Information sending method and apparatus, information receiving method and apparatus, and communication system

Abstract

Embodiments of the present application provide an information receiving method and apparatus, an information sending method and apparatus, and a communication system. The information sending apparatus comprises a first processing unit, the first processing unit controlling a terminal device to perform the following operations: the terminal device acquiring data related to channel state information (CSI); and the terminal device sending the data and first information to a network device, the first information being information related to a layer index and / or layer sorting of the data.

Description

Methods, apparatus and communication systems for sending and receiving information Technical Field

[0001] The embodiments of this application relate to the field of communication technology. Background Technology

[0002] In 3GPP Release 18, the application of Artificial Intelligence (AI) and Machine Learning (ML) models or functions—specifically AI / ML models or functions—to the air interface was studied. This included applying AI / ML models or functions to Channel State Information (CSI) feedback compression. AI / ML-based CSI feedback compression employs a two-sided model, where the AI / ML model or function resides on both the User Equipment (UE) side and the Network (NW) side (i.e., the gNB side). In Rel-18, AI / ML-based feedback compression compresses CSI in the spatial frequency domain (SF) (SF-AI / ML CSI compression).

[0003] For example, for a two-sided model, on the UE side, the UE performs measurements on a reference signal (e.g., Channel State Information-Reference Signal, CSI-RS) to obtain the radio channel; then, the UE can further obtain the feature vector of the radio channel, and this feature vector will be used as the input of the AI / ML model or function on the UE side, i.e., the input of the encoder, to compress the CSI; then, the UE sends the output of the encoder as a CSI feedback report or to the gNB; the gNB uses the received CSI feedback as the input of the AI / ML model or function on the gNB side, i.e., the input of the decoder; after decompression using the decoder, the decoder outputs the reconstructed CSI.

[0004] In Release 19, a further investigation was conducted on the AI / ML-based CSI compression feedback enhancement sub-use case (TSF-AI / ML CSI compression) in the temporal spatial frequency (TSF) domain. This sub-use case utilizes historical CSI information through AI / ML methods (e.g., RNN / GRU / LSTM models) to assist in CSI compression at the current moment, aiming to achieve a lower compression ratio or higher feedback accuracy.

[0005] It should be noted that the above introduction to the technical background is only for the purpose of providing a clear and complete explanation of the technical solutions of this application and facilitating understanding by those skilled in the art. It should not be assumed that these technical solutions are known to those skilled in the art simply because they have been described in the background section of this application.

[0006] Summary of the Invention

[0007] Operations targeting AI / ML models or functions can include: model inference, model performance monitoring, and data collection for model training.

[0008] For CSI compression using a bilateral model, during model inference, the UE-side model performs CSI compression, while the gNB-side model performs decompression. During model performance monitoring, the UE reports the ground truth CSI to the gNB; in some cases, the ground truth CSI can be reported based on a high-resolution codebook. During model training data collection, the UE collects the ground truth CSI; in some cases, the ground truth CSI can be reported based on a high-resolution codebook.

[0009] The inventors discovered that for spatiotemporal frequency domain CSI compression feedback, there is no corresponding mechanism to ensure the consistency of the temporal layer order of the feedback CSI during the inference phase. This results in the temporal information of layer X helping to compress the CSI information of layer Y at the current moment. Furthermore, for data collection methods based on legacy codebooks, the collected data is unaware of its layer index / layer order. Once the layer order changes, it will lead to poor model training performance or incorrect calculation of model monitoring performance values. Therefore, ensuring the consistency of layer indexes and / or layer order is a technical problem that needs to be solved.

[0010] To address one or more of the above-mentioned problems, embodiments of this application provide a method, apparatus, and communication system for sending and receiving information.

[0011] According to one aspect of the embodiments of this application, an apparatus for transmitting information is provided, applied to a terminal device, the apparatus including a first processing unit, the first processing unit controlling the terminal device to perform the following operations:

[0012] The terminal device acquires data related to Channel State Information (CSI); and

[0013] The terminal device sends the data and first information to the network device, wherein the first information is information related to the layer index and / or layer sorting of the data.

