexity required to implement models with different functions is different, and the corresponding CSI processing delay requirements are also different.

[0122] Exemplarily, the model information includes the model group to which the model belongs, and the first correspondence is the correspondence between the model group and the CSI processing latency requirement. The network device determines the CSI processing latency requirement corresponding to the CSI report based on the model group to which the first model used for the CSI report belongs and the correspondence between the model group and the CSI processing latency requirement. Different model groups may correspond to different CSI processing latency requirements.

[0123] Exemplarily, the model information includes a CSI measurement resource used to obtain model input information (or a CSI measurement resource set to which the CSI measurement resource belongs), and the first correspondence is a correspondence between the CSI measurement resource (or a CSI measurement resource set) and the CSI processing delay requirement. The network device determines the CSI processing delay requirement corresponding to the CSI report based on the CSI measurement resource (or a CSI measurement resource set to which the CSI measurement resource belongs) used by the input information of the first model used for the CSI report, and the correspondence between the CSI measurement resource (or a CSI measurement resource set) and the CSI processing delay requirement. Different CSI measurement resources (or CSI measurement resource sets) may correspond to different CSI processing delay requirements.

[0124] Exemplarily, the model information includes the number of output bits of the model, and the first corresponding relationship is the corresponding relationship between the number of output bits and the CSI processing delay requirement. The network device determines the CSI processing delay requirement corresponding to the CSI report based on the number of output bits of the first model used for the CSI report, and the corresponding relationship between the number of output bits and the CSI processing delay requirement. Among them, different numbers of output bits can have a corresponding relationship with different CSI processing delay requirements. For example, when the number of output bits of the model is within a first range, it corresponds to one value of the CSI processing delay requirement; when the number of output bits of the model is within a second range, it corresponds to another value of the CSI processing delay requirement, wherein the first range and the second range are different. If the number of output bits of the model is variable, that is, the model supports multiple different numbers of output bits, then the number of output bits of the model here is the maximum number of output bits supported by the model.

[0125] Exemplarily, the model information includes the output content of the model, and the first corresponding relationship is the corresponding relationship between the output content and the CSI processing delay requirement. The output content may include PMI, CQI, RI, RSRP, etc. The network device determines the CSI processing delay requirement corresponding to the CSI report based on the output content of the first model used for the CSI report and the corresponding relationship between the output content and the CSI processing delay requirement. Different output contents may have a corresponding relationship with different CSI processing delay requirements. For example, when the model outputs PMI bits, it corresponds to a larger CSI processing delay requirement; when the model outputs RSRP, it corresponds to a smaller CSI processing delay requirement. For example, when the model outputs predicted PMI bits, it corresponds to a larger CSI processing delay requirement; when the model outputs compressed PMI bits, it corresponds to a smaller CSI processing delay requirement.

[0126] In some embodiments, the division of the model groups is related to at least one of the following: model level, model complexity, and model resolution. In some embodiments, the division of the model groups is performed by the terminal device and reported by the terminal device to the network device; or, the division of the model groups is performed by the network device and configured by the network device to the terminal device.

[0127] Here, different model groups can correspond to different model levels, different model complexities, and different model resolutions. In other words, network devices or terminal devices can group models based on model level, model complexity, or model resolution, with different model groups corresponding to different CSI processing latency requirements. The division of model groups can be performed by the terminal device and reported to the network device, or performed by the network device and configured for the terminal device.

[0128] For example, the model groups may be divided according to model identifiers, for example, model group 1 includes models with model identifiers 2, 4, and 5, and model group 2 includes models with model identifiers 1 and 3. Model group 1 and model group 2 correspond to different CSI processing delay requirements.

[0129] In some implementations, the first correspondence is configured by the network device to the terminal device; or, the first correspondence is reported by the terminal device to the network device; or, the first correspondence is agreed upon by a protocol.

[0130] Exemplarily, the network device determines a first correspondence and configures it to the terminal device.

[0131] Exemplarily, the terminal device determines the first corresponding relationship and reports it to the network device.

[0132] Exemplarily, the protocol stipulates a first corresponding relationship, and the network device and the terminal device obtain the first corresponding relationship according to the protocol.

[0133] As an implementation method, the first correspondence relationship is reported by the terminal device to the network device, which can be implemented in the following ways:

[0134] 1) The first correspondence is reported by the terminal device to the network device through UE capability information. The UE capability information includes the model information supported by the terminal device and the CSI processing delay requirements corresponding to each supported model information.

[0135] Here, the terminal device sends UE capability information to the network device, and the network device receives the UE capability information sent by the terminal device. The UE capability information includes model information supported by the terminal device and the CSI processing delay requirements corresponding to each supported model information.

[0136] Exemplarily, the UE capability information includes the models supported by the terminal device (such as model ID or model function, etc.) and the CSI processing delay requirements corresponding to each supported model.

[0137] 2) The first corresponding relationship is reported by the terminal device to the network device through model indication information, where the model indication information is used to indicate the model information and the CSI processing delay requirement corresponding to the model information.

[0138] Here, the terminal device sends model indication information to the network device, and the network device receives the model indication information sent by the terminal device. The model indication information is used to indicate model information related to the model used by the terminal device and the CSI processing delay requirements corresponding to the model information.

[0139] In one scenario, if the terminal device finds that the performance of the current model is poor through model monitoring, the recommended model can be indicated to the network device through model indication information, and the CSI processing delay requirement corresponding to the recommended model can also be indicated to the network device through model indication information.

[0140] Exemplarily, the model indication information is used to indicate the model used by the terminal device and the CSI processing delay requirement corresponding to the model.

[0141] In some embodiments, the above-mentioned CSI processing delay requirement includes a first delay requirement and / or a second delay requirement; the first delay requirement is used to determine the first requirement that the interval between the first OFDM symbol and the second OFDM symbol needs to meet; the second delay requirement is used to determine the second requirement that the interval between the third OFDM symbol and the second OFDM symbol needs to meet; wherein, the first OFDM symbol is the last OFDM symbol of the PDCCH carrying DCI, and the DCI is used to trigger the target CSI report; the second OFDM symbol is the first OFDM symbol of the PUSCH carrying the target CSI report; and the third OFDM symbol is the last OFDM symbol of the CSI measurement resource corresponding to the target CSI report.

[0142] Here, the first delay requirement can be recorded as Z, and the second delay requirement can be recorded as Z'. The first requirement can be recorded as T proc,CSI , the second requirement can be recorded as T' proc,CSI Alternatively, the second requirement is the second delay requirement. In some implementations, T proc,CSI The relationship between Z and T' proc,CSI The relationship between T and Z' can refer to the above introduction related to "CSI processing delay", specifically: if PUSCH only contains CSI, then T proc,CSI =(Z)(2048+144)·κ2 -μ ·T c ; If CSI and data / HARQ-ACK are multiplexed in PUSCH, then T proc,CSI =(Z+d)·(2048+144)·κ2 -μ ·T c For subcarrier spacing of 15 / 30 / 60 / 120kHz, the values ​​of d are {2,2,3,4} respectively. proc,CSI =(Z′)(2048+144)·κ2 -μ ·T c .

