Dataset classification method and apparatus

Abstract

Provided in the present application are a dataset classification method and apparatus. The method comprises: receiving first configuration information, wherein the first configuration information is used for configuring a parameter related to data collection; determining that an association identifier corresponding to a first set associated with the first configuration information is in a first state, and / or an association identifier corresponding to a second set associated with the first configuration information is in the first state; and determining the value of each association identifier that is in the first state, wherein the determined value of each association identifier that is in the first state is used for dataset classification. By means of the present application, a dataset can be correctly classified in the absence of an association identifier, thereby avoiding the problem of a classification error caused by the absence of an association identifier configuration.

Description

A dataset classification method and apparatus

[0001] This application claims priority to Chinese Patent Application No. 202510377479.9, filed on March 26, 2025, entitled “A Dataset Classification Method and Apparatus”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of artificial intelligence technology, and in particular to a dataset classification method and apparatus. Background Technology

[0003] Currently, with the application and development of artificial intelligence (AI) technology, AI models have shown broad application prospects in many fields, covering industrial automation, gaming, agriculture, energy, environmental protection and many other aspects. They have also been widely used in the field of wireless communication, achieving even better performance.

[0004] Before AI model generation, during the data collection phase, when the network needs to distribute reference signal resources, it also distributes an association identifier representing their physical conditions. The terminal device generates a dataset, categorizes the dataset based on the association identifier, and trains the corresponding AI model. A Channel State Information Report Configuration (CSI-reportConfig) associates an association identifier for set A and an association identifier for set B. Due to different configuration methods from different vendors, or because the association identifiers for set A and set B associated with the same CSI-reportConfig may not be distributed simultaneously, this can lead to missing association identifiers for set A and / or set B. Since the association identifier is the basis for dataset classification—one association identifier corresponds to one type of data—how to classify the dataset when association identifiers are missing is a technical problem that urgently needs to be solved by those in the field. Summary of the Invention

[0005] This application proposes a dataset classification method and apparatus that can correctly classify datasets even when association identifiers are missing, thus avoiding classification errors caused by missing association identifier configurations.

[0006] In a first aspect, embodiments of this application provide a dataset classification method. This method can be applied to a terminal-side device, which may be a terminal device, a component within the terminal device (e.g., a processor, chip, circuit, or chip system), or a logic module or software capable of implementing all or part of the terminal device's functions. The method includes: receiving first configuration information, the first configuration information being used to configure parameters related to data collection; determining that an association identifier corresponding to a first set associated with the first configuration information is in a first state, and / or an association identifier corresponding to a second set associated with the first configuration information is in a first state; and determining the value of the association identifier in the first state, the determined value of the association identifier in the first state being used for dataset classification.

[0007] In the above method, after the terminal device receives the first configuration information, it can determine that the association identifier corresponding to a certain set associated with the first configuration information is in a missing state, or that the association identifiers corresponding to both sets associated with the first configuration information are in a missing state. Then, it determines the value of the association identifier in the missing state and classifies the dataset based on the determined value of the association identifier in the missing state. In this way, the dataset can be correctly classified even when the association identifier is missing, avoiding the problem of classification errors caused by missing association identifier configuration.

[0008] In one possible implementation, the association identifier corresponding to the second set associated with the first configuration information is in a first state, and the method further includes: determining that the association identifier corresponding to the first set associated with the first configuration information is in a second state.

[0009] In another possible implementation, determining the value of the association identifier in the first state includes: determining that the value of the association identifier in the first state is the value of the association identifier corresponding to the first set associated with the first configuration information.

[0010] Specifically, determining that the value of the association identifier in the first state is the value of the association identifier corresponding to the first set associated with the first configuration information includes: determining that the value of the association identifier corresponding to the second set associated with the first configuration information is the value of the association identifier corresponding to the first set associated with the first configuration information.

[0011] In the above method, by reusing the value of the association identifier corresponding to the first set associated with the first configuration information, the value of the association identifier corresponding to the second set associated with the first configuration information can be determined. Then, the second set can be correctly classified based on the value of the association identifier corresponding to the second set associated with the first configuration information, thereby avoiding the problem of classification error due to missing association identifier configuration.

[0012] In another possible implementation, receiving the first configuration information includes: receiving the first configuration information at time t; the method further includes: receiving second configuration information at time (tk), the second configuration information being used to configure parameters related to data collection, and the association identifier corresponding to the second set associated with the second configuration information being in a second state; determining the value of the association identifier in the first state includes: determining the value of the association identifier in the first state as the value of the association identifier corresponding to the second set associated with the second configuration information.

[0013] Specifically, determining that the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the second configuration information includes: determining that the value of the association identifier corresponding to the second set associated with the first configuration information is the value of the association identifier corresponding to the second set associated with the second configuration information.

[0014] In the above method, by reusing the value of the association identifier corresponding to the second set associated with the second configuration information used to configure data collection related parameters at adjacent time points, the value of the association identifier corresponding to the second set associated with the first configuration information can be determined. Then, the second set can be correctly classified based on the value of the association identifier corresponding to the second set associated with the first configuration information, thereby avoiding the problem of classification error due to missing association identifier configuration.

[0015] In another possible implementation, the method further includes: receiving third configuration information, wherein the association identifier corresponding to the first set associated with the third configuration information is in a second state, and the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information.

[0016] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a second state, and determining the value of the association identifier in the first state includes: determining the value of the association identifier in the first state as the value of the association identifier corresponding to the second set associated with the third configuration information.

[0017] Specifically, determining that the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the third configuration information includes: determining that the value of the association identifier corresponding to the second set associated with the first configuration information is the value of the association identifier corresponding to the second set associated with the third configuration information.

[0018] In the above method, when the values ​​of the association identifiers corresponding to the first set associated with the two configuration information are equal, the association identifiers corresponding to the second set associated with the first configuration information are in a missing state, and the association identifiers corresponding to the second set associated with the third configuration information are in a second state, by reusing the value of the association identifiers corresponding to the second set associated with the third configuration information, the value of the association identifiers corresponding to the second set associated with the first configuration information can be determined. Then, based on the value of the association identifiers corresponding to the second set associated with the first configuration information, the second set can be correctly classified, thereby avoiding the problem of classification errors due to missing association identifier configurations.

[0019] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a first state, and the method further includes: determining that the first data pair associated with the first configuration information and the third data pair associated with the third configuration information are the same type of dataset.

[0020] The method described above employs a classification principle: when the values ​​of the association identifiers corresponding to the first sets associated with two configuration information pieces are equal, and the association identifiers corresponding to the second sets associated with these two configuration information pieces are both missing, the data pairs corresponding to these two configuration information pieces belong to the same dataset category. This approach enables the correct classification of datasets with missing association identifiers when such configurations are not configured correctly.

[0021] In another possible implementation, the association identifier corresponding to the first set associated with the first configuration information is in a first state, and the association identifier corresponding to the second set associated with the first configuration information is in a first state. The method further includes: receiving fourth configuration information, wherein the association identifier corresponding to the first set associated with the fourth configuration information is in a first state, and the association identifier corresponding to the second set associated with the fourth configuration information is in a first state; and determining that the first data pair associated with the first configuration information and the fourth data pair associated with the fourth configuration information are of the same type of dataset.

[0022] The method described above employs a classification principle: when the association identifiers for the first set associated with two configuration information pieces are both missing, and the association identifiers for the second set associated with these two configuration information pieces are also missing, the data pairs corresponding to these two configuration information pieces belong to the same dataset category. This approach enables the correct classification of datasets with missing association identifiers when such configurations are not configured correctly.

[0023] In another possible implementation, the first state represents the missing state, and the second state represents the not-missing state.

[0024] Optionally, the first state can also represent an unconfigured state, and the second state can also represent a configured state.

[0025] Secondly, embodiments of this application provide a dataset classification method. This method can be applied to a network-side device, which may be a network device, a component within the network device (e.g., a processor, chip, circuit, or chip system), or a logic module or software capable of implementing all or part of the functions of the network device. The method includes: sending first configuration information, wherein the first configuration information is used to configure parameters related to data collection, and the association identifier corresponding to a first set associated with the first configuration information is in a first state, and / or the association identifier corresponding to a second set associated with the first configuration information is in a first state.

[0026] In the above method, after the terminal device receives the first configuration information, it can determine that the association identifier corresponding to a certain set associated with the first configuration information is in a missing state, or that the association identifiers corresponding to both sets associated with the first configuration information are in a missing state. Then, it determines the value of the association identifier in the missing state and classifies the dataset based on the determined value of the association identifier in the missing state. In this way, the dataset can be correctly classified even when the association identifier is missing, avoiding the problem of classification errors caused by missing association identifier configuration.

[0027] In one possible implementation, the association identifier corresponding to the second set associated with the first configuration information is in a first state, and the association identifier corresponding to the first set associated with the first configuration information is in a second state.

[0028] In another possible implementation, the value of the association identifier in the first state is the value of the association identifier corresponding to the first set associated with the first configuration information.

[0029] In the above method, by reusing the value of the association identifier corresponding to the first set associated with the first configuration information, the value of the association identifier corresponding to the second set associated with the first configuration information can be determined. Then, the second set can be correctly classified based on the value of the association identifier corresponding to the second set associated with the first configuration information, thereby avoiding the problem of classification error due to missing association identifier configuration.

[0030] In another possible implementation, sending the first configuration information includes sending the first configuration information at time t. The method further includes sending the second configuration information at time (tk). The second configuration information is used to configure parameters related to data collection. The association identifier corresponding to the second set associated with the second configuration information is in a second state. The value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the second configuration information.

[0031] In the above method, by reusing the value of the association identifier corresponding to the second set associated with the second configuration information used to configure data collection related parameters at adjacent time points, the value of the association identifier corresponding to the second set associated with the first configuration information can be determined. Then, the second set can be correctly classified based on the value of the association identifier corresponding to the second set associated with the first configuration information, thereby avoiding the problem of classification error due to missing association identifier configuration.

[0032] In another possible implementation, the method further includes: sending third configuration information, wherein the association identifier corresponding to the first set associated with the third configuration information is in a second state, and the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information.

[0033] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a second state, and the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the third configuration information.

[0034] In the above method, when the values ​​of the association identifiers corresponding to the first set associated with the two configuration information are equal, the association identifiers corresponding to the second set associated with the first configuration information are in a missing state, and the association identifiers corresponding to the second set associated with the third configuration information are in a second state, by reusing the value of the association identifiers corresponding to the second set associated with the third configuration information, the value of the association identifiers corresponding to the second set associated with the first configuration information can be determined. Then, based on the value of the association identifiers corresponding to the second set associated with the first configuration information, the second set can be correctly classified, thereby avoiding the problem of classification errors due to missing association identifier configurations.

[0035] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a first state, and the first data pair associated with the first configuration information and the third data pair associated with the third configuration information are the same type of dataset.

[0036] The method described above employs a classification principle: when the values ​​of the association identifiers corresponding to the first sets associated with two configuration information pieces are equal, and the association identifiers corresponding to the second sets associated with these two configuration information pieces are both missing, the data pairs corresponding to these two configuration information pieces belong to the same dataset category. This approach enables the correct classification of datasets with missing association identifiers when such configurations are not configured correctly.

[0037] In another possible implementation, the association identifier corresponding to the first set associated with the first configuration information is in a first state, and the association identifier corresponding to the second set associated with the first configuration information is in a first state. The method further includes: sending fourth configuration information, wherein the association identifier corresponding to the first set associated with the fourth configuration information is in a first state, and the association identifier corresponding to the second set associated with the fourth configuration information is in a first state; the first data pair associated with the first configuration information and the fourth data pair associated with the fourth configuration information are of the same type of dataset.

[0038] The method described above employs a classification principle: when the association identifiers for the first set associated with two configuration information pieces are both missing, and the association identifiers for the second set associated with these two configuration information pieces are also missing, the data pairs corresponding to these two configuration information pieces belong to the same dataset category. This approach enables the correct classification of datasets with missing association identifiers when such configurations are not configured correctly.

[0039] In another possible implementation, the first state represents the missing state, and the second state represents the not-missing state.

[0040] Optionally, the first state can also represent an unconfigured state, and the second state can also represent a configured state.

[0041] Thirdly, embodiments of this application provide a dataset classification device, which can be a terminal device, a component in the terminal device (e.g., a processor, chip, circuit, or chip system), or a logic module or software that can implement all or part of the functions of the terminal device.

