Communication method and related device

Abstract

The invention provides a communication method and a related device, and aims to improve the processing performance of AI / ML (Artificial Intelligence / Markup Language). The method comprises: a network device sending first information to a terminal device, the first information being used for indicating M resource sets, each of the M resource sets comprising at least one resource, M being a positive integer; correspondingly, the terminal equipment receives the first information and determines a first data set according to N effective resource sets in M resource sets, the first data set comprises at least one piece of first data, a first effective resource set in the N effective resource sets meets a first constraint condition, and N is a positive integer smaller than or equal to M; the terminal equipment sends first report information to network equipment, wherein the first report information comprises the first data set; correspondingly, the network device receives the first report information.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and in particular to a communication method and related apparatus. BACKGROUND

[0002] When artificial intelligence (AI) / machine learning (ML) technology is applied to a wireless communication system, it can be suitable for a variety of use cases, such as modulation, coding, transmitters, receivers, multi-antenna technology, positioning technology, etc. The AI / ML technology can be applied in network devices and / or terminal devices, i.e., AI / ML models are deployed at the network side and / or the terminal device side. Whether it is a network side model or a terminal side model, for some use cases, the network device needs to indicate or configure the corresponding resources (e.g., reference signal resources) to the terminal device for measurement by the terminal device, so as to generate measurement results for inference / monitoring of the terminal side model or the network side model.

[0003] However, in some cases, the processing result of AI / ML cannot meet the needs, and there is an urgent need for a method to improve the processing performance of AI / ML. SUMMARY

[0004] The present application provides a communication method and related apparatus to improve the processing performance of AI / ML.

[0005] In a first aspect, the present application provides a communication method, which can be applied to a first communication apparatus. For example, the communication apparatus can be a terminal device, or it can also be a component (such as a chip, a chip system, etc.) configured in the terminal device, or it can also be a logic module or software capable of realizing all or part of the functions of the terminal device, and the present application does not limit this. Hereinafter, for the convenience of understanding and description, the terminal device is taken as an example of the first communication apparatus to describe the method.

[0006] Exemplarily, the method comprises: receiving first information from a network device, the first information being used to indicate M resource sets, each of the M resource sets comprising at least one resource, M being a positive integer; determining a first data set according to N valid resource sets in the M resource sets, the first data set comprising at least one first data, a first valid resource set in the N valid resource sets satisfying a first constraint condition, N being a positive integer less than or equal to M; and sending first reporting information to the network device, the first reporting information comprising the first data set.

[0007] Wherein, at least one first data can be understood as one data or multiple data. In other words, the first data set comprises one data or multiple data.

[0008] Optionally, M is an integer greater than 1. That is, the first information is used to indicate a plurality of resource sets.

[0009] Optionally, N is an integer less than M. That is, one or more valid resource sets are included in the M resource sets (N is not 0), or no valid resource set is included in the M resource sets (N is equal to 0). It can also be said that at least one invalid resource set is included in the M resource sets, and the invalid resource set is the remaining resource set in the M resource sets except for the N valid resource sets, and the invalid resource set does not satisfy the above first constraint condition.

[0010] Based on the technical solution, the terminal device uses the first constraint condition to filter the resource set notified by the network device to obtain a valid resource set, and obtains corresponding valid data based on the valid resource set, which is reported to the network device. Since the valid resource set is obtained by considering the case that the resource cannot be obtained or cannot be measured, and the valid data obtained based on the valid resource set is used as the input of the AI / ML model, the method provided in the present application realizes the filtering of the input of the AI / ML model, so that the processing result of the AI / ML can meet the demand, and thus the processing performance of the AI / ML is improved.

[0011] In combination with the first aspect, in some implementations of the first aspect, the method further includes: in a case where N satisfies a second constraint condition, sending the first report information to the network device; or in a case where N does not satisfy the second constraint condition, the first report information does not include the first data set.

[0012] That is, in a case where N does not satisfy the second constraint condition, the terminal device does not include the first data set in the information sent to the network device.

[0013] In the second aspect, the present application provides a communication method, which can be applied to a second communication device. For example, the communication device can be a network device, or can be a component (such as a chip, a chip system, etc.) configured in the network device, or can be a logic module or software capable of realizing all or part of the function of the network device, and the present application does not limit this. In the following, for the convenience of understanding and description, the method is described by taking the network device as an example of the second communication device.

[0014] Exemplarily, the method comprises: sending first information to a terminal device, the first information being used for indicating M resource sets, each of the M resource sets comprising at least one resource, M being a positive integer; and receiving first reported information from the terminal device, the first reported information comprising a first data set, the first data set being determined according to N valid resource sets in the M resource sets, a first valid resource set in the N valid resource sets satisfying a first constraint condition, N being a positive integer less than or equal to M.

[0015] Based on the technical solution, the network device informs the terminal device of the resource sets, so that the terminal device screens the resource sets informed by the network device using the first constraint condition to obtain valid resource sets, and obtains corresponding valid data based on the valid resource sets, which is reported to the network device. Since the valid resource sets are resources obtained by considering the case that resources cannot be acquired or cannot be measured, and the valid data obtained based on the valid resources is the input of the AI / ML model, the method provided in the present application realizes screening of the input of the AI / ML model, so that the processing result of the AI / ML can meet the demand, thereby improving the processing performance of the AI / ML.

[0016] In combination with the first and second aspects, in some implementations of the first and second aspects, the receiving the first reported information from the terminal device comprises: receiving the first reported information from the terminal device in a case where N satisfies a second constraint condition; or in a case where N does not satisfy the second constraint condition, the first reported information does not comprise the first data set.

[0017] Optionally, the second constraint condition comprises one of the following: N=M, M-N is less than or equal to a first preset value, or N is greater than or equal to a second preset value.

[0018] In combination with the first and second aspects, in some implementations of the first and second aspects, the first valid resource set is at least one of the following: a pre-defined valid resource set in the N valid resource sets, a configured or indicated valid resource set in the N valid resource sets, or any one of the N valid resource sets.

[0019] In some implementations of the first and second aspects, the first constraint includes at least one of the following: the first set of valid resources is carried on valid physical resources, the valid physical resources including valid time domain resources and / or valid frequency domain resources; a terminal device processing capability corresponding to the first set of valid resources meets a requirement; the first set of valid resources is earlier than or not later than a reference resource corresponding to a first task, the first task including processing the first set of valid resources; resources included in the first set of valid resources are in an activated state or a configured state; or, resources included in the first set of valid resources are not misconfigured.

[0020] The valid physical resources can be informed by the network device to the terminal device.

[0021] In some implementations of the first and second aspects, the valid physical resources include downlink time units or flexible time units informed by the network device; the valid physical resources do not include uplink time units or flexible time units informed by the network device; the valid physical resources do not include measurement gaps; the valid physical resources include valid downlink bandwidth parts (BWPs) or valid downlink carriers.

[0022] Optionally, the valid downlink carriers include activated downlink carriers and / or non-dormant downlink carriers.

[0023] Optionally, the valid downlink BWPs include activated downlink BWPs and / or non-dormant downlink BWPs.

[0024] In some implementations of the first and second aspects, the first set of valid resources is carried on the valid physical resources informed by the network device, including that at least one resource in the first set of valid resources is carried on the valid physical resources, or all resources in the first set of valid resources are carried on the valid physical resources.

[0025] Optionally, the at least one resource in the first set of valid resources is carried on the valid physical resources, including that part of the resources in the first set of valid resources are carried on the valid time-frequency resources. The number of the part of the resources is greater than or equal to a first threshold.

[0026] Optionally, the at least one resource in the first set of valid resources is carried on the valid physical resources, including that part of the resources in the first set of valid resources are not carried on the valid time-frequency resources. The number of the part of the resources is equal to or less than a second threshold.

[0027] It can be understood that the first threshold and the second threshold can be predefined or indicated by a network device. The first threshold and the second threshold can be the same or different.

[0028] With reference to the first and second aspects, in some implementations of the first and second aspects, the terminal device processing capability corresponding to the first set of valid resources meets the requirement, including that a terminal device processing capability corresponding to a first task meets the requirement, the first task including processing based on the first set of valid resources.

[0029] Optionally, the first task includes one or more of the following: first CSI measurement, first CSI inference, first CSI monitoring, first CSI generation, or first CSI reporting.

[0030] With reference to the first and second aspects, in some implementations of the first and second aspects, the terminal device processing capability corresponding to the first task meets the requirement, including that a processing latency requirement required for performing the first task is met, and / or, at a starting time unit corresponding to the first task, a remaining terminal device processing capability is greater than or equal to a terminal device processing capability required for performing the first task.

[0031] Optionally, the terminal device processing capability corresponding to the first task meets the requirement, including that the remaining terminal device processing capability is less than or equal to the terminal device processing capability required for performing the first task, and the first task is not ignored.

[0032] Wherein, the first task is not ignored means that a priority of the first task is higher than that of another task that is occupying the terminal device processing capability, so that the another task is not continued to be performed, and the terminal device processing capability is released to perform the first task.

[0033] Optionally, the terminal device processing capability includes at least one of the following: a computing capability of the terminal device, an inference capability of the terminal device, a storage capability of the terminal device, or a processing latency of the terminal device.

[0034] With reference to the first and second aspects, in some implementations of the first and second aspects, an invalid resource set in the M resource sets does not meet the first constraint condition, the invalid resource set being a remaining resource set in the M resource sets other than the N sets of valid resources.

[0035] With reference to the first and second aspects, in some implementations of the first and second aspects, the second data set corresponding to the invalid resource set is not included in the first reporting information, or a value of a field corresponding to the second data set in the first reporting information corresponds to an "invalid" state.

[0036] It can be understood that the second data set corresponding to the invalid resource set is not included in the first reporting information, which means that there is no field corresponding to the second data set in the reporting information.

[0037] In some implementations of the first and second aspects, the first data includes at least one of the following: measurement results, inference results, or monitoring results, wherein the measurement results are obtained by measuring the N valid resource sets, the inference results are obtained by inferring based on the N valid resource sets, and the monitoring results are obtained by monitoring based on the N valid resource sets.

[0038] In some implementations of the first and second aspects, the first data set includes N first data, and the N first data correspond to the N valid resource sets one by one.

[0039] In other words, the N first data included in the first data set are obtained by processing the N valid resource sets respectively.

[0040] In some implementations of the first and second aspects, the M resource sets are M measurement resource sets, the N resource sets are N measurement resource sets, the first data are channel state information (CSI) obtained based on the N measurement resource sets, and the first reporting information includes a first CSI report obtained based on the N measurement resource sets.

[0041] Optionally, any one of the M resource sets is a first measurement resource set, and the first measurement resource set includes one or more first measurement resources. The first measurement resource is a synchronization signal resource, a broadcast signal resource, or a reference signal (RS) resource.

[0042] In some implementations of the first and second aspects, the first reporting information further includes at least one of the following: a number of first data included in the first data set, identification information or time information corresponding to the N valid resource sets, information of the first constraint condition satisfied by the N valid resource sets, identification information or time information corresponding to an invalid resource set, or information of the first constraint condition not satisfied by the invalid resource set, wherein the invalid resource set is a remaining resource set in the M resource sets except the N valid resource sets.

[0043] The information of the first constraint condition satisfied by the N valid resource sets can be understood as information of the first constraint condition satisfied by each of the N valid resource sets, or information of the first constraint condition satisfied by a first valid resource set of the N valid resource sets. The information of the first constraint condition not satisfied by the invalid resource set can be understood as information of the first constraint condition not satisfied by each of the invalid resource sets.

[0044] Optionally, when the M resource sets are M resource sets that are not overlapped in time domain, the M resource sets can be identified by time corresponding thereto. Since the N valid resource sets belong to the M resource sets, the N valid resource sets can also be identified by time information corresponding thereto.

[0045] In a third aspect, a communication apparatus is provided, which includes modules or units for implementing the method in any of the above aspects and / or any of the possible implementation manners of the above aspects. It should be understood that each module or unit can realize the corresponding function by executing a computer program.

[0046] In a fourth aspect, a communication apparatus is provided, which includes a processor configured to perform the method in any of the above aspects and / or any of the possible implementation manners of the above aspects.

[0047] The apparatus can further include a memory configured to store instructions and data. The memory is coupled to the processor, and the processor, when executing the instructions stored in the memory, can implement the method described in the above aspects.

[0048] The apparatus can further include a communication interface (or referred to as a communication circuit) configured to enable the apparatus to communicate with other devices. Exemplarily, the communication interface can be a transceiver, a circuit, a bus, a module, or other types of communication interfaces.

[0049] In a fifth aspect, a chip system is provided, which includes at least one processor configured to support the functions involved in any of the above aspects and / or any of the possible implementation manners of the above aspects, for example, receiving or processing data and / or information involved in the above method.

[0050] In a possible design, the chip system further includes a memory configured to store program instructions and data, and the memory is located in or outside the processor.

[0051] The chip system can be composed of a chip, or can include a chip and other discrete devices.

[0052] In a sixth aspect, the present application provides a computer readable storage medium, including a computer program, which, when executed on a computer, causes the computer to implement the method in any of the above aspects and any possible implementation of the aspect.

[0053] In a seventh aspect, the present application provides a computer program product, which includes a computer program (also referred to as code or instructions), which, when executed, causes a computer to perform the method in any of the above aspects and any possible implementation of the aspect.

[0054] In an eighth aspect, the present application provides a communication system, including the terminal device and the network device described above. The terminal device is configured to perform the method in the first aspect and any possible implementation of the aspect. The network device is configured to perform the method in the second aspect and any possible implementation of the aspect.

[0055] It should be understood that the third aspect to the eighth aspect of the present application correspond to the technical solutions of the first aspect or the second aspect of the present application, and the beneficial effects achieved by each aspect and the corresponding possible implementation are similar, which will not be repeated. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1 is an architecture schematic diagram of a communication system suitable for the method provided by the embodiments of the present application;

[0057] Figure 2 is a schematic diagram of a channel state information (CSI) report carrying a CSI measurement result provided by the embodiments of the present application;

[0058] Figure 3 is a schematic diagram of a CSI report carrying a CSI monitoring result provided by the embodiments of the present application;

[0059] Figure 4 is a schematic diagram of a high-layer report information carrying a CSI measurement / monitoring result provided by the embodiments of the present application;

[0060] Figure 5 is a schematic diagram of a resource set colliding with an uplink symbol provided by the embodiments of the present application;

[0061] Figure 6 is another schematic diagram of a resource set colliding with an uplink symbol provided by the embodiments of the present application;

[0062] Figure 7 is a schematic diagram of a central processing unit (CPU) of a terminal device being occupied provided by the embodiments of the present application;

[0063] Figure 8 is a schematic flowchart of a communication method provided by the embodiments of the present application;

[0064] Figure 9 FIG. 1 is a schematic diagram of reporting a first data set according to an embodiment of the present application;

[0065] Figure 10 FIG. 2 is a schematic diagram of a relationship between a first valid resource set and a valid physical resource according to an embodiment of the present application;

[0066] Figure 11 FIG. 3 is a schematic diagram of downlink BWP switching according to an embodiment of the present application;

[0067] Figure 12 FIG. 4 is a schematic diagram of a downlink carrier according to an embodiment of the present application;

[0068] Figure 13 FIG. 5 is a schematic diagram of a remaining terminal device processing capability according to an embodiment of the present application;

[0069] Figure 14 FIG. 6 is a schematic diagram of a relationship between a processing delay requirement and a processing delay according to an embodiment of the present application;

[0070] Figure 15 FIG. 7 is a schematic diagram of a type of first data being a measurement result according to an embodiment of the present application;

[0071] Figure 16 FIG. 8 is a schematic diagram of a type of first data being an inference result according to an embodiment of the present application;

[0072] Figure 17 FIG. 9 is a schematic diagram of obtaining a monitoring result according to an embodiment of the present application;

[0073] Figure 18 FIG. 10 is a schematic diagram of a type of first data being a monitoring result according to an embodiment of the present application;

[0074] Figure 19 FIG. 11 is a schematic block diagram of an apparatus according to an embodiment of the present application;

[0075] Figure 20 FIG. 12 is another schematic block diagram of an apparatus according to an embodiment of the present application. DETAILED DESCRIPTION

[0076] The technical solutions in the present application will be described below with reference to the drawings.

[0077] To facilitate understanding of the embodiments of the present application, the following points are first explained:

[0078] First, in the present application, the use of prefixes such as "first", "second", and the like is merely for the convenience of distinguishing different things belonging to the same category of names, and does not impose any constraints on the order, size, or number of things. For example, "first constraint condition" and "second constraint condition" are merely different constraint conditions, and do not limit the number or priority of the constraint conditions; for another example, "first task" and "second task" are merely different tasks, and there is no time sequence, size relationship, or priority relationship between them.

[0079] Second, in the present application, indication includes direct indication (also known as explicit indication) and indirect indication (also known as implicit indication). Among them, direct indication of information A means including information A; indirect indication of information A can mean indicating information A through the correspondence between information A and information B and directly indicating information B; or indicating information A through a preset rule that can be used to determine A according to B and directly indicating information B. Among them, the correspondence between information A and information B and the preset rule can be predefined, pre-stored, pre-burned, or pre-configured.

[0080] Third, for the convenience of understanding, the method provided by the present application is described in the present application by means of multiple drawings, and these drawings are only examples and should not constitute any limitation on the present application. For example, the order of the steps shown in the drawings can be simply changed according to their functions and internal logic; for another example, the steps in the drawings can all be executed, or only a part of them can be executed, as long as the same function as in the embodiments of the present application can be achieved.

[0081] Fourth, in the present application, "at least one" means one or more, and "multiple" means two or more. "And / or" describes the association between the associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent the following situations: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it, but does not rule out the case where the associated objects before and after it represent an "and" relationship, and the specific meaning expressed can be understood in conjunction with the context. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c; a and b; a and c; b and c; or a and b and c. Where a, b, and c can be single or multiple.

[0082] Fifth, in the present application, "sending" and "receiving" represent the direction of signal transmission. For example, "sending the first report information to the network device" can be understood as that the destination of the information is the network device, which can include direct transmission through the air interface, and also includes indirect transmission through the air interface by other units or modules. "Receiving the first report information from the terminal device" can be understood as that the source of the first report information is the terminal device, which can include direct reception from the terminal device through the air interface, and also includes indirect reception from the terminal device through the air interface by other units or modules. "Sending" can also be understood as "output" of the chip interface, and "receiving" can also be understood as "input" of the chip interface.