[0143] In some embodiments, the interval between the first OFDM symbol and the second OFDM symbol must be greater than or equal to T proc,CSI(Unit is OFDM symbol), otherwise the terminal device does not report CSI.

[0144] In some embodiments, when the CSI measurement resource is a non-periodic CSI-RS / CSI-IM resource, the interval between the third OFDM symbol and the second OFDM symbol must be greater than or equal to T' proc,CSI (Unit is OFDM symbol), otherwise the terminal device does not perform CSI measurement and / or CSI reporting.

[0145] In some embodiments, when the CSI measurement resource is a periodic or semi-persistent CSI-RS / CSI-IM resource, the interval between the third OFDM symbol and the second OFDM symbol must be greater than or equal to Z' (in OFDM symbols), otherwise the terminal device does not perform CSI measurement.

[0146] In some embodiments, if the PUSCH carrying the target CSI report contains multiple CSI reports that need to be updated, the first requirement and the second requirement can be determined based on the maximum value of the CSI processing delay requirements corresponding to the multiple CSI reports, that is, Z = max m＝0,…,M-1 (Z(m)), Z′=max m＝0,…,M-1(Z′(m)), M represents the number of the multiple CSI reports (i.e., the number of CSI reports that need to be updated contained in the PUSCH), and Z(m) represents the CSI processing delay requirement corresponding to the CSI report with index m or the m-th CSI report in the M CSI reports. The method for determining the CSI processing delay requirement for the multiple CSI reports may be different. For example, assume that the PUSCH carries three CSI reports that need to be updated, namely, CSI report 1 and CSI report 2 based on AI / ML, and CSI report 3 based on the traditional codebook (non-AI / ML), and these CSI reports are measured based on non-periodic CSI-RS / CSI-IM. Then the terminal device can determine the corresponding CSI processing delay requirement 1 (corresponding to Z) and CSI processing delay requirement 2 (corresponding to Z') according to model 1 used by CSI reporting 1; determine the corresponding CSI processing delay requirement 3 (corresponding to Z) and CSI processing delay requirement 4 (corresponding to Z') according to model 2 used by CSI reporting 2; and determine the corresponding CSI processing delay requirement 5 (corresponding to Z) and CSI processing delay requirement 6 (corresponding to Z') according to the content reported by CSI reporting 3 and the CSI processing delay requirements defined in the existing protocol. At this time, the first requirement that the interval between the first OFDM symbol and the second OFDM symbol needs to meet can be determined according to the maximum value among processing delay requirement 1, CSI processing delay requirement 3 and CSI processing delay requirement 5; the second requirement that the interval between the third OFDM symbol and the second OFDM symbol needs to meet can be determined according to the maximum value among processing delay requirement 2, CSI processing delay requirement 4 and CSI processing delay requirement 6.

[0147] In some implementations, the CSI processing latency requirement may be expressed in the following ways:

[0148] 1) First representation: In the first correspondence, the CSI processing latency requirement is represented by the value of the CSI processing latency requirement, or by the level corresponding to the CSI processing latency requirement. The CSI processing latency requirement values ​​corresponding to different levels are configured by the network equipment or agreed upon by the protocol.

[0149] Here, the CSI processing delay requirement in the first corresponding relationship may be directly the value of the CSI processing delay requirement, such as the value of Z / Z', or may be the level corresponding to the CSI processing delay requirement (which may be called the delay requirement level).

[0150] Exemplarily, the network device and the terminal device pre-agree on the values ​​of the CSI processing delay requirements corresponding to different levels. When the terminal device reports the first corresponding relationship, the CSI processing delay requirement in the first corresponding relationship is represented by the delay requirement level, and the network device can determine the corresponding value of the CSI processing delay requirement according to the delay requirement level. Referring to the following Table 5, the network device and the terminal device can pre-agree on the values ​​of Z / Z' corresponding to the three delay requirement levels respectively. The value of Z / Z' is also related to the subcarrier spacing. When the terminal device reports the first corresponding relationship, one of the delay requirement levels 1, 2, and 3 is used to represent a CSI processing delay requirement in the first corresponding relationship. The network device can determine the corresponding value of Z / Z' according to the delay requirement level. Among them, the definition of the subcarrier spacing can refer to the previous description.

[0151] Table 5

[0152] 2) Second representation: In the first correspondence, the CSI processing delay requirement is represented by the value of the first offset, or by the level corresponding to the first offset. The first offset is the offset of the CSI processing delay requirement relative to the reference CSI processing delay requirement. The reference CSI processing delay requirement is configured by the network device, agreed upon by the protocol, or preset. The values ​​of the first offsets corresponding to different levels are configured by the network device or agreed upon by the protocol.

[0153] Here, the CSI processing delay requirement is equal to the reference CSI processing delay requirement plus a first offset (or referred to as the first offset value). The CSI processing delay requirement in the first corresponding relationship can be represented by the value of the first offset or the level corresponding to the first offset (which can be referred to as the delay requirement level). The network device can determine the value of the first offset based on the level corresponding to the first offset, and further determine the value of the CSI processing delay requirement based on the value of the first offset and the value of the reference CSI processing delay requirement.

[0154] As an implementation method, the value of the reference CSI processing delay requirement can be the value of Z / Z' specified in the 5G protocol. For the sake of distinction, the reference CSI processing delay requirement is referred to as Z l / Z l ', the reference CSI processing delay requirement is the CSI processing delay requirement for traditional CSI reporting, while the CSI processing delay requirement in the embodiment of the present application is the CSI processing delay requirement for AI / ML-based CSI reporting.

[0155] For example, the first delay requirement Z in the CSI processing delay requirement is Z l+r, where r is the portion of the first offset corresponding to Z; the second delay requirement Z' in the CSI processing delay requirement = Z l '+r', r' is the portion of the first offset corresponding to Z'.

[0156] Exemplarily, the network device and the terminal device pre-agree on the values ​​of the first offsets corresponding to different levels. When the terminal device reports the first corresponding relationship, the level of the first offset is used to represent the CSI processing delay requirement in the first corresponding relationship. The network device can determine the value of the first offset according to the corresponding level of the first offset, and then determine the value of the CSI processing delay requirement according to the value of the first offset and the reference CSI processing delay requirement. Referring to Table 6 below, the network device and the terminal device can pre-agree on the values ​​of r / r' corresponding to the three delay requirement levels. The value of r / r' is also related to the subcarrier spacing. When the terminal device reports the first corresponding relationship, one of the delay requirement levels 1, 2, and 3 is used to represent an r / r' value, and then represents a CSI processing delay requirement in the first corresponding relationship. The network device can determine the corresponding r / r' value according to the delay requirement level, and then determine the value of Z / Z'. Wherein, the definition of the subcarrier spacing can refer to the previous description.