[0042] In one possible implementation, the dataset classification device may include modules, units, or means that correspond one-to-one with the methods / operations / steps / actions described in the first aspect. These modules, units, or means may be hardware circuits, software, or a combination of hardware circuits and software.

[0043] In one possible implementation, the dataset classification device includes: a processing unit and a transceiver unit. The transceiver unit is configured to receive first configuration information, which is used to configure parameters related to data collection. The processing unit is configured to determine that an association identifier corresponding to a first set associated with the first configuration information is in a first state, and / or an association identifier corresponding to a second set associated with the first configuration information is in a first state. The processing unit is further configured to determine the value of the association identifier in the first state, and the determined value of the association identifier in the first state is used for dataset classification.

[0044] In one possible implementation, the association identifier corresponding to the second set associated with the first configuration information is in a first state, and the processing unit is further configured to determine that the association identifier corresponding to the first set associated with the first configuration information is in a second state.

[0045] In another possible implementation, the processing unit is configured to determine that the value of the association identifier in the first state is the value of the association identifier corresponding to the first set associated with the first configuration information.

[0046] In another possible implementation, the transceiver unit is configured to receive the first configuration information at time t, and the transceiver unit is also configured to receive the second configuration information at time (tk), the second configuration information being used to configure parameters related to data collection, and the association identifier corresponding to the second set associated with the second configuration information being in a second state; the processing unit is configured to determine that the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the second configuration information.

[0047] In another possible implementation, the transceiver unit is further configured to receive third configuration information, wherein the association identifier corresponding to the first set associated with the third configuration information is in a second state, and the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information.

[0048] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a second state, and the processing unit is used to determine that the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the third configuration information.

[0049] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a first state, and the processing unit is used to determine that the first data pair associated with the first configuration information and the third data pair associated with the third configuration information are the same type of dataset.

[0050] In another possible implementation, the association identifier corresponding to the first set associated with the first configuration information is in a first state, and the association identifier corresponding to the second set associated with the first configuration information is in a first state. The transceiver unit is further configured to receive fourth configuration information, wherein the association identifier corresponding to the first set associated with the fourth configuration information is in a first state, and the association identifier corresponding to the second set associated with the fourth configuration information is in a first state. The processing unit is further configured to determine that the first data pair associated with the first configuration information and the fourth data pair associated with the fourth configuration information are of the same type of dataset.

[0051] In another possible implementation, the first state represents the missing state, and the second state represents the not-missing state.

[0052] For the technical effects of the third aspect or possible implementation, please refer to the introduction of the technical effects of the first aspect or corresponding implementation.

[0053] Fourthly, embodiments of this application provide a dataset classification device, which can be a network device, a component in the network device (e.g., a processor, chip, circuit, or chip system), or a logic module or software that can implement all or part of the functions of the network device.

[0054] In one possible implementation, the dataset classification device may include modules, units, or means that correspond one-to-one with the methods / operations / steps / actions described in the second aspect. These modules, units, or means may be hardware circuits, software, or a combination of hardware circuits and software.

[0055] In one possible implementation, the dataset classification device includes a processing unit and a transceiver unit. The processing unit is configured to send first configuration information through the transceiver unit. The first configuration information is used to configure parameters related to data collection. The association identifier corresponding to the first set associated with the first configuration information is in a first state, and / or the association identifier corresponding to the second set associated with the first configuration information is in a first state.

[0056] In one possible implementation, the association identifier corresponding to the second set associated with the first configuration information is in a first state, and the association identifier corresponding to the first set associated with the first configuration information is in a second state.

[0057] In another possible implementation, the value of the association identifier in the first state is the value of the association identifier corresponding to the first set associated with the first configuration information.

[0058] In another possible implementation, the transceiver unit is configured to send the first configuration information at time t, and the transceiver unit is also configured to send the second configuration information at time (tk). The second configuration information is used to configure parameters related to data collection. The association identifier corresponding to the second set associated with the second configuration information is in a second state, and the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the second configuration information.

[0059] In another possible implementation, the transceiver unit is further configured to send third configuration information, wherein the association identifier corresponding to the first set associated with the third configuration information is in a second state, and the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information.

[0060] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a second state, and the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the third configuration information.

[0061] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a first state, and the first data pair associated with the first configuration information and the third data pair associated with the third configuration information are the same type of dataset.

[0062] In another possible implementation, the association identifier corresponding to the first set associated with the first configuration information is in a first state, and the association identifier corresponding to the second set associated with the first configuration information is in a first state. The transceiver unit is further configured to send fourth configuration information, wherein the association identifier corresponding to the first set associated with the fourth configuration information is in a first state, and the association identifier corresponding to the second set associated with the fourth configuration information is in a first state; the first data pair associated with the first configuration information and the fourth data pair associated with the fourth configuration information are of the same type of dataset.

[0063] In another possible implementation, the first state represents the missing state, and the second state represents the not-missing state.

[0064] For the technical effects of the fourth aspect or possible implementation, please refer to the introduction of the technical effects of the second aspect or corresponding implementation.

[0065] Fifthly, embodiments of this application provide a dataset classification apparatus, which includes at least one processor that invokes a computer program or instructions stored in a memory to execute the method described in the first aspect or a possible implementation thereof.

[0066] In one possible implementation, the dataset classification device also includes memory and a communication interface. Optionally, the memory and processor are integrated together.

[0067] In one possible implementation, the memory is located outside the dataset classification device.

[0068] In a sixth aspect, embodiments of this application provide a dataset classification apparatus, which includes at least one processor that invokes a computer program or instructions stored in a memory to execute the method described in the second aspect or a possible implementation thereof.

[0069] In one possible implementation, the dataset classification device also includes memory and a communication interface. Optionally, the memory and processor are integrated together.

[0070] In one possible implementation, the memory is located outside the dataset classification device.

[0071] In a seventh aspect, embodiments of this application provide a chip device including at least one processor, the at least one processor being configured to execute computer programs or instructions to implement any of the above aspects or possible implementations of any of the above aspects.

[0072] In one possible implementation, the input of the chip device corresponds to the receiving operation in any of the above-mentioned aspects or possible implementations, and the output of the chip device corresponds to the transmitting operation in any of the above-mentioned aspects or possible implementations.

[0073] Optionally, the processor is coupled to the memory via an interface.

[0074] Optionally, the chip device may also include a memory storing computer program instructions.

[0075] Eighthly, embodiments of this application provide a computer-readable storage medium storing a computer program or instructions that, when executed on a processor, implement the methods described above.

[0076] Ninthly, embodiments of this application provide a computer program product that includes a computer program or instructions that, when executed on a processor, implement the method described in any of the above aspects.

[0077] In a tenth aspect, embodiments of this application provide a communication system comprising: the apparatus as described in the fifth aspect and the apparatus as described in the sixth aspect. Attached Figure Description

[0078] Figure 1A is a schematic diagram of the architecture of a communication system provided in an embodiment of this application;

[0079] Figure 1B is a schematic diagram of the architecture of another communication system provided in an embodiment of this application;

[0080] Figure 1C is a schematic diagram of a possible application framework in the communication system provided in an embodiment of this application;

[0081] Figure 1D is a schematic diagram of another possible application framework in the communication system provided in the embodiments of this application;

[0082] Figure 2 is a schematic diagram of a neuron structure;

[0083] Figure 3 is a schematic diagram of a neural network structure;

[0084] Figure 4 is a schematic diagram of wide beam and narrow beam;

[0085] Figures 5 and 6 are schematic diagrams of AI beam management;

[0086] Figure 7 is a schematic diagram of several possible sparse beam patterns;

[0087] Figure 8 is a schematic diagram of a periodic CSI-RS configuration;

[0088] Figure 9 is a schematic diagram of an aperiodic CSI-RS configuration;

[0089] Figure 10 is a schematic diagram of a dataset partitioning process;

[0090] Figure 11 is a schematic diagram of a CSI report configuration associated with a missing associated ID for set B;

[0091] Figure 12 is a schematic diagram of a dataset classification method provided in an embodiment of this application;

[0092] Figure 13 is a schematic diagram of determining the value of the association identifier corresponding to the second set according to an embodiment of this application;

[0093] Figure 14 is a schematic diagram of another method for determining the value of the association identifier corresponding to the second set according to an embodiment of this application;

[0094] Figure 15 is a schematic diagram of a dataset partitioning provided in an embodiment of this application;

[0095] Figure 16 is a schematic diagram of another dataset partitioning provided in an embodiment of this application;

[0096] Figure 17 is a schematic diagram of another dataset partitioning provided in an embodiment of this application;

[0097] Figure 18 is a schematic diagram of another dataset classification method provided in an embodiment of this application;

[0098] Figure 19 is a schematic diagram of another dataset classification method provided in an embodiment of this application;

[0099] Figure 20 is a schematic diagram of a dataset classification device provided in an embodiment of this application;

[0100] Figure 21 is a schematic diagram of another dataset classification device provided in an embodiment of this application;

[0101] Figure 22 is a schematic diagram of a chip system architecture provided in an embodiment of this application;

[0102] Figure 23 is a schematic diagram of the interaction between a terminal-side device and a network-side device according to an embodiment of this application. Detailed Implementation

[0103] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0104] References to "one embodiment" or "some embodiments" as described in this application mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0105] In the description of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: 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.

[0106] It is understood that in this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information to indicate A, it can be understood that the instruction information carries A, directly indicates A, or indirectly indicates A.

[0107] In this application, the information indicated by the instruction information is called the information to be instructed. In specific implementations, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index; indirectly instructing the information to be instructed by instructing other information, where there is a relationship between the other information and the information to be instructed; or instructing only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent.

[0108] The information to be instructed can be sent as a whole or divided into multiple sub-information messages, and the sending period and / or timing of these sub-information messages can be the same or different. This application does not limit the specific sending method. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the transmitting device by sending configuration information to the receiving device.

[0109] It is understood that "send" and "receive" in this application refer to the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which can include direct transmission via the air interface or indirect transmission via the air interface from other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which can include direct reception from YY via the air interface or indirect reception from YY via the air interface from other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0110] In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via buses, wiring, or interfaces.

[0111] It is understandable that information may undergo necessary processing, such as encoding and modulation, between the source and destination, but the destination can understand the valid information from the source. Similar statements in this application can be interpreted in a similar way and will not be elaborated further.

[0112] The communication method provided in this application can be applied to cellular communication systems related to the 3rd generation partnership project (3GPP), such as 4th generation (4G) communication systems, such as long term evolution (LTE) communication systems. For example, LTE communication systems may include LTE frequency division duplex (FDD) communication systems and LTE time division duplex (TDD) communication systems. It can also be applied to 5th generation (5G) communication systems, such as 5G new radio (NR) communication systems, or to various future communication systems and future communication networks. The method provided in this application can also be applied to Bluetooth systems, Wireless Fidelity (WiFi) systems, LoRa systems, or vehicle-to-everything (V2X) systems, communication systems supporting the integration of multiple wireless technologies, device-to-device (D2D) systems, vehicle-to-everything (V2X) communication systems, machine-to-machine (M2M) communication systems, machine-type communication (MTC) systems, and Internet of Things (IoT) communication systems or other communication systems. The method provided in this application can also be applied to satellite communication systems, wherein the satellite communication system can be integrated with the above-mentioned communication systems. The wireless communication systems involved in this application also include, but are not limited to, wireless local area network (WLAN) systems and narrowband Internet of Things (NB-IoT) systems.

[0113] In a communication system, one network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. The term "network element" can also be replaced by an entity, network entity, device, communication equipment, communication module, node, communication node, etc. This application uses a network element as an example for description. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device. It is understood that the terminal device in this application can be replaced by a first network element, and the network device can be replaced by a second network element, both performing the corresponding communication methods described in this application.

[0114] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, thus requiring increasingly diverse demands. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This characteristic makes network planning, network configuration, and / or resource scheduling increasingly complex. Furthermore, as network functions become more powerful, such as supporting higher spectrum, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming, and / or supporting beam management, network energy efficiency has become a hot research topic. These new demands, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, artificial intelligence (AI) technology can be introduced into wireless communication networks to achieve network intelligence. To support AI technology in wireless networks, AI nodes may also be introduced.