[0014] According to another aspect of the embodiments of this application, an apparatus for receiving information is provided, applied to a network device, characterized in that the apparatus includes a second processing unit, the second processing unit controlling the network device to perform the following operations:

[0015] Sending Channel State Information Reference Signal (CSI-RS) to terminal equipment; and

[0016] The terminal device receives channel state information (CSI) related data and first information, wherein the first information is information related to the layer index and / or layer order of the data.

[0017] One of the beneficial effects of this application embodiment is that: the terminal device sends the layer index and / or layer sorting related information of the data to the network device, thereby, during the model inference, model performance monitoring and model training stages, the layer index and / or layer sorting related information of the data can be perceived, thereby ensuring the performance of AI / ML model training, inference and monitoring, and improving the performance of the communication system.

[0018] Specific embodiments of this application are disclosed in detail with reference to the following description and accompanying drawings, indicating how the principles of this application can be adopted. It should be understood that the embodiments of this application are not limited in scope. Within the spirit and scope of the appended claims, embodiments of this application include many changes, modifications, and equivalents.

[0019] Features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0020] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, whole, step, or component, but does not exclude the presence or addition of one or more other features, wholes, steps, or components. Attached Figure Description

[0021] The elements and features described in one drawing or embodiment of this application may be combined with elements and features shown in one or more other drawings or embodiments. Furthermore, in the drawings, similar reference numerals denote corresponding parts in several drawings and can be used to indicate corresponding parts used in more than one embodiment.

[0022] Figure 1 is a schematic diagram of a communication system according to an embodiment of this application;

[0023] Figure 2 is a schematic diagram of feedback enhancement for AI / ML-based CSI compression (TSF-AI / ML CSI compression) in the spatiotemporal frequency domain;

[0024] Figure 3 is a schematic diagram of a method for sending information according to an embodiment of this application;

[0025] Figure 4(A) is a schematic diagram showing the reporting layer index / layer sorting;

[0026] Figure 4(B) is a schematic diagram of implicit reporting layer index / layer sorting;

[0027] Figure 5 is a schematic diagram of the mapping relationship between feature vectors and layers in an embodiment of this application;

[0028] Figure 6 is a schematic diagram of the mapping relationship between PMI and layer in an embodiment of this application;

[0029] Figure 7 is a schematic diagram of the mapping relationship between the ground truth channel feature vector and the layer in an embodiment of this application;

[0030] Figure 8 is a schematic diagram of a method for receiving information according to an embodiment of the second aspect of this application;

[0031] Figure 9 is a schematic diagram of an information transmission device according to an embodiment of this application;

[0032] Figure 10 is a schematic diagram of an information receiving device according to an embodiment of this application;

[0033] Figure 11 is a schematic block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0034] Referring to the accompanying drawings, the foregoing and other features of this application will become apparent from the following description. Specific embodiments of this application are specifically disclosed in the description and drawings, illustrating partial implementations in which the principles of this application can be adopted. It should be understood that this application is not limited to the described embodiments; rather, it includes all modifications, variations, and equivalents falling within the scope of the appended claims. Various embodiments of this application are described below with reference to the accompanying drawings. These embodiments are merely exemplary and not intended to limit the scope of this application.

[0035] In the embodiments of this application, the terms "first," "second," etc., are used to distinguish different elements by name, but do not indicate the spatial arrangement or chronological order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one or more of the terms listed in association and all combinations thereof. The terms "comprising," "including," "having," etc., refer to the presence of the stated features, elements, components, or assemblies, but do not exclude the presence or addition of one or more other features, elements, components, or assemblies.

[0036] In the embodiments of this application, the singular forms "a," "the," etc., including the plural forms, should be broadly understood as "a kind" or "a class" rather than limited to the meaning of "an." Furthermore, the term "the" should be understood to include both the singular and plural forms, unless the context explicitly indicates otherwise. Additionally, the term "according to" should be understood as "at least partially based on…," and the term "based on" should be understood as "at least partially based on…," unless the context explicitly indicates otherwise.

[0037] In the embodiments of this application, the term "communication network" or "wireless communication network" may refer to a network that conforms to any of the following communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), etc.