[0083] In other words, sending and receiving can be between devices, for example, between the terminal device and the network device; or can be within the device, for example, between components, modules, chips, software modules or hardware modules within the device through a bus, wire or interface.

[0084] Sixth, in the embodiments of the present application, "when", "if" and "when" all refer to the device making corresponding processing under certain objective conditions, and are not limited to time, and do not require the device to have a judgment action when implemented, nor does it mean that there are other limitations.

[0085] Seventh, in the present application, "example", "exemplarily", "for example" or "such as" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "example", "exemplarily", "for example" or "such as" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "example", "exemplarily", "for example" or "such as" is intended to present the relevant concept in a specific manner.

[0086] The technical solutions provided in the present application can be applied to various communication systems, for example: a 5th generation (5G) or new radio (NR) system, a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD) system, a wireless local area network (WLAN) system, a satellite communication system, a future communication system such as a 6th generation (6G) mobile communication system, or a fusion system of multiple systems, and the like. The technical solutions provided in the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and an internet of things (IoT) communication system or other communication systems.

[0087] A device in a communication system can send a signal to another device or receive a signal from another device. The signal can include information, signaling, or data, etc. The device can also be replaced by an entity, a network entity, a communication device, a communication module, a node, a communication node, etc. The device is taken as an example for description in the present disclosure. For example, the communication system can include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device. It can be understood that the terminal device in the present disclosure can be replaced by a first communication apparatus, and the network device can be replaced by a second communication apparatus, both of which perform the corresponding communication method in the present disclosure.

[0088] The radio access network (RAN) device in the present application is a device with wireless transceiving function. The radio access network device can provide wireless communication function service and can access terminal devices to a wireless network. The radio access network device can refer to a radio access network (RAN) node (or device) applied to a cellular network (or mobile network) to access terminal devices to a wireless network, and can also be a zigbee base station, a BT master, a BLE master, a Lora base station, and a Wi-Fi access point.

[0089] The network device can be a base station. The base station can broadly cover various names in the following or be replaced with the following names, such as: Node B (Node B), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), primary station, secondary station, multi-mode wireless (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. The base station can also refer to a communication module, modem, or chip for setting in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device assuming a base station function in D2D, V2X, M2M communication, a network side device in 6G network, a device assuming a base station function in future communication system, etc. The base station can support networks of the same or different access technologies. Alternatively, the RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in vehicle to everything (V2X) technology can be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network device. In some deployments, the network device mentioned in the embodiments of the present application can be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the network device can include gNB-CU-CP, gNB-CU-UP and gNB-DU.

[0090] In some deployments, wireless access is facilitated by a plurality of RAN nodes in cooperation to serve a terminal, different RAN nodes respectively implementing part of the functionalities of a base station. For example, a RAN node can be a CU, a DU, a CU-CP, a CU-UP, or a RU, etc. A CU and a DU can be separately arranged, or can also be included in the same network element, for example, in a BBU. A RU can be included in a radio frequency device or a radio frequency unit, for example, in a RRU, an AAU, or a RRH.

[0091] A RAN node can support one or more types of fronthaul interfaces, different fronthaul interfaces respectively corresponding to DUs and RUs having different functions. If the fronthaul interface between a DU and a RU is a common public radio interface (CPRI), the DU is configured to implement one or more of the baseband functions, and the RU is configured to implement one or more of the radio frequency functions. If the fronthaul interface between the DU and the RU is another interface, compared with the CPRI, part of the baseband functions of the downlink and / or the uplink, such as one or more of precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / adding a cyclic prefix (CP) for the downlink, or one or more of digital beamforming (BF), or fast Fourier transform (FFT) / removing the CP for the uplink, are moved from the DU to the RU for implementation. In a possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the splitting manner between the DU and the RU is different, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0092] Taking eCPRI Cat A as an example, for downlink transmission, the DU is configured to implement layer mapping and one or more functions (i.e., one or more of encoding, rate matching, scrambling, modulation, and layer mapping) before layer mapping, and other functions (e.g., one or more of resource element (RE) mapping, digital BF, or IFFT / add CP) after layer mapping are implemented in the RU. For uplink transmission, the DU is configured to implement demapping and one or more functions (i.e., one or more of decoding, de-rate matching, de-scrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping) before demapping, and other functions (e.g., one or more of digital BF or FFT / CP removal) after demapping are implemented in the RU. It can be understood that the function descriptions of the DU and the RU corresponding to various types of eCPRI can refer to the eCPRI protocol, which will not be described here.

[0093] In a possible design, the processing unit in the BBU for implementing baseband functions is referred to as a baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is referred to as a baseband low (BBL) unit.

[0094] In different systems, the CU (or CU-CP and CU-UP), DU, or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (open-RAN, O-RAN, or ORAN) system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. Any of the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module. That is, the network device in this application can be a virtualized device, which is implemented by general hardware and instantiated virtualized functions, or special hardware and instantiated virtualized functions. The general hardware can be a server, such as a cloud server.

[0095] The network device can include the foregoing access network device, and can also include an operation administration and maintenance (OAM) device and / or a core network (CN) device. For the CN device, at least one of a location management function (LMF), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), an application function (AF), a network data analytics function (NWDAF), a network exposure function (NEF), a network slice selection function (NSSF), and a policy control function (PCF) can be included; and for the OAM device, an element management system (EMS) can be included, and a network management system (NMS) can also be included.

[0096] It should be understood that the network device in the embodiments of the present application can also be referred to as a "network side" or a "network part".

[0097] In the embodiments of the present application, the apparatus for implementing the function of the network device can be the network device, or can be an apparatus capable of supporting the network device to implement the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The apparatus can be installed in the network device or used in matching with the network device. In the embodiments of the present application, only the apparatus for implementing the function of the network device is taken as an example for description, and the scheme of the embodiments of the present application is not limited.

[0098] The terminal device in the present application can also be referred to as a user equipment (UE), an access terminal, a user unit, a user 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.

[0099] The terminal device in the embodiments of the present application can include a terminal device, a chip or circuit in the terminal device, an entity associated with the terminal device.

[0100] The chip or circuit in the terminal device includes at least one of components inside the terminal device, such as a chip, a central processing unit (CPU), a network processing unit (NPU), and a terminal radio frequency module.

[0101] The entity associated with the terminal device includes a terminal-side server, a computing / processing node, a computing / processing entity, a computing / processing unit, an OTT server, etc. The terminal device interacts with relevant information (such as data) through communication with the associated network entity. For example, the associated network entity and the terminal device belong to the same manufacturer. Due to model training, model selection, etc., it can not be performed on the terminal device, but on the OTT server on the terminal side. Therefore, the "terminal device" in the embodiments of the present application also includes the OTT server on the terminal side.

[0102] It should be understood that the terminal device in the embodiments of the present application can also be referred to as "terminal side" (UE side) or "terminal part" (UE part).

[0103] The terminal device can be a device providing voice / data, for example, a handheld device with wireless connection function, a vehicle-mounted device, etc. At present, some examples of terminals are: mobile phone, tablet computer, notebook computer, palm computer, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication function, computing device or other processing device connected to a wireless modem, wearable device, terminal device in a 5G network, or terminal device in a future evolved public land mobile network (PLMN), etc., device in a zigbee network, device in a Lora network, Bluetooth (BT) slave, BLE slave, Wi-Fi station (STA), etc. The embodiments of the present application are not limited thereto.

[0104] The terminal device can also be a terminal device in an IoT system, also known as an IoT node. IoT is an important part of the future development of information technology, and its main technical feature is to connect objects through communication technology and network, so as to realize the intelligent network of man-machine interconnection and object-object interconnection. Connection can be through broadband technology or through narrowband technology. IoT technology can achieve mass connection, deep coverage and terminal power saving through, for example, narrowband (NB) technology. IoT technology includes reflection communication technology, spread spectrum technology, ultra wide band (UWB), etc., which will not be described here.

[0105] In addition, the terminal device can also include a smart printer, a train detector, a gas station sensor, and the like, and the main functions include collecting data (part of the terminal device), receiving control information and downlink data of a network device, and transmitting electromagnetic waves to transmit uplink data to the network device.

[0106] By way of example and without limitation, in the embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing, and shoes. The wearable device is a portable device that can be directly worn on the body or integrated into the clothes or accessories of the user. The wearable device is not only a hardware device, but also a powerful function achieved through software support and data interaction and cloud interaction. The general wearable smart device includes a full function, a large size, and can realize complete or partial functions without relying on a smart phone, such as a smart watch or smart glasses, and focuses on a certain application function and needs to cooperate with other devices such as a smart phone, such as various smart wristbands and smart jewelry for monitoring vital signs.

[0107] In the embodiments of the present application, the device for implementing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to implement the function, such as a chip system, which can be installed in the terminal device or used in combination with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices. In the embodiments of the present application, only the device for implementing the function of the terminal device is taken as an example for description, and the scheme of the embodiments of the present application is not limited.

[0108] The terminal device in the present application can be a hardware device, or a software function running on a special hardware, or a software function running on a general hardware, or a virtualized device, such as a general hardware and an instantiated virtualization function, or a special hardware and an instantiated virtualization function. The general hardware can be a server, such as a cloud server.

[0109] The network device and / or the terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on the water surface; and can also be deployed on an airplane, a balloon, and a satellite in the air. The present application does not limit the scenario in which the network device and the terminal device are located.

[0110] Figure 1 FIG. 1 is a schematic diagram of a communication system 10 suitable for the method provided in the embodiments of the present application. Figure 1 FIG. 1 shows a schematic diagram of a possible, non-limiting system architecture. As Figure 1As shown, the communication system 10 includes a radio access network (RAN) 100 and a core network 200. Optionally, the communication system 10 also includes an Internet 300. The RAN 100 can include at least one RAN node (e.g., 110a and 110b in FIG. 1), and can also include at least one terminal device (e.g., 120a-120j in FIG. 1). The terminal devices can be connected to the RAN devices by wireless means. The terminal devices and the terminal devices, and the RAN devices and the RAN devices, can be connected to each other by wired or wireless means. The RAN nodes 110 are connected to the core network 200 by wireless or wired means. The core network devices in the core network 200 and the RAN nodes 110 in the RAN 100 can be different physical devices, respectively, or can be the same physical device integrated with the logical functions of the core network and the logical functions of the RAN. Figure 1 Figure 1

[0111] Figure 1 The communication system 10 can include other network devices, such as wireless relay devices and wireless backhaul devices, etc., which are not shown in FIG. 1. Figure 1

[0112] The RAN 100 can be a 3rd generation partnership project (3GPP) related cellular system, such as a 4G, 5G mobile communication system, or a future-oriented evolved system (e.g., a 6G mobile communication system). The RAN 100 can also be an ORAN, a cloud radio access network (CRAN), or a zigbee network system, or a wireless fidelity (Wi-Fi) system. The RAN 100 can also be a communication system that combines two or more of the above systems.

[0113] The RAN nodes can be satellite-based base stations, such as the satellite base station 110a, or can be indoor base stations, such as micro base stations or indoor stations 110b. It should be understood that the specific technology and specific device form of the wireless access network device is not limited in the present application. For ease of description, the following describes the base station as an example of the wireless access network device.

[0114] The terminal devices can be satellite-based terminal devices, such as the helicopter or unmanned aerial vehicle 120i in FIG. 1, or can be ground-based terminal devices, such as the ground-based terminal devices 120a-120j in FIG. 1. Figure 1 Figure 1 ​​​​The mobile phones 120a, 120e, 120f, and 120j, the vehicle 120b, the computer 110b, the printer 120h, and the like in FIG. 1.

[0115] Optionally, the terminal device can also be configured to function as a RAN node. For example, a UE can be configured to function as a scheduling entity that provides sidelink signals between terminal devices in vehicle-to-everything (V2X), device-to-device (D2D), or peer-to-peer (P2P), and the like.

[0116] The RAN nodes and the terminal devices can be of fixed positions or movable. The RAN nodes and the terminal devices can be deployed on land, including indoors or outdoors, handheld, or vehicle-mounted; can be deployed on water; or can be deployed on airplanes, airships, and artificial satellites in the air. Embodiments of the present application do not limit application scenarios of the RAN nodes and the terminal devices.

[0117] The roles of the RAN nodes and the terminal devices can be relative, for example, Figure 1 The helicopter or the drone 120i in FIG. 1 can be configured as a RAN node, which is a RAN node for the terminal device 120j that accesses the RAN 100 through the 120i; but for the RAN node 110a, the 120i is a terminal device, that is, the 110a and the 120i communicate through a wireless air interface protocol. Of course, the 110a and the 120i can also communicate through an interface protocol between RAN nodes, in which case, the 120i is also a RAN node relative to the 110a. Therefore, the RAN nodes and the terminal devices can be collectively referred to as communication devices, Figure 1 The 110a, 110b, and 120a-120j in FIG. 1 can be referred to as communication apparatuses with their respective corresponding functions, for example, a communication device with a RAN node function or a communication device with a terminal function.

[0118] In embodiments of the present application, the functions of the RAN nodes can also be performed by modules (such as chips) in the RAN nodes, or by control subsystems containing RAN node functions. The control subsystems containing RAN node functions herein can be control centers in the application scenarios of the terminals of smart grids, industrial control, intelligent transportation, smart cities, and the like. The functions of the terminal devices can also be performed by modules (such as chips) in the terminal devices, or by devices containing terminal device functions. The present application does not limit this.

[0119] With the development of AI / ML technology, AI / ML technology is increasingly applied in wireless communication networks, such as 5G new radio (NR) systems. When AI / ML is applied in air interface wireless communication systems, it can be applied to various use cases, such as modulation, coding, transmitters, receivers, multi-antenna technology, positioning technology, etc. Among them, for the application of AI / ML in multi-antenna technology, it includes AI / ML-based CSI feedback, AI / ML-based beam management (BM) technology, etc.

[0120] In the following, AI / ML-based air interface use cases are introduced based on AI / ML-based CSI feedback, AI / ML-based BM technology, and AI / ML-based positioning technology.

[0121] 1. AI / ML-based CSI feedback includes AI / ML-based CSI compression and AI / ML-based CSI prediction. Among them, AI / ML-based CSI compression is to compress and decompress the downlink CSI information measured by the terminal device through AI / ML technology. Illustratively, the terminal device delivers the compressed CSI information to the network device through the air interface, and restores it at the network device side. Since AI / ML has higher compression ratio and better CSI restoration capability than traditional compression algorithms, more CSI information can be fed back with less air interface overhead, so that the network device can achieve more accurate downlink precoding. AI / ML-based CSI prediction is to predict the downlink CSI at future time based on the current / historical downlink CSI through AI / ML technology. After obtaining the prediction result, the network side and the terminal side can use the predicted CSI for precoding, so that the predicted CSI is more matched to the channel state at the time when the downlink data is scheduled, thereby overcoming channel aging and achieving more accurate downlink precoding.

[0122] It can be understood that for the CSI feedback use case, the data for model training includes CSI.

[0123] 2. AI / ML-based BM technology refers to using AI / ML technology to predict the transmission and / or reception beams of network devices and / or terminal devices, and using AI / ML to infer a small number of beam scanning results to obtain the preferred beam, so as to obtain the preferred beam for communication with less beam scanning cost. It can be seen that AI / ML-based BM technology does not need to scan a large number of beams to obtain the preferred beam as in traditional schemes.

[0124] Exemplarily, for spatial domain BM, a preferred beam among a large number of candidate beams can be predicted by scanning a small number of beams, without scanning all the candidate beams, thereby avoiding the overhead problem. The small number of beams correspond to a small number of sparse beams or wide beams, and the large number of candidate beams correspond to a large number of dense beams or narrow beams.

[0125] Exemplarily, for time domain BM, a preferred beam at a future time can be predicted by scanning beams at a current / historical time, without scanning beams at the future time again, thereby avoiding the overhead problem.

[0126] It can be understood that, for the BM use case, the data for model training includes beam information, such as beam identity (ID), RSRP corresponding to the beam, and the like.

[0127] 3. In the AI / ML-based positioning technology, the channel information measured by using the AI / ML technology is used to infer an intermediate parameter for a traditional positioning method, or directly obtain a position coordinate value. Compared with the traditional positioning method, the AI / ML-based positioning method can obtain more accurate intermediate parameters or position coordinate values.

[0128] It can be understood that, for the positioning technology use case, the data for model training includes channel information and / or position information. The channel information includes power information, phase information, time delay information, distance information, speed information, channel scattering information, line of sight (LOS) / non-line-of-sight (NLOS) information, and the like.

[0129] When AI / ML is applied to a wireless communication system, a network element node for performing AI / ML inference can include two cases of bilateral models and unilateral models. The bilateral models and the unilateral models are described in detail as follows.

[0130] 1. Bilateral model: For an air interface characteristic / use case, a network device and a terminal device each have an AI / ML model, and in the inference process, the AI / ML model on the network device side and the AI / ML model on the terminal device side need to be paired to complete the entire inference process of the air interface characteristic. Taking CSI compression as an example, the AI / ML model on the terminal device side infers the original CSI to achieve the compression effect, and feeds back the inference output CSI (i.e., compressed CSI) to the network device through the air interface; after receiving the compressed CSI, the network device infers the compressed CSI through the AI / ML model on the network device side to achieve the decompression effect, thereby obtaining the restored CSI.

[0131] It can be understood that, for the network device side AI / ML model and the terminal device side AI / ML model with good matching degree, the CSI restored by the network device side is closer to the original CSI; for the network device side AI / ML model and the terminal device side AI / ML model with poor matching degree, the difference between the CSI restored by the network device side and the original CSI can be large.

[0132] 2. Unilateral model: for an air interface feature / use case, only deploying an AI / ML model (referred to as a network device side AI / ML model) on the network device side for inference or deploying an AI / ML model (referred to as a terminal device side AI / ML model) on the terminal side for inference can complete the entire inference process of the air interface feature. For example, a BM use case or a positioning technology use case, only deploying an AI / ML model on one side can complete the entire inference process.

[0133] The unilateral model includes a network side model or a terminal side model. For the network side model, the terminal device can report measurement information to the network device as model input data for model inference, training or monitoring; for the terminal side model, the terminal device can report inference results or monitoring results to the network device. However, whether it is a network side model or a terminal side model, for some use cases, the network device needs to indicate or configure corresponding resources (for example, reference signal resources) to the terminal device for measurement of the terminal device to generate the above-mentioned reported measurement information or for inference or monitoring of the terminal side model.

[0134] The following is a detailed introduction to the network side model and the terminal side model for an air interface use case.