[0115] Please refer to Figure 1A, which is a schematic diagram of the architecture of a communication system provided in an embodiment of this application. The application scenario of this application will be described using the communication system 100 architecture shown in Figure 1A as an example. The communication system 100 includes at least one network device, such as network device 110 shown in Figure 1A. The communication system 100 may also include at least one terminal device, such as terminal device 120 and terminal device 130 shown in Figure 1A. Network device 110 and terminal devices (such as terminal devices 120 and 130) can communicate via a wireless link. The communication devices in this communication system, for example, network device 110 and terminal device 120, can communicate via multi-antenna technology.

[0116] Please refer to Figure 1B, which is a schematic diagram of the architecture of another communication system provided in this application embodiment. The communication system 200 includes at least one network device, such as network device 110 shown in Figure 1B. The communication system 200 may also include at least one terminal device, such as terminal device 120 and terminal device 130 shown in Figure 1B. Compared to the communication system 100 shown in Figure 1A, the communication system 200 shown in Figure 1B further includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building training datasets or training AI models.

[0117] In one possible implementation, network device 110 can send data related to the training of the AI ​​model to AI network element 140, which then constructs a training dataset and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. AI network element 140 can send the results of operations related to the AI ​​model to network device 110, which then forwards them to the terminal device. For example, the results of operations related to the AI ​​model may include at least one of the following: a trained AI model, model evaluation results, or test results. Exemplarily, a portion of the trained AI model may be deployed on network device 110, and another portion on the terminal device. Alternatively, the trained AI model may be deployed on network device 110. Or, the trained AI model may be deployed on the terminal device.

[0118] It should be understood that Figure 1B illustrates the example of AI network element 140 being directly connected to network device 110. In other scenarios, AI network element 140 can also be connected to a terminal device. Alternatively, AI network element 140 can be connected to both network device 110 and a terminal device simultaneously. Alternatively, AI network element 140 can also be connected to network device 110 through a third-party network element. This application embodiment does not limit the connection relationship between AI network element and other network elements. Figure 1B uses AI network element 140 as a single network element as an example; AI network element 140 can also be configured as a module in network device and / or terminal device, for example, in network device 110 or terminal device as shown in Figure 1B. This application does not impose limitations.

[0119] It should be noted that Figures 1A and 1B are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 1A and 1B. In practical applications, the communication system may include multiple network devices or multiple terminal devices. This application does not limit the number of network devices and terminal devices included in the communication system.

[0120] It should be understood that the network devices and terminal devices in Figures 1A and 1B can be hardware, software based on functional division, or a combination of both. The network devices and terminal devices described below can be any of the network devices and terminal devices described below. It should be noted that the methods described in the embodiments of this application can be applied to the communication systems shown in Figures 1A and 1B.

[0121] (1) Terminal equipment, also known as user equipment (UE), user unit, user station, mobile station (MS), remote station, mobile device, mobile terminal (MT), terminal, wireless communication equipment, etc., is a device that provides voice or data connectivity to a user. Specifically, it includes devices that provide voice connectivity to a user, devices that provide data connectivity to a user, or devices that provide both voice and data connectivity to a user. For example, it may include handheld devices with wireless connectivity or processing devices connected to a wireless modem. This terminal equipment can communicate with the core network via a radio access network (RAN), exchanging voice or data with the RAN, or interacting with the RAN to exchange voice and data. Currently, terminal devices can be: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices (such as smartwatches, smart bracelets, pedometers, etc.), in-vehicle devices (such as cars, bicycles, electric vehicles, airplanes, ships, trains, high-speed trains, etc.), virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, smart home devices (such as refrigerators, televisions, air conditioners, electricity meters, etc.), intelligent robots, workshop equipment, wireless terminals in self-driving vehicles, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, or flying devices (such as intelligent robots, hot air balloons, drones, airplanes), etc. Terminal devices can also be other devices with terminal functions; for example, a terminal device can also be a device that performs terminal functions in D2D communication.Terminal devices can also include vehicle-to-everything (V2X) terminal devices, machine-to-machine / machine-type communications (M2M / MTC) terminal devices, internet of things (IoT) terminal devices, light UEs, reduced capability UEs (REDCAP UEs), subscriber units, subscriber stations, mobile stations, remote stations, access points (APs), remote terminals, access terminals, user terminals, user agents, or user devices, and drone equipment. For example, this can include mobile phones (or "cellular" phones), computers with mobile terminal devices, portable, pocket-sized, handheld, and computer-embedded mobile devices, etc. Examples include personal communication service (PCS) telephones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices, or other processing devices connected to a wireless modem. It also includes limited devices, such as devices with low power consumption, limited storage capacity, or limited computing power. Examples include information sensing devices such as barcode scanners, radio frequency identification (RFID), sensors, global positioning systems (GPS), and laser scanners. In this application, terminal devices with wireless transceiver capabilities and chips that can be installed in the aforementioned terminal devices are collectively referred to as terminal devices.

[0122] As an example and not a limitation, in the embodiments of this application, when the terminal device can be a wearable device, wearable devices can also be called wearable smart devices. Wearable devices are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, accessories, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly defined, wearable smart devices include those with comprehensive functions, large size, and the ability to achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those focused on a specific application function that require cooperation with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0123] It should be noted that, in the embodiments of this application, the device used to implement the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing the functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This device can be installed in the terminal device or used in conjunction with the terminal device. In the embodiments of this application, the chip system can be composed of chips, or it can include chips and other discrete devices. In this embodiment, the terminal device is used as an example to illustrate the device used to implement the functions of the terminal device, and this does not constitute a limitation on the solutions of the embodiments of this application.

[0124] (2) A network device is a device deployed in a wireless access network to provide wireless communication functions for terminal devices. A network device may also be called a wireless access network (RAN) entity, access network equipment, wireless access network device, access node, wireless node, or network node, etc.

[0125] For example, the network device can be an access network device for a cellular system related to the 3GPP (3rd Generation Partnership Project). For instance, a fourth-generation (4G) mobile communication system or a 5G mobile communication system. The network device can also be an access network device in an open RAN (O-RAN or ORAN) or cloud radio access network (CRAN). Alternatively, the network device can also be an access network device in a communication system formed by the integration of two or more of the above communication systems.

[0126] Network equipment includes, but is not limited to: evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved Node B, or home Node B (HNB)), baseband unit (BBU), access point (AP), relay station, macro base station, micro base station, wireless relay node, donor node or similar, or combinations thereof, in Wi-Fi systems; radio controller, wireless backhaul node, transmitting and receiving point (TRP), transmitting point (TP), master station, slave station, motor slide retainer (MSR) node, transmission node, or transceiver node in CRAN scenarios. Network equipment can also be access network equipment in 5G mobile communication systems. For example, a next-generation NodeB (gNB), TRP, TP in a New Radio (NR) system, or one or a group of antenna panels (including multiple antenna panels) of a base station in a 5G mobile communication system. Alternatively, network equipment can also be a network node constituting a gNB or transmission point. For example, a central unit (CU), a distributed unit (DU), or a radio unit (RU). Network equipment can also be a baseband unit (BBU), a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH). Network equipment can also refer to communication modules, modems, or chips used in the aforementioned equipment or devices. Network equipment can also be a mobile switching center and equipment that performs base station functions in D2D, V2X, and M2M communications, network-side equipment in next-generation communication networks, and equipment that performs base station functions in future communication systems. Network equipment can support networks with the same or different access technologies. Network devices can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, in V2X technology, network devices can be roadside units (RSUs).

[0127] Network equipment can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of that mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0128] In some deployments, the network devices mentioned in the embodiments of this application may be devices including CU, DU, or CU and DU, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes. For example, the network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0129] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0130] RAN nodes can support one or more types of fronthaul interfaces, each corresponding to a DU and RU with different functions. If the fronthaul interface between the DU and RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and RU is another type of interface, relative to CPRI, some downlink and / or uplink baseband functions, such as, for downlink, precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition (CP), are moved from the DU to the RU; and for uplink, digital beamforming (BF), or one or more of fast Fourier transform (FFT) / cyclic prefix removal (CP), are moved from the DU to the RU. In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the segmentation between DU and RU differs, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0131] Taking eCPRI Cat A as an example, for downlink transmission, the DU is configured to implement one or more functions before and after layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping), while other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more functions of inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) are moved to the RU. For uplink transmission, the DU is configured to implement one or more functions before and after demapping (i.e., decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and demapping), while other functions after demapping (e.g., digital BF or one or more functions of fast Fourier transform (FFT) / removing CP) are moved to the RU. Understandably, the functional descriptions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol, and will not be elaborated here.

[0132] In one possible implementation, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0133] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0134] It should be noted that, in the embodiments of this application, the device used to implement the functions of the network device can be a network device itself; it can also be a device capable of supporting the network device in implementing the functions, such as a chip system, hardware circuit, software module, or hardware circuit plus software module. This device can be installed in the network device or used in conjunction with the network device. In the embodiments of this application, the chip system can be composed of chips or may include chips and other discrete devices. In this embodiment, the device used to implement the functions of the network device is described as a network device, and this does not constitute a limitation on the solutions of the embodiments of this application.

[0135] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware or general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0136] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network devices, terminal devices, or core network devices, etc. Alternatively, the AI ​​node can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or core network elements, etc.

[0137] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0138] It can also be understood that AI nodes can be independent devices, integrated into the same device to implement different functions, or they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the AI ​​nodes described above. Optionally, an AI node can be an AI network element or an AI module.

[0139] Please refer to Figure 1C, which is a schematic diagram of a possible application framework in a communication system provided in this application embodiment. As shown in Figure 1C, network elements in the communication system are connected through interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in operation administration and maintenance (OAM), are equipped with one or more AI modules (only one is shown in Figure 1C for clarity). The access network node can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be equipped with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are set in CU-CP and / or CU-UP. The method described in this application embodiment can be applied to the communication system shown in Figure 1C. It should be noted that the method described in this application embodiment can be applied to the communication system described in Figure 1C.

[0140] The AI ​​module in Figure 1C is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0141] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0142] Please refer to Figure 1D, which is a schematic diagram of another possible application framework in the communication system provided in the embodiments of this application. As shown in Figure 1D, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​module shown in Figure 1C, used to implement AI-related functions. The RIC includes near-real-time RIC (near-RT RIC) and non-real-time RIC (non-RT RIC). The non-real-time RIC mainly processes non-real-time information, such as data with low latency requirements, where the latency can be on the order of seconds. The real-time RIC mainly processes near-real-time information, such as data with relatively high latency requirements, where the latency can be on the order of tens of milliseconds. The method described in the embodiments of this application can be applied to the communication system shown in Figure 1D.

[0143] The near real-time RIC is used for model training and inference. For example, it can be used to train an AI model and then use that AI model for inference. The near real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data. Optionally, the near real-time RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the near real-time RIC delivers the inference result to the DU, and the DU sends it to the RU.

[0144] The non-real-time RIC is also used for model training and inference. For example, it can be used to train an AI model and then use that model for inference. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the non-real-time RIC delivers the inference results to the DU, which then forwards them to the RU.

[0145] The near real-time RIC and non-real-time RIC can also be set up as separate network elements. Optionally, the near real-time RIC and non-real-time RIC can also be part of other devices. For example, the near real-time RIC can be set in the RAN node (e.g., in CU, DU), while the non-real-time RIC can be set in the OAM, cloud server, core network device, or other network device.

[0146] In another possible implementation, the network device can be a network device equipped with one or more AI modules. The network device can be one or more devices in the core network, access network (RAN) node, or OAM as shown in Figure 1C. For example, the AI ​​module can be a RIC as shown in Figure 1D, such as a near real-time RIC or a non-real-time RIC. For example, the near real-time RIC is located in the RAN node (e.g., in the CU, DU), while the non-real-time RIC is located in the OAM, a cloud server, a core network device, or other network devices. The RIC can obtain subsets from multiple terminal devices from the RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU), reassemble them into a training dataset #2, and be trained based on the training dataset #2. Exemplarily, the near real-time RIC and the non-real-time RIC can also be set up separately as a network element, and the network device can be either a near real-time RIC or a non-real-time RIC.

[0147] To better understand the solutions provided in the embodiments of this application, some terms, concepts or processes involved in the embodiments of this application will be introduced below.