[0038] Furthermore, communication between devices in a communication system can be carried out according to communication protocols at any stage, including but not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G and 5G, New Radio (NR), 6G and future communication, and / or other currently known or future communication protocols.

[0039] In the embodiments of this application, the term "network device" refers, for example, to a device in a communication system that connects a terminal device to a communication network and provides services to that terminal device. Network devices may include, but are not limited to, the following devices: base station (BS), access point (AP), transmission reception point (TRP), broadcast transmitter, mobile management entity (MME), gateway, server, radio network controller (RNC), base station controller (BSC), etc.

[0040] The term "base station" can include, but is not limited to, NodeBs (or NBs), evolved NodeBs (eNodeBs or eNBs), 5G base stations (gNBs), 6G base stations, and future base stations, etc. It can also include Remote Radio Heads (RRHs), Remote Radio Units (RRUs), relays, or low-power nodes (e.g., femto, pico, etc.). The term "base station" can encompass some or all of its functions, and each base station can provide communication coverage to a specific geographic area. The term "cell" can refer to a base station and / or its coverage area, depending on the context in which the term is used.

[0041] In the embodiments of this application, the terms "User Equipment" (UE) or "Terminal Equipment" (TE) refer, for example, to a device that accesses a communication network and receives network services through a network device. User equipment can be fixed or mobile, and may also be referred to as a mobile station (MS), terminal, user, subscriber station (SS), access terminal (AT), station, mobile terminal (MT), etc.

[0042] The terminal device may include, but is not limited to, the following devices: cellular phone, personal digital assistant (PDA), wireless modem, wireless communication device, handheld device, machine-type communication device, laptop computer, cordless phone, smartphone, smartwatch, digital camera, etc.

[0043] For example, in scenarios such as the Internet of Things (IoT), user devices can also be machines or devices used for monitoring or measurement, including but not limited to: machine-type communication (MTC) terminals, vehicle-mounted communication terminals, device-to-device (D2D) terminals, machine-to-machine (M2M) terminals, terminals that support sidelink communication, and so on.

[0044] Furthermore, the terms "network side" or "network equipment side" refer to one side of the network, which can be a base station or include one or more network devices as described above. The terms "user side," "terminal side," or "terminal equipment side" refer to the side of the user or terminal, which can be a UE or include one or more terminal devices as described above. Unless otherwise specified, "equipment" can refer to either network equipment or terminal equipment.

[0045] Without causing confusion, the terms “uplink control signal” and “uplink control information (UCI)” or “physical uplink control channel (PUCCH)” are interchangeable, as are the terms “uplink data signal” and “uplink data information (PUSCH)”.

[0046] The terms “downlink control signal” and “downlink control information (DCI)” or “physical downlink control channel (PDCCH)” are interchangeable, as are the terms “downlink data signal” and “downlink data information (PDSCH)” or “physical downlink shared channel (PDSCH)”.

[0047] Additionally, uplink signals can include uplink data signals and / or uplink control signals and / or PRACH and / or SRS (sounding reference signal), etc., and can also be referred to as uplink transmission (UL transmission), uplink information, or uplink channel. Sending / receiving uplink transmission on uplink resources can be understood as using that uplink resource to send / receive the uplink transmission. Downlink signals can include downlink data signals and / or downlink control signals and / or synchronization signals (SS, such as PSS / SSS) and / or broadcast channel (PBCH) and / or SSB (SS / PBCH block, including PSS, SSS, and PBCH and their DMRS) and / or CSI-RS, etc., and can also be referred to as downlink transmission (DL transmission), downlink information, or downlink channel. Sending / receiving downlink transmission on downlink resources can be understood as using that downlink resource to send / receive the downlink transmission.

[0048] In the embodiments of this application, higher-layer signaling may be, for example, Radio Resource Control (RRC) signaling; RRC signaling may include, for example, RRC messages, such as broadcast / public RRC messages / signaling (e.g., Master Information Block (MIB), System Information (SI), Private RRC messages / signaling; or RRC Information Element (RRC IE); or information fields (or information fields included in information fields) included in RRC messages or RRC Information Elements. Higher-layer signaling may also be, for example, Medium Access Control (MAC) signaling; or MAC control element (MAC CE). However, this application is not limited to these.