[0135] For the network side model, in some use cases, the network side cannot directly obtain the data required for model operation (such as training, inference or monitoring, etc.), and the terminal device needs to obtain the data and then feed back to the network device. The data here can be measurement results obtained by the terminal device by measuring the downlink signal sent by the network device.

[0136] Figure 2 is a schematic diagram of a CSI report carrying a CSI measurement result provided by an embodiment of the present application. As shown in Figure 2 , the data type required by the network side model is the CSI measurement result, and the resource indicated or configured by the network device to the terminal device is the reference signal (RS) resource set. As shown in Figure 2 , the terminal device measures the RS resource set #1 configured / indicated by the network device, generates the CSI measurement result #1, and feeds it back to the network device in the CSI report #1 (which can be carried in the physical layer signaling). As shown in Figure 2As shown in (b), the UE performs measurements on RS resource sets #1 to #4 configured / indicated by the network device, obtaining CSI measurement results #1 to #4, and then feeds them back to the network device in CSI report #1. In this way, after obtaining CSI report #1, the network device can use it for model training, inference, or monitoring, or directly generate precoding or beamforming.

[0137] For the terminal-side model, the terminal device can obtain measurement results by measuring the downlink signals sent by the network device, or inference or monitoring results based on these measurement results. In other words, the network side needs the terminal device to provide feedback on the model inference results or model monitoring results. The model monitoring results are obtained by the terminal device measuring the resources configured or indicated by the network device, and then comparing these measurement results with the model inference results. For example, the model monitoring results could be the correlation or similarity between the two; higher correlation or similarity indicates more accurate model inference.

[0138] Figure 3 This is a schematic diagram illustrating how a CSI report carries CSI monitoring results, as provided in an embodiment of this application. Figure 3 As shown, the data type required by the network-side model is the CSI monitoring result, the resources indicated or configured by the network device to the terminal device are the RS resource set, and the terminal-side model is a predictive model for predicting CSI. Figure 3 As shown in (a), the terminal device measures the RS resource set #1 configured or indicated by the network device, obtaining CSI measurement result #1. The terminal device compares the CSI measurement result #1 with the CSI prediction result #1 obtained from the prediction model to obtain CSI monitoring result #1, and then feeds it back to the network device in the CSI report #1. Figure 3 As shown in (b), the terminal device performs measurements on the RS resource sets #1 to #4 configured / indicated by the network device, obtaining CSI measurement results #1 to #4. These results are then compared with CSI prediction results #1 to #4 to obtain CSI monitoring results #1 to #4. The four CSI monitoring results are then carried in CSI report #1 and fed back to the network device. Upon receiving CSI report #1, the network device can understand the monitoring performance of the terminal-side model and perform lifecycle management (LCM) on the terminal-side model, such as model activation / deactivation, model switching, and model selection.

[0139] The data type required by the network side is a CSI measurement result or a monitoring result, and the resource set indicated or configured by the network device to the terminal device is an RS resource set. The terminal device performs measurement on the RS resource set #1 to resource set #N configured / indicated by the network device to obtain a CSI measurement result #1 to measurement result #N, or obtains a CSI monitoring result #1 to monitoring result #N based on the CSI measurement result #1 to measurement result #N. Then, as shown in Figure 4 The network device can feed back the CSI measurement / monitoring result #1 to measurement / monitoring result #N to the network device in the data collection signaling (high-layer signaling). In this way, after the network device obtains the data collection signaling reported by the terminal device, the network device can use the CSI measurement result to perform network-side model training, inference, monitoring, or the like, or use the CSI monitoring result to perform LCM on the terminal-side model.

[0140] Because the amount of data required by the data collection operation is large, the resource configured or indicated by the network device to the terminal device is generally periodic, or non-periodic and multiple resources are indicated at one time, so as to save overhead. However, these resources may not be measured by the terminal device due to some reasons, so that the data (including measurement results, inference results, or monitoring results, etc.) corresponding to the resources configured or indicated by the network device cannot be all fed back to the network device by the terminal device, and thus the processing result of AI / ML cannot meet the requirement.

[0141] Reason one, the resource indicated or configured by the network device conflicts with an uplink (UL) symbol or a flexible symbol of time division duplexing (TDD), so that the network device cannot send corresponding downlink information on the resource.

[0142] Figure 5 is a schematic diagram of resource set collision with uplink symbols provided by an embodiment of the present application. As shown in Figure 5 (a) of FIG. 1, all RSs in the RS resource set #1 configured by the network device conflict with UL symbols, so that the RS signals cannot actually be sent; as shown in Figure 5 (b) of FIG. 1, part of the RSs (RS #3 and RS #4) in the RS resource set #1 configured by the network device conflict with UL symbols, so that the RS signals cannot actually be sent. In this way, the terminal device cannot measure the corresponding resource, and thus cannot generate a measurement result.

[0143] Figure 6 is another schematic diagram of resource set collision with uplink symbols provided by an embodiment of the present application. As shown in Figure 6As shown, in scenario 1, the network device configures or indicates the terminal device with 4 RS resource sets #1-#4, and indicates / configures the terminal device to report multiple measurement results in one CSI report; in scenario 2, the network device configures or indicates the terminal device with 6 RS resources #1-#6, and indicates / configures the terminal device to report multiple measurement results in one CSI report. For scenario 1, RS resource set #3 and RS resource set #4 cannot be measured by the terminal device due to partial collision with the UL symbol. For scenario 2, RS resource #2 and RS resource #5 cannot be measured by the terminal device due to partial collision with the UL symbol.

[0144] In summary, in the case where the resource set configured or indicated by the network device collides with the uplink symbol, the terminal device cannot successfully report the measurement results corresponding to all the multiple resources configured or indicated.

[0145] Reason two, in the case where the network device indicates or configures resources, due to the conflict between the measurement, inference, or monitoring of part of the resources and other measurement, inference, or monitoring tasks in the process of the terminal device, the terminal device cannot generate the corresponding data (for example, measurement results, inference results, or monitoring results).

[0146] Figure 7 is a schematic diagram of the central processing unit (CPU) of the terminal device provided by an embodiment of the present application. As shown, Figure 7 The terminal device includes 2 CSI tasks: CSI task #1 and CSI task #2. For CSI task #2, the data type required by the network side is the CSI measurement result or monitoring result, and the resource indicated or configured by the network device to the terminal device is multiple RS resources: RS #1-RS #3. For CSI task #1, the network device indicates the terminal device to measure RS resource RS #A at T1 through DCI, and reports to the network device at T3 through CSI report #A; for CSI task #2, the network device indicates the terminal device to measure multiple RS resources: RS #1-RS #3 at T2 through DCI, obtains multiple CSI measurement results (CSI measurement result #1, CSI measurement result #2, and CSI measurement result #3) or monitoring results (CSI monitoring result #1, CSI monitoring result #2, and CSI monitoring result #3), and reports the obtained multiple CSI measurement results or monitoring results to the network device at T4 through CSI report #B.

[0147] Due to the limited computing power of the terminal device, multiple CSI tasks cannot be executed in parallel. The computing power of the terminal device is embodied as the total CPU-occupied CPU. As shown, Figure 7As shown, it is assumed that the total amount of CPU available for the terminal device is C, the CSI task #1 corresponds to the required CPU L, the duration is from T1 to T3, the CSI task #2 corresponds to the required CPU L'>C-L, and the duration is from T2 to T4. RS#1 is located between T1 and T3, which overlaps in time with the CSI task #1, causing the CPU required by the terminal device to perform the CSI task #2 to be unable to be met (i.e., between T2 and T3, the number of CPUs required by the CSI task #2 L' is greater than the number of CPUs not occupied C-L), so the terminal device cannot obtain the CSI measurement result #1 / monitoring result #1 corresponding to RS#1; and RS#2 and RS#3 are located after T3, which do not overlap with the CSI task #1, at this time, the remaining unoccupied CPU returns to C>L, so the CPU required by the terminal device to perform the CSI task #2 can be met, and the CSI measurement result #2 / monitoring result #2 corresponding to RS#2 and the CSI measurement result #3 / monitoring result #3 corresponding to RS#3 can be obtained. Different CSI tasks corresponding to RSs can be indicated by different DCIs, for example, the RS corresponding to the CSI task #1 is indicated by DCI#A, and the RS corresponding to the CSI task #2 is indicated by DCI#B.

[0148] Since in the current way of processing the feedback resource set, the terminal side and the network side do not consider the case where the resource cannot be obtained or cannot be measured, i.e., the data (measurement results / inference results / monitoring results, etc.) corresponding to the configured / indicated resource cannot be completely fed back by the terminal device, which causes the terminal device to be unable to perform the corresponding task and report the generated corresponding data, and further causes the AI / ML processing result to be unable to meet the demand, affecting the AI / ML processing performance.

[0149] Therefore, how to filter the resources to generate corresponding data to realize the filtering of the input of the AI / ML model under the consideration of the case where the resource cannot be obtained or cannot be measured becomes a problem to be solved.

[0150] Therefore, the embodiments of the present application provide a communication method and related apparatus, in which the terminal device filters the resources notified by the network device under the consideration of the case where the resource cannot be obtained or cannot be measured, and obtains the corresponding effective data based on the effective resource set obtained by the filtering, and then takes the obtained effective data as the input of the AI / ML model, thereby realizing the filtering of the input of the AI / ML model, and thus the AI / ML processing performance can be improved.

[0151] Before introducing the method provided by the embodiments of the present application, the terms involved in the embodiments of the present application are introduced.

[0152] 1, Artificial intelligence operation.

[0153] The artificial intelligence operation (also referred to as model operation) in this application includes at least one of the following: data collection, model training, model updating, model inference, model monitoring, or model management.

[0154] The data collection is used for, for example, model training, model updating, data analysis, model inference, or model monitoring, etc. In the data collection process, data corresponding to different data features can be collected into different data sets, and different models are trained, so that the model can be better adapted to a certain specific feature in the inference stage to obtain better performance. Model updating can be understood as retraining of the model. Model inference is a process of obtaining model output data by inputting data to the trained model. The purpose of model monitoring is to ensure the reliability of the model. The network device and / or the terminal device can adopt model monitoring to observe the performance of model inference, and when the performance decreases, the model needs to be switched or deactivated. Model management is a management operation on the model, which can include, for example, model selection, model switching, model activation, model deactivation, etc.

[0155] It can be understood that the reliability of the model or the performance of the model inference can be affected by environmental changes. When the channel environment changes, if the model can no longer be well adapted to the channel environment, the reliability of the model will decrease, and in turn the accuracy of the inference will decrease.

[0156] It can also be understood that the "model operation" in the embodiment can also be referred to as "function operation", and the above model training, model updating, model inference, model monitoring can be replaced by function training, function updating, function inference, function monitoring (or performance monitoring) respectively. The function here can correspond to the function of artificial intelligence.

[0157] For the data collection process in the artificial intelligence operation, the terminal device often needs to obtain data. Some of the data are obtained or generated by the terminal device in the communication process with the network device.

[0158] 2, resource.

[0159] The "resource" in this application is used to represent the communication process in which the terminal device generates data, or the received / transmitted signal in the communication process. The channel resource (including one or more of time domain resource, frequency domain resource, code domain resource, or space domain resource) corresponding to the received / transmitted signal, or the channel corresponding to the received / transmitted signal.

[0160] Since the terminal device usually needs to measure the reference signal when generating data, the "resource" type in the present application can be a reference signal resource. Illustratively, the reference signal resource can include a synchronization signal block (SSB) resource, a physical broadcast channel (PBCH) resource, or an RS resource. Among them, the RS includes a demodulation reference signal (DMRS), a tracking reference signal (TRS), a channel state information (CSI)-RS (referred to as CSI-RS), or a positioning reference signal (PRS).

[0161] It can be understood that the "resource" in the present application can also be referred to as a "signal". Specifically, the signal includes a downlink signal used by the terminal device for measurement, such as a reference signal, a synchronization signal block (SSB) signal, a physical layer broadcast channel (PBCH) signal, etc.

[0162] For one resource, which can be referred to as a target resource, the target resource can be used by the terminal device for processing to obtain a corresponding target data. The processing here can include measurement, inference, or monitoring operations, etc. When the target data is a measurement result, it can include PMI, RI, RSRP, etc.

[0163] Illustratively, the target resource can be any one of the N valid resource sets or any one of the M resource sets in the following, or any one of the first valid resource set, or any one of the invalid resource set. The target data can be one data in the first data set below.

[0164] Taking CSI feedback as an example, the target resource includes a CSI-RS resource. The terminal device can process the target data based on the target resource, such as PMI or a channel matrix.

[0165] One resource corresponds to one resource ID. For a CSI-RS resource, its ID can be nzp-CSI-RS-ResourceId or zp-CSI-RS-ResourceId.

[0166] Exemplarily, the target data can be one of the first data set, e.g., the first data, or the second data.

[0167] For one resource set, which can be referred to as a target resource set, the target resource set includes at least one target resource.

[0168] Exemplarily, the target resource set can be any one of the N valid resource sets or the M resource sets, or the first valid resource set, or the invalid resource set.

[0169] Specifically, the information of the at least one target resource constituting the target resource set is informed by the network device. For example, the network device informs the identification information of the at least one target resource, wherein the identification of each target resource corresponds to one target resource. Taking the CSI-RS resource set CSI-RS-ResourceSet as an example, the network device informs the terminal device of at least one CSI-RS-ResourceId, wherein each corresponds to one CSI-RS resource.

[0170] In one example, the terminal device processes each resource in the target resource set to obtain a target data. If the target resource set includes K (K is an integer greater than 1) resources, the terminal device correspondingly obtains K target data.

[0171] Taking CSI feedback as an example, the target resource set includes K CSI-RS resources. The terminal device can process each resource in the K CSI-RS resources to obtain a target data, e.g., a pre-coding matrix indication (PMI) or a channel matrix. That is, K corresponding target data can be obtained for the K CSI-RS resources. It should be understood that, since CSI prediction needs to use multiple data located at different time domain positions as model input for training / inference / monitoring, etc., the terminal device can carry the K target data in one report information.

[0172] In another example, the terminal device processes each target resource set to obtain a target data, or in other words, each target resource set corresponds to one target data. If the target resource set includes K resources, the terminal device also only obtains one corresponding data. Alternatively, M>1 target resource sets correspond to M target data, and N>1 target resource sets correspond to N target data.

[0173] It should be understood that the target resource set herein can be a valid resource set below or an invalid resource set below; for the valid resource set, it corresponds to valid data (e.g., the first data below), and for the invalid resource set, it corresponds to invalid data (e.g., the second data below). The association / correspondence between the target resource set and the target data can be informed by the network device (e.g., through target control information). In this way, the terminal device can determine information of the corresponding target data set based on the target resource set, such as the number, type, target reporting information for carrying the target data set, etc.

[0174] The association / correspondence between the target resource set and the target data can be informed by the network device (e.g., through target control information). In this way, the terminal device can determine information of the corresponding target data set based on the target resource set, which includes the number, type, target reporting information for carrying the target data set, etc.

[0175] For the case of one target data for one target resource set. Taking beam management as an example, one target resource set includes K CSI-RS resources or SSB resources, and the terminal device obtains one or a group of processing information (such as reference signal receiving power (RSRP) information and / or CSI-RS resource indicator (RI) (referred to as CRI) / SSB resource indicator (RI) (referred to as SSBRI) information) based on the K CSI-RS resources as one target data; or the terminal device obtains K RSRPs by processing each CSI-RS target resource, and obtains one or a group of beams with better RSRP by comparing the K RSRPs, and the RSRP information corresponding to the one or a group of beams with better RSRP as one target data. Therefore, for one target resource set, the terminal device can carry the 1 target data in one reporting information.

[0176] For the case of multiple target data for multiple target resource sets. Taking CSI feedback as an example, each target resource set in the K target resource sets includes one CSI-RS resource, and the terminal device can process to obtain one target data, such as PMI or channel matrix, based on each target resource in the K CSI-RS target resources. That is, K target data can be obtained for the K CSI-RS target resources respectively. Since CSI prediction needs to use multiple data located at different time domain positions as model input for training / inference / monitoring, etc. model operation, the terminal device can carry the K target data in one reporting information.

[0177] One resource set corresponds to one resource set ID, for example, for a resource set consisting of CSI-RS resources, the resource set ID corresponds to NZP-CSI-RS-ResourceSetId or ZP-CSI-RS-ResourceSetId.

[0178] Optionally, the target resource set corresponds to a target measurement resource set (e.g., the first measurement resource set). The first measurement resource set includes one or more target resources (e.g., the first measurement resource). For example, for CSI feedback or beam management, the UE performs measurement based on the reference signal and obtains corresponding data, which is fed back to the network device through the CSI report. In this way, the target data set is obtained based on measurement on the target measurement resource set. Correspondingly, the target data includes CSI information. The target reporting information (e.g., the first reporting information) includes the target CSI report (e.g., the first CSI report information). The target task (e.g., the first task) includes the target CSI reporting task (e.g., the first CSI reporting task).

[0179] In summary, in the example of CSI feedback or beam management, the obtained target data includes one or more of the following 1) to 3):

[0180] 1) Channel response information; for example, one or more of PMI, precoding matrix, precoding vector, eigenvector, eigenmatrix, channel vector, channel matrix, layer indicator (LI), rank indicator (RI), etc.

[0181] 2) Channel quality information; for example, one or more of RSRP, signal to interference plus noise ratio (SINR), channel quality indicator (CQI), etc.

[0182] 3) Beam information; for example, one or more of CRI, SSBRI, etc.

[0183] It should be understood that the beam information can also be referred to as reference signal identification information. The one or more of 1) to 3) above can be collectively referred to as CSI information.

[0184] It should also be understood that the type / format / quantity of the target data is related to the number of target resources included in the target resource set. If the target resource set includes K resources, the type of target data includes channel quality information and / or beam information, such as RSRP and / or CRI / SSBRI. If the target resource set includes one resource, the type of target data includes channel response information, such as PMI or channel matrix.

[0185] 3. Control information.

[0186] It should be understood that the target resource set is informed to the terminal device by the network device through target control information (e.g., the first information below). The target control information is also referred to as target first information. Optionally, the target control information informs resource set information corresponding to the target resource set, where the resource set information includes composition information of the resource set, and the composition information includes resources constituting the resource set, such as which resources constitute the resource set. Optionally, the target control information informs resource information corresponding to the target resource, where the resource information includes resource ID, time-frequency resource location, port information, mapping manner, power information, used sequence, and / or resource repetition period of the target resource.