[0148] I. Terminology Explanation

[0149] (1) Artificial intelligence: to give machines human intelligence, using computer hardware and software to simulate certain intelligent behaviors of humans, including machine learning and many other methods.

[0150] (2) Machine learning (ML): Learning models or rules from raw data. There are many different machine learning methods, such as neural networks (NN), decision trees, support vector machines, etc.

[0151] (3) AI Model: This refers to a function model that maps an input of a certain dimension to an output of a certain dimension, and its parameters are obtained through machine learning training. For example, f(x) = ax 2 +b is a quadratic function model, which can be viewed as an AI model. a and b correspond to the parameters of the model, which can be obtained through machine learning training.

[0152] (4) Neural network: Here it refers to artificial neural network, which is a mathematical model that imitates the behavior characteristics of animal neural networks to perform distributed parallel information processing. It is a special form of AI model.

[0153] (5) Dataset: Data used for model training, validation and testing in machine learning. The quantity and quality of the data will affect the effect of machine learning.

[0154] (6) Model training: By selecting a suitable loss function, the model parameters are trained using an optimization algorithm to minimize the value of the loss function.

[0155] (7) Hyperparameters: parameters such as the number of layers in the neural network, the number of neurons, the activation function, and the loss function.

[0156] (8) Loss function: used to measure the difference between the model’s predicted value and the true value.

[0157] (9) Model testing: Evaluate model performance using test data after training.

[0158] (10) Model application: Use the trained model to solve practical problems.

[0159] II. Artificial Intelligence and Machine Learning

[0160] (1) Machine Learning:

[0161] Machine learning is an important technological approach to achieving artificial intelligence. Machine learning can be divided into supervised learning, unsupervised learning, and reinforcement learning.

[0162] (2) Supervised learning:

[0163] Supervised learning, based on collected sample values ​​and labels, uses machine learning algorithms to learn the mapping relationship between sample values ​​and labels, and expresses this learned mapping relationship using a machine learning model. The process of training the machine learning model is the process of learning this mapping relationship. For example, in signal detection, the noisy received signal is the sample, and the corresponding real constellation point is the label. Machine learning aims to learn the mapping relationship between samples and labels through training, that is, to enable the machine learning model to learn a signal detector. During training, the model parameters are optimized by calculating the error between the model's predicted values ​​and the real labels. Once the mapping relationship is learned, it can be used to predict the sample label of each new sample. The mapping relationship learned in supervised learning can include linear mappings and nonlinear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0164] (3) Unsupervised learning:

[0165] Unsupervised learning relies solely on collected sample values, using algorithms to discover inherent patterns within the samples. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals; that is, the model learns the mapping relationship from sample to sample, which is called self-supervised learning. During training, model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used for signal compression and decompression recovery applications; common algorithms include autoencoders and generative adversarial networks.

[0166] (4) Reinforcement learning:

[0167] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have explicit "correct" action labels. The algorithm needs to interact with the environment to obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each user based on the total system throughput feedback from the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and the optimal decision action. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action." Reinforcement learning training is achieved through iterative interaction with the environment.

[0168] (5) Deep Neural Networks

[0169] Deep neural networks (DNNs) are a specific implementation of machine learning. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems rely on extensive expert knowledge to design communication modules, while DNN-based deep learning communication systems can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0170] The idea behind DNNs originates from the neuronal structure of the brain. Each neuron performs a weighted summation of its input values, and the result is passed through a non-linear function to produce the output. See Figure 2, which is a schematic diagram of a neuron structure. Specifically, assume the neuron's input is x = [x0, ..., x...]. n The weights corresponding to the inputs are w = [w0, ..., w0]. n The bias of the weighted summation is b. The nonlinear function can take many forms; one example is the max{0,x} maximum value function. The effect of a neuron's execution can be... Please refer to Figure 3, which is a schematic diagram of a neural network structure. A DNN typically has a multi-layered structure, with each layer containing multiple neurons. The input layer processes the received values ​​through neurons and then passes them to the hidden layers. Similarly, the hidden layers then pass the computation results to the final output layer, producing the final output of the DNN.

[0171] DNNs typically have more than one hidden layer, and these hidden layers often directly affect the ability to extract information and fit functions. Increasing the number of hidden layers or widening the width of each layer can improve the function fitting ability of a DNN. The weights in each neuron are the parameters of the DNN network model. The model parameters are optimized through the training process, enabling the DNN network to extract data features and express mapping relationships. DNNs generally use supervised or unsupervised learning strategies to optimize model parameters.

[0172] Based on their construction methods, DNNs can be divided into feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). Figure 3 shows an FNN network, characterized by complete pairwise connections between neurons in adjacent layers. This makes FNNs typically require a large amount of storage space, resulting in high computational complexity.

[0173] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time-series data (discrete sampling along the time axis) and image data (two-dimensional discrete sampling) can both be considered grid-like data. CNNs do not use all the input information at once for computation; instead, they use a fixed-size window to extract a portion of the information for convolution operations, which significantly reduces the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (such as people and objects in an image representing different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0174] Recurrent Neural Networks (RNNs) are a type of distributed neural network (DNN) that utilizes feedback time-series information. Their input includes the current input value and their own output value from the previous time step. RNNs are well-suited for acquiring temporally correlated sequence features, and are particularly applicable to applications such as speech recognition and channel coding / decoding.

[0175] The FNN, CNN, and RNN mentioned above are common neural network structures, all built upon neurons. As introduced above, each neuron performs a weighted summation operation on its input values, and the result is passed through a nonlinear function to produce the output. We call the weights of the weighted summation operation and the nonlinear function in the neural network the parameters of the neural network. Taking a neuron with max{0,x} as the nonlinear function as an example, we perform... The parameters of the operated neuron are weights w = [w0, ..., w nThe weighted summation bias is b, and the nonlinear function is max{0,x}. The parameters of all neurons in a neural network constitute the parameters of that neural network.

[0176] III. Beam Management

[0177] A beam is a communication resource. In the NR protocol, a beam can be represented as a spatial filter, or spatial parameters. The beam used to transmit signals can be called the transmission beam (Tx beam), or a spatial domain transmit filter, or spatial domain transmit parameter; the beam used to receive signals can be called the reception beam (Rx beam), or a spatial domain receiver filter, or spatial domain receive parameter.

[0178] The transmitting beam can refer to the distribution of signal strength in different directions in space after a signal is transmitted through an antenna, while the receiving beam can refer to the distribution of signal strength in different directions in space of a wireless signal received from an antenna.

[0179] Beams can be identified by their identifier (ID). For example, a beam ID can be a Channel State Information Reference Signal Resource Indicator (CSI-RS, CRI), or it can be a bit in a bitmap corresponding to the beam. For instance, the number of bits in the bitmap is equal to the total number of beams associated with the network device in a single beam management inference task.

[0180] With the advancement of wireless communication technology, communication systems face increasing service demands, which place higher requirements on system capacity and communication latency. To address these challenges, fifth-generation mobile communication systems (5G) have introduced high-frequency bands above 6 GHz. These high-frequency bands offer advantages in both bandwidth and frequency compared to mid- and low-frequency bands below 6 GHz, thus providing higher transmission rates and system capacity. However, due to the weak penetration and strong path fading effect of high-frequency signals, their propagation distance is limited, and coverage is also restricted. Thanks to massive MIMO technology, high-frequency communication systems typically employ a large number of antennas for beamforming, thereby achieving considerable beam gain to compensate for the limited propagation distance caused by the high-frequency propagation characteristics. Effective beam management becomes crucial to achieving beamforming gain. To achieve beam management, existing technologies employ methods such as layered scanning to reduce beam scanning overhead. This involves first scanning a wide beam, and then scanning a small portion of a narrow beam within the wide beam, thereby reducing overhead. Please refer to Figure 4, which illustrates a wide beam and a narrow beam. A wide beam refers to a beam whose transmitting or receiving antenna has a relatively large radiation range when transmitting or receiving signals. Wide beams are typically used in applications requiring broadcast signals to a large area or a wide coverage area. It can provide a wider coverage area, but the signal strength is relatively weaker. A narrow beam refers to a beam whose transmitting or receiving antenna has a relatively small radiation range. Narrow beams are typically used in applications requiring signal focusing on a specific target or area. It can provide higher signal strength and higher directivity, but the coverage area is relatively smaller.

[0181] Beam selection is primarily accomplished through reference signals and corresponding beam measurements. Specifically, reference signals mainly include the synchronization signal block (SSB) and the channel state information-reference signal (CSI-RS). The SSB is a cell broadcast signal, comprising the primary synchronization signal (PSS), secondary synchronization signal (SSS), physical broadcast channel (PBCH), and demodulation reference signal (DMRS). The SSB is transmitted periodically according to cell configuration, and its function extends beyond beam management, also including initial access and time-frequency synchronization. Simply put, the SSB signal can be considered a wide-beam signal. Correspondingly, the CSI-RS signal is a user-level signal; the network configures one or more CSI-RS resources for users based on actual conditions. Similarly, the CSI-RS signal is not only used for beam management but also for channel quality measurements; it can be simply understood as a narrow-beam signal.

[0182] Traditional beam management systems perform a two-step beam scan during the service beam selection phase: The first phase scans the SSB (wide beam), during which the terminal device measures and reports the reference signal received power (RSRP) of the SSB beam to the network side. The second phase, based on the RSRP reported by the terminal device, the network side selects the SSB beam with the highest RSRP and configures CSI-RS resource scanning to scan the narrow beams covered by this SSB beam to determine the optimal beam. During the narrow beam scanning process configured by the network side, a Transmission Configuration Indication (TCI) status message containing quasico-location (QCL) information instructs the terminal device to use a fixed wide beam for reception. The terminal device feeds back the measurement results to the network side, which then determines the optimal beam for subsequent data transmission based on the measurement results. Each TCI status message may include a reference signal resource identifier. The reference signal resource identifier can be at least one of the following: non-zero power (NZP) channel state information reference signal (CSI-RS) resource identifier (NZP-CSI-RS-ResourceId) or SSB index (SSB-Index).

[0183] In recent years, AI technology has played a significant role in beam management, particularly in reducing beam scanning overhead. Typically, the AI ​​takes the received power of a wide beam or a sparsely scanned narrow beam measured at the terminal device as input. The model infers and outputs a Top-k list of candidate narrow beams (the RSRP value or ID of the output beam set). The network then performs a scan based on these Top-k candidate beams to ultimately determine the optimal beam. The AI ​​model can typically be deployed at either the terminal device or the network device.

[0184] Assuming the precoding matrix in the transmitter's codebook corresponds to 64 shaped beams, traditional schemes require scanning all 64 beams to determine the optimal beam. However, AI-assisted sparse beam scanning only needs to scan a subset of the beams in the codebook, such as the 16 beams scanned in Figure 5. There are many ways to select a subset of beams from the codebook for scanning, and each selected beam combination is called a sparse beam pattern. Refer to Figures 5 and 6, which are schematic diagrams of AI beam management. The transmitter uses the precoding matrix from the sparse beam pattern to precode and transmit a reference signal. The receiver receives the reference signal, determines the measurement of the received reference signal, and inputs it into the AI ​​beam prediction model. The AI ​​beam prediction model outputs the optimal Top-K beam index. The receiver feeds back the Top-K beam index to the transmitter. Optionally, when K>1, the transmitter scans these K shaped beams and transmits the beam-shaped reference signal. The receiver uses an energy detection method to measure the energy of these K reference signals and selects the one with the strongest energy as the optimal beam.

[0185] Figure 5 shows only one sparse beam pattern. Please refer to Figure 7, which is a schematic diagram of several possible sparse beam patterns. Figure 7(a) shows a sparse beam pattern corresponding to 8 beams, Figure 7(b) shows a sparse beam pattern corresponding to 16 beams, Figure 7(c) shows a sparse beam pattern corresponding to 16 beams, and Figure 7(d) shows a sparse beam pattern corresponding to 32 beams. In practical applications, different sparse beam patterns may be selected under different channel environments. For example, in narrow areas such as alleys and subway stations, the main channel path is often distributed within a narrow range, and designing a uniformly spaced sparse beam pattern is often inefficient. In addition, the transmitter and receiver may have high power consumption requirements and want to minimize the number of beam scans, so the sparse beam pattern may contain fewer shaped beams. Furthermore, when the transmitter changes its transmission codebook, such as to an irregular beam codebook, it will also cause changes in the sparse pattern.