[0157] Table 6

[0158] Step 902: The network device triggers the terminal device to perform CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting; the terminal device determines whether to perform CSI reporting and / or whether to update CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

[0159] In some embodiments, the network device triggers the terminal device to perform CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting, which can be achieved in the following manner: the network device determines, based on the CSI processing delay requirement, a first requirement that the interval between the first OFDM symbol and the second OFDM symbol needs to meet, and / or a second requirement that the interval between the third OFDM symbol and the second OFDM symbol needs to meet; the network device triggers the terminal device to perform CSI reporting through DCI in accordance with the first requirement and / or the second requirement, and the interval between the first OFDM symbol and the second OFDM symbol meets the first requirement, and / or the interval between the third OFDM symbol and the second OFDM symbol meets the second requirement.

[0160] Here, the first delay requirement in the CSI processing delay requirement can be recorded as Z, and the first requirement can be recorded as T proc,CSI , T proc,CSIThe relationship between Z and Z can be referred to the above description related to “CSI processing delay”. The interval between the first OFDM symbol and the second OFDM symbol meets the first requirement, which means that the interval between the first OFDM symbol and the second OFDM symbol is greater than or equal to the first requirement.

[0161] Here, the second delay requirement in the CSI processing delay requirement can be recorded as Z'; when the CSI measurement resource corresponding to the CSI reporting is a non-periodic measurement resource, the second requirement can be recorded as T' proc,CSI , T' proc,CSI The relationship between Z' and the second requirement can be referred to in the aforementioned description of "CSI processing delay." Alternatively, the second requirement is Z'. When the CSI measurement resource corresponding to the CSI reporting is a periodic or semi-continuous measurement resource, the second requirement is the second latency requirement, Z'. The interval between the third OFDM symbol and the second OFDM symbol meeting the second requirement means that the interval between the third OFDM symbol and the second OFDM symbol is greater than or equal to the second requirement.

[0162] In some embodiments, the terminal device determines whether to perform CSI reporting and / or whether to update the CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting. This can be achieved in the following manner: if the terminal device determines that the CSI processing delay requirement can be met, the terminal device determines to perform CSI reporting; if the terminal device determines that the CSI processing delay requirement cannot be met, the terminal device determines not to perform CSI reporting, or not to update the CSI reporting.

[0163] Case 1) The terminal device determines, based on the first delay requirement, that the interval between the first OFDM symbol and the second OFDM symbol must meet the first requirement; if the interval between the first OFDM symbol and the second OFDM symbol is greater than or equal to the first requirement, the terminal device determines to perform the CSI reporting; if the interval between the first OFDM symbol and the second OFDM symbol is less than the first requirement, the terminal device determines not to perform the CSI reporting.

[0164] Here, the first delay requirement can be recorded as Z, and the first requirement can be recorded as T proc,CSI , T proc,CSI The relationship between Z and CSI can refer to the above introduction related to "CSI processing delay".

[0165] Case 2) When the CSI measurement resource corresponding to the CSI reporting is a non-periodic measurement resource, the terminal device determines, based on the second delay requirement, that the interval between the third OFDM symbol and the second OFDM symbol needs to meet the second requirement; if the interval between the third OFDM symbol and the second OFDM symbol is greater than or equal to the second requirement, the terminal device determines to perform the CSI reporting; if the interval between the third OFDM symbol and the second OFDM symbol is less than the second requirement, the terminal device determines not to perform CSI reporting, or not to update the CSI reporting.

[0166] Here, the second delay requirement can be recorded as Z', and the second requirement can be recorded as T' proc,CSI , T' proc,CSI The relationship between Z and Z' can refer to the above introduction related to "CSI processing delay".

[0167] Case 3) When the CSI measurement resource corresponding to the CSI report is a periodic or semi-continuous measurement resource, if the interval between the third OFDM symbol and the second OFDM symbol is greater than or equal to the second delay requirement, the terminal device determines to perform the CSI reporting; and / or, if the interval between the third OFDM symbol and the second OFDM symbol is less than the second delay requirement, the terminal device determines not to update the CSI reporting.

[0168] The technical solution of the embodiment of the present application is that since different models require different complexities for online training and inference, the terminal device and network device can determine different CSI processing delay requirements for different models, thereby supporting flexible switching between different models without exceeding the processing capability of the terminal device and ensuring the accuracy of CSI feedback.

[0169] The technical solutions of the embodiments of the present application are illustrated below with reference to specific application examples.

[0170] Application Example 1

[0171] FIG10 is a second flow chart of a method for determining a processing delay requirement provided in an embodiment of the present application. As shown in FIG10 , the method includes all or part of the following contents:

[0172] Step 1001: The network device determines a CSI processing delay requirement corresponding to a CSI report based on a first model, where the CSI report is an AI / ML-based CSI report and the first model is a model used for the CSI report.

[0173] Here, the manner in which the network device determines the CSI processing delay requirement corresponding to the CSI reporting based on the first model may refer to the description related to FIG. 9 .

[0174] Step 1002: The terminal device determines a CSI processing delay requirement corresponding to a CSI report based on a first model, where the CSI report is an AI / ML-based CSI report and the first model is a model used for the CSI report.

[0175] Here, the terminal device determines the CSI processing delay requirement corresponding to the CSI reporting based on the first model, and reference can be made to the description related to the aforementioned Figure 9.

[0176] Step 1003: The network device triggers the terminal device to perform AI / ML-based CSI reporting through DCI according to the CSI processing delay requirement corresponding to the CSI reporting.

[0177] The CSI processing delay requirement includes a first delay requirement and / or a second delay requirement. The first delay requirement can be denoted as Z, and the second delay requirement can be denoted as Z'. The first delay requirement is used to determine the requirement that the interval between the first OFDM symbol and the second OFDM symbol must meet (denoted as the first requirement); the second delay requirement is used to determine the requirement that the interval between the third OFDM symbol and the second OFDM symbol must meet (denoted as the second requirement); wherein, the first OFDM symbol is the last OFDM symbol of the PDCCH carrying DCI, and the DCI is used to trigger CSI reporting; the second OFDM symbol is the first OFDM symbol of the PUSCH carrying the CSI reporting; and the third OFDM symbol is the last OFDM symbol of the CSI measurement resource corresponding to the CSI reporting.

[0178] In some embodiments, the network device determines the requirement that the interval between the first OFDM symbol and the second OFDM symbol needs to meet (referred to as the first requirement) based on the first delay requirement; the network device triggers the terminal device to perform AI / ML-based CSI reporting through DCI, wherein the interval between the first OFDM symbol and the second OFDM symbol meets the first requirement, that is, the interval between the first OFDM symbol and the second OFDM symbol is greater than or equal to the first requirement. If the interval between the first OFDM symbol and the second OFDM symbol does not meet the first requirement, the network device may assume that the terminal device will not perform CSI reporting, that is, the network device does not need to receive the CSI reported by the terminal. Here, the relationship between the first requirement and the first delay requirement can refer to the description related to the aforementioned Figure 9.