[0187] Regarding the signaling manner of the target control information, the target control information can include high-layer signaling and / or physical layer signaling. The target control information informs the target resource set, and it can also be said that the target control information configures or indicates the target resource set.

[0188] In an example, the target control information includes high-layer signaling configuring the target resource set. For example, when the type of the target resource is CSI-RS, the target control information includes high-layer signaling CSI-ReportConfig or CSI-ResourceConfig, and the corresponding CSI reporting type is periodic CSI. For another example, the target control information includes high-layer signaling (e.g., a control element (CE) of a media access control (MAC) layer, referred to as a MAC CE) or an activation command (e.g., activation DCI), and the corresponding CSI reporting type is semi-persistent CSI. Specifically, when the target control information configures the UE to generate / report data in a periodic manner, the target data includes data obtained by the terminal device processing the target resource set in one period. When the target resource configured by the target control information is a periodic resource or the target resource set is a periodic resource set, the target data includes data obtained by the UE processing the target resource set in one period.

[0189] In another example, the target control information includes physical layer signaling indicating the target resource set. For example, when the type of the target resource is CSI-RS, the target control information includes a CSI request field in downlink control information (DCI), and the corresponding CSI reporting type is aperiodic CSI. It should be understood that the target control information can be implemented by indicating one or more of a plurality of candidate resource set configurations, wherein the resource information corresponding to any one of the plurality of candidate resource set configurations is configured by high layer signaling.

[0190] 4、Data.

[0191] The data in the embodiments of the present application includes data obtained in a communication network, such as signal processing information, channel information, and radio frequency information.

[0192] The signal processing information includes information generated in a baseband signal processing process, such as information generated in a signal sampling, modulation, demodulation, encoding, decoding, precoding, resource mapping, and / or digital filtering process.

[0193] The channel information includes information corresponding to a channel environment, such as at least one of or a combination of power information, amplitude information, phase information, time delay information, multipath information, signal propagation time information, distance information, speed information, large-scale channel information, small-scale channel information, channel scattering information, LOS / NLOS information, and the like. For example, the data in the CSI use case and the BM use case is embodied as channel information CSI, and the data in the positioning use case is embodied as channel information and / or position information.

[0194] The radio frequency information includes information generated in an analog processing process, such as information generated in a digital-to-analog conversion, analog-to-digital conversion, digital pre-distortion, frequency conversion, radio frequency modulation, radio frequency demodulation, power amplification, low noise amplification, analog filtering, and / or duplex processing.

[0195] 5、Time unit.

[0196] The time unit in the embodiments of the present application refers to a continuous time resource in time. For example, one time unit is one or more transmission time intervals (TTIs), one or more time slots, or one or more time domain symbols. Further, the one or more TTIs are continuous in time; the one or more time slots are continuous in time; and the one or more time domain symbols are continuous in time.

[0197] Optionally, the time unit can also be a subframe.

[0198] In the embodiments of the present application, the time interval between two time units includes: a time interval between the start time of one time unit and the start time of another time unit; a time interval between the start time of one time unit and the end time of another time unit; a time interval between the end time of one time unit and the start time of another time unit; or a time interval between the end time of one time unit and the end time of another time unit.

[0199] Similarly, the time interval between two resources can be understood as: a time interval between the time unit corresponding to one resource and the time unit corresponding to another resource. Or, the time interval between two resources is the time interval between the two time units corresponding to the two resources. The description of the time interval between two time units can be referred to the foregoing description, which will not be repeated here.

[0200] Wherein, one time unit is earlier (or not later) than another time unit includes: the start time of one time unit is earlier (or not later) than the start time or end time of another time unit, or the end time of one time unit is earlier (or not later) than the start time or end time of another time unit. One time unit is later (or not earlier) than another time unit includes: the start time of one time unit is later (or not earlier) than the start time or end time of another time unit, or the end time of one time unit is later (or not earlier) than the start time or end time of another time unit.

[0201] Exemplarily, the start time unit can also be referred to as a start time, and the start time refers to the start time or end time of the time unit in which the start time unit is located. The end time unit can also be referred to as an end time, and the end time refers to the start time or end time of the time unit in which the end time unit is located.

[0202] The method provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0203] Figure 8 is a schematic flowchart of the communication method 800 provided by the embodiments of the present application. In Figure 8 In the flowchart shown, the method is shown from the perspective of the interaction between the terminal device and the network device, but the present application does not limit the execution subject of the method. For example, Figure 8 The terminal device in the foregoing embodiments can be replaced by a chip, a chip system, or a processor supporting the terminal device to implement the method, and can also be a logic module or software capable of implementing all or part of the functions of the terminal device, Figure 8The network device in the method can be replaced by a chip, a chip system, or a processor supporting the network device to implement the method, and can also be a logic module or software capable of implementing all or part of the network device functions.

[0204] Figure 8 The illustrated communication method 800 can include S801-S803. The steps in the method 800 are described in detail below.

[0205] S801, the network device sends first information to the terminal device, the first information being used for notifying M resource sets. Correspondingly, the terminal device receives the first information from the network device.

[0206] Each of the M resource sets includes at least one resource, or each of the M resource sets includes one resource or multiple resources. For example, in CSI feedback, any one resource set can include one resource, and in beam management, any one resource set can include multiple resources.

[0207] M is a positive integer. For example, when M is equal to 1, the first information is used for notifying one resource set to obtain one first data. For example, in beam management, the first information notifies the terminal device to measure a CSI-RS set in one time unit to obtain one measurement result (corresponding to one first data below); when M is greater than 1, the first information is used for indicating multiple resource sets to obtain multiple first data. For example, in CSI prediction, the first information notifies the terminal device to measure multiple CSI-RSs in different time units to obtain multiple measurement results (corresponding to multiple first data below); for example, in beam management, the first information notifies the terminal device to measure multiple CSI-RS sets in different time units to obtain multiple measurement results (corresponding to multiple first data below); for example, in CSI prediction / beam management, the first information notifies the terminal device to measure multiple CSI-RS / CSI-RS sets in different time units, and the terminal device can obtain multiple prediction results (corresponding to multiple first data below) through inference; for another example, in CSI prediction / beam management, the first information notifies the terminal device to measure multiple CSI-RS / CSI-RS sets in different time units and monitor the prediction results corresponding to the different time units, and the terminal device can obtain multiple prediction results (corresponding to multiple first data below) through monitoring.

[0208] Optionally, the M resource sets are respectively carried on different time units. The description of the time unit can refer to the description in the foregoing terminology section, which is not repeated here.

[0209] It can be understood that when the M resource sets are respectively carried on different time units, the M resource sets can be respectively used for the terminal device to measure channel information on different time units and obtain corresponding measurement results, inference results or monitoring results. This M resource sets respectively carried on different time units is configured for a use case suitable for time domain prediction. For example, the terminal device measures the M resource sets respectively located on the M historical time units to obtain M measurement results corresponding to different historical time points as model inputs, so as to obtain one or more prediction results of a predicted future time point through model inference as the output of the model.

[0210] The notification in the present application can include configuration and / or indication, that is, the first information is used for configuring and / or indicating the M resource sets.

[0211] Optionally, the first information can be carried in a high layer signal or a physical layer signaling.

[0212] An example, the first information is carried in a high layer signaling. When the type of the resource is a CSI-RS, the first information includes a high layer signaling CSI-ReportConfig or CSI-ResourceConfig, and the corresponding CSI reporting type is periodic CSI; or the first information includes a high layer signaling (for example, a MAC CE) or an activation command (for example, activation DCI), and the corresponding CSI reporting type is semi-persistent CSI. Specifically, when the first information configures the terminal device to generate / report data in a periodic manner, the following first data set includes data obtained by the terminal device processing a resource set in a period. When the resource configured by the first information is a periodic resource or the resource set configured by the first information is a periodic resource set, the following first data set includes data obtained by the terminal device processing a resource set in a period.

[0213] Another example, the first information is carried in a physical layer signaling. When the type of the resource is a CSI-RS, the first information includes a CSI request field in a DCI, and the corresponding CSI reporting type is aperiodic CSI. It should be understood that the first information can be implemented by indicating one or more configurations in a plurality of candidate resource set configurations, and the resource information corresponding to any one of the plurality of candidate resource set configurations and configured by the high layer signaling.

[0214] Optionally, the first information includes resource set information of the M resource sets, and the resource set information includes composition information of the resource set. The composition information includes resources constituting the resource set, for example, which resources constitute the resource set.

[0215] It can be understood that the resources constituting the resource set can be determined by resource information, which includes one or more of the following: resource ID of the resource, time-frequency resource location, port information, mapping method, power information, used sequence, or resource repetition period, etc.

[0216] S802, the terminal device determines a first data set according to N valid resource sets in M resource sets, and the first data set includes at least one first data. That is, the first data set is generated by the terminal device excluding invalid resource sets in M resource sets and using only N valid resource sets. Or, the other invalid resource sets in M resource sets except N valid resource sets are not used to generate the data reported by the UE.

[0217] Since part or all of the M resource sets notified by the first information may not be processed by the terminal device due to factors such as conflict with valid physical resources, insufficient terminal device processing capacity, etc., and thus cannot generate valid data. The resource set that cannot generate valid data is referred to as an invalid resource set in this application, and the terminal device should ignore these invalid data sets when reporting, and only consider the remaining valid resource sets, i.e. the above-mentioned N valid resource sets. The first valid resource set in the N valid resource sets satisfies the first constraint condition, and the first constraint condition information can be predefined or indicated by the network device.

[0218] Wherein, N is an integer less than or equal to M.

[0219] Exemplarily, N is an integer less than M, that is, the M resource sets include at least one invalid resource set, and the at least one invalid resource set does not satisfy the first constraint condition. That is, there are resource sets in the M valid resource sets that cannot be processed due to factors such as conflict, insufficient processing capacity, etc.

[0220] It can be understood that if the M valid resource sets are all invalid resource sets, the terminal device cannot obtain the first data set.

[0221] Exemplarily, N is a positive integer less than or equal to M, that is, the M resource sets include at least one valid resource set. In this way, the terminal device can process the valid resource set and determine at least one first data.

[0222] Optionally, the terminal device determines the first data set according to N valid resource sets in M resource sets, including: the terminal device processes according to N valid resource sets to obtain the first data set: measurement, inference or monitoring.

[0223] Optionally, the first data set includes one first data. For example, the terminal device measures N = 1 valid resource set to obtain one measurement result as the first data. For example, the terminal device measures N ≥ 1 valid resource sets and infers one inference result based on the measurement results as the first data. For another example, the terminal device measures N ≥ 1 valid resource sets and monitors one inference result based on the measurement results to obtain one monitoring result as the first data.

[0224] Optionally, the first data set includes a plurality of first data. For example, the terminal device measures N > 1 valid resource sets to obtain a plurality of measurement results as the first data set, each measurement result in the first data set being one first data. For example, the terminal device measures N ≥ 1 valid resource sets and infers a plurality of inference results based on the measurement results as the first data set, each inference result in the first data set being one first data. For another example, the terminal device measures N ≥ 1 valid resource sets and monitors a plurality of inference results based on the measurement results to obtain a plurality of monitoring results as the first data set, each monitoring result in the first data set being one first data.

[0225] Optionally, the N valid resource sets are respectively carried on different time units. In this way, the terminal device can obtain channel information on N time units based on the N valid resource sets carried on the different time units.

[0226] Exemplarily, when the first data set includes a plurality of first data, the plurality of first data can act on or correspond to different time units. For example, the plurality of measurement results correspond to measurement results of N different effective resources respectively, where the N different effective resources are carried on a plurality of different time units. In CSI prediction or beam prediction, each of the plurality of measurement results is measured on an RS resource in a historical time unit. For another example, the plurality of inference results act on a plurality of different time units, where each inference result represents an inference result acting on one of the plurality of different time units. In CSI prediction or beam prediction, the plurality of inference results are a plurality of prediction results, and each of the plurality of prediction results acts on a future time unit. For another example, the plurality of monitoring results correspond to a plurality of different time units, and each of the plurality of monitoring results represents a result of monitoring one of the plurality of inference results, where the one of the plurality of inference results represents an inference result acting on one of the plurality of different time units. In CSI prediction or beam prediction, the plurality of inference results are a plurality of prediction results, and each of the plurality of prediction results acts on a future time unit. The plurality of monitoring results are results of performance monitoring on the plurality of prediction results.

[0227] Optionally, S803, the terminal device sends first reporting information to the network device, where the first reporting information includes the first data set. Correspondingly, the network device receives the first reporting information from the terminal device.

[0228] It should be understood that the reporting information in the embodiments of the present application is used to carry data. For target reporting information (e.g., the first reporting information), it is used to carry a target data set generated by the terminal device.

[0229] Optionally, the first reporting information is carried in physical layer signaling, such as uplink control information (UCI), or carried in high layer signaling, such as radio resource control (RRC) signaling or media access control (MAC) signaling.

[0230] Optionally, a time unit carrying the first reporting information, also referred to as a time unit where the first reporting information is located, is, for example, one of at least one time unit (e.g., a time domain symbol) occupied by the first reporting information. Specifically, the time unit can be one or more of a start time unit, an end time unit, a predefined time unit, or a time unit determined by notification information of the network device in the at least one time unit occupied by the first reporting information.

[0231] It should be understood that there is a correspondence between the target resource set and the target reporting information. Specifically, the terminal device processes the target resource set to obtain the corresponding target data and reports it in the corresponding target reporting information. The association / correspondence between the target resource set and the target reporting information can be notified by the network device (e.g., through target control information). In this way, the terminal device can determine the target data set based on the target resource set and carry the target data set in the corresponding target reporting information. Specifically, a target control message simultaneously notifies both the target resource set and the uplink resources carrying the target reporting information. For example, for CSI feedback or beam management, the target control information notifies the target resource set (CSI-RS set) of resource set information and / or resource information, and notifies the target reporting information (CSI reporting information) of the corresponding uplink resource information (e.g., time domain / frequency domain / code domain / spatial domain resources), such as physical uplink control channel (PUCCH) / physical uplink shared channel (PUSCH). In this way, the terminal device can carry the CSI information determined by the CSI-RS set into the CSI reporting information and send it.

[0232] It should be noted that whether the terminal device sends the first reporting information to the network device can be notified by the network device to the terminal device. For example, the network device can notify the terminal device to send the first reporting information via first information. That is, the first information can also be used to notify the terminal device to send the first reporting information to the network device; in other words, the information of the M resource sets and the sending of the first reporting information are notified by the same first information.

[0233] Figure 9 This is a schematic diagram of the first data set to be reported provided in an embodiment of this application. For example... Figure 9 In Scenario 1, the network device indicates four RS resource sets to the terminal device: RS resource set #1, RS resource set #2, RS resource set #3, and RS resource set #4. Each RS resource set includes multiple RS resources, and each RS resource set corresponds to a first data set. Each first data set includes a set of RSRPs and / or a set of CRIs. RS resource set #1 corresponds to first data #1, RS resource set #2 corresponds to first data #2, RS resource set #3 corresponds to first data #3, and RS resource set #4 corresponds to first data #4. RS resource sets #3 and #4 are invalid resource sets. Therefore, the CSI report sent by the terminal device to the network device includes first data #1 and first data #2, but does not include first data #3 and first data #4.

[0234] like Figure 9 In scenario 2, the network device indicates four RS resources to the terminal device: RS resource #1, RS resource #2, RS resource #3, and RS resource #4. Each of the four RS resources corresponds to a set of first data, and each set of first data includes a set of RSRPs and / or a set of CRIs. Specifically, RS resource #1 corresponds to first data #1, RS resource #2 corresponds to first data #2, RS resource #3 corresponds to first data #3, and RS resource #4 corresponds to first data #4. RS resources #3 and #4 are invalid resource sets; therefore, the CSI report sent by the terminal device to the network device includes first data #1 and first data #2, but excludes first data #3 and first data #4.

[0235] In this embodiment, the terminal device uses a first constraint to filter the resource set notified by the network device to obtain a valid resource set, and obtains corresponding valid data based on the valid resource set, which is then reported to the network device. Since the valid resource set considers situations where resources are unavailable or unmeasurable, and the valid data obtained based on the valid resources serves as input to the AI / ML model, the method provided in this application filters the input to the AI / ML model, making the AI / ML processing results more readily available and thus improving the processing performance of AI / ML.

[0236] In this application, the N valid resource sets among the M resource sets are determined or selected based on whether the first valid resource set satisfies the first constraint condition. This first valid resource set belongs to either the M resource sets or the N resource sets. Further, the following illustrates three methods for determining the first valid resource set:

[0237] Method 1: The first valid resource set is a predefined valid resource set among M valid resource sets or N valid resource sets. For example, the first valid resource set is the first or last resource set among N valid resource sets.

[0238] Method 2: The first valid resource set is the set of valid resources that are configured or indicated among M valid resource sets or N valid resource sets.

[0239] For method one or method two, if the first set of valid resources satisfies the first constraint condition, then N sets of valid resources can be determined.

[0240] Exemplarily, the N valid resource sets are the first N or the last N resource sets in the M resource sets, or are N resource sets not earlier than the first valid resource set, or are N resource sets not later than the first valid resource set, or are N pre-configured resource sets in the M valid resource sets.

[0241] In a third mode, the first valid resource set is any one of the N valid resource sets.

[0242] For the third mode, if any one of the M resource sets satisfies the first constraint condition, it is determined that the resource set belongs to the N valid resource sets. That is, the N valid resource sets are composed of the resource sets in the M resource sets that satisfy the first constraint condition.

[0243] Optionally, the first constraint condition includes at least one of the following: a first constraint condition 1, the first valid resource set is carried on a valid physical resource, the valid physical resource including a valid time domain resource and / or a valid frequency domain resource; a second constraint condition 2, a terminal device processing capability corresponding to the first valid resource set meets a requirement; a third constraint condition 3, the first valid resource set is earlier than or not later than a reference resource corresponding to a first task, the first task including processing the first valid resource set; a fourth constraint condition 4, resources included in the first valid resource set are in an activated state or a configured state; or a fifth constraint condition 5, resources included in the first valid resource set are not incorrectly configured.

[0244] It can be understood that the first constraint condition can be one or more of the first constraint condition 1 to the fifth constraint condition 5. If the first constraint condition is multiple of the first constraint condition 1 to the fifth constraint condition 5, the first valid resource set needs to satisfy each of the multiple conditions, so that the first valid resource set is considered to satisfy the first constraint condition. Conversely, if any one of the multiple conditions is not satisfied, it is considered that the first valid resource set does not satisfy the first constraint condition.