[0186] The AI-assisted beam scanning scheme described above essentially utilizes the principle of super-resolution. It interpolates and infers the reference signal measurements of all shaped beams using only the reference signal measurements of a portion of the shaped beams, thereby predicting the optimal shaped beam index. However, the super-resolution capability learned by the AI ​​beam prediction model corresponds one-to-one with the sparse beam pattern. When the transmitter uses different sparse beam patterns, the beam measurements measured by the receiver will also be different. Traditional AI beam models cannot be applied to different sparse beam patterns.

[0187] IV. CSI-RS Measurement Resources and CSI Report Configuration

[0188] In the existing protocol, the configuration of CSI-RS measurement resources and the feedback of CSI reports both support three configuration modes: periodic, semi-persistent, and aperiodic. Please refer to Table 1, as shown in the table below:

[0189] Table 1

[0190] In the periodic CSI-RS configuration, the network side configures the CSI transmission period (every N slots) and offset (symbol offset within the period) and informs the UE, and transmits according to the configured period and offset. Please refer to Figure 8, which is a schematic diagram of a periodic CSI-RS configuration. In Figure 8(a), the network side configures the CSI transmission period to be every 5 slots and offset = 0, and transmits CSI according to the configured CSI transmission period. In Figure 8(b), the network side configures the CSI transmission period to be every 5 slots and offset = 3, and transmits CSI according to the configured CSI transmission period. In Figure 8(c), the network side configures the CSI transmission period to be every 10 slots and offset = 3, and transmits CSI according to the configured CSI transmission period.

[0191] In the semi-static CSI-RS configuration, the network side configures the CSI transmission period (every N slots) and offset (symbol offset within the period) and informs the UE, but whether or not transmission actually occurs is determined by the media access control element (MAC CE). The MAC CE activates / deactivates CSI-RS transmission and notifies the terminal device.

[0192] In the aperiodic CSI-RS configuration, the terminal device is notified of each CSI-RS transmission via DCI signaling. The aperiodic CSI-RS configuration also supports configuring the transmission of multiple CSI-RS resources at once, configured using a set of parameters [m, K], where m is the interval of the CSI-RS resources and K is the number of CSI-RS resources. See Figure 9, which is a schematic diagram of an aperiodic CSI-RS configuration. Aperiodic CSI is configured via DCI 1, specifically using parameters [m, K], where m is the interval of the CSI-RS resources and K is the number of CSI-RS resources, where K = 4. The interval between predicted CSIs is n. The configuration of the three types of CSI report feedback is similar to the above and will not be repeated here.

[0193] VI. Network-side conditions

[0194] Currently, both beam management and CSI prediction applications mention the need for alignment between network-side physical conditions and terminal-side conditions. These physical conditions may include network-side transceiver unit (TxRU) mappings, downtilt angles, base station types, and carrier frequencies. Changes in these physical conditions can lead to significant differences in the magnitude and distribution of the RSRP value of the transmitted beam. If the terminal device does not distinguish between these network-side physical conditions and mixes data from different network-side conditions for training, or trains the model under condition A and infers under condition B, this can result in the model failing to converge or exhibiting poor inference performance. Therefore, associated IDs are designed to represent the changing physical conditions on the network side. Each associated ID corresponds to a specific combination of network-side physical conditions. This associated ID is sent along with the reference signal resource set so that the terminal device can distinguish the data sent by the network side under different physical environments. For example, during the data collection phase, when the network needs to distribute reference signal resources, it also distributes an associated ID representing its physical conditions. The terminal device generates a dataset and classifies it according to the associated ID, and trains the corresponding model. Therefore, the default approach is that a set of network-side physical conditions corresponds to one or two associated IDs, and one associated ID corresponds to a type of data. During the inference phase, when the network distributes the model input data, it also distributes an associated ID to identify the current state. After obtaining the ID, the terminal device selects the corresponding model for inference and obtains accurate results.

[0195] During the data collection phase, a CSI report configuration (CSI-reportConfig) is associated with the associated IDs of set A (setA) and set B (setB). When two CSI report configurations have the same associated ID for set A and the same associated ID for set B, the two data pairs associated with the two CSI report configurations are classified into one data set. See Figure 10, which illustrates a dataset partitioning process. CSI report configuration 1 (CSI-reportConfig#1) corresponds to data pair #1 (pair#1). The associated ID value for set A (setA) is 1, and the associated ID value for set B (setB) is 2. CSI report configuration 2 (CSI-reportConfig#2) corresponds to data pair #2 (pair#2). The associated ID value for set A is 1, and the associated ID value for set B is 2. Since the associated ID value for set A associated with CSI report configuration 1 is the same, the two data pairs associated with the two CSI report configurations are classified into one data set. If the associated ID of set A associated with CSI report configuration 2 is the same as the associated ID of set B associated with CSI report configuration 1, and the associated ID of set B associated with CSI report configuration 2 is the same as the associated ID of set B associated with CSI report configuration 2, then data pair #1 and data pair #2 belong to the same dataset.

[0196] However, in practical applications, due to different configuration methods of some manufacturers, or because the associated IDs of set A and set B associated with the same CSI report configuration may not be issued simultaneously, the associated IDs of set A and / or set B may be missing. For example, please refer to Figure 11, which is a schematic diagram of a missing associated ID of set B associated with a CSI report configuration. This further leads to the inability to correctly classify the data pairs corresponding to the CSI report configuration. If all data pairs that cannot be correctly classified are lost, it will result in a waste of resources. If all datasets with missing associated IDs are regarded as the same category, it will lead to incorrect dataset classification. Therefore, in order to solve the above problems, the embodiments of this application propose the following solutions.

[0197] Please refer to Figure 12. Figure 12 is a schematic diagram of a dataset classification method provided in an embodiment of this application. The method shown in Figure 12 can be applied to terminal-side devices and network-side devices. The terminal-side device can be a terminal device, or a component applied in the terminal device (e.g., a processor, chip, circuit, or chip system), or a logic module or software that can implement all or part of the functions of the terminal device. The network-side device can be a network device, or a component applied in the network device (e.g., a processor, chip, circuit, or chip system), or a logic module or software that can implement all or part of the functions of the network device. In the embodiments shown in Figure 12 below, the terminal-side device is taken as a terminal device and the network-side device is taken as a network device for description. The method includes, but is not limited to, the following steps:

[0198] Step S1201: The network device sends the first configuration information.

[0199] Accordingly, the terminal device receives the first configuration information.

[0200] The first configuration information is used to configure parameters related to data collection. Specifically, it configures the data collection object, which includes a first set and a second set. In other words, the first configuration information configures relevant information about the first set and the second set. The first configuration information is associated with a first data pair, which includes both the first set and the second set. The first set can be a set of reference signal resources. The second set can also be a set of reference signal resources. Optionally, the first set is not a subset of the second set, or the second set is not a subset of the first set. That is, the intersection of the first set and the second set is empty.

[0201] For example, the first configuration information can also be called Channel State Information Report Configuration (CSI-reportConfig). The first set can also be called set A (setA), and the second set can also be called set B (setB).

[0202] Step S1202: The terminal device determines that the association identifier corresponding to the first set associated with the first configuration information is in a first state, and / or the association identifier corresponding to the second set associated with the first configuration information is in a first state.

[0203] The process by which the terminal device determines the first set and the second set associated with the first configuration information may include: associating the first configuration information with two Channel State Information Resource Configuration Identifiers (CSI-ResourceConfigIDs), identifying the corresponding two resources through these two CSI-ResourceConfigIDs, and thus determining the first set and the second set. For example, if CSI-reportconfig is associated with two CSI-ResourceConfigIDs, the two corresponding resources can be determined based on these two CSI-ResourceConfigIDs, and setA and setB can be determined based on these two resources. Optionally, the first configuration information may associate the reference signal-related parameters corresponding to the two reference signal resource sets (the first set and the second set), such as the time-frequency resources occupied by the reference signal and the transmission period of the reference signal.

[0204] The association identifier can be network-side condition identifier information. This network-side condition identifier information can refer to the identifier of the network-side conditions applicable to the intelligent model, or it can refer to the network-side conditions under which the training data used by the intelligent model was collected. Since the training data used by the intelligent model is collected under certain network-side conditions, when configuring the terminal device to execute the intelligent model, the configured intelligent model needs to be applicable to the current network-side conditions. That is, the network-side conditions during inference should be consistent with the network-side conditions when the training data of the intelligent model was determined. Only in this way can the intelligent model achieve better inference performance.

[0205] Furthermore, since each associated ID corresponds to a specific network-side condition, the network sends the corresponding associated ID along with the reference signal resource set. This allows the terminal device to distinguish data sent by the network under different physical environments. For example, during the data collection phase, the network sends the reference signal resource set along with associated IDs representing its physical conditions. The terminal device generates a dataset, categorizes it according to the associated IDs, and trains the corresponding intelligent model. A set of network-side physical conditions corresponds to one or two associated IDs, and one associated ID corresponds to one type of data. During the inference phase, the network also sends the associated IDs corresponding to the input data when sending the model input data. After obtaining the associated ID, the terminal device selects the corresponding intelligent model for inference to obtain accurate results.

[0206] The network-side conditions corresponding to this network-side condition identifier information may include one or more of the following: spatial arrangement of physical beams, beam gain, antenna height, base station type, carrier frequency, antenna downtilt angle, or environmental parameters. For example, environmental parameters may include building density or topography.

[0207] Here, the first state represents the absent state. The first state can also represent the unconfigured state. The association identifier corresponding to the first set can also be described as the association identifier associated with the first set, and the association identifier corresponding to the second set can also be described as the association identifier associated with the second set.

[0208] Wherein, the terminal device determines that the association identifier corresponding to the first set associated with the first configuration information is in a first state, and / or the association identifier corresponding to the second set associated with the first configuration information is in a first state, which may include: the terminal device determining that the association identifier corresponding to the first set associated with the first configuration information is in a first state, and may also include: the terminal device determining that the association identifier corresponding to the second set associated with the first configuration information is in a first state, and may also include: the terminal device determining that the association identifier corresponding to the first set associated with the first configuration information is in a first state and the association identifier corresponding to the second set associated with the first configuration information is in a first state.

[0209] Step S1203: The terminal device determines the value of the associated identifier in the first state.

[0210] Specifically, the value of the association identifier in the first state is used for dataset classification. The terminal device can classify the set corresponding to the association identifier based on the value of the association identifier in the first state, or the terminal device can classify the data pair corresponding to the association identifier based on the value of the association identifier in the first state.

[0211] Since two scenarios may occur in step S1202—first, the association identifier corresponding to one set associated with the first configuration information is in the first state; and second, the association identifiers corresponding to both sets associated with the first configuration information are in the first state—the following will describe how the terminal device determines the value of the association identifier in the first state from two aspects:

[0212] Firstly, in the first case, the association identifier corresponding to a certain set associated with the first configuration information is in a first state. For example, the association identifier corresponding to the first set associated with the first configuration information is in a first state, or the association identifier corresponding to the second set associated with the first configuration information is in a first state. Then, determining the value of the association identifier in the first state includes determining the value of the association identifier corresponding to the first set or determining the value of the association identifier corresponding to the second set.

[0213] In one possible implementation, the association identifier corresponding to the second set associated with the first configuration information is in a first state, and the method further includes: determining that the association identifier corresponding to the first set associated with the first configuration information is in a second state.

[0214] The second state indicates a non-missing state. The second state can also indicate a configured state. Determining that the association identifier corresponding to the first set associated with the first configuration information is in the second state may include: determining the value of the association identifier corresponding to the first set associated with the first configuration information.

[0215] In one example, please refer to Figure 11, where the association identifier corresponding to the first set (setA) associated with the first configuration information (CSI-reportConfig#1) is in the second state and the value of the association identifier is 1, that is, associated ID = 1. The association identifier corresponding to the second set (setB) associated with the first configuration information is in the first state, that is, the absent state.

[0216] The following describes how, under the premise that the association identifier corresponding to the second set associated with the first configuration information is in a first state and the association identifier corresponding to the first set associated with the first configuration information is in a second state, the value of the association identifier in the first state, i.e., the value of the association identifier corresponding to the second set associated with the first configuration information, can be determined using the following three methods, as detailed below:

[0217] Method 1: In another possible implementation, determining the value of the association identifier in the first state includes: determining that the value of the association identifier in the first state is the value of the association identifier corresponding to the first set associated with the first configuration information.