[0049] In the embodiments of this application, "at least one" and "one or more" can be used interchangeably, and "multiple" and "more than one" can be used interchangeably. "Multiple" means at least two, or two or more.

[0050] In this application embodiment, "predefined" refers to what is specified by the protocol or determined according to the rules specified by the protocol, and does not require additional configuration. "Configuration / instruction" refers to what the network device directly or indirectly configures / instructs through higher-layer signaling and / or physical layer signaling. Configuration / instruction can be achieved by introducing higher-layer parameters into the higher-layer signaling. Higher-layer parameters refer to information fields and / or information elements / information units / information cells (IEs) in the higher-layer signaling. Physical layer signaling refers to, for example, control information (DCI) carried by the physical downlink control channel or control information carried by the sequence, but is not limited to these.

[0051] For ease of description, the following text uses a base station as an example of an access network device.

[0052] In the following explanation, without causing confusion, “if…”, “in the case of…” and “when…” can be used interchangeably.

[0053] The following examples illustrate the scenarios of embodiments of this application, but this application is not limited thereto.

[0054] Figure 1 is a schematic diagram of a communication system according to an embodiment of this application, illustrating the case of a terminal device and a network device as examples. As shown in Figure 1, the communication system 100 may include a network device 101, a terminal device 102, and a terminal device 103. For simplicity, Figure 1 only illustrates the case of two terminal devices and one network device, but the embodiments of this application are not limited to this.

[0055] In this embodiment of the application, network device 101, terminal device 102, and terminal device 103 can transmit existing services or services that can be implemented in the future. For example, these services may include, but are not limited to: enhanced mobile broadband (eMBB), massive machine-type communication (mMTC), ultra-reliable and low-latency communication (URLLC), and related communications of terminal devices with reduced capabilities, etc.

[0056] Terminal devices 102 and 103 can be in RRC_IDLE, RRC_INACTIVE, or RRC_CONNECTED states. Terminal devices 102 and 103 can also communicate with network device 101. For example, taking terminal device 102 as an example, terminal device 102 can send data to network device 101 or perform data retransmission. Network device 101 can send paging messages to terminal device 102 or send data to terminal device 102, and terminal device 102 can receive data sent by network device 101. Furthermore, different terminal devices can also communicate with each other; for example, terminal device 102 and terminal device 103 can exchange data.

[0057] It is worth noting that Figure 1 shows that both terminal device 102 and terminal device 103 are within the coverage area of ​​network device 101, but this application is not limited to this. Terminal device 102 and terminal device 103 may both be outside the coverage area of ​​network device 101, or one of terminal device 102 and terminal device 103 may be within the coverage area of ​​network device 101 while the other is outside the coverage area of ​​network device 101.

[0058] In the embodiments of this application, one or more AI / ML models can be configured and run in network devices and / or terminal devices. AI / ML models can be used for various signal processing functions in wireless communication, such as CSI prediction, CSI compression, beam prediction, positioning management, etc.; this application is not limited thereto.

[0059] Figure 2 is a schematic diagram of spatiotemporal frequency domain-based AI / ML-based CSI compression feedback enhancement (TSF-AI / ML CSI compression). As shown in Figure 2, on the UE side, the CSI measurement results are subjected to matrix decomposition (e.g., SVD decomposition (singular value decomposition) or EVD decomposition (eigenvalue decomposition)) to obtain a feature vector. This feature vector is input to the encoder, which generates CSI feedback information. On the network side, the decoder decodes the CSI feedback information sent by the UE to generate the reconstructed CSI.

[0060] In some embodiments, the encoder and decoder on the UE side can employ AI / ML methods (e.g., RNN / LSTM / GRU cascaded Transformer / CNN models). AI / ML methods can utilize temporal information (also known as historical CSI information, side information, or similar names) to assist in current CSI compression and / or decompression, aiming to achieve higher compression ratios or higher feedback accuracy.

[0061] When using time-domain information for CSI compression and / or decompression, the availability and / or usability of this information are easily affected by factors such as rank changes, CSI dropping (e.g., layer-priority-based CSI dropping), and loss of uplink control information (UCI). When time-domain information is unavailable or cannot be obtained, the performance of the AI / ML model will deteriorate, or it may even become unusable.