[0245] For the first constraint condition 1, the first valid resource set is carried on a valid physical resource. It can also be said that the first valid resource set overlaps with the valid physical resource.

[0246] Conversely, the invalid resource set other than the N valid resource sets in the M valid resource sets is not carried on the valid physical resource. Or, the invalid resource set does not overlap with the valid physical resource, or the invalid resource set is carried on an invalid physical resource, or the invalid resource set overlaps or conflicts with the invalid physical resource.

[0247] The effective physical resource is an effective physical resource informed by the network device, or an effective physical resource determined according to the informed information of the network device. The invalid physical resource is a physical resource other than the effective physical resource, and the invalid physical resource includes invalid time domain resources and / or invalid frequency domain resources.

[0248] The above-mentioned "not carried on the effective time-frequency resource" can also be referred to as "carried on the invalid time-frequency resource".

[0249] It can be understood that the carrying in the present application can be understood as time domain overlap. For example, for A carried on B, it can be understood that all time domain resources of A overlap with B, or part of the time domain resources of A overlap with B; for A not carried on B, it can be understood that all time domain resources of A do not overlap with B, or part of the time domain resources of A do not overlap with B.

[0250] Therefore, the first effective resource set carried on the effective physical resource can include that at least one resource in the first effective resource set is carried on the effective physical resource, or all resources in the first effective resource set are carried on the effective physical resource.

[0251] Scenario 1: At least one resource in the first effective resource set is carried on the effective physical resource.

[0252] Exemplarily, if the first effective resource set includes multiple resources, when one or more resources in the first effective resource set are carried on the effective physical resource, it is considered that the first effective resource set is carried on the effective physical resource.

[0253] It can be understood that the other resources in the first effective resource set other than the one or more resources carried on the effective physical resource can be carried on the effective physical resource or not carried on the effective physical resource.

[0254] Conversely, at least one resource in the invalid resource set is not carried on the effective time-frequency resource.

[0255] Example 1: If any one resource in the first effective resource set is carried on the effective physical resource, the first effective resource set is carried on the effective physical resource. Conversely, all resources in the invalid resource set are not carried on the effective physical resource.

[0256] In example two, if at least one resource in the first valid resource set is carried on the valid physical resource, and the number of resources in the first valid resource set carried on the valid physical resource is greater than or equal to the first resource threshold (or referred to as satisfying the first resource threshold), or the number of resources in the first valid resource set not carried on the valid physical resource is equal to or less than the second resource threshold (or referred to as satisfying the second resource threshold), the first valid resource set is carried on the valid physical resource. Conversely, the number of resources in the invalid resource set carried on the valid physical resource does not satisfy the first resource threshold, or the number of resources in the invalid resource set not carried on the valid physical resource does not satisfy the second resource threshold.

[0257] Optionally, the first resource threshold can be predefined or notified by the network device. For example, the first resource threshold can be determined by the number of resources in the first valid resource set not carried on the valid physical resource, for example, the first resource threshold is equal to the number of resources not carried on the valid physical resource, or is the number of resources not carried on the valid physical resource plus or minus an offset value.

[0258] Similarly, the second resource threshold can be predefined or notified by the network device. For example, the second resource threshold can be determined by the number of resources in the first valid resource set carried on the valid physical resource.

[0259] Figure 10 is a schematic diagram of the relationship between the first valid resource set and the valid physical resource provided by the embodiments of the present application. As shown in Figure 10 RS resource set #1 includes 4 RS resources: RS resource #1, RS resource #2, RS resource #3, or RS resource #4. Among them, RS resource #1 and RS resource #2 overlap with the valid physical resource, RS resource #3 and RS resource #4 overlap with the invalid physical resource, that is, there are two RS resources in RS resource set #1 overlapping with the valid resource, so according to the definition of the first valid resource set, it can be determined that RS resource set #1 is the first valid resource set.

[0260] Scenario 2: All resources in the first valid resource set are carried on the valid physical resource.

[0261] For example, if all resources in the first valid resource set are carried on the valid physical resource, it is considered that the first valid resource set is carried on the valid physical resource. Conversely, any one resource in the invalid resource set is not carried on the valid physical resource.

[0262] The valid physical resource in the present application will be described in detail below in connection with cases 1 to 4.

[0263] Case 1: The valid physical resource includes a downlink time unit or a flexible time unit notified by the network device.

[0264] In other words, the valid physical resource corresponds to the downlink time unit or flexible time unit informed by the network device. Conversely, the invalid time-frequency resource does not include the downlink time unit or flexible time unit informed by the network device, or in other words, the invalid time-frequency resource corresponds to the uplink symbol informed by the network device.

[0265] Since the uplink time unit cannot be used to transmit downlink information, only when the network device informs that a certain time-frequency resource corresponds to the downlink time unit or flexible time unit, the physical resource can be used to carry the valid resource or valid resource set. For example, the downlink reference signal or reference signal set used by the terminal device to receive and generate data. Conversely, if the network device informs that a certain time-frequency resource corresponds to the uplink time unit, the physical resource cannot be used to carry the valid resource or valid resource set.

[0266] Exemplarily, the network device informs the terminal device that the valid physical resource corresponds to the downlink symbol or flexible symbol through the configuration information TDD-UL-DL-ConfigDedicated and / or TDD-UL-DL-ConfigurationCommon; or, the network device informs the terminal device that the invalid time-frequency resource corresponds to the uplink symbol through the configuration information; or, the network device informs the terminal device that the symbol type corresponding to the time unit of the invalid time-frequency resource does not include the downlink symbol or flexible symbol through the configuration information. Wherein, the uplink symbol cannot be used to carry the downlink information such as reference signal on the resource set.

[0267] Exemplarily, the network device informs the terminal device to receive the downlink channel or downlink information on the valid physical resource, thereby implicitly informing that the valid physical resource corresponds to the downlink symbol. Or, the network device informs the terminal device to transmit the uplink channel or uplink information on the invalid physical resource, thereby implicitly informing that the invalid physical resource corresponds to the uplink symbol.

[0268] Exemplarily, the network device indicates that the valid physical resource corresponds to the downlink symbol or flexible symbol through the slot format indication information; or, the network device indicates that the invalid physical resource corresponds to the uplink symbol through the slot format indication information. Wherein, the slot format indication information may be, for example, the DCI in the format of DCI format 2_0.

[0269] Case 2, the valid physical resource does not include the uplink time unit or flexible time unit informed by the network device.

[0270] In the present application, “does not include” can also be referred to as “does not correspond to”. Conversely, the invalid time-frequency resource includes the uplink time unit or flexible time unit informed by the network device.

[0271] Since the flexible time unit can be configured or indicated as an uplink time unit or a downlink time unit, when the flexible time unit is configured or indicated as an uplink time unit, the flexible time unit is an invalid physical resource; when the flexible time unit is configured or indicated as a downlink time unit, the flexible time unit is a valid physical resource.

[0272] Similar to case 1, if the network device informs that a certain physical resource corresponds to an uplink time unit or a flexible time unit, the physical resource cannot be used to carry a valid resource or a valid resource set.

[0273] For example, the network device informs the terminal device that the valid physical resource corresponds to a downlink symbol through configuration information TDD-UL-DL-ConfigDedicated and / or TDD-UL-DL-ConfigurationCommon; or the network device informs the terminal device that the symbol type corresponding to the time unit of the invalid physical resource includes an uplink symbol or a flexible symbol through the configuration information.

[0274] For example, the network device informs the terminal device to receive downlink channels or downlink information on the valid physical resource, thereby implicitly informing that the valid physical resource corresponds to a downlink symbol; or the network device informs the terminal device to transmit uplink channels or uplink information on the invalid time-frequency resource, thereby implicitly informing that the invalid physical resource corresponds to an uplink symbol.

[0275] For example, the network device indicates that the valid time-frequency resource corresponds to a downlink symbol through slot format notification information, or the network device indicates that the invalid time-frequency resource corresponds to an uplink symbol or a flexible symbol through the slot format notification information.

[0276] Case 3: The valid physical resource does not include a measurement gap. Conversely, the invalid time-frequency resource includes a measurement gap.

[0277] Since the measurement gap is usually used for terminal device to perform adjacent area measurement, in the time domain resource corresponding to the measurement gap, the terminal device cannot transmit and receive signals, and thus cannot receive signals on the resource or resource set and generate corresponding data.

[0278] Case 4: The valid physical resource includes a valid downlink BWP or a valid downlink carrier. Conversely, the invalid physical resource includes an invalid downlink BWP or an invalid downlink carrier.

[0279] Optionally, the valid BWP includes an activated BWP. Conversely, the invalid BWP includes a non-activated BWP. It can be understood that the BWP in the non-activated state can no longer be valid after BWP switching occurs.

[0280] Optionally, a valid BWP includes a non-dormant BWP. Conversely, an invalid BWP includes a dormant BWP. It can be understood that a BWP in an active state may become effective after a BWP switch occurs. The non-dormant state can also be referred to as the deactivated state.

[0281] Optionally, a valid downlink carrier includes an active downlink carrier. Conversely, an invalid downlink carrier includes an inactive downlink carrier. It is understood that an inactive downlink carrier becomes invalid after a carrier handover or carrier deactivation.

[0282] Optionally, valid downlink carriers include non-dormant downlink carriers. Conversely, invalid downlink carriers include dormant downlink carriers.

[0283] For M resource sets with a relatively long time span, such as the time interval between each resource set being on the order of tens of milliseconds (ms), there may be a switching of effective physical resources between two resource sets, such as BWP switching, carrier switching, or carrier entering a dormant state. This would make some resource sets (such as the resource sets before the effective time-frequency resource switching) effective, while other resource sets (such as the resource sets after the effective time-frequency resource switching) ineffective.

[0284] Figure 11 This is a schematic diagram of downlink BWP handover provided in an embodiment of this application. The RS resource set #1 notified to the terminal device by the network device is carried on the first downlink BWP, and the RS resource set #2 is carried on the second downlink BWP. When both RS resource set #1 and RS resource set #2 are valid resource sets, the terminal device can obtain the first data #1 based on RS resource set #1 and the first data #2 based on RS resource set #2.

[0285] like Figure 11 As shown, before the BWP handover, the first downlink BWP is an invalid downlink BWP, and the second downlink BWP is a valid downlink BWP. Therefore, before the BWP handover, RS resource set #1 is an invalid resource set, and RS resource set #2 is a valid resource set. After the BWP handover, the first downlink BWP is a valid downlink BWP, and the second downlink BWP is an invalid downlink BWP. Therefore, after the BWP handover, RS resource set #1 is a valid resource set, and RS resource set #2 is an invalid resource set. If, after the BWP handover, it is necessary to report CSI reports #1 corresponding to RS resource sets #1 and #2, then the first data #1 will be included in the CSI report #1.

[0286] Figure 12is a schematic diagram of a downlink carrier provided by an embodiment of the present application. The network device informs the terminal device that the RS resource set #1 is carried on the first downlink carrier, and the RS resource set #2 is carried on the second downlink carrier. In the case that the RS resource set #1 and the RS resource set #2 are both valid resource sets, the terminal device can obtain the first data #1 based on the RS resource set #1, and can obtain the first data #2 based on the RS resource set #2.

[0287] As shown in Figure 12 , the first downlink carrier is a valid downlink carrier, and the second downlink carrier is an invalid downlink carrier. Therefore, the first data #1 is included in the CSI report #1 corresponding to the RS resource set #1 and the RS resource set #2.

[0288] It can be understood that the valid time-frequency resource can include one or more of the above-mentioned cases 1 to 4.

[0289] For the first constraint condition 2: the terminal device processing capability corresponding to the first valid resource set meets the demand. In other words, the terminal device processing capability demand for processing the first valid resource set can be met.

[0290] On the contrary, the terminal device processing capability corresponding to the invalid resource set in the M resource sets cannot meet the demand. In other words, the terminal device processing capability demand for processing the invalid resource set cannot be met.

[0291] Since the terminal device needs certain terminal device processing capability for measuring, reasoning, monitoring, etc. for a resource set, when the network device informs the terminal device to perform multiple tasks at the same time, the terminal device may face the problem of insufficient processing capability, so as to be unable to complete part of the tasks. Exemplarily, if the processing capability required by the task corresponding to the resource set is met, the terminal device continues to execute the task and generates the corresponding first data. Conversely, if the processing capability required by the task corresponding to the resource set is not met, the task may be stopped, so that the data expected to be generated by the task cannot be generated. The data corresponding to such a task is referred to as second data in the present application, and the second data is invalid data, and the resource set is an invalid resource set.

[0292] Optionally, the terminal device processing capability corresponding to the first valid resource set meets the demand, including: the terminal device processing capability corresponding to the first task meets the demand, or in other words, the terminal device processing capability demand required for executing the first task can be met. The terminal device processing capability demand required for executing the first task is also referred to as the terminal device processing capability demand corresponding to the first task. The first task includes processing based on the first valid resource set.

[0293] Conversely, the terminal device processing capability corresponding to the invalid resource set is insufficient, including that the terminal device processing capability corresponding to the second task does not meet the requirement, or in other words, the terminal device processing capability corresponding to the second task is insufficient, or in other words, the terminal device processing capability requirement for executing the second task is not met. Wherein, the second task includes processing based on the invalid resource set, and the terminal device processing capability requirement for executing the second task is also referred to as the terminal device processing capability requirement corresponding to the second task.

[0294] Exemplarily, the terminal device processing capability can correspond to a processing unit, which can also be referred to as a processing factor, and the processing unit is a quantitative processing capability value. Therefore, the terminal device processing capability requirement corresponding to the first task can be met, which can be understood as that the total processing units required by at least one task including the first task in the time unit corresponding to the first task does not exceed the total processing units available to the terminal device, or the processing units required by the first task in the time unit corresponding to the first task does not exceed the remaining processing units of the terminal device. Conversely, the terminal device processing capability requirement corresponding to the second task is not met, which can be understood as that the total processing units required by at least one task including the second task in the time unit corresponding to the second task exceeds the total processing units available to the terminal device, or the processing units required by the second task in the time unit corresponding to the second task exceeds the remaining processing units of the terminal device.

[0295] Wherein, the time unit corresponding to the xth task (such as the first task or the second task) can include at least one time unit included in the duration of the xth task. The starting time unit in the at least one time unit, or any time unit in the at least one time unit, or a time unit pre-defined and / or notified by the network device in the at least one time unit.

[0296] In this application, the M resource sets notified by the network device to the terminal device can correspond to multiple data, which includes the first data and the second data. In this way, the first report information includes the valid first data and does not include the invalid second data. In the traditional CSI reporting, one resource set is used to generate one data, and if the terminal device processing capability requirement for the resource set cannot be met, the terminal device will also carry a CSI data in the corresponding report information, which is an old CSI data that is not updated. In this application, since the old data that is not updated has been reported before, it has no additional contribution to the data processing of the network device this time, and therefore can be ignored as the second data and does not need to be carried into the first report information, so as to save the overhead.

[0297] Optionally, the terminal device processing capability comprises one or more of: a computing capability of the terminal device, an inference capability of the terminal device, a storage capability of the terminal device, or a processing latency of the terminal device.

[0298] Therefore, the computing capability of the terminal device can be quantified as a computing capability factor, the inference capability of the terminal device can be quantified as an inference capability factor, and the storage capability of the terminal device can be quantified as a storage capability factor.

[0299] In one possible implementation, the terminal device processing capability corresponding to the first task meets the requirement, which comprises: at the starting time unit corresponding to the first task, the remaining terminal device processing capability is greater than or equal to the terminal device processing capability required for executing the first task; otherwise, at the starting time unit corresponding to the second task, the remaining terminal device processing capability is less than or equal to the terminal device processing capability required for executing the second task.

[0300] In the above, the remaining terminal device processing capability greater than or equal to the terminal device processing capability required for executing the first task can also be referred to as: the remaining terminal device processing capability meets the terminal device processing capability requirement for executing the first task. The remaining terminal device processing capability less than or equal to the terminal device processing capability required for executing the second task can also be referred to as: the remaining terminal device processing capability does not meet the terminal device processing capability requirement for executing the second task. The description about the second task can refer to the foregoing description and will not be repeated here.

[0301] For example, assuming that the total processing capability of the terminal device is quantified as C, at the starting time unit corresponding to the first task, at least one task that has been performed or is about to start (for example, the starting time unit corresponding to the task about to start is the same as that of the first task) occupies the processing capability L, and the processing capability required for the first task is L', then if L'<=C-L, the remaining terminal device processing capability is greater than or equal to the terminal device processing capability required for executing the first task; if L'>C-L, the remaining terminal device processing capability is less than or equal to the terminal device processing capability required for executing the second task.

[0302] The first task and the second task in the present application can both be referred to as target tasks, and thus the starting time unit corresponding to the first task and the starting time unit corresponding to the second task can both be referred to as a starting time unit corresponding to a target task; the ending time unit corresponding to the first task and the ending time unit corresponding to the second task can both be referred to as an ending time unit corresponding to a target task.

[0303] The target task (e.g., the first task, the second task) in the embodiments of the present application is a task of processing a target resource or a target resource set by the terminal device. For example, the first task is used for processing a first valid resource set, and the second task is used for processing an invalid resource set.

[0304] Specifically, the target task corresponds to a CSI processing task. The CSI processing task can include at least one of CSI measurement, CSI inference, CSI monitoring, CSI generation, CSI reporting, and the like.

[0305] Optionally, the target task includes processing, such as measurement, inference, monitoring, and the like, of the target resource set by the terminal device.

[0306] Optionally, the target task includes generating corresponding target data by the terminal device based on the processing of the target resource set.

[0307] Optionally, the target task includes reporting the corresponding target data by the terminal device.

[0308] The target task can be notified to the terminal device based on target control information.

[0309] Optionally, the starting time unit corresponding to the target task can be a time unit carrying target first information. For example, one of the at least one time unit occupied by the target first information, which can be one or more of a starting time unit, an ending time unit, a predefined time unit, or a time unit determined by the notification information of the network device. The target first information refers to the first information used to notify the target task corresponding resource set.

[0310] Optionally, the starting time unit corresponding to the target task can be a time unit carrying the target resource set. For example, one of the at least one time unit occupied by the resource set, which can be a time unit carrying one target resource in the target resource set. The target resource can be one or more of the first target resource, the last target resource, the predefined target resource, or the target resource determined by the notification information of the network device. The target resource set can be the resource set corresponding to the target task. One of the at least one time unit occupied by the resource set can be a starting time unit, an ending time unit, or a predefined time unit and / or a time unit determined by the notification information of the network device.