[0179] In other embodiments, the network device determines the requirement that the interval between the third OFDM symbol and the second OFDM symbol needs to meet (referred to as the second requirement) based on the second delay requirement; the network device triggers the terminal device to perform AI / ML-based CSI reporting through DCI, wherein the interval between the third OFDM symbol and the second OFDM symbol meets the second requirement, that is, the interval between the third OFDM symbol and the second OFDM symbol is greater than or equal to the second requirement. If the interval between the third OFDM symbol and the second OFDM symbol does not meet the second requirement, the network device may assume that the terminal device will not perform corresponding CSI measurement or CSI reporting, that is, the network device does not need to receive the CSI reported by the terminal. Here, the relationship between the second requirement and the second delay requirement can refer to the description related to the aforementioned Figure 9.

[0180] Step 1004: The terminal device determines whether to perform AI / ML-based CSI reporting or update AI / ML-based CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

[0181] If the CSI processing delay requirement can be met, the terminal device reports the AI / ML-based CSI through the PUSCH; otherwise, the terminal device does not report the AI / ML-based CSI, or the terminal device does not update the AI / ML-based CSI reporting. There are several specific situations:

[0182] Case 1) In some implementations, the terminal device determines the first requirement T that the interval between the first OFDM symbol and the second OFDM symbol needs to meet based on the first delay requirement Z. proc,CSI If the interval between the first OFDM symbol and the second OFDM symbol is greater than or equal to the first requirement, the terminal device performs AI / ML-based CSI reporting through PUSCH; otherwise, the terminal does not perform AI / ML-based CSI reporting. Specifically, if the CSI report is not multiplexed with other signals, the terminal device ignores the DCI and does not send PUSCH, that is, does not send CSI reporting. If the CSI report is multiplexed with other signals, the terminal device sends PUSCH, which only carries other signals and does not carry CSI.

[0183] Case 2) In some other implementations, if the CSI reporting is aperiodic CSI reporting, and the CSI measurement resource corresponding to the CSI reporting is an aperiodic CSI-RS / CSI-IM resource, the terminal device determines the second requirement T' that the interval between the third OFDM symbol and the second OFDM symbol needs to meet based on the second delay requirement Z'. proc,CSI, if the interval between the third OFDM symbol and the second OFDM symbol is greater than or equal to the second requirement, the terminal device performs AI / ML-based CSI reporting through PUSCH; otherwise, the terminal does not perform AI / ML-based CSI reporting or update AI / ML-based CSI reporting. Specifically, if the CSI report is not multiplexed with other signals, the terminal ignores the DCI and does not send PUSCH, that is, does not send CSI reporting. If the CSI report is multiplexed with other signals, the terminal device sends PUSCH, which carries other signals and CSI reporting, but does not require CSI measurement and updating of the CSI report in the PUSCH.

[0184] Case 3) In another embodiment, if the CSI reporting is non-periodic CSI reporting, and the CSI measurement resource corresponding to the CSI reporting is a periodic or semi-persistent CSI-RS / CSI-IM resource, then if the interval between the third OFDM symbol and the second OFDM symbol is greater than or equal to the second delay requirement Z', the terminal device performs AI / ML-based CSI reporting through PUSCH; otherwise, the terminal device still performs CSI reporting through PUSCH, but does not need to perform CSI measurement and update the CSI reporting in PUSC.

[0185] Application Example 2

[0186] FIG11 is a flowchart diagram of a third method for determining a processing delay requirement according to an embodiment of the present application. As shown in FIG11 , the method includes all or part of the following:

[0187] Step 1101: The terminal device determines the CSI processing delay requirement corresponding to the CSI reporting based on the model information of the first model and the first correspondence, where the CSI reporting is an AI / ML-based CSI reporting, the first model is the model used for the CSI reporting, and the first correspondence is the correspondence between the model information and the CSI processing delay requirement.

[0188] Here, the manner in which the terminal device determines the CSI processing delay requirement corresponding to the CSI reporting may refer to the description related to the aforementioned FIG. 9 .

[0189] Step 1102: The terminal device reports the first corresponding relationship to the network device.

[0190] Here, the first correspondence is the correspondence between the model information and the CSI processing delay requirement, wherein the model information includes at least one of the following: the model identifier, the function of the model, the model group to which the model belongs, the CSI measurement resources used to obtain the model input information, the output bit number of the model, the maximum output bit number of the model, and the output content of the model.

[0191] Here, the terminal device reports the first correspondence to the network device, which can be achieved in the following ways:

[0192] Method 1: The terminal device reports the CSI processing latency requirements corresponding to different model information to the network device.

[0193] Here, the terminal device reports the CSI processing latency requirements corresponding to different model information to the network device, which can be achieved through the following methods:

[0194] 1) The terminal device reports the CSI processing delay requirements corresponding to different model information to the network device.

[0195] Exemplarily, the terminal device reports different Z / Z' values ​​for different models, so that the network device determines the corresponding Z / Z' value according to the model used for AI / ML-based CSI reporting.

[0196] Exemplarily, the terminal device reports different Z / Z' values ​​for different model groups, so that the network device determines the corresponding Z / Z' value according to the model group to which the model used for the AI / ML-based CSI reporting belongs.

[0197] Exemplarily, the terminal device reports different Z / Z' values ​​for different CSI measurement resources, so that the network device determines the corresponding Z / Z' value according to the CSI measurement resource used for the CSI report.

[0198] Exemplarily, the terminal device reports different Z / Z' values ​​for different model output bits (or model maximum output bits), thereby allowing the network device to determine the corresponding Z / Z' value based on the output bit number (or maximum output bit number) of the model used for AI / ML-based CSI reporting.

[0199] Exemplarily, the terminal device reports different Z / Z' values ​​for different model output contents, thereby enabling the network device to determine the corresponding Z / Z' value based on the output content of the model used for AI / ML-based CSI reporting.

[0200] 2) The terminal device reports to the network device the level of CSI processing delay requirement corresponding to different model information (which may be called the delay requirement level).

[0201] Here, the network device and the terminal device pre-agree on the values ​​of the CSI processing delay requirements corresponding to different levels. The terminal device only needs to report the delay requirement level, and the network device can determine the corresponding CSI processing delay requirement based on the delay requirement level.

[0202] For example, referring to Table 5 above, the network device and the terminal device can pre-agree on the values ​​of Z / Z' corresponding to the three delay requirement levels. The value of Z / Z' is also related to the subcarrier spacing. The terminal device reports the delay requirement level corresponding to different model information, and the network device can determine the value of Z / Z' corresponding to the different model information based on the delay requirement level.

[0203] Method 2: The terminal device reports to the network device the offset (called the first offset) of the CSI processing delay requirement corresponding to different model information relative to the reference CSI processing delay requirement. The CSI processing delay requirement is equal to the reference CSI processing delay requirement plus the first offset. Here, the reference CSI processing delay requirement is pre-agreed upon by the terminal device and the network device, and the first offset is reported by the terminal device to the network device for the network device to determine the CSI processing delay requirement corresponding to the AI / ML-based CSI reporting.