[0218] Specifically, determining that the value of the association identifier in the first state is the value of the association identifier corresponding to the first set associated with the first configuration information includes: determining that the value of the association identifier corresponding to the second set associated with the first configuration information is the value of the association identifier corresponding to the first set associated with the first configuration information.

[0219] This can be understood as follows: when the association identifier corresponding to the first set associated with the first configuration information is not missing, but the association identifier corresponding to the second set associated with the first configuration information is missing, the value of the association identifier corresponding to the first set associated with the first configuration information can be directly reused. That is, the value of the association identifier corresponding to the second set associated with the first configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information.

[0220] Optionally, after the terminal device determines that the value of the association identifier corresponding to the second set associated with the first configuration information is the value of the association identifier corresponding to the first set associated with the first configuration information, it can classify the second set based on the determined value of the association identifier corresponding to the second set associated with the first configuration information. The specific classification method depends on the implementation of the terminal device. For example, the datasets with the same value of the association identifier corresponding to the second set in the configuration information received by the terminal device can be divided into the same type of data.

[0221] In one example, please refer to Figure 13, which is a schematic diagram of determining the value of the association identifier corresponding to the second set according to an embodiment of this application. The value of the association identifier corresponding to the first set (setA) associated with the first configuration information (CSI-reportConfig#1) is 1. The association identifier corresponding to the second set (setB) associated with the first configuration information (CSI-reportConfig#1) is in a first state, i.e., a missing state. Therefore, the value of the association identifier corresponding to the second set (setB) associated with the first configuration information (CSI-reportConfig#1) is the value of the association identifier corresponding to the first set (setA) associated with CSI-reportConfig#1, which is equal to 1. That is to say, the second set (setB) can directly reuse the association identifier corresponding to its paired first set (setA). Pairing refers to resource sets under the same CSI-reportConfig.

[0222] In the above method, by reusing the value of the association identifier corresponding to the first set associated with the first configuration information, the value of the association identifier corresponding to the second set associated with the first configuration information can be determined. Then, the second set can be correctly classified based on the value of the association identifier corresponding to the second set associated with the first configuration information, thereby avoiding the problem of classification error due to missing association identifier configuration.

[0223] Method 2: In another possible implementation, the terminal device receiving the first configuration information includes: receiving the first configuration information at time t. The method further includes: receiving the second configuration information at time (tk), the second configuration information being used to configure parameters related to data collection, and the association identifier corresponding to the second set associated with the second configuration information being in a second state; determining the value of the association identifier in the first state includes: determining that the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the second configuration information.

[0224] The second configuration information is the configuration information for parameters related to data collection at the nearest time to time t. For an explanation of the second configuration information, please refer to the description of the first configuration information. Time (tk) is the nearest time to time t, where (tk) represents a time before time t, differing from time t by k time steps. Determining the value of the association identifier in the first state as the value of the association identifier corresponding to the second set associated with the second configuration information may include: determining the value of the association identifier corresponding to the second set associated with the first configuration information as the value of the association identifier corresponding to the second set associated with the second configuration information.

[0225] The above process can be understood as follows: when the association identifier corresponding to the second set associated with the first configuration information is in the first state, i.e. missing state, the value of the association identifier corresponding to the second set associated with the second configuration information can be reused. The second configuration information is the configuration information of the parameters related to configuration data collection at the nearest time to time t. That is, the value of the association identifier corresponding to the second set associated with the first configuration information is the value of the association identifier corresponding to the second set associated with the second configuration information.

[0226] It should be noted that the association identifier corresponding to the first set associated with the second configuration information can be in either a first state or a second state, and this embodiment of the application does not limit this. Optionally, the intersection between the first set associated with the second configuration information and the second set associated with the second configuration information is empty.

[0227] Optionally, after the terminal device determines that the value of the association identifier corresponding to the second set associated with the first configuration information is the value of the association identifier corresponding to the second set associated with the second configuration information, it can classify the second set based on the determined value of the association identifier corresponding to the second set associated with the first configuration information. The specific classification method depends on the implementation of the terminal device. For example, the datasets with the same value of the association identifier corresponding to the second set in the configuration information received by the terminal device can be divided into the same type of data.

[0228] In one example, please refer to Figure 14, which is a schematic diagram of another method for determining the value of the association identifier corresponding to the second set according to an embodiment of this application. The value of the association identifier corresponding to the first set (setA) associated with the first configuration information (CSI-reportConfig#t) is 1. The value of the association identifier corresponding to the second set (setB) associated with the first configuration information (CSI-reportConfig#t) is the first state, i.e., the absent state. The value of the association identifier corresponding to the first set (setA) associated with the second configuration information (CSI-reportConfig#t-1) is 1. The second configuration information is the data collected at the nearest time to time t for configuration data collection. The relevant parameter configuration information, time t is the time when the first configuration information is received, the value of the association identifier corresponding to the second set (setB) associated with the second configuration information (CSI-reportConfig#t-1) is B, the terminal device determines that the value of the association identifier corresponding to the second set (setB) associated with the first configuration information (CSI-reportConfig#t) is equal to B.

[0229] In the above method, by reusing the value of the association identifier corresponding to the second set associated with the second configuration information used to configure data collection related parameters at adjacent time points, the value of the association identifier corresponding to the second set associated with the first configuration information can be determined. Then, the second set can be correctly classified based on the value of the association identifier corresponding to the second set associated with the first configuration information, thereby avoiding the problem of classification error due to missing association identifier configuration.

[0230] Method 3: In another possible implementation, the method further includes: the terminal device receiving third configuration information, wherein the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information.

[0231] Optionally, the intersection between the first set associated with the third configuration information and the second set associated with the third configuration information is empty.

[0232] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a second state. Determining the value of the association identifier in the first state includes: determining that the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the third configuration information, that is, determining that the value of the association identifier corresponding to the second set associated with the first configuration information is the value of the association identifier corresponding to the second set associated with the third configuration information.

[0233] The above process can be understood as follows: when the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information, and the association identifier corresponding to the second set associated with the third configuration information is in the second state, the value of the association identifier corresponding to the second set associated with the first configuration information is the value of the association identifier corresponding to the second set associated with the third configuration information.

[0234] In other words, if the values ​​of the association identifiers corresponding to one set in two configuration information are equal, and the association identifier corresponding to the set associated with one configuration information is in the first state, i.e. missing state, then the value of the association identifier in the first state is the value of the association identifier corresponding to the set associated with the other configuration information (specifically, the value of the association identifier corresponding to the set whose values ​​are not equal).

[0235] In one example, please refer to Table 2, which is a schematic diagram of the same type of dataset provided in the embodiments of this application. There are 5 configuration information, namely CSI-reportConfig#1, CSI-reportConfig#2, CSI-reportConfig#3, CSI-reportConfig#4, and CSI-reportConfig#5, which correspond to 5 data pairs, namely pair#1, pair#2, pair#3, pair#4, and pair#5. Among them, the associated IDs of set A and set B in pair#1 and pair#5 are in the first state, that is, the missing state. At this time, since the associated IDs corresponding to set B in pair#1, pair#2, and pair#3 are all the same, the specific value is A. Therefore, pair#1, pair#2, and pair#3 are classified into the same type of dataset. And because the associated IDs corresponding to set A in pair#3, pair#4, and pair#5 are also the same... Since the IDs are the same, and the specific value is 2, pairs #3, pairs #4, and pairs #5 belong to the same dataset class. Thus, pairs #1 through #5 are all in the same dataset class. Therefore, for pairs #1 and pairs #5, when the associated ID is missing, it can be assigned any value belonging to the same dataset class. For example, if the associated ID corresponding to set A of pair #1 is missing, it can be assigned the value 1 or 2, meaning the associated ID corresponding to set A of pair #1 can be 1 or 2. Similarly, if the associated ID corresponding to set B of pair #5 is missing, it can be assigned the value A or B, meaning the associated ID corresponding to set B of pair #5 can be A or B.

[0236] Table 2

[0237] The above example can be understood as employing a more flexible data pair classification method. The terminal device classifies the dataset according to either of the two associated IDs. If either set A or set B is missing, the data category is first divided according to the existing one, and then the missing value is assigned any corresponding value in that category.

[0238] In the above method, when the values ​​of the association identifiers corresponding to the first set associated with the two configuration information (first configuration information and third configuration information) are equal, the association identifiers corresponding to the second set associated with the first configuration information are in a missing state, and the association identifiers corresponding to the second set associated with the third configuration information are in a second state, by reusing the value of the association identifiers corresponding to the second set associated with the third configuration information, the value of the association identifiers corresponding to the second set associated with the first configuration information can be determined. Then, based on the value of the association identifiers corresponding to the second set associated with the first configuration information, the second set can be correctly classified, thereby avoiding the problem of classification errors due to missing association identifier configurations.

[0239] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a first state, and the method further includes: the terminal device determining that the first data pair associated with the first configuration information and the third data pair associated with the third configuration information are the same type of dataset.

[0240] The above process can be understood as follows: if the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information, and the association identifier corresponding to the second set associated with the third configuration information is in the first state, then the terminal device determines that the first data pair associated with the first configuration information and the third data pair associated with the third configuration information are the same type of dataset.

[0241] In other words, for two sets of configuration information, if the associated IDs of one set associated with the two sets are equal, and the associated IDs of the other set associated with the two sets are both in the first state (missing state), then the data pairs corresponding to these two sets of configuration information belong to the same dataset. For two data pairs, as long as the associated IDs of one set (set A or set B) are equal, these two data pairs can be classified into one dataset. In this case, if the associated ID of one dataset in a data pair (e.g., data pair 1) is missing, the associated ID of the remaining dataset is used. If the associated ID of the dataset in any other data pair (e.g., data pair 2) is equal to the associated ID of the dataset in data pair 1, then they belong to the same dataset; that is, data pair 1 and data pair 2 belong to the same dataset.

[0242] Please refer to Figure 15. Figure 15 is a schematic diagram of a dataset partitioning provided in an embodiment of this application. There are three configuration information, namely CSI-reportConfig#1, CSI-reportConfig#2, and CSI-reportConfig#3. The three configuration information correspond to three data pairs, namely data pair #1 (pair#1), data pair #2 (pair#2), and data pair #3 (pair#3). The value of the association identifier corresponding to the first set (setA) of the three data pairs is equal to 10001. The association identifiers corresponding to the second set (setB) of the three data pairs are all in the first state, that is, the absent state. Since the values ​​of the association identifiers corresponding to the first set of the three data pairs are all the same, and the association identifiers corresponding to the second set (setB) of the three data pairs are all in the first state, these three data pairs belong to the same type of dataset.

[0243] Please refer to Figure 16, which is a schematic diagram of another dataset partitioning provided in the embodiment of this application. There are three configuration information, namely CSI-reportConfig#4, CSI-reportConfig#5, and CSI-reportConfig#6. The three configuration information correspond to three data pairs, namely data pair #4, data pair #5, and data pair #6. The association identifiers corresponding to the first set (setA) of the three data pairs are all in the first state, that is, the absent state. The value of the association identifier corresponding to the second set (setB) of the three data pairs is equal to 10001. Since the values ​​of the association identifiers corresponding to the second set of the three data pairs are all the same, and the association identifiers corresponding to the first set of the three data pairs are all in the first state, these three data pairs belong to the same type of dataset.

[0244] The method described above employs a classification principle: when the values ​​of the association identifiers corresponding to the first sets associated with two configuration information pieces are equal, and the association identifiers corresponding to the second sets associated with these two configuration information pieces are both missing, the data pairs corresponding to these two configuration information pieces belong to the same dataset category. This approach enables the correct classification of datasets with missing association identifiers when such configurations are not configured correctly.

[0245] It should be noted that the above is based on the premise that the association identifier corresponding to the second set associated with the first configuration information is in the first state and the association identifier corresponding to the first set associated with the first configuration information is in the second state. The specific method for determining the value of the association identifier corresponding to the second set associated with the first configuration information can also be that the association identifier corresponding to the first set associated with the first configuration information is in the first state and the association identifier corresponding to the second set associated with the first configuration information is in the second state. For details on how to determine the association identifier corresponding to the first set associated with the first configuration information, please refer to the above description.