[0311] Optionally, the starting time unit corresponding to the target task can be a time unit carrying a reference resource set, which is a predefined one of the M resource sets or a resource set determined by the network device's notification information. For example, the last Pth resource set of the M resource sets.

[0312] In the time unit carrying the reference resource set, the definition of a specific time unit or the definition of a specific resource in the reference resource set is similar to that of the time unit carrying the target resource set. Therefore, it is not repeated here.

[0313] Further, the target resource set or the reference resource set is not later than a reference resource (e.g., CSIreference resource). The reference resource corresponds to a time-frequency resource. The reference resource is determined by the time unit where the first reporting information is located, and is not later than or earlier than the time unit where the first reporting information is located, and differs from the time unit where the first reporting information is located by a time interval, wherein the time interval can be predefined and / or determined by the network device's notification information. For the target resource set or the reference resource set: optionally, all resources of the target resource set or the reference resource set are not later than the reference resource or the reference resource set; optionally, part of the resources of the target resource set or the reference resource set are not later than the reference resource or the reference resource set.

[0314] Optionally, the starting time unit corresponding to the target task can be a first offset time unit, which is later than the time unit carrying the target first information and has a first time interval with the time unit carrying the target first information.

[0315] Exemplarily, the first time interval can refer to an interval or offset between a position of the first offset time unit and a position of the time unit carrying the target first information. For example, the first time interval is an interval or offset between a starting position of the first offset time unit and a starting position of the time unit carrying the target first information; or, the first time interval is an interval or offset between the starting position of the first offset time unit and an ending position of the time unit carrying the target first information; or, the first time interval is an interval or offset between the starting position of the first offset time unit and a middle position of the time unit carrying the target first information. For another example, the first time interval is an interval or offset between a middle position of the first offset time unit and the starting position of the time unit carrying the target first information; or, the first time interval is an interval or offset between the middle position of the first offset time unit and the ending position of the time unit carrying the target first information; or, the first time interval is an interval or offset between the middle position of the first offset time unit and the middle position of the time unit carrying the target first information. For another example, the first time interval is an interval or offset between an ending position of the first offset time unit and the starting position of the time unit carrying the target first information; or, the first time interval is an interval or offset between the ending position of the first offset time unit and the ending position of the time unit carrying the target first information; or, the first time interval is an interval or offset between the ending position of the first offset time unit and the middle position of the time unit carrying the target first information.

[0316] The middle position of the time unit can be any position between the starting position of the time unit and the ending position of the time unit.

[0317] Optionally, the starting time unit corresponding to the target task can be a second offset time unit, which is later than the time unit carrying the target resource set and has a second time interval with the time unit carrying the target resource set.

[0318] The second time interval is similar to the first time interval. Descriptions about the second time interval can be obtained by replacing the first offset time unit in the above examples of the first time interval with the second offset time unit and replacing the time unit carrying the target first information with the time unit carrying the target resource set, and thus details are not described herein.

[0319] Optionally, the starting time unit corresponding to the target task can be a third offset time unit, which is earlier than the time unit carrying the target report information and has a third time interval with the time unit carrying the target report information.

[0320] The third time interval is similar to the first time interval. For the description of the third time interval, the first frequency shift time unit in the above example of the first time interval can be replaced by the third frequency shift time unit, and the time unit carrying the target first information is replaced by the time unit carrying the target report information, and thus the description is not repeated here.

[0321] The start time unit corresponding to the target task is similar to the start time unit corresponding to the target task. Optionally, the end time unit corresponding to the target task is later than the start time unit corresponding to the target task, and the start time unit corresponding to the target task has a fourth time interval.

[0322] The fourth time interval is similar to the first time interval. For the description of the fourth time interval, the first frequency shift time unit in the above example of the first time interval can be replaced by the end time unit corresponding to the target task, and the time unit carrying the target first information is replaced by the start time unit corresponding to the target task, and thus the description is not repeated here.

[0323] Optionally, the end time unit of the target task is the time unit where the first report information is located.

[0324] It can be understood that the time range between the start time unit corresponding to the target task and the end time unit corresponding to the target task is called the duration of the target task.

[0325] It can also be understood that the first time interval, the second time interval, the third time interval and the fourth time interval can be the same or different. One or more of the first time interval, the second time interval, the third time interval and the fourth time interval can be predefined or notified by the network device.

[0326] Figure 13 is a schematic diagram of the processing capacity of the remaining terminal device provided by the embodiments of the present application. As shown in Figure 13As shown, the total processing capacity of the terminal device is quantified as C, at the starting time unit T2 corresponding to the CSI task #2, the terminal device is executing the CSI task #1, and the execution of the CSI task #1 occupies the terminal device processing capacity L, and the processing capacity required by the CSI task #2 is L'. If L'≤C-L, that is, the remaining terminal device processing capacity is greater than or equal to the terminal device processing capacity required for executing the CSI task #2, the terminal device processing capacity corresponding to the CSI task #2 meets the requirement; if L'>C-L, that is, the remaining terminal device processing capacity is less than the terminal device processing capacity required for executing the CSI task #2, the terminal device processing capacity corresponding to the CSI task #2 does not meet the requirement. Wherein, the RS corresponding to different CSI tasks can be indicated by different DCI, for example, the RS corresponding to the CSI task #1 is indicated by DCI#A, and the RS corresponding to the CSI task #2 is indicated by DCI#B.

[0327] Further, the terminal device processing capacity corresponding to the first task meets the requirement, including: at the starting time unit corresponding to the first task, the remaining terminal device processing capacity is less than or equal to the terminal device processing capacity required for executing the first task, and the first task is not ignored; otherwise, at the starting time unit corresponding to the second task, the remaining terminal device processing capacity is less than or equal to the terminal device processing capacity required for executing the second task, and the second task is not ignored.

[0328] The above-mentioned not ignored means that the priority of the first task is higher than the other task that is occupying the terminal device processing capacity, and when the first task needs to be executed, the other task can stop or pause, thereby releasing the terminal device processing capacity for executing the first task.

[0329] Or, the above-mentioned not ignored means that the priority of the first task is higher than the other task that will occupy the terminal device processing capacity, and when the first task needs to be executed, the other task stops or pauses, and the first task is executed. Further, the starting time unit corresponding to the other task is the same as the starting time unit corresponding to the first task.

[0330] Exemplarily, a total processing capacity of the terminal device is quantified as C, at a starting time unit corresponding to the first task / second task, at least one task being executed and / or about to be executed by the terminal device occupies a processing capacity L, and a processing capacity required by the first task is L'. If L'>C-L, i.e., the remaining processing capacity of the terminal device is less than the processing capacity required by the first task, but the first task is not ignored due to a higher priority, the at least one task being executed and / or about to be executed is suspended, the processing capacity C of the terminal device is restored, and the first task is executed; if L'>C-L, i.e., the remaining processing capacity of the terminal device is less than the processing capacity required by the second task, but the second task is ignored by the terminal device due to a lower priority.

[0331] In another possible implementation, the processing capacity of the terminal device required by the first task is satisfied, including that a processing time delay requirement required by the first task is satisfied, and otherwise, a processing time delay requirement required by the second task is not satisfied.

[0332] The processing time delay requirement required by the terminal device for executing the first task is satisfied, which means that a processing time delay of the first task is longer than or not shorter than a processing time delay requirement of the first task; or means that a time unit in which the first report information is located is later than or not earlier than an ending time unit corresponding to the processing time delay requirement of the first task, the ending time unit is later than a starting time unit of the first task, and a time interval between the ending time unit and the starting time unit corresponds to the processing time delay requirement of the first task; or means that the starting time unit of the first task is earlier than or not later than a starting time unit corresponding to the processing time delay requirement of the first task, the starting time unit is earlier than the time unit in which the first report information is located, and a time interval between the starting time unit and the time unit in which the first report information is located corresponds to the processing time delay requirement of the first task.

[0333] The processing time delay requirement required by the terminal device for executing the second task is not satisfied, which means that a processing time delay of the second task is shorter than or not longer than a processing time delay requirement of the second task; or means that the time unit in which the first report information is located is not later than or earlier than an ending time unit corresponding to the processing time delay requirement of the second task, the ending time unit is later than a starting time unit of the second task, and a time interval between the ending time unit and the starting time unit corresponds to the processing time delay requirement of the second task; or means that the starting time unit of the second task is not earlier than or later than a starting time unit corresponding to the processing time delay requirement of the second task, the starting time unit is earlier than the time unit in which the first report information is located, and a time interval between the starting time unit and the time unit in which the first report information is located corresponds to the processing time delay requirement of the second task.

[0334] The processing delay of the first task and the processing delay of the second task can be referred to as a processing delay of a target task.

[0335] Optionally, the processing delay of the target task corresponds to a time interval between a time unit carrying the target first information and a time unit in which the first report information is located. The description of the target first information can be referred to as the foregoing description, which is not described here.

[0336] Optionally, the processing delay of the target task corresponds to a time interval between a time unit carrying the target resource set and a time unit in which the first report information is located. The description of the target resource can be referred to as the foregoing description, which is not described here.

[0337] Optionally, the processing delay requirement of the target task corresponds to a time interval between a time unit carrying the reference resource set and a time unit in which the first report information is located. The description of the reference resource set can be referred to as the foregoing description, which is not described here.

[0338] Similarly, the processing delay requirement of the first task and the processing delay requirement of the second task can be referred to as a processing delay requirement of a target task. The processing delay requirement of the target task is embodied as a time length required by the terminal device to execute the target task, for example, can be a shortest time length required by the terminal device to execute the target task.

[0339] It can be understood that if the actual processing delay of the target task is shorter than the processing delay requirement of the target task, it means that the terminal device cannot complete the target task (for example, the second task) within the processing delay of the target task, and thus cannot generate valid data (for example, the second data). Conversely, the terminal device can complete the target task (for example, the first task) within the processing delay of the target task, and thus can generate valid data (for example, the first data).

[0340] Optionally, a specific value of the processing delay requirement of the target task can be predefined, and / or notified by the network device, and / or reported by the terminal device.

[0341] Figure 14 FIG. 1 is a schematic diagram of a relationship between a processing delay requirement and a processing delay provided by an embodiment of the present application. The network device notifies the terminal device of two resource sets: RS resource set #1 and RS resource set #2. The RS resource set #1 corresponds to the first task, the RS resource set #2 corresponds to the second task, the processing delay requirement required for executing the first task is delay requirement #1, and the processing delay requirement required for executing the second task is delay requirement #2. It is assumed that the first data #1 can be obtained based on the RS resource set #1, the first data #2 can be obtained based on the RS resource set #2, and the first data #1 and the first data #2 can be carried in the CSI report for reporting. As shown in FIG. 1, the processing delay requirement #1 is longer than the processing delay #1, and the processing delay requirement #2 is longer than the processing delay #2.Figure 14 As shown, the processing delay of the first task that the terminal device side can actually perform is processing delay #1, and the processing delay #1 is greater than the processing delay requirement #1, that is, the processing delay requirement required by the terminal device to perform the first task is met; the processing delay of the second task that the terminal device side can actually perform is processing delay #2, and the processing delay #2 is less than the processing delay requirement #2, that is, the processing delay requirement required by the terminal device to perform the second task is not met. Therefore, the RS resource set #1 is a valid resource set, and the first data #1 can be carried in the CSI report for reporting, while the RS resource set #2 is an invalid resource set, and the first data #2 can not be reported.

[0342] For the first constraint condition 3: the first valid resource set is earlier than or not later than the reference resource corresponding to the first task. Conversely, the invalid resource set in the M resource sets other than the N valid resource sets is not earlier than or later than the reference resource corresponding to the second task.

[0343] The description of the first task can refer to the related description in the foregoing, which will not be described here.

[0344] The reference resource may be, for example, a CSI reference resource. The reference resource is determined by the time unit in which the first reporting information is located, and the reference resource is earlier than or not later than the time unit in which the first reporting information is located, and differs from the time unit in which the first reporting information is located by a time interval.

[0345] Optionally, the time interval may be predefined or notified by the network device.

[0346] Optionally, the first valid resource set is earlier than or not later than the reference resource corresponding to the first task, including: all or part of the resources in the first valid resource set are earlier than or not later than the reference resource corresponding to the first task.

[0347] For the target resource set or the reference resource set, all resources of the target resource set or the reference resource set are not later than the reference resource or the reference resource set; or part of the resources of the target resource set or the reference resource set are not later than the reference resource or the reference resource set.

[0348] Considering that the reference resource usually corresponds to a resource at which the terminal device has completed CSI measurement and started to generate CSI data, therefore, the resource set for measurement should not be later than the reference resource corresponding to the same task, otherwise, valid data cannot be generated. In this way, if the resource set corresponding to the second task is later than the reference resource corresponding to the second task, the second data corresponds to invalid data.

[0349] For the first constraint condition 4: the resources included in the first valid resource set are in an activated state or a configured state. Conversely, the invalid resource sets in the M resource sets other than the N valid resource sets are in a non-activated state or an unconfigured state.

[0350] Similar to the configuration of the valid downlink carrier or the valid BWP described above, if a resource set in the M resource sets is deactivated or the task corresponding to the resource set is reconfigured / deconfigured, the resource set in the deactivated state or the resource set after the task reconfiguration / deconfiguration cannot generate valid data. For example, the semi-persistent CSI is deactivated, and the periodic CSI is reconfigured / deconfigured.

[0351] For the first constraint condition 5: the resources included in the first valid resource set are not incorrectly configured. In other words, the invalid resource sets in the M resource sets other than the N valid resource sets are incorrectly configured.

[0352] It can be understood that if the terminal device has configuration errors or indication errors in some or all of the M resource sets, for example, the processing capability of the terminal device cannot meet the processing capability required by the to-be-processed resource set, or the signal corresponding to the resource set cannot be successfully received by the terminal device, or the network device does not configure the number, time interval, and period of the reference signal according to the reference signal pattern supported by the terminal device. In this case, the terminal device also cannot generate valid data.

[0353] Optionally, the first data in the first data set includes at least one of the following types of data: a first measurement result, a first inference result, or a first monitoring result. In other words, the type of the first data includes one or more of the following types: a first measurement result, a first inference result, or a first monitoring result.

[0354] The first measurement result is obtained by measuring the N valid resource sets. The first measurement result can be applied to model operations of a network side model, such as training, inference, or monitoring. It should be understood that the first measurement result can also be referred to as first measurement information.

[0355] The target data corresponds to information obtained by measuring the target resource set by the terminal device, which is referred to as measurement result. The measurement result can also be referred to as measurement information. Optionally, the at least one first data includes a measurement result obtained by measuring the N valid resource sets.

[0356] That is, any one of the N first data includes a first measurement result, which is obtained by measuring a corresponding one of the N valid resource sets.

[0357] Figure 15is a schematic diagram of the first data provided by the embodiment of the present application, the type of which is measurement result. The network device informs the terminal device of four resource sets, and the four resource sets are respectively carried on four different time units: RS resource set #1 is carried on time unit #1, RS resource set #2 is carried on time unit #2, RS resource set #3 is carried on time unit #3, and RS resource set #4 is carried on time unit #4. Assuming that the terminal device measures RS resource set #1 to obtain measurement result #1, measures RS resource set #2 to obtain measurement result #2, measures RS resource set #3 to obtain measurement result #3, and measures RS resource set #4 to obtain measurement result #4.

[0358] As shown in Figure 15 , RS resource set #1 and RS resource set #2 in the four resource sets are valid resource sets, and RS resource set #3 and RS resource set #4 are invalid resource sets, so the terminal device feeds back measurement result #1 and measurement result #2 to the network device through CSI report #1, but does not feed back measurement result #3 and measurement result #4. Among them, measurement result #1 and measurement result #2 can be called first data.

[0359] Exemplarily, if any one of the first data in the first resource set is called a target data, then one target data can include one measurement result, or include one or more groups of measurement results. For example, for CSI prediction, one target data includes a group of measurement results, each of which is obtained by the terminal device measuring one resource set containing multiple resources (the multiple resources are respectively carried on different time units). For example, for spatial beam prediction in beam management, one target data includes one measurement result, which can be a CRI / SSBRI or an RSRP; or one target data includes a group of measurement results, which can include multiple CRIs / SSBRIs or multiple RSRPs. For example, for time domain beam prediction in beam management, one target data includes one group of measurement results or multiple groups of measurement results (for example, each group of measurement results includes a CRI / SSBRI, an RSRP, multiple CRIs / SSBRIs, and / or multiple RSRPs). Each / each group of measurement results is a measurement result obtained by the terminal device measuring a resource set carried on different time units.

[0360] That is, taking CSI feedback as an example, one target data includes measured channel response information. Taking beam management as an example, one target data includes measured beam information and / or measured channel quality information. It should be understood that a set of measurement results in one target data can contain multiple types of measurement results. For example, for beam management, a set of measurement results can contain CRI / SSBRI information and RSRP information.

[0361] It should be noted that when the terminal device reports the above target data containing measurement results to the network device, the network device can use the data for model training, model inference, model monitoring, or other artificial intelligence operations, or non-artificial intelligence operations. Specifically, for model training, the network device can use the measurement results contained in the target data as the input of model training after collecting a large amount of target data; for model inference, the network device can infer the measurement results contained in one target data; for model monitoring, the network device can use the measurement results contained in one or more target data for monitoring.

[0362] The first inference result is obtained based on the N sets of valid resources. The first inference result can correspond to the inference output of the terminal-side model. It should be understood that the inference result can also be referred to as a prediction result, an inference result, a processing result, or inference information.

[0363] The information obtained by the terminal device based on the target resource set is referred to as inference result. The inference result can also be referred to as inference information.

[0364] Further, the at least one first data includes inference results generated according to the N sets of valid resources.

[0365] The inference result in the present application includes information obtained by the terminal device processing information obtained based on the resource set. The processing here can be based on artificial intelligence operation or non-artificial intelligence operation.

[0366] Optionally, the terminal device can first obtain the corresponding measurement result according to the target resource set, and then use the measurement result to obtain the inference result; or the terminal device can directly generate the corresponding inference result according to the target resource set. For the latter, the terminal device directly infers the unmeasured original target resource set information (for example, directly uses the received target resource set as the model input, and the model can support both channel measurement inference and prediction, etc. CSI or beam management inference), to obtain the inference result. The target resource set is any one of the N sets of valid resources.

[0367] Exemplarily, taking CSI feedback as an example, the inference result includes an inferred channel response information, such as a predicted PMI, a predicted channel matrix, a predicted eigenvector, and the like. Taking beam management as an example, the inference result includes an inferred beam information and / or an inferred channel quality information, where the inferred channel quality information may be, for example, a predicted RSRP, and the inferred beam information may be, for example, a predicted CRI / SSBRI.