[0204] Here, the terminal device reports the first offset corresponding to different model information to the network device, which can be achieved in the following ways:

[0205] 1) The terminal device reports the value of the first offset corresponding to different model information to the network device.

[0206] For example, the terminal device reports different first offset values ​​for different models, so that the network device determines the corresponding first offset value according to the model used for AI / ML-based CSI reporting, and then determines the corresponding Z / Z' value in combination with the reference CSI processing delay requirement.

[0207] Exemplarily, the terminal device reports different first offset values ​​for different model groups, so that the network device determines the corresponding first offset value based on the model group in which the model used for the AI / ML-based CSI reporting is located, and then determines the corresponding Z / Z' value in combination with the reference CSI processing delay requirement.

[0208] Exemplarily, the terminal device reports different first offset values ​​for different CSI measurement resources, so that the network device determines the corresponding first offset value based on the CSI measurement resource used for the CSI report, and then determines the corresponding Z / Z' value in combination with the reference CSI processing delay requirement.

[0209] Exemplarily, the terminal device reports different first offset values ​​for different model functions, so that the network device determines the corresponding first offset value according to the function of the model used for CSI reporting, and then determines the corresponding Z / Z' value in combination with the reference CSI processing delay requirement.

[0210] Exemplarily, the terminal device reports different first offset values ​​for different model output bits (or model maximum output bits), so that the network device determines the corresponding first offset value based on the output bit number (or maximum output bit number) of the model used for AI / ML-based CSI reporting, and then determines the corresponding Z / Z' value in combination with the reference CSI processing delay requirement.

[0211] Exemplarily, the terminal device reports different first offset values ​​for different model output contents, thereby enabling the network device to determine the corresponding first offset value based on the output content of the model used for AI / ML-based CSI reporting, and then determine the corresponding Z / Z' value in combination with the reference CSI processing delay requirement.

[0212] 2) The terminal device reports to the network device the level (which may be called the delay requirement level) corresponding to the first offset corresponding to different model information.

[0213] Here, the network device and the terminal device have pre-agreed on the values ​​of the first offset corresponding to different levels. The terminal device only needs to report the delay requirement level. The network device can determine the corresponding first offset based on the delay requirement level, and then determine the corresponding CSI processing delay requirement in combination with the reference CSI processing delay requirement.

[0214] For example, referring to Table 6 above, the network device and the terminal device can pre-agree on the values ​​of r / r' corresponding to the three delay requirement levels. The value of r / r' is also related to the subcarrier spacing. The terminal device reports the delay requirement level corresponding to different model information. The network device can determine the value of r / r' corresponding to the different model information based on the delay requirement level, and then determine the corresponding Z / Z' value in combination with the reference CSI processing delay requirement value.

[0215] Step 1103: The network device determines a CSI processing delay requirement corresponding to the CSI reporting based on the model information of the first model and the first corresponding relationship.

[0216] Here, the manner in which the network device determines the CSI processing delay requirement corresponding to the CSI reporting may refer to the description related to FIG. 9 .

[0217] Step 1104: The network device triggers the terminal device to perform AI / ML-based CSI reporting through DCI according to the CSI processing delay requirement corresponding to the CSI reporting.

[0218] Here, the network device triggers the terminal device to perform AI / ML-based CSI reporting through DCI according to the CSI processing delay requirements corresponding to the CSI reporting. Please refer to the relevant descriptions of Figures 9 and 10 above.

[0219] Step 1105: The terminal device determines whether to perform AI / ML-based CSI reporting or update AI / ML-based CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

[0220] Here, the terminal device may determine whether it needs to perform AI / ML-based CSI reporting or update AI / ML-based CSI reporting based on the CSI processing delay requirements corresponding to the CSI reporting. Please refer to the relevant descriptions of Figures 9 and 10 above.

[0221] Step 1106: If AI / ML-based CSI reporting is required, the terminal device performs AI / ML-based CSI reporting.

[0222] The preferred embodiments of the present application are described in detail above in conjunction with the accompanying drawings. However, the present application is not limited to the specific details in the above embodiments. Within the technical concept of the present application, the technical solution of the present application can be subjected to a variety of simple modifications, and these simple modifications all fall within the scope of protection of the present application. For example, the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present application will no longer describe the various possible combinations separately. For another example, the various different embodiments of the present application can also be arbitrarily combined, as long as they do not violate the idea of ​​the present application, they should also be regarded as the contents disclosed in the present application. For another example, under the premise of no conflict, the various embodiments and / or the technical features in each embodiment described in the present application can be arbitrarily combined with the prior art, and the technical solution obtained after the combination should also fall within the scope of protection of the present application.

[0223] It should also be understood that in the various method embodiments of the present application, the sequence numbers of the above-mentioned processes do not imply a precedence in the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. In addition, in the embodiments of the present application, the terms "downlink," "uplink," and "sidelink" are used to indicate the transmission direction of signals or data, where "downlink" is used to indicate the first direction of transmission of signals or data from a site to a user equipment in a cell, "uplink" is used to indicate the second direction of transmission of signals or data from a user equipment in a cell to a site, and "sidelink" is used to indicate the third direction of transmission of signals or data from user equipment 1 to user equipment 2. For example, "downlink signal" indicates that the transmission direction of the signal is the first direction. In addition, in the embodiments of the present application, the term "and / or" is merely a description of the association relationship between associated objects, indicating that three relationships can exist. Specifically, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0224] FIG12 is a schematic diagram of the first structure of a device for determining a processing delay requirement according to an embodiment of the present application, which is applied to a terminal device. As shown in FIG12 , the device for determining a processing delay requirement includes:

[0225] Determination unit 1201 is used to determine, based on a first model, a CSI processing delay requirement corresponding to a channel state information CSI report, where the CSI report is an AI / ML-based CSI report and the first model is a model used for the CSI report; and based on the CSI processing delay requirement corresponding to the CSI report, determine whether to perform the CSI report and / or whether to update the CSI report.

[0226] In some embodiments, the determining unit 1201 is configured to determine a CSI processing delay requirement corresponding to the CSI reporting based on model information of the first model and a first correspondence, where the first correspondence is a correspondence between the model information and the CSI processing delay requirement.

[0227] In some embodiments, the model information includes at least one of the following: an identifier of the model, a function of the model, a model group to which the model belongs, CSI measurement resources used to obtain model input information, the number of output bits of the model, the maximum number of output bits of the model, and the output content of the model.

[0228] In some embodiments, the division of the model groups is related to at least one of the following: model level, model complexity, and model resolution.

[0229] In some implementations, the division of the model groups is performed by the terminal device and reported to the network device by the terminal device; or, the division of the model groups is performed by the network device and configured to the terminal device by the network device.