[0246] Secondly, the association identifier corresponding to the first set associated with the first configuration information is in a first state, and the association identifier corresponding to the second set associated with the first configuration information is in a first state.

[0247] In another possible implementation, the method further includes: receiving fourth configuration information, wherein the association identifier corresponding to the first set associated with the fourth configuration information is in a first state, and the association identifier corresponding to the second set associated with the fourth configuration information is in a first state; and determining that the first data pair associated with the first configuration information and the fourth data pair associated with the fourth configuration information are the same type of dataset.

[0248] In other words, for two sets of configuration information, if the association identifiers corresponding to the first set associated with the two sets of configuration information are both in the first state, and the association identifiers corresponding to the second set associated with the two sets of configuration information are both in the first state, then the two data pairs corresponding to the two sets of configuration information are of the same type of data, the first set associated with the two sets of configuration information is of the same type of data, and the second set associated with the two sets of configuration information is of the same type of data. That is, if both associated IDs in a data pair are missing (i.e., the associated IDs of set A and set B are both in the first state), then all data pairs belonging to this category are of the same type of data, and set A and set B are also of the same type of data.

[0249] Please refer to Figure 17, which is a schematic diagram of another dataset partitioning provided in an embodiment of this application. There are three configuration information, namely CSI-reportConfig#7, CSI-reportConfig#8, and CSI-reportConfig#9. The three configuration information correspond to three data pairs, namely data pair #7, data pair #8, and data pair #9. The association identifiers corresponding to the first set (setA) of the three data pairs are all in the first state, that is, the absent state. The association identifiers corresponding to the second set (setB) of the three data pairs are all in the first state, that is, the absent state. Since the association identifiers corresponding to the first set (setA) of the three data pairs are all in the first state, and the association identifiers corresponding to the second set (setB) of the three data pairs are all in the first state, these three data pairs are the same type of dataset.

[0250] The method described above employs a classification principle: when the association identifiers for the first set associated with two configuration information pieces are both missing, and the association identifiers for the second set associated with these two configuration information pieces are also missing, the data pairs corresponding to these two configuration information pieces belong to the same dataset category. This approach enables the correct classification of datasets with missing association identifiers when such configurations are not configured correctly.

[0251] In the method described in Figure 12, after the terminal device receives the first configuration information, it can determine that the association identifier corresponding to a certain set associated with the first configuration information is in a missing state, or that the association identifiers corresponding to both sets associated with the first configuration information are in a missing state. Then, the value of the association identifier in the missing state is determined, and the dataset is classified based on the determined value of the association identifier in the missing state. In this way, the dataset can be correctly classified even when the association identifier is missing, avoiding the problem of classification error caused by missing association identifier configuration.

[0252] Please refer to Figure 18. Figure 18 is a schematic diagram of another dataset classification method provided in this application embodiment. The method shown in Figure 18 can be applied to terminal-side devices and network-side devices. The terminal-side device can be a terminal device, or a component applied in the terminal device (e.g., a processor, chip, circuit, or chip system), or a logic module or software that can implement all or part of the functions of the terminal device. The network-side device can be a network device, or a component applied in the network device (e.g., a processor, chip, circuit, or chip system), or a logic module or software that can implement all or part of the functions of the network device. In the embodiments shown in Figure 18 below, the terminal-side device is taken as a terminal device and the network-side device is taken as a network device for description. The method includes, but is not limited to, the following steps:

[0253] Step S1801: Configure the Channel State Information Report (CSI-reportConfig) for network device configuration data collection.

[0254] Specifically, the Channel State Information Report Configuration (CSI-reportConfig) for network device configuration data collection includes: the network device determining the first configuration information. For a related explanation of the first configuration information, please refer to the relevant description of the first configuration information in step S1201, which will not be repeated here.

[0255] Step S1802: The network device sends the Channel State Information Report Configuration (CSI-reportConfig) to the terminal device.

[0256] Specifically, the process of the network device sending the Channel State Information Report Configuration (CSI-reportConfig) to the terminal device includes: the network device sending the first configuration information to the terminal device, which can be referred to in step S1201 and will not be repeated here.

[0257] Step S1803: The terminal device extracts the associated IDs of setA and setB.

[0258] Specifically, the terminal device extracts the associated IDs of setA and setB, including: the terminal device determines the associated IDs corresponding to the first set (setA) associated with the first configuration information and the associated IDs corresponding to the second set (setB) associated with the first configuration information. For details, please refer to the relevant description in step S1202, which will not be repeated here.

[0259] Step S1804: The terminal device determines whether the associated identifier is missing.

[0260] Specifically, the terminal device determines whether the associated identifier is missing, including: the terminal device determines that the associated identifier corresponding to the first set (setA) associated with the first configuration information is in the first state, and / or the associated identifier corresponding to the second set (setB) associated with the first configuration information is in the first state. For details, please refer to the relevant description in step S1202, which will not be repeated here.

[0261] Step S1805: The terminal device completes the missing association identifier.

[0262] Specifically, the terminal device completes the missing association identifier by determining the value of the association identifier in the first state and completing it. For details, please refer to the relevant description in step S1203, which will not be repeated here.

[0263] Step S1806: The terminal device completes data classification.

[0264] Specifically, the terminal device completes data classification based on the missing association identifiers.

[0265] In the method described in Figure 18, after the terminal device receives the first configuration information, it can determine that the association identifier corresponding to a certain set associated with the first configuration information is in a missing state, or that the association identifiers corresponding to both sets associated with the first configuration information are in a missing state. Then, the value of the association identifier in the missing state is determined, and the dataset is classified based on the determined value of the association identifier in the missing state. In this way, the dataset can be correctly classified even when the association identifier is missing, avoiding the problem of classification error caused by missing association identifier configuration.

[0266] In the above embodiments, the deployment of the terminal-side AI model can be implemented on a chip inside the terminal device or in a location outside the device, such as in the host of an over-the-top (OTT) system or a cloud server. The network side needs to issue CSI-RS instructions and configure different CSI-RS resources to support the scanning of the terminal-side AI model. These functions can be performed by the network device. It should be noted that Figure 19 takes terminal-side AI model training as an example. Please refer to Figure 19. Figure 19 is a schematic diagram of another dataset classification method provided by the embodiments of this application. The method shown in Figure 19 can be applied to both terminal-side devices and network-side devices. The terminal-side device can be a terminal device, or a component applied in the terminal device (e.g., processor, chip, circuit, or chip system, etc.), or a logic module or software that can realize all or part of the functions of the terminal device. The network-side device can be a network device, or a component applied in the network device (e.g., processor, chip, circuit, or chip system, etc.), or a logic module or software that can realize all or part of the functions of the network device. The embodiment shown in Figure 19 below uses a terminal-side device as a terminal device and a network-side device as a network device for description. The method includes, but is not limited to, the following steps:

[0267] Step S1901: Network devices jointly encode and compress the representation.

[0268] Step S1902: The network device sends an association identifier to the terminal device.

[0269] The association identifier is the association identifier corresponding to the first set and / or the association identifier corresponding to the second set.

[0270] Step S1903: The network device sends a first set (setA) and / or a second set (setB) to the terminal device.

[0271] Accordingly, the terminal device receives a first set (setA) and / or a second set (setB) from the network device.

[0272] It should be noted that steps S1902 and S1903 can be executed simultaneously or at different times, and this application embodiment does not limit this.

[0273] It should be noted that after steps S1902 and S1903, the terminal device determines that the associated identifier corresponding to the first set is in a first state, and / or the associated identifier corresponding to the second set is in a first state, and the terminal device determines the value of the associated identifier in the first state. Refer to the relevant descriptions in steps S1202 and S1203 for details.

[0274] Step S1904: The terminal device sends the second set (setB) and the associated identifier corresponding to the second set (setB) to the OTT system.

[0275] Step S1905: OTT system retrieval and merging, mixed training.

[0276] Step S1906: The OTT system sends the training results to the terminal device.

[0277] Step S1907: The terminal device generates a training report.

[0278] Step S1908: The terminal device reports the model training results to the network device.

[0279] In the method described in Figure 19, after the terminal device receives the first configuration information, it can determine that the association identifier corresponding to a certain set associated with the first configuration information is in a missing state, or that the association identifiers corresponding to both sets associated with the first configuration information are in a missing state. Then, the value of the association identifier in the missing state is determined, and the dataset is classified based on the determined value of the association identifier in the missing state. In this way, the dataset can be correctly classified even when the association identifier is missing, avoiding the problem of classification error caused by missing association identifier configuration.

[0280] The methods of the embodiments of this application have been described in detail above, and the apparatus of the embodiments of this application is provided below.

[0281] Please refer to Figure 20. Figure 20 is a schematic diagram of the structure of a dataset classification device 2000 provided in an embodiment of this application. The dataset classification device 2000 may include modules, units, or means that correspond one-to-one with the methods / operations / steps / actions executed by the terminal-side device or network-side device in the above method embodiments. The modules, units, or means may be hardware circuits, software, or a combination of hardware circuits and software.

[0282] In one possible implementation, the dataset classification device 2000 may include a processing unit 2001 and a transceiver unit 2002, the specific details of which are as follows:

[0283] The processing unit 2001 is used for data processing. The transceiver unit 2002 can implement corresponding communication functions. The transceiver unit 2002 can also be called a communication interface or a communication module.

[0284] Optionally, the dataset classification device 2000 may further include a storage unit, which can be used to store instructions and / or data. The processing unit 2001 can read the instructions and / or data in the storage module to enable the implementation of the aforementioned method embodiments.

[0285] Optionally, the transceiver unit 2002 may include a sending unit and a receiving unit. The sending unit is used to perform the sending operation in the above method embodiments. The receiving unit is used to perform the receiving operation in the above method embodiments.

[0286] It should be noted that the dataset classification device 2000 may include a sending unit but not a receiving unit. Alternatively, the dataset classification device 2000 may include a receiving unit but not a sending unit. Specifically, it depends on whether the above-described scheme executed by the dataset classification device 2000 includes both sending and receiving actions.

[0287] Optionally, the dataset classification device 2000 is used to perform the actions performed by the terminal-side device in the embodiments shown in Figures 12, 18, or 19 above. For details, please refer to the relevant descriptions in the embodiments shown in Figures 12, 18, or 19 above; they will not be elaborated upon here. For example, the dataset classification device 2000 is used to perform the following scheme:

[0288] The transceiver unit 2002 is used to receive first configuration information, which is used to configure parameters related to data collection; the processing unit 2001 is used to determine that the association identifier corresponding to the first set associated with the first configuration information is in a first state, and / or the association identifier corresponding to the second set associated with the first configuration information is in a first state; the processing unit 2001 is also used to determine the value of the association identifier in the first state, which is used for dataset classification.

[0289] In one possible implementation, the association identifier corresponding to the second set associated with the first configuration information is in a first state, and the processing unit 2001 is further configured to determine that the association identifier corresponding to the first set associated with the first configuration information is in a second state.

[0290] In another possible implementation, the processing unit 2001 is used to determine that the value of the association identifier in the first state is the value of the association identifier corresponding to the first set associated with the first configuration information.

[0291] In another possible implementation, the transceiver unit 2002 is configured to receive the first configuration information at time t, and the transceiver unit 2002 is also configured to receive the second configuration information at time (tk), the second configuration information being used to configure parameters related to data collection, and the association identifier corresponding to the second set associated with the second configuration information being in a second state; the processing unit 2001 is configured to determine that the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the second configuration information.

[0292] In another possible implementation, the transceiver unit 2002 is further configured to receive third configuration information, wherein the association identifier corresponding to the first set associated with the third configuration information is in a second state, and the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information.

[0293] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a second state, and the processing unit 2001 is used to determine that the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the third configuration information.

[0294] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a first state, and the processing unit 2001 is used to determine that the first data pair associated with the first configuration information and the third data pair associated with the third configuration information are the same type of dataset.

[0295] In another possible implementation, the association identifier corresponding to the first set associated with the first configuration information is in a first state, and the association identifier corresponding to the second set associated with the first configuration information is in a first state. The transceiver unit 2002 is further configured to receive fourth configuration information, wherein the association identifier corresponding to the first set associated with the fourth configuration information is in a first state, and the association identifier corresponding to the second set associated with the fourth configuration information is in a first state. The processing unit 2001 is further configured to determine that the first data pair associated with the first configuration information and the fourth data pair associated with the fourth configuration information are the same type of dataset.