[0368] In a possible implementation, the one or more inference results in the first data set are not one-to-one corresponding to the N sets of valid resources, that is, the terminal device can generate N model inputs according to the N sets of valid resources, and the number of inference results is related to the model structure, and is not necessarily bound to the number of model inputs. The number of inference results can be N or other numbers. Therefore, when the type of the first data is an inference result, the first data set can include one or more first data.

[0369] In another possible implementation, each of the N first data included in the first data set includes a first inference result, which is inferred based on a corresponding one of the N sets of valid resources. That is, the N inference results in the first data set are one-to-one corresponding to the N sets of valid resources, or each of the N sets of valid resources is used to generate an inference result.

[0370] It can be understood that if the first data set includes multiple inference results, the multiple inference results act on multiple different time units. For example, in a CSI prediction or beam management scenario, the output of the model is multiple predicted CSI information, and the multiple predicted CSI information respectively acts on multiple future time instants, which can be understood as multiple different time units.

[0371] Figure 16 is a schematic diagram of the type of the first data provided by the embodiment of the application, which is an inference result. The network device notifies the terminal device of four resource sets, and the four resource sets are respectively carried on four different time units: the RS resource set #1 is carried on the time unit #1, the RS resource set #2 is carried on the time unit #2, the RS resource set #3 is carried on the time unit #3, and the RS resource set #4 is carried on the time unit #4. It is assumed that the terminal device can obtain a measurement result #1 by measuring the RS resource set #1, a measurement result #2 by measuring the RS resource set #2, a measurement result #3 by measuring the RS resource set #3, and a measurement result #4 by measuring the RS resource set #4.

[0372] As Figure 16As shown, RS resource set #1 and RS resource set #2 of the four resource sets are valid resource sets, and RS resource set #3 and RS resource set #4 are invalid resource sets. The terminal device takes the measurement results #1 and #2 corresponding to the valid resource sets as model inputs for inference, obtains inference results #1 and #2 acting on time units #5 and #6, and feeds back the inference results #1 and #2 to the network device through the CSI report #1. The inference results #1 and #2 can be referred to as first data.

[0373] Similar to the measurement results described above, one target data can contain one inference result, or one or more groups of inference results. One group of measurement results in one target data can contain multiple types of inference results.

[0374] The first monitoring result is obtained based on the monitoring of the N valid resource sets. The first monitoring result can be applied to the model operation of the network-side model, such as model selection, model activation, or model deactivation. The monitoring result can also correspond to the monitoring output of the terminal-side model. It should be understood that the monitoring result can also be referred to as monitoring information.

[0375] The target data corresponds to the information obtained by the terminal device based on the performance monitoring of the target resource set, which is referred to as a monitoring result. The monitoring result can also be referred to as monitoring information.

[0376] The monitoring result in this embodiment includes information obtained by monitoring the inference result based on the information obtained by the terminal device based on the target resource set. Specifically, the information obtained based on the target resource set includes the measurement results obtained by measuring the target resource set, and the inference result includes the inference result corresponding to the target resource set.

[0377] Optionally, the at least one first data includes a monitoring result determined according to the N valid resource sets.

[0378] For example, the terminal device monitors the inference result of the network-side model based on the measurement results of the N valid resource sets to obtain a monitoring result. The monitoring result can correspond to the monitoring output of the terminal-side model, for example, the terminal device monitors the inference result of the terminal-side model based on the measurement results of the N valid resource sets to obtain a monitoring result.

[0379] Specifically, the inference results {C#1, C#2, …, C#L} of the terminal device are applied to the time-frequency resource sets {R#1, R#2, …, R#L} respectively. In order to monitor the performance / inference accuracy of the inference results, the monitoring resource sets {Mo#1, Mo#2, …, Mo#L} corresponding to {R#1, R#2, …, R#L} can be notified, so that the terminal device can obtain the measurement results corresponding to {R#1, R#2, …, R#L} by measuring {Mo#1, Mo#2, …, Mo#L}, also known as ground truth, and the measurement results correspond to {G#1, G#2, …, G#L} respectively. Then, the measurement results {G#1, G#2, …, G#L} are compared with the corresponding inference results {C#1, C#2, …, C#L} respectively, and the inference accuracy can be obtained.

[0380] That is, the monitoring result corresponds to the inference accuracy information. It should be understood that the inference accuracy information herein is also referred to as intermediate key performance indicator (KPI) or prediction accuracy information. The inference accuracy information is used to represent the similarity between the model inference result and the corresponding ground truth, such as generalized cosine similarity (GCS), squared generalized cosine similarity (SGCS), normalized mean square error (NMSE), beam information prediction accuracy, reference signal identifier prediction accuracy, RSRP prediction accuracy, positioning information prediction accuracy, etc. Among them, the ground truth corresponds to the measurement result obtained by measurement.

[0381] The association / correspondence relationship between the target resource set corresponding to the monitoring result (such as {Mo#1, Mo#2, …, Mo#L}) and the inference result corresponding to the monitoring result (such as {C#1, C#2, …, C#L}) can be notified by the network device (for example, by the first information). In this way, the terminal device can determine the inference result corresponding to the target resource set and perform monitoring. Similarly, the association / correspondence relationship between the inference result corresponding to the monitoring result (such as {C#1, C#2, …, C#L}) and the measurement result corresponding to the monitoring result (such as {G#1, G#2, …, G#L}) can also be notified by the network device, so that the terminal device can use the measurement result to monitor the corresponding inference result to obtain the monitoring result.

[0382] Figure 17 is a schematic diagram of obtaining a monitoring result provided by an embodiment of the present application. As shown in FIG. 8, the network device can notify the terminal device of the target resource set {R#1, R#2, …, R#L} and the monitoring resource set {Mo#1, Mo#2, …, Mo#L} corresponding to the target resource set {R#1, R#2, …, R#L}. The terminal device can obtain the inference result {C#1, C#2, …, C#L} corresponding to the target resource set {R#1, R#2, …, R#L} by performing inference on the target resource set {R#1, R#2, …, R#L}. The terminal device can obtain the measurement result {G#1, G#2, …, G#L} corresponding to the target resource set {R#1, R#2, …, R#L} by measuring the monitoring resource set {Mo#1, Mo#2, …, Mo#L}. The terminal device can compare the measurement result {G#1, G#2, …, G#L} with the corresponding inference result {C#1, C#2, …, C#L} to obtain the monitoring result. Figure 17As shown, the network device indicates the CSI-RS#A to the terminal device at T1 through DCI, the CSI-RS#A corresponds to the CSI task#1, and the inference result {C#1, C#2} of the CSI task#1 corresponds to the CSI report#A1 and the CSI report#A2 respectively, that is, the inference result {C#1, C#2} is applied to the time-frequency resource {R#1=T3, R#2=T4} respectively. In order to monitor the CSI task#1, the network device indicates the CSI-RS#B1 and the CSI-RS#B2 to the terminal device at T2 through DCI to trigger the CSI task#2, the CSI-RS#B1 and the CSI-RS#B2 correspond to the monitoring resource {Mo#1, Mo#2} respectively. In this way, the terminal device can measure the true values G#1 and G#2 at T3 and T4 respectively based on the CSI-RS#B1 and the CSI-RS#B2, compare G#1 with the inference result C#1 to obtain the accuracy of C#1 inference, that is, the monitoring result A#1, compare G#2 with the inference result C#2 to obtain the accuracy of C#2 inference, that is, the monitoring result A#2, and report A#1 and A#2 in the CSI report#B corresponding to the CSI task#2 at T5.

[0383] Exemplarily, taking the CSI feedback as an example, the type of the target data includes the channel response information based on monitoring, such as the prediction accuracy information of PMI, the prediction accuracy information of channel matrix, the prediction accuracy information of eigenvector, etc. Taking the beam management as an example, the type of the target data includes the beam information based on monitoring and / or the channel quality information based on monitoring, wherein the channel quality information based on monitoring is, for example, the prediction accuracy information of RSRP, and the beam information based on monitoring is, for example, the prediction accuracy information of CRI.

[0384] It can be understood that any one of the N first data includes a first monitoring result, which is obtained based on monitoring of a corresponding one of the N sets of valid resources. Here, the “monitoring based on a corresponding one of the N sets of valid resources” means monitoring performance by using information obtained from the set of valid resources.

[0385] That is, the first monitoring result is obtained based on monitoring of a corresponding inference result of a first measurement result, and the first measurement result is obtained for a corresponding one of the N sets of valid resources.

[0386] Figure 18is a schematic diagram of the first data provided by the embodiment of the present application, the type of which is monitoring result. The network device informs the terminal device of four resource sets, and the four resource sets are respectively carried on four different time units: RS resource set #1 is carried on time unit #1, RS resource set #2 is carried on time unit #2, RS resource set #3 is carried on time unit #3, and RS resource set #4 is carried on time unit #4. Assuming that the terminal device measures RS resource set #1 to obtain measurement result #1, measures RS resource set #2 to obtain measurement result #2, measures RS resource set #3 to obtain measurement result #3, and measures RS resource set #4 to obtain measurement result #4.

[0387] As shown in Figure 18 , four times correspond to one CSI prediction result respectively: time unit #1 corresponds to CSI prediction result #1, time unit #2 corresponds to CSI prediction result #2, time unit #3 corresponds to CSI prediction result #3, and time unit #4 corresponds to CSI prediction result #4. Assuming that the terminal device can obtain one monitoring result according to the CSI measurement result and the CSI prediction result corresponding to each time unit, four monitoring results corresponding to the four resource sets are obtained: CSI monitoring result #1, CSI monitoring result #2, CSI monitoring result #3, and CSI monitoring result #4. Since RS resource set #1 and RS resource set #2 in the four resource sets are valid resource sets, and RS resource set #3 and RS resource set #4 are invalid resource sets, monitoring result #1 and monitoring result #2 are fed back to the network device through CSI report #1. Among them, monitoring result #1 and monitoring result #2 can be referred to as first data.

[0388] Similar to the above measurement result, one target data can contain one monitoring result, or one group or more groups of monitoring results. One group of monitoring results in one target data can contain multiple types of monitoring results.

[0389] Optionally, the monitoring result can include a network performance result, which is a performance result based on an inference result.

[0390] Exemplarily, the terminal device can take the throughput corresponding to each of the multiple space-time-frequency resources as the network performance result, and report the multiple throughput information obtained by statistics to the network device. In the case that the terminal device reports the network performance result, the target resource further includes a downlink data channel and / or a downlink demodulation reference signal (DMRS), and the target data further includes the network performance result.

[0391] Exemplarily, the network performance result can be, for example, a block error rate (BLER), a throughput, an RSRP, an SINR, etc.

[0392] Optionally, the first data set includes N first data, the N first data correspond to the N effective resource sets one by one, and a measurement result, an inference result, or a monitoring result of any one of the N first data is determined according to a corresponding one of the N effective resource sets.

[0393] Exemplarily, taking the measurement result as an example of the first data type, the relationship between the N first data and the N effective resource sets is introduced as follows: in a CSI prediction / beam management scenario, the N effective resource sets correspond to N RS resource sets, and the N RS resource sets can obtain N CSI measurement information, which is measured by the terminal device on the N effective resource sets.

[0394] It should be understood that the terminal device does not need to generate or feed back the measurement result, the inference result, or the monitoring result corresponding to the (M-N) invalid resource sets.

[0395] Optionally, the invalid resource set in the M resource sets does not satisfy the first constraint condition, and the invalid resource set is a remaining resource set in the M resource sets except for the N effective resource sets.

[0396] It can be understood that when N is an integer less than M, the M resource sets include at least one invalid resource set.

[0397] Optionally, the terminal device does not send the second data set corresponding to the invalid resource set, or the information sent by the terminal device to the network device does not include the second data set.

[0398] The information sent by the terminal device to the network device can be the first reporting information. That is, the first reporting information does not include the second data set corresponding to the invalid resource set.

[0399] Exemplarily, when the M resource sets include at least one invalid resource set, the at least one invalid resource set corresponds to one or more invalid second data, and the one or more invalid second data form a second data set. Since the second data set is invalid data corresponding to the invalid resource set, the terminal device does not send the second data set, or the information sent by the terminal device does not include the second data set.

[0400] Similar to the first data set, the at least one invalid resource set corresponds to at least one second data in the second data set one by one.

[0401] Optionally, the terminal device does not include the second data corresponding to the invalid resource set in the first data set sent to the network device. That is, if the M resource sets include at least one invalid resource set, the terminal device does not send the second data corresponding to the invalid resource set, or the terminal device does not include the second data in the first data set sent to the network device.

[0402] Optionally, the value of the field corresponding to the second data set in the first reporting information corresponds to the "invalid" state.

[0403] Optionally, the "invalid" state can also be referred to as "meaningless" or "Null" or "default".

[0404] Optionally, when the M resource sets include at least one invalid resource set, the at least one invalid resource set corresponds to one or more invalid second data, and the one or more invalid second data form the second data set. At this time, the terminal device can still report the second data set through the first reporting information, but the reported second data set does not refer to valid data, but corresponds to the "invalid" state.

[0405] Specifically, the second data set is carried by a field of X bits, which can be filled with a specific bit sequence. The bit sequence or the code point corresponding to the field is not used to represent valid data, but is used to represent the "invalid" state. For example, the bit sequence is all "0" or all "1", or other bit sequences not used to represent the first data.

[0406] Optionally, the bit sequence / code point corresponding to the "invalid" state can be predefined or preconfigured by the network device.

[0407] Similar to the type of the first data, the type of the second data in the second data set includes any one of the following three types: a second measurement result, a second inference result, or a second monitoring result.

[0408] For the network device, it is desirable to receive as much valid data generated by the terminal device as possible, or data generated by the valid resource / resource set of the terminal device. If there is no valid resource set in the M resource sets, or the number of valid resource sets is not enough, the data generated by these resource sets (i.e., the first data) cannot bring sufficient performance to the inference / monitoring of the network device. Therefore, in this case, the network device can not need the terminal device to report these data (i.e., the first data set), and the terminal device will only report the first data set when the valid resource set meets the second constraint condition. That is, the first data set is included in the first reporting information when N meets the second constraint condition. Conversely, the terminal device will not report the first data set.

[0409] The second constraint condition includes one or more of the following: N=M, M-N is less than or equal to a first preset value, N is greater than or equal to a second preset value, or N is a positive integer.

[0410] For the second constraint condition 1: N=M. That is, the M resource sets do not include invalid resource sets, or in other words, the M resource sets are all valid resource sets.

[0411] The definition of the second constraint condition 1 takes into account that the M resource sets notified by the network device to the terminal device are the minimum resource set requirements for the first data set to meet the quality requirements. If any one of the M resource sets is an invalid resource set and cannot be used to generate part of the data in the first data set, the quality of the first data set cannot meet the requirements of the network device / terminal device. In this case, the first data set cannot be used by the network device.

[0412] For example, if the first data includes measurement results for N resource sets, only when the network device can obtain M measurement results of all N=M resource sets, can the inference performance of the network side model be guaranteed. For example, if the first data includes inference results for N resource sets, only when the terminal device can obtain all N=M resource sets, the inference results based on the measurement results of the N resource sets can guarantee the inference performance of the UE side model. For another example, if the first data includes monitoring results for N resource sets, only when the terminal device can obtain M measurement results of all N=M resource sets, the monitoring results based on the M measurement results can deliver complete monitoring information.

[0413] Conversely, when N<M (at least one invalid resource set is included in the M resource sets), the task N does not meet the first constraint condition, and the terminal device does not send the first data set to the network device.

[0414] For the second constraint condition 2: M - N is less than or equal to a first preset value Q1 (Q1 is a positive integer). That is, the number of invalid resource sets in the M resource sets is less than or equal to the first preset value. Or rather, N is less than or equal to M, and if N < M, M - N is less than or equal to the first preset value.

[0415] For the second constraint condition 3: N is greater than or equal to a second preset value Q2 (Q2 is a positive integer). That is, the number of valid resource sets in the M resource sets is greater than or equal to the second preset value.

[0416] Defining the second constraint condition 2 or the second constraint condition 3 is to consider that when the number of valid resource sets is too small, or the number of invalid resource sets is too large, the quality of the first data set generated by the valid resource sets cannot meet the data requirements of the network device / terminal device. In this case, the first data set cannot be used by the network device.

[0417] For example, if the first data includes measurement results for N resource sets, then only when the network device can obtain measurement results for M - N < Q1 or N > Q2 valid resource sets can the inference performance of the network - side model be guaranteed. Another example, if the first data includes inference results for N resource sets, then only when the terminal device can obtain M - N < Q1 or N > Q2 valid resource sets can the inference results obtained by reasoning based on their measurement results guarantee the inference performance of the UE - side model. Another example, if the first data includes monitoring results for N resource sets, then only when the terminal device can obtain N measurement results for M - N < T1 or N > T2 valid resource sets can the monitoring results obtained by monitoring based on the N measurement results transmit complete monitoring information.

[0418] Conversely, if M - N is equal to or greater than Q1 (the number of invalid resource sets included in the M resource sets is equal to or greater than the first resource set threshold), or if N is equal to or less than Q2, that is, if the first constraint condition is not satisfied, then the terminal device does not send the first data set to the network device.

[0419] It should be understood that the value of Q1 can be predefined or determined by the notification information of the network device. The value of Q2 can be predefined or determined by the notification information of the network device.

[0420] For the second constraint condition 4: N is a positive integer. That is, there is at least one valid resource set in the M resource sets.

[0421] Defining the second constraint condition 4 is to consider that if the M valid resource sets include at least one valid resource set, then the first data corresponding to the at least one valid resource set can at least provide partial information for the network device, and thus can be fed back by the terminal device to the network device.

[0422] For example, if the first data includes measurement results for N>0 resource sets, the measurement results can at least provide inputs for inference of the network-side model. For another example, if the first data includes inference results for N>0 resource sets, the inference results can at least provide some information for the network side. For another example, if the first data includes monitoring results for N>0 resource sets, the monitoring results can at least provide some performance monitoring information for the network side.

[0423] On the contrary, N=0 (none of the M resource sets is a valid resource set), i.e., all correspond to invalid resource sets, then the second constraint condition is not met, and the UE does not send the first data set to the network device. In this case, the first data set cannot be generated or cannot be used by the network device.