[0230] In some implementations, the first correspondence is configured by the network device to the terminal device; or, the first correspondence is reported by the terminal device to the network device; or, the first correspondence is agreed upon by a protocol.

[0231] In some embodiments, the first correspondence is reported by the terminal device to the network device, including: the first correspondence is reported by the terminal device to the network device through UE capability information, the UE capability information includes model information supported by the terminal device and the CSI processing delay requirements corresponding to each supported model information; or, the first correspondence is reported by the terminal device to the network device through model indication information, the model indication information is used to indicate the model information and the CSI processing delay requirements corresponding to the model information.

[0232] In some implementations, in the first corresponding relationship, the CSI processing delay requirement is represented by a value of the CSI processing delay requirement, or is represented by a level corresponding to the CSI processing delay requirement.

[0233] In some implementations, the values ​​of the CSI processing delay requirements corresponding to different levels are configured by the network device or agreed upon by the protocol.

[0234] In some embodiments, in the first correspondence, the CSI processing delay requirement is represented by the value of a first offset, or by a level corresponding to the first offset, where the first offset is the offset of the CSI processing delay requirement relative to a reference CSI processing delay requirement, and the reference CSI processing delay requirement is configured by a network device or agreed upon by a protocol.

[0235] In some implementations, the values ​​of the first offsets corresponding to different levels are configured by the network device or agreed upon by the protocol.

[0236] In some embodiments, the determining unit 1201 is configured to determine whether to perform the CSI reporting if it is determined that the CSI processing delay requirement can be met; and / or, if it is determined that the CSI processing delay requirement cannot be met, determine not to perform the CSI reporting, or not to update the CSI reporting.

[0237] In some embodiments, the CSI processing delay requirement includes a first delay requirement and / or a second delay requirement; the first delay requirement is used to determine the first requirement that the interval between the first OFDM symbol and the second OFDM symbol needs to meet; the second delay requirement is used to determine the second requirement that the interval between the third OFDM symbol and the second OFDM symbol needs to meet; wherein, the first OFDM symbol is the last OFDM symbol of the PDCCH carrying the DCI, and the DCI is used to trigger the CSI report; the second OFDM symbol is the first OFDM symbol of the PUSCH carrying the CSI report; and the third OFDM symbol is the last OFDM symbol of the CSI measurement resource corresponding to the CSI report.

[0238] In some implementations, the CSI reporting is a CSI reporting obtained by AI / ML-based CSI compression and / or a CSI reporting obtained by AI / ML-based CSI prediction.

[0239] Those skilled in the art should understand that the description related to the apparatus for determining the processing delay requirement in the embodiment of the present application can be understood with reference to the description related to the method for determining the processing delay requirement in the embodiment of the present application.

[0240] FIG13 is a second schematic diagram of the structure of the apparatus for determining the processing delay requirement provided in an embodiment of the present application, which is applied to a network device. As shown in FIG13 , the apparatus for determining the processing delay requirement includes:

[0241] A determining unit 1301 is configured to determine a CSI processing delay requirement corresponding to a CSI report based on a first model, where the CSI report is an AI / ML-based CSI report, and the first model is a model used for the CSI report;

[0242] The triggering unit 1302 is used to trigger the terminal device to perform the CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

[0243] In some embodiments, the determining unit 1301 is configured to determine a CSI processing delay requirement corresponding to the CSI reporting based on model information of the first model and a first correspondence, where the first correspondence is a correspondence between the model information and the CSI processing delay requirement.

[0244] In some embodiments, the model information includes at least one of the following: an identifier of the model, a function of the model, a model group to which the model belongs, CSI measurement resources used to obtain model input information, the number of output bits of the model, the maximum number of output bits of the model, and the output content of the model.

[0245] In some embodiments, the division of the model groups is related to at least one of the following: model level, model complexity, and model resolution.

[0246] In some implementations, the division of the model groups is performed by the terminal device and reported to the network device by the terminal device; or, the division of the model groups is performed by the network device and configured to the terminal device by the network device.

[0247] In some implementations, the first correspondence is configured by the network device to the terminal device; or, the first correspondence is reported by the terminal device to the network device; or, the first correspondence is agreed upon by a protocol.

[0248] In some embodiments, the first correspondence is reported by the terminal device to the network device, including: the first correspondence is reported by the terminal device to the network device through UE capability information, the UE capability information includes model information supported by the terminal device and the CSI processing delay requirements corresponding to each supported model information; or, the first correspondence is reported by the terminal device to the network device through model indication information, the model indication information is used to indicate the model information and the CSI processing delay requirements corresponding to the model information.

[0249] In some implementations, in the first corresponding relationship, the CSI processing delay requirement is represented by a value of the CSI processing delay requirement, or is represented by a level corresponding to the CSI processing delay requirement.

[0250] In some implementations, the values ​​of the CSI processing delay requirements corresponding to different levels are configured by the network device or agreed upon by the protocol.

[0251] In some embodiments, in the first correspondence, the CSI processing delay requirement is represented by the value of a first offset, or by a level corresponding to the first offset, where the first offset is the offset of the CSI processing delay requirement relative to a reference CSI processing delay requirement, and the reference CSI processing delay requirement is configured by the network device or agreed upon by a protocol.

[0252] In some implementations, the values ​​of the first offsets corresponding to different levels are configured by the network device or agreed upon by the protocol.

[0253] In some embodiments, the CSI processing delay requirement includes a first delay requirement and / or a second delay requirement; the first delay requirement is used to determine the first requirement that the interval between the first OFDM symbol and the second OFDM symbol needs to meet; the second delay requirement is used to determine the second requirement that the interval between the third OFDM symbol and the second OFDM symbol needs to meet; wherein, the first OFDM symbol is the last OFDM symbol of the PDCCH carrying the DCI, and the DCI is used to trigger the CSI report; the second OFDM symbol is the first OFDM symbol of the PUSCH carrying the CSI report; and the third OFDM symbol is the last OFDM symbol of the CSI measurement resource corresponding to the CSI report.

[0254] In some embodiments, the trigger unit 1302 is used to determine, based on the CSI processing delay requirement, a first requirement that the interval between the first OFDM symbol and the second OFDM symbol needs to meet, and / or a second requirement that the interval between the third OFDM symbol and the second OFDM symbol needs to meet; according to the first requirement and / or the second requirement, trigger the terminal device to perform the CSI reporting through DCI, and the interval between the first OFDM symbol and the second OFDM symbol meets the first requirement, and / or the interval between the third OFDM symbol and the second OFDM symbol meets the second requirement; wherein, the first OFDM symbol is the last OFDM symbol of the PDCCH carrying the DCI, and the DCI is used to trigger the CSI reporting; the second OFDM symbol is the first OFDM symbol of the PUSCH carrying the CSI reporting; the third OFDM symbol is the last OFDM symbol of the CSI measurement resource corresponding to the CSI reporting.

[0255] In some implementations, the CSI report is a CSI report obtained by AI / ML-based CSI compression and / or a CSI report obtained by AI / ML-based CSI prediction.