[0296] In another possible implementation, the first state represents the missing state, and the second state represents the not-missing state.

[0297] It should be noted that the implementation and beneficial effects of each module can also be described in the corresponding descriptions of the method embodiments shown in Figures 12, 18 or 19.

[0298] Optionally, the dataset classification device 2000 is used to perform the actions performed by the network-side device in the embodiments shown in Figures 12, 18, or 19 above. For details, please refer to the relevant descriptions in the embodiments shown in Figures 12, 18, or 19 above; they will not be elaborated here. For example, the dataset classification device 2000 is used to perform the following scheme:

[0299] The processing unit 2001 is used to send first configuration information through the transceiver unit 2002. The first configuration information is used to configure parameters related to data collection. The association identifier corresponding to the first set associated with the first configuration information is in a first state, and / or the association identifier corresponding to the second set associated with the first configuration information is in a first state.

[0300] In one possible implementation, the association identifier corresponding to the second set associated with the first configuration information is in a first state, and the association identifier corresponding to the first set associated with the first configuration information is in a second state.

[0301] In another possible implementation, the value of the association identifier in the first state is the value of the association identifier corresponding to the first set associated with the first configuration information.

[0302] In another possible implementation, the transceiver unit 2002 is used to send the first configuration information at time t, and the transceiver unit 2002 is also used to send the second configuration information at time (tk). The second configuration information is used to configure parameters related to data collection. The association identifier corresponding to the second set associated with the second configuration information is in a second state, and the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the second configuration information.

[0303] In another possible implementation, the transceiver unit 2002 is further configured to send third configuration information, wherein the association identifier corresponding to the first set associated with the third configuration information is in a second state, and the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information.

[0304] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a second state, and the value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the third configuration information.

[0305] In another possible implementation, the association identifier corresponding to the second set associated with the third configuration information is in a first state, and the first data pair associated with the first configuration information and the third data pair associated with the third configuration information are the same type of dataset.

[0306] In another possible implementation, the association identifier corresponding to the first set associated with the first configuration information is in a first state, and the association identifier corresponding to the second set associated with the first configuration information is in a first state. The transceiver unit 2002 is further configured to send fourth configuration information, wherein the association identifier corresponding to the first set associated with the fourth configuration information is in a first state, and the association identifier corresponding to the second set associated with the fourth configuration information is in a first state; the first data pair associated with the first configuration information and the fourth data pair associated with the fourth configuration information are of the same type of dataset.

[0307] In another possible implementation, the first state represents the missing state, and the second state represents the not-missing state.

[0308] It should be noted that the implementation and beneficial effects of each module can also be described in accordance with the corresponding descriptions of the method embodiments shown in Figures 12, 18, or 19. The module division in this application embodiment is illustrative and is merely a logical functional division; in actual implementation, there may be other division methods.

[0309] The processing unit 2001 in the above embodiments can be implemented by at least one processor or processor-related circuitry. The transceiver unit 2002 can be implemented by a transceiver or transceiver-related circuitry. The transceiver unit 2002 can also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0310] Please refer to Figure 21. Figure 21 is a schematic diagram of the structure of a dataset classification device 2100 provided in an embodiment of this application. The dataset classification device 2100 may include modules, units, or means that correspond one-to-one with the methods / operations / steps / actions executed by the terminal-side device or network-side device in the above method embodiments. The modules, units, or means may be hardware circuits, software, or a combination of hardware circuits and software.

[0311] The dataset classification device 2100 includes at least one processor 2101. Optionally, it also includes a communication interface 2103 and a memory 2102. The processor 2101, memory 2102, and communication interface 2103 are interconnected via a bus 2104. Optionally, the processor 2101 and memory 2102 can be integrated together.

[0312] The memory 2102 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), and is used for related computer programs and data. The communication interface 2103 is used for receiving and sending data.

[0313] The processor 2101 can be one or more central processing units (CPUs). When the processor 2101 is a CPU, the CPU can be a single-core CPU or a multi-core CPU.

[0314] The processor 2101 in the dataset classification device 2100 is used to read computer programs or instructions stored in the memory 2102 to implement the functions of the above-mentioned processing unit, and the communication interface 2103 in the dataset classification device 2100 is used to implement the functions of the above-mentioned transceiver unit.

[0315] Please refer to Figure 22, which is a schematic diagram of a chip system architecture provided in an embodiment of this application. This chip system architecture can be used in network-side devices and / or terminal-side devices. Input / output control is used to manage the input and output signals of the device; for example, input / output control can be represented as a modem, keyboard, mouse, touchscreen, etc. Input / output control may also be part of a processor. In one possible implementation, the chip input corresponds to the receiving operation in any of the above embodiments, and the chip output corresponds to the transmitting operation in any of the above embodiments. The receiver / transmitter is used to communicate with other devices. The receiver / transmitter may include a modem for modulating information or demodulating modulated information. The antenna is used to transmit or receive signals. Communication control is used to establish a connection. Storage may include random access memory (RAM) or read-only memory (ROM). Storage may be used to store code that can be executed by a processor to implement corresponding functions. Processors may include intelligent hardware devices such as general-purpose processors, digital signal processors (DSPs), central processing units (CPUs), field-programmable gate arrays (FPGAs), graphics processing units (GPUs), neural processing units, etc.

[0316] In one example, please refer to Figure 23, which is a schematic diagram of the interaction between a terminal-side device and a network-side device provided in an embodiment of this application. Taking a chip system architecture for the terminal-side device as an example, the terminal-side device establishes a communication connection with the network-side device through a communication control module. The terminal-side device receives signaling and reference signals sent by the network-side device through an antenna and a receiver, and sends a CSI report to the network-side device through a transmitter and an antenna. The terminal-side device processes the measurement results of each measurement through a processor and stores the measurement results in a memory.

[0317] This application also provides a computer-readable storage medium storing a computer program or instructions that, when executed on a processor, implement the method performed by a terminal-side device or a network-side device in the above method embodiments.

[0318] This application also provides a computer program product, which includes a computer program or instructions that, when run on a processor, implement the method executed by the terminal-side device or network-side device in the above method embodiments.

[0319] This application also provides a communication system, which includes the terminal-side device and the network-side device described in the above embodiments. The terminal-side device is used to perform some or all of the operations performed by the terminal-side device in the above method embodiments, and the network-side device is used to perform some or all of the operations performed by the network-side device in the above method embodiments.

[0320] It is understood that the processor in the embodiments of this application may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0321] The method steps in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a base station or terminal. Of course, the processor and storage medium can also exist as discrete components in the base station or terminal.

[0322] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0323] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0324] In the description of this application, terms such as "first", "second", "S1201" or "S1202" are used only for the purpose of distinguishing descriptions and for the convenience of context. Different sequence numbers do not have specific technical meanings themselves and should not be construed as indicating or implying relative importance, nor should they be construed as indicating or implying the order of execution of operations. The order of execution of each process should be determined by its function and internal logic.

Claims

1. A dataset classification method, characterized in that, include: Receive first configuration information, which is used to configure parameters related to data collection; Determine that the association identifier corresponding to the first set associated with the first configuration information is in a first state, and / or the association identifier corresponding to the second set associated with the first configuration information is in a first state; The value of the association identifier in the first state is determined, and the determined value of the association identifier in the first state is used for dataset classification.

2. The method according to claim 1, characterized in that, The association identifier corresponding to the second set associated with the first configuration information is in a first state, and the method further includes: It is determined that the association identifier corresponding to the first set associated with the first configuration information is in the second state.

3. The method according to claim 2, characterized in that, Determining the value of the associated identifier in the first state includes: The value of the associated identifier in the first state is determined to be the value of the associated identifier corresponding to the first set associated with the first configuration information.

4. The method according to claim 2, characterized in that, The method of receiving the first configuration information includes: receiving the first configuration information at time t, and the method further includes: At time (tk), the second configuration information is received. The second configuration information is used to configure parameters related to data collection. The association identifier corresponding to the second set associated with the second configuration information is in the second state. Determining the value of the associated identifier in the first state includes: The value of the association identifier in the first state is determined to be the value of the association identifier corresponding to the second set associated with the second configuration information.

5. The method according to claim 2, characterized in that, The method further includes: Receive third configuration information, wherein the association identifier corresponding to the first set associated with the third configuration information is in a second state, and the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information.

6. The method according to claim 5, characterized in that, The association identifier corresponding to the second set associated with the third configuration information is in a second state. Determining the value of the association identifier in the first state includes: The value of the association identifier in the first state is determined to be the value of the association identifier corresponding to the second set associated with the third configuration information.

7. The method according to claim 5, characterized in that, The association identifier corresponding to the second set associated with the third configuration information is in a first state, and the method further includes: It is determined that the first data pair associated with the first configuration information and the third data pair associated with the third configuration information are of the same type of dataset.

8. The method according to claim 1, characterized in that, The method further includes: The association identifier corresponding to the first set associated with the first configuration information is in a first state, and the association identifier corresponding to the second set associated with the first configuration information is in a first state. Receive fourth configuration information, wherein the association identifier corresponding to the first set associated with the fourth configuration information is in a first state, and the association identifier corresponding to the second set associated with the fourth configuration information is in a first state; It is determined that the first data pair associated with the first configuration information and the fourth data pair associated with the fourth configuration information are of the same type of dataset.

9. The method according to any one of claims 2-8, characterized in that, The first state represents the missing state, and the second state represents the not missing state.

10. A dataset classification method, characterized in that, include: Send first configuration information, which is used to configure parameters related to data collection. The association identifier corresponding to the first set associated with the first configuration information is in a first state, and / or the association identifier corresponding to the second set associated with the first configuration information is in a first state.

11. The method according to claim 10, characterized in that, The association identifier corresponding to the second set associated with the first configuration information is in a first state, and the association identifier corresponding to the first set associated with the first configuration information is in a second state.

12. The method according to claim 11, characterized in that, The value of the association identifier in the first state is the value of the association identifier corresponding to the first set associated with the first configuration information.

13. The method according to claim 11, characterized in that, Sending the first configuration information includes: sending the first configuration information at time t, and the method further includes: At time (tk), a second configuration information is sent. The second configuration information is used to configure parameters related to data collection. The association identifier corresponding to the second set associated with the second configuration information is in a second state. The value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the second configuration information.

14. The method according to claim 11, characterized in that, The method further includes: Send third configuration information, wherein the association identifier corresponding to the first set associated with the third configuration information is in a second state, and the value of the association identifier corresponding to the first set associated with the third configuration information is equal to the value of the association identifier corresponding to the first set associated with the first configuration information.

15. The method according to claim 14, characterized in that, The association identifier corresponding to the second set associated with the third configuration information is in the second state. The value of the association identifier in the first state is the value of the association identifier corresponding to the second set associated with the third configuration information.

16. The method according to claim 14, characterized in that, The association identifier corresponding to the second set associated with the third configuration information is in the first state. The first data pair associated with the first configuration information and the third data pair associated with the third configuration information are of the same type of dataset.

17. The method according to claim 10, characterized in that, The method further includes: The association identifier corresponding to the first set associated with the first configuration information is in a first state, and the association identifier corresponding to the second set associated with the first configuration information is in a first state. Send fourth configuration information, wherein the association identifier corresponding to the first set associated with the fourth configuration information is in a first state, and the association identifier corresponding to the second set associated with the fourth configuration information is in a first state; The first data pair associated with the first configuration information and the fourth data pair associated with the fourth configuration information are of the same type of dataset.

18. The method according to any one of claims 11-17, characterized in that, The first state represents the missing state, and the second state represents the not missing state.

19. A dataset classification device, characterized in that, The apparatus includes units for performing the steps of the method as described in any one of claims 1-18.

20. A dataset classification device, characterized in that, The apparatus includes at least one processor, which is configured to invoke a computer program or instructions stored in a memory to perform the method as described in any one of claims 1-18.

21. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions that, when executed on a processor, implement the method as described in any one of claims 1-18.

22. A computer program product, characterized in that, The computer program product includes a computer program or instructions that, when run on a processor, implement the method as described in any one of claims 1-18.

23. A system, characterized in that, Includes apparatus for performing the method as claimed in any one of claims 1-9 and apparatus for performing the method as claimed in any one of claims 10-18.

Images