[0424] Optionally, in the case where N does not meet the second constraint condition, the reporting of the first data set is ignored. Or, in the case where N does not meet the second constraint condition, the first data set is not included in the first reporting information. Or, in the case where N does not meet the second constraint condition, the terminal device does not send the first data set to the network device. Ignored can also be referred to as: canceled, discarded, or skipped.

[0425] It can be understood that the first data set is not included in the first reporting information, and the terminal device does not send the first data set to the network device, which can be understood as: the terminal device does not generate the first data set (or the terminal device ignores the generation of the first data set), or the terminal device generates the first data set but does not send the first data set.

[0426] Optionally, the first reporting information further includes at least one of: the number of first data included in the first data set, the identification information and / or time information corresponding to the N valid resource sets, the information of the first constraint condition met by the N valid resource sets, the identification information or time information corresponding to the invalid resource sets, or the information of the first constraint condition not met by the invalid resource sets.

[0427] Since the network device can not know which resource sets in the M resource sets can be effectively processed by the terminal device and which resource sets cannot be effectively processed, for example, even in the case where the first constraint condition is not met, some high-capability terminal devices can still be able to effectively process and obtain the first data. Therefore, in this case, the terminal device needs to actively report the number of first data in the first data set to the network device.

[0428] In addition, since the network device also wants to know which resource set or resource sets the first data in the first data set obtained by the terminal device is processed for, the terminal device can report time information or identification information corresponding to the N valid resource sets to the network device.

[0429] Optionally, the identification information can include sequence number information corresponding to the N valid resource sets and / or the first data set. The sequence number information can be at least one of the following: a sequence number of the N valid resource sets in the M resource sets, a sequence number of each of the N valid resource sets in the M resource sets, a sequence number of the first data set corresponding to the N valid resource sets in a plurality of data sets corresponding to the M resource sets, and a sequence number of each of the first data corresponding to the N valid resource sets in a plurality of data corresponding to the M resource sets.

[0430] Optionally, the time information can include time information corresponding to the N valid resource sets and / or the first data set, such as at least one of the following: a radio frame sequence number, a time slot sequence number, a symbol sequence number, and absolute time information (such as universal time coordinated (UTC) time).

[0431] As described above, the network device can not know which resource sets in the M resource sets the terminal device can effectively process, and thus the network device wants to know the reason why the terminal device reports that the N valid resource sets can be effectively processed and / or the reason why the terminal device reports that the invalid resource set cannot be effectively processed. That is, the network device wants to obtain information of the first constraint condition satisfied by the N valid resource sets.

[0432] Exemplarily, for the N valid resource sets or the first data set, the terminal device can report which or which of a plurality of first constraint conditions that the N valid resource sets satisfy. For the invalid resource set or the second data set, the terminal device can report which or which of a plurality of first constraint conditions that the invalid resource set does not satisfy.

[0433] The above-mentioned information of the first constraint condition satisfied by the N valid resource sets can be information of the first constraint condition satisfied by each of the N valid resource sets, such as which or which of the first constraint conditions are satisfied. Or the information of the first constraint condition satisfied by the first valid resource set in the N valid resource sets, such as which or which of the first constraint conditions are satisfied. Or, for any one of the plurality of first constraint conditions, the terminal device reports which or which of the N valid resource sets satisfy the constraint condition.

[0434] The information about the first constraint condition not met by the reported invalid resource set can be information about the first constraint condition not met by each invalid resource set in the reported invalid resource set, for example, which first constraint condition or which first constraint conditions are not met. Alternatively, for any one of the plurality of first constraint conditions, the terminal device reports which resource set or which resource sets in the invalid resource set do not meet the constraint condition.

[0435] Optionally, the M resource sets are M measurement resource sets, the N resource sets are N measurement resource sets, the first data is CSI obtained based on the N measurement resource sets, and the first reporting information includes a first CSI report obtained based on the N measurement resource sets.

[0436] It can be understood that the M resource sets are M measurement resource sets, and the first valid resource set is a first valid measurement resource set. At this time, the first task includes one or more of the following: first CSI measurement, first CSI inference, first CSI monitoring, first CSI generation, or first CSI reporting.

[0437] Exemplarily, in a CSI feedback or beam management scenario, the terminal device performs measurement based on a reference signal to obtain first data, and feeds back the first data to the network device through a CSI report. The first data includes CSI information, and therefore the first reporting information includes the CSI report, and the first task includes first CSI measurement and first CSI reporting.

[0438] Optionally, the M resource sets include a first measurement resource set, the first measurement resource set includes one or more first measurement resources, and the first measurement resource is a synchronization signal resource, a broadcast signal resource, or a reference signal resource.

[0439] The first measurement resource set is any one of the M resource sets.

[0440] The above Figures 1 to 18 The method provided by the embodiments of the present application is described in detail below. Figure 19 and Figure 20 The device provided by the embodiments of the present application is described in detail.

[0441] Figure 19 and Figure 20 The schematic diagram of the possible device provided by the embodiments of the present application is shown. The device can be used to realize the functions of the terminal device or the network device in the above-mentioned method embodiments, and therefore can also realize the beneficial effects possessed by the above-mentioned method embodiments.

[0442] Figure 19 is a schematic block diagram of the device provided by the embodiments of the present application. As Figure 19As shown, the apparatus 1900 includes a transceiver module 1910 and a processing module 1920.

[0443] One possible design is that the apparatus 1900 is configured to implement the functions of a terminal device in the method embodiments described above. Figure 8

[0444] For example, the transceiver module 1910 is configured to receive first information from a network device, where the first information is used to indicate M sets of resources, each of the M sets of resources includes at least one resource, and M is a positive integer; and the processing module 1920 is configured to determine a first data set according to N valid sets of resources from the M sets of resources, where the first data set includes at least one first data, a first valid set of resources from the N valid sets of resources satisfies a first constraint condition, and N is a positive integer less than or equal to M; and the transceiver module 1910 is further configured to send first reporting information to the network device, where the first reporting information includes the first data set.

[0445] Optionally, the transceiver module 1910 is further configured to send the first reporting information to the network device in a case where N satisfies a second constraint condition.

[0446] More detailed description of the transceiver module 1910 and the processing module 1920 above can be directly obtained by referring to the related description in the embodiments of the apparatus 1900 shown in Figure 8 and will not be repeated here.

[0447] Another possible design is that the apparatus 1900 is configured to implement the functions of a network device in the method embodiments described above. Figure 8

[0448] For example, the transceiver module 1910 is configured to send first information to a terminal device, where the first information is used to indicate M sets of resources, each of the M sets of resources includes at least one resource, and M is a positive integer; and receive first reporting information from the terminal device, where the first reporting information includes a first data set, the first data set is determined according to N valid sets of resources from the M sets of resources, a first valid set of resources from the N valid sets of resources satisfies a first constraint condition, and N is a positive integer less than or equal to M.

[0449] Optionally, the transceiver module 1910 is further configured to receive the first reporting information from the network device in a case where N satisfies a second constraint condition.

[0450] More detailed description of the transceiver module 1910 and the processing module 1920 above can be directly obtained by referring to the related description in the embodiments of the apparatus 1900 shown in Figure 8 and will not be repeated here.​​

[0451] It is to be noted that the apparatus 1900 can include the sending module but not the receiving module. Or, the apparatus 1900 can include the receiving module but not the sending module. Specifically, whether the apparatus 1900 includes the sending module or the receiving module depends on whether the above-mentioned scheme includes the sending action or the receiving action. It can be understood that the apparatus 1900 can also be referred to as a communication apparatus since it has the communication function.

[0452] Figure 20 is another schematic block diagram of the apparatus provided by the embodiments of the present application. As shown in Figure 20 the apparatus 2000 includes one or more processors 2010. The processor 2010 can be a general purpose processor or a special purpose processor, etc. For example, it can be a baseband processor or a central processing unit. The baseband processor can be used to process the communication protocol and the communication data, and the central processing unit can be used to control the apparatus (e.g., a terminal device, a network device or a chip, etc.), execute the software program, and process the data of the software program.

[0453] Optionally, in one design, the processor 2010 can include a program (which can also be referred to as code or instruction) that can be run on the processor 2010, so that the apparatus 2000 performs the method performed by the terminal device or the network device in the above-mentioned method embodiments. In yet another possible design, the apparatus 2000 includes a circuit (not shown) for implementing the functions of the terminal device or the network device in the above-mentioned method embodiments. Figure 20

[0454] Exemplarily, the processor 2010 can be used to execute the computer program or instruction in the memory, so as to implement the steps performed by the terminal device or the network device in the method embodiments of any one of the above-mentioned embodiments. Figure 8

[0455] Optionally, the apparatus 2000 can include one or more memories 2020, which have a program (which can also be referred to as code or instruction) stored thereon. The program can be run on the processor 2010, so that the apparatus 2000 performs the method performed by the terminal device or the network device in the above-mentioned embodiments.

[0456] ​​Optionally, the processor 2010 and / or the memory 2020 can include an artificial intelligence (AI) module for implementing AI-related functions. The AI module can be implemented by software, hardware, or a combination of software and hardware. For example, the AI module can include a radio intelligent controller (RIC) module. The AI module can be a near-real-time RIC or a non-real-time RIC.

[0457] Optionally, the processor 2010 and / or the memory 2020 can also store data. The processor and the memory can be separately arranged or integrated together.

[0458] Optionally, the apparatus 2000 can also include a communication interface 2030 (or referred to as a communication circuit). The processor 2010 can also be referred to as a processing unit, which controls the apparatus (e.g., a terminal device or a network device). The communication interface 2030 can also be referred to as a transceiver unit, a transceiver, a transceiver circuit, or a transceiver, etc., which implements the transceiving function of the apparatus.

[0459] Optionally, the apparatus 2000 also includes a communication interface 2030. The processor 2010 and the communication interface 2030 are coupled to each other. It can be understood that the communication interface 2030 can be a transceiver or an input / output interface.

[0460] It can be understood that, since the apparatus 2000 has a communication function, it can also be referred to as a communication apparatus.

[0461] When the apparatus 2000 is used to implement the method in the above method embodiment, the processor 2010 is configured to perform the functions of the processing unit, and the communication interface 2030 is configured to perform the functions of the transceiver module. Whether the communication interface 2030 is configured to transmit or receive depends on whether the apparatus 2000 performs a transmitting action or a receiving action in the scheme it implements. Figure 8

[0462] When the apparatus 2000 is a chip applied to a terminal device, the chip implements the functions of the terminal device in the above method embodiment. The chip of the terminal device receives a signal from other modules (such as a radio frequency module or an antenna) in the terminal device. The signal can be transmitted by a network device to the terminal device. Alternatively, the chip of the terminal device transmits a signal to other modules (such as a radio frequency module or an antenna) in the terminal device. The signal can be transmitted by the terminal device to a network device.

[0463] ​When the apparatus 2000 is a chip applied to a network device, the chip implements the functions of the network device in the method embodiments. The chip of the network device receives a signal from other modules (such as a radio frequency module or an antenna) in the network device, and the signal can be sent by a terminal device to the network device. Alternatively, the chip of the network device sends a signal to other modules (such as a radio frequency module or an antenna) in the network device, and the signal can be sent by the network device to a terminal device.

[0464] It can be understood that when the apparatus 2000 is a terminal device or a network device, the communication interface 2030 can be a transceiver, and specifically can include a transmitter and a receiver. The transmitter is configured to send a signal, and the receiver is configured to receive a signal.

[0465] When the apparatus 2000 is a chip applied to a terminal device or a network device, the communication interface 2030 can be an input / output circuit. The input circuit can be configured to receive, and the output interface can be configured to send.

[0466] It should be understood that the processor is also the processing circuit. Alternatively, the processor can be one or a combination of the following: 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 device, a discrete gate or transistor logic device, or a discrete hardware component, or can be a combination of the foregoing one or more, such as a processor core. The general-purpose processor can be a microprocessor, or any conventional processor, etc.

[0467] It should also be appreciated that the above-described memory can be volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. Where nonvolatile memory is utilized, this can be read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which acts as the external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM). It is noted that the memory of the systems and methods described herein is intended to include, among others, these and any other suitable types of memory.

[0468] In some embodiments of the present application, a computer program product is also provided, which, when running on a processor, can implement the encoding method implemented by the first communication device in the above method embodiments, or can implement the decoding method implemented by the second communication device in the above method embodiments.

[0469] In some embodiments of the present application, a computer readable storage medium is also provided, which contains computer instructions, which, when running on a processor, can implement the encoding method implemented by the first communication device in the above method embodiments, or can implement the decoding method implemented by the second communication device in the above method embodiments.

[0470] In some embodiments of the present application, a communication system is also provided, which includes the terminal device and the network device described above.

[0471] It should be noted that the method embodiments described above can be applied in a chip or implemented by a chip. Illustratively, the chip can be an integrated circuit chip with signal processing capability. In the implementation process, the steps of the above method embodiments can be completed by the integrated logic circuit of the hardware in the chip or the instructions in the form of software.

[0472] The steps of the method disclosed in the embodiments of the present application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor. The software module can be located in the storage medium in the art, such as random storage, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, register, etc. The storage medium is located in the memory, and the processor reads the information in the memory, and combines the hardware to complete the steps of the above method.

[0473] The method provided by the above embodiments can be realized by software, hardware, firmware or any combination thereof, in whole or in part. When implemented by software, it can be realized in whole or in part in the form of a computer program product. The computer program product can include one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the flow or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website site, computer, server or data center to another website site, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic disk), optical media (such as DVD), or semiconductor media (such as solid state disk (SSD)) and the like.

[0474] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0475] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the system, device and unit described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0476] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, another division mode can be used. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0477] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. can be located in one place or distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0478] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0479] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing 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 methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and various program code storage media.

[0480] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method, characterized in that, include: Receive first information from a network device, the first information being used to indicate M resource sets, each of the M resource sets including at least one resource, where M is a positive integer; Based on N valid resource sets from the M resource sets, a first data set is determined, the first data set including at least one first data set, and the first valid resource set from the N valid resource sets satisfies a first constraint condition, where N is a positive integer less than or equal to M; Send a first reporting message to the network device, the first reporting message including the first data set.

2. The method according to claim 1, characterized in that, The first set of valid resources is at least one of the following: a predefined set of valid resources among the N sets of valid resources; a set of valid resources that are configured or indicated among the N sets of valid resources; or any one of the N sets of valid resources.

3. The method according to claim 1 or 2, characterized in that, The first constraint includes at least one of the following: The first set of valid resources is carried on valid physical resources, which include valid time-domain resources and / or valid frequency-domain resources; The processing capacity of the terminal devices corresponding to the first set of valid resources meets the requirements; The first set of valid resources is earlier than or no later than the reference resources corresponding to the first task, and the first task includes processing the first set of valid resources. The resources included in the first set of valid resources are either activated or configured; or, The resources included in the first set of valid resources are not misconfigured.

4. The method according to claim 3, characterized in that, The effective physical resources include downlink time units or flexible time units notified by the network device. The effective physical resources do not include the uplink time units or flexible time units notified by the network device. The effective physical resources do not include measurement gaps; The effective physical resources include effective downlink portion bandwidth (BWP) or effective downlink carrier.

5. The method according to claim 3 or 4, characterized in that, The first set of valid resources is carried on valid physical resources, including: at least one resource in the first set of valid resources is carried on the valid physical resources, or all resources in the first set of valid resources are carried on the valid physical resources.

6. The method according to any one of claims 3 to 5, characterized in that, The requirement that the processing capacity of the terminal device corresponding to the first set of effective resources meets the demand includes: the processing capacity of the terminal device corresponding to the first task meets the demand, wherein the first task includes processing based on the first set of effective resources.

7. The method according to claim 6, characterized in that, The terminal device processing capability corresponding to the first task meets the requirements, including: the processing latency requirement for executing the first task is met, and / or, in the starting time unit corresponding to the first task, the remaining terminal device processing capability is greater than or equal to the terminal device processing capability required to execute the first task.

8. The method according to any one of claims 2 to 7, characterized in that, The invalid resource set among the M resource sets does not satisfy the first constraint condition. The invalid resource set is the remaining resource set among the M resource sets excluding the N valid resource sets.

9. The method according to claim 8, characterized in that, The first reported information does not include the second data set corresponding to the invalid resource set, or, The value of the field in the first reported information that corresponds to the second data set is "invalid".

10. The method according to any one of claims 1 to 9, characterized in that, N satisfies the second constraint condition, which includes one of the following: N = M, MN is less than or equal to the first preset value, or N is greater than or equal to the second preset value.

11. The method according to claim 10, characterized in that, Sending the first reporting information to the network device includes: If N satisfies the second constraint condition, send a first reporting message to the network device; or... If N does not satisfy the second constraint, the first data set is not included in the first reported information.

12. The method according to any one of claims 1 to 11, characterized in that, The first data includes at least one of the following types of data: first measurement result, first inference result, or first monitoring result; The first measurement result is obtained by measuring the N sets of valid resources, the first inference result is obtained by inference based on the N sets of valid resources, and the first monitoring result is obtained by monitoring the N sets of valid resources.

13. The method according to any one of claims 1 to 12, characterized in that, The first data set includes N first data items, and each of the N first data items corresponds one-to-one with one of the N valid resource sets.

14. The method according to any one of claims 1 to 13, characterized in that, The M resource sets are M measurement resource sets, the N resource sets are N measurement resource sets, the first data is Channel State Information (CSI) obtained based on the N measurement resource sets, and the first reported information includes a first CSI report obtained based on the N measurement resource sets.

15. The method according to any one of claims 1 to 14, characterized in that, The first reported information also includes at least one of the following: the number of first data contained in the first data set, the identification information or time information corresponding to the N valid resource sets, the information of the first constraint condition satisfied by the N valid resource sets, the identification information or time information corresponding to the invalid resource set, or the information of the first constraint condition not satisfied by the invalid resource set, wherein the invalid resource set is the remaining resource set in the M resource sets excluding the N valid resource sets.

16. A communication method, characterized in that, include: Send first information to the terminal device, the first information being used to indicate M resource sets, each of the M resource sets including at least one resource, where M is a positive integer; The system receives first reported information from the terminal device. The first reported information includes a first data set, which is determined based on N valid resource sets out of the M resource sets. The first valid resource set out of the N valid resource sets satisfies a first constraint condition, where N is a positive integer less than or equal to M.

17. A communication device, characterized in that, Includes functional modules for implementing the method as described in any one of claims 1 to 16.

18. A communication device, characterized in that, include: One or more processors and communication circuitry, the communication circuitry being used by the communication device to perform at least one of signal input or output; the one or more processors being used to implement the method as described in any one of claims 1 to 16.

Images