[0256] Those skilled in the art should understand that the description related to the apparatus for determining the processing delay requirement in the embodiment of the present application can be understood with reference to the description related to the method for determining the processing delay requirement in the embodiment of the present application.

[0257] Figure 14 is a schematic diagram of a communication device 1400 provided in an embodiment of the present application. The communication device can be a terminal device or a network device. The communication device 1400 shown in Figure 14 includes a processor 1410, which can call and execute a computer program from a memory to implement the method in the embodiment of the present application.

[0258] Optionally, as shown in FIG14 , the communication device 1400 may further include a memory 1420. The processor 1410 may call and execute a computer program from the memory 1420 to implement the method in the embodiment of the present application.

[0259] The memory 1420 may be a separate device independent of the processor 1410 , or may be integrated into the processor 1410 .

[0260] Optionally, as shown in FIG14 , the communication device 1400 may further include a transceiver 1430 , and the processor 1410 may control the transceiver 1430 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices.

[0261] The transceiver 1430 may include a transmitter and a receiver. The transceiver 1430 may further include an antenna, and the number of antennas may be one or more.

[0262] Optionally, the communication device 1400 may specifically be a network device in an embodiment of the present application, and the communication device 1400 may implement the corresponding processes implemented by the network device in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0263] Optionally, the communication device 1400 may specifically be a mobile terminal / terminal device of an embodiment of the present application, and the communication device 1400 may implement the corresponding processes implemented by the mobile terminal / terminal device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0264] Figure 15 is a schematic structural diagram of a chip according to an embodiment of the present application. The chip 1500 shown in Figure 15 includes a processor 1510, which can call and run a computer program from a memory to implement the method according to the embodiment of the present application.

[0265] Optionally, as shown in FIG15 , the chip 1500 may further include a memory 1520. The processor 1510 may call and execute a computer program from the memory 1520 to implement the method in the embodiment of the present application.

[0266] The memory 1520 may be a separate device independent of the processor 1510 , or may be integrated into the processor 1510 .

[0267] Optionally, the chip 1500 may further include an input interface 1530. The processor 1510 may control the input interface 1530 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0268] Optionally, the chip 1500 may further include an output interface 1540. The processor 1510 may control the output interface 1540 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0269] Optionally, the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0270] Optionally, the chip can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0271] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0272] FIG16 is a schematic block diagram of a communication system 1600 provided in an embodiment of the present application. As shown in FIG16 , the communication system 1600 includes a terminal device 1610 and a network device 1620 .

[0273] Among them, the terminal device 1610 can be used to implement the corresponding functions implemented by the terminal device in the above method, and the network device 1620 can be used to implement the corresponding functions implemented by the network device in the above method. For the sake of brevity, they are not repeated here.

[0274] It should be understood that the processor of the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0275] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0276] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0277] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.

[0278] Optionally, the computer-readable storage medium can be applied to the network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0279] Optionally, the computer-readable storage medium can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0280] An embodiment of the present application also provides a computer program product, including computer program instructions.

[0281] Optionally, the computer program product can be applied to the network device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0282] Optionally, the computer program product can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0283] The embodiment of the present application also provides a computer program.

[0284] Optionally, the computer program can be applied to the network device in the embodiments of the present application. When the computer program runs on a computer, the computer executes the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not described here.

[0285] Optionally, the computer program can be applied to the mobile terminal / terminal device in the embodiments of the present application. When the computer program runs on the computer, the computer executes the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0286] Those skilled in the art will appreciate that the units and algorithmic steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0287] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0288] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0289] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0290] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0291] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0292] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for determining a processing delay requirement, the method comprising: The terminal device determines, based on the first model, a CSI processing delay requirement corresponding to the channel state information CSI reporting, where the CSI reporting is a CSI reporting based on artificial intelligence / machine learning AI / ML, and the first model is a model used for the CSI reporting; The terminal device determines whether to perform the CSI reporting and / or whether to update the CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

2. The method according to claim 1, wherein: The terminal device determines, based on the first model, a CSI processing delay requirement corresponding to the CSI reporting, including: The terminal device determines the CSI processing delay requirement corresponding to the CSI reporting based on the model information of the first model and the first corresponding relationship, where the first corresponding relationship is the corresponding relationship between the model information and the CSI processing delay requirement.

3. The method according to claim 2, wherein: The model information includes at least one of the following: an identifier of the model, a function of the model, a model group to which the model belongs, a CSI measurement resource used to obtain model input information, an output bit number of the model, a maximum output bit number of the model, and output content of the model.

4. The method according to claim 3, wherein: The division of the model groups is related to at least one of the following: model level, model complexity, and model resolution.

5. The method according to claim 3 or 4, wherein: The division of the model groups is performed by the terminal device and reported by the terminal device to the network device; or, The model groups are divided by a network device and configured to the terminal device by the network device.

6. The method according to any one of claims 2 to 5, wherein: The first corresponding relationship is configured by the network device to the terminal device; or, The first corresponding relationship is reported by the terminal device to the network device; or, The first corresponding relationship is agreed upon in the protocol.

7. The method according to claim 6, wherein: The first corresponding relationship is reported by the terminal device to the network device, including: The first corresponding relationship is reported by the terminal device to the network device through UE capability information, where the UE capability information includes model information supported by the terminal device and CSI processing delay requirements corresponding to each supported model information; or, The first corresponding relationship is reported by the terminal device to the network device through model indication information, and the model indication information is used to indicate model information and the CSI processing delay requirement corresponding to the model information.

8. The method according to any one of claims 2 to 7, wherein: In the first corresponding relationship, the CSI processing delay requirement is represented by a value of the CSI processing delay requirement, or is represented by a level corresponding to the CSI processing delay requirement.

9. The method according to claim 8, wherein: The values ​​of the CSI processing delay requirements corresponding to different levels are configured by the network device or agreed upon by the protocol.

10. The method according to any one of claims 2 to 7, wherein: In the first corresponding relationship, the CSI processing delay requirement is represented by the value of a first offset, or by a level corresponding to the first offset, and the first offset is the offset of the CSI processing delay requirement relative to a reference CSI processing delay requirement, and the reference CSI processing delay requirement is configured by a network device or agreed upon by a protocol.

11. The method according to claim 10, wherein: The values ​​of the first offsets corresponding to different levels are configured by the network device or agreed upon by the protocol.

12. The method according to any one of claims 1 to 11, wherein: The terminal device determines, based on the CSI processing delay requirement corresponding to the CSI reporting, whether to perform the CSI reporting and / or whether to update the CSI reporting, including: If the terminal device determines that the CSI processing delay requirement can be met, the terminal device determines to perform the CSI reporting; and / or, If the terminal device determines that the CSI processing delay requirement cannot be met, the terminal device determines not to perform the CSI reporting, or does not update the CSI reporting.