[0062] Furthermore, the temporal relevance of CSI determines whether historical CSI information is helpful for current CSI compression and / or decompression. Too low a relevance will result in invalid input to the AI / ML model, which will not only fail to improve CSI compression performance but may even be treated as noise by the AI / ML model, leading to performance degradation. Therefore, AI / ML is more suitable for scenarios with good temporal CSI relevance, typically corresponding to low UE movement speeds or layers with low rank values ​​and / or large eigenvalues.

[0063] In the embodiments of this application, CSI compression can also be called "CSI encoding", "CSI generation" or similar names, and the results of CSI compression, CSI encoding or CSI generation operations are called CSI feedback information, CSI reporting information or similar names.

[0064] In the embodiments of this application, CSI decompression may also be referred to as "CSI decoding", "CSI reconstruction", "CSI recovery", "CSI rebuilding" or similar names.

[0065] In the embodiments of this application, the AI / ML model may also be referred to as an AI / ML method, AI / ML unit, AI / ML function, or AI / ML element, or similar names. On the UE side, the AI / ML model may also be referred to as an encoder, CSI generation part, or similar names. On the network device side, the AI / ML model may also be referred to as a decoder, CSI reconstruction part, or similar names.

[0066] It should be noted that the use cases applicable to the operation processing methods of AI / ML models or functions in the embodiments of this application include, but are not limited to, CSI compression feedback. However, those skilled in the art will understand that the embodiments of this application are also applicable to various other use cases and / or scenarios that apply AI / ML models or functions.

[0067] First aspect of the embodiments

[0068] In the scenario of TSF-AI / ML CSI compression feedback enhancement in the spatiotemporal frequency domain, as shown in Figure 2, time-domain information (i.e., historical CSI information) needs to be utilized, and this time-domain information is divided into layers. When the rank is X, the time-domain information of layer 1 helps compress the layer 1 CSI information at the current time, the time-domain information of layer 2 helps compress the layer 2 CSI information at the current time, and so on, with layer X helping to compress the layer X CSI information at the current time.

[0069] In this scenario: During the training data collection phase, the collection of training data must ensure the consistency of the temporal layer order or that the layer order is perceptible; during the inference phase, if the layer order of the CSI reported by the terminal device (UE) changes and the network device (NW) cannot perceive this change, the temporal information of layer X will help compress the CSI information of layer Y at the current moment, resulting in performance degradation; during the model performance monitoring phase, the UE needs to report the true CSI (ground truth CSI) to the NW. The NW obtains the monitoring performance value by calculating the difference between the true CSI (ground truth CSI) and the reconstructed CSI for each layer. When the layer order between the ground truth CSI and the reconstructed CSI is inconsistent, the monitoring performance value calculation is incorrect, which leads to inaccurate subsequent Life Cycle Management (LCM) operations and affects the performance of the communication system.

[0070] To address the aforementioned problems or at least similar issues, embodiments of this application provide a method for transmitting information, which is applied to a multiple-antenna (MIMO) communication system and will be described from the perspective of a terminal device.

[0071] Figure 3 is a schematic diagram of a method for sending information according to an embodiment of this application. As shown in Figure 3, from the perspective of the terminal device (UE), the method includes:

[0072] 301: The terminal device acquires data related to Channel State Information (CSI); and

[0073] 302: The terminal device sends the data and first information to the network device, wherein the first information is information related to the layer index and / or layer sorting of the data.

[0074] In some embodiments, the data in operations 301 and 302 includes at least one of the following:

[0075] Channel eigenvectors are used for channel state information (CSI) in downlink scheduling.

[0076] Wherein, the channel feature vector is a channel feature vector related to the collection of training data; and / or, the channel feature vector is a channel feature vector related to the collection of performance monitoring data.

[0077] For example, in a CSI compression scenario, during the training data collection phase, the data in operations 301 and 302 may include: channel feature vectors related to the AI / ML model input, and ground-truth channel feature vectors related to the AI / ML model output. The ground