13. The method according to any one of claims 1 to 12, wherein: The CSI processing delay requirement includes a first delay requirement and / or a second delay requirement; The first delay requirement is used to determine a first requirement that an interval between a first orthogonal frequency division multiplexing OFDM symbol and a second OFDM symbol needs to meet; The second delay requirement is used to determine a second requirement that an interval between the third OFDM symbol and the second OFDM symbol needs to meet; Among them, the first OFDM symbol is the last OFDM symbol of the physical downlink control channel PDCCH carrying DCI, and the DCI is used to trigger the CSI report; the second OFDM symbol is the first OFDM symbol of the physical uplink shared channel PUSCH carrying the CSI report; the third OFDM symbol is the last OFDM symbol of the CSI measurement resource corresponding to the CSI report.

14. The method according to any one of claims 1 to 13, wherein: The CSI report is a CSI report obtained by CSI compression based on AI / ML and / or a CSI report obtained by CSI prediction based on AI / ML.

15. A method for determining a processing delay requirement, the method comprising: The network device determines, based on the first model, a CSI processing delay requirement corresponding to the CSI reporting, where the CSI reporting is an AI / ML-based CSI reporting, and the first model is a model used by the CSI reporting; The network device triggers the terminal device to perform the CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

16. The method according to claim 15, wherein: The network device determines, based on the first model, a CSI processing delay requirement corresponding to the CSI reporting, including: The network device determines a CSI processing delay requirement corresponding to the CSI reporting based on the model information of the first model and a first corresponding relationship, where the first corresponding relationship is a corresponding relationship between the model information and the CSI processing delay requirement.

17. The method according to claim 16, wherein: The model information includes at least one of the following: an identifier of the model, a function of the model, a model group to which the model belongs, a CSI measurement resource used to obtain model input information, an output bit number of the model, a maximum output bit number of the model, and output content of the model.

18. The method according to claim 17, wherein: The division of the model groups is related to at least one of the following: model level, model complexity, and model resolution.

19. The method according to claim 17 or 18, wherein: The model groups are divided by the terminal device and reported to the network device by the terminal device; or, The model groups are divided by the network device and configured to the terminal device by the network device.

20. The method according to any one of claims 16 to 19, wherein: The first corresponding relationship is configured by the network device to the terminal device; or, The first corresponding relationship is reported by the terminal device to the network device; or, The first corresponding relationship is agreed upon in the protocol.

21. The method according to claim 20, wherein: The first corresponding relationship is reported by the terminal device to the network device, including: The first corresponding relationship is reported by the terminal device to the network device through UE capability information, where the UE capability information includes model information supported by the terminal device and CSI processing delay requirements corresponding to each supported model information; or, The first corresponding relationship is reported by the terminal device to the network device through model indication information, and the model indication information is used to indicate model information and the CSI processing delay requirement corresponding to the model information.

22. The method according to any one of claims 16 to 21, wherein: In the first corresponding relationship, the CSI processing delay requirement is represented by a value of the CSI processing delay requirement, or is represented by a level corresponding to the CSI processing delay requirement.

23. The method according to claim 22, wherein: The values ​​of the CSI processing delay requirements corresponding to different levels are configured by the network device or agreed upon by the protocol.

24. The method according to any one of claims 16 to 21, wherein: In the first corresponding relationship, the CSI processing delay requirement is represented by the value of a first offset, or by a level corresponding to the first offset, the first offset is the offset of the CSI processing delay requirement relative to a reference CSI processing delay requirement, and the reference CSI processing delay requirement is configured by the network device or agreed upon by a protocol.

25. The method according to claim 24, wherein: The values ​​of the first offsets corresponding to different levels are configured by the network device or agreed upon by the protocol.

26. The method according to any one of claims 15 to 25, wherein: The CSI processing delay requirement includes a first delay requirement and / or a second delay requirement; The first delay requirement is used to determine a first requirement that an interval between a first OFDM symbol and a second OFDM symbol needs to meet; The second delay requirement is used to determine a second requirement that an interval between the third OFDM symbol and the second OFDM symbol needs to meet; The first OFDM symbol is the last OFDM symbol of the PDCCH carrying the DCI. The DCI is used to Trigger the CSI report; the second OFDM symbol is the first OFDM symbol of the PUSCH carrying the CSI report; the third OFDM symbol is the last OFDM symbol of the CSI measurement resource corresponding to the CSI report.

27. The method according to any one of claims 15 to 26, wherein: The network device triggers the terminal device to perform the CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting, including: The network device determines, based on the CSI processing delay requirement, a first requirement that an interval between a first OFDM symbol and a second OFDM symbol needs to meet, and / or a second requirement that an interval between a third OFDM symbol and a second OFDM symbol needs to meet; The network device triggers the terminal device to report the CSI through DCI according to the first requirement and / or the second requirement, the interval between the first OFDM symbol and the second OFDM symbol meets the first requirement, and / or the interval between the third OFDM symbol and the second OFDM symbol meets the second requirement; Among them, the first OFDM symbol is the last OFDM symbol of the PDCCH carrying the DCI, and the DCI is used to trigger the CSI report; the second OFDM symbol is the first OFDM symbol of the PUSCH carrying the CSI report; the third OFDM symbol is the last OFDM symbol of the CSI measurement resource corresponding to the CSI report.

28. The method according to any one of claims 15 to 27, wherein: The CSI report is a CSI report obtained by CSI compression based on AI / ML and / or a CSI report obtained by CSI prediction based on AI / ML.

29. A device for determining a processing delay requirement, applied to a terminal device, the device comprising: A determination unit is used to determine, based on a first model, a CSI processing delay requirement corresponding to a channel state information CSI report, where the CSI report is an AI / ML-based CSI report, and the first model is a model used for the CSI report; based on the CSI processing delay requirement corresponding to the CSI report, determine whether to perform the CSI report and / or whether to update the CSI report.

30. A device for determining a processing delay requirement, applied to a network device, the device comprising: A determining unit, configured to determine, based on a first model, a CSI processing delay requirement corresponding to a CSI report, wherein the CSI report is an AI / ML-based CSI report, and the first model is a model used by the CSI report; A trigger unit is used to trigger the terminal device to perform the CSI reporting based on the CSI processing delay requirement corresponding to the CSI reporting.

31. A terminal device, comprising: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory, so that the terminal device executes the method as claimed in any one of claims 1 to 14.

32. A network device comprising: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory so that the network device executes the method as claimed in any one of claims 15 to 28.

33. A chip, comprising: A processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 14, or a method as claimed in any one of claims 15 to 28.

34. A computer-readable storage medium for storing a computer program, wherein the computer program causes a computer to execute the method according to any one of claims 1 to 14, or the method according to any one of claims 15 to 28.

35. A computer program product comprising computer program instructions, the computer program instructions causing a computer to execute the method of any one of claims 1 to 14, or any one of claims 15 to 28.

36. A computer program, the computer program causing a computer to execute the method of any one of claims 1 to 14, or any one of claims 15 to 28.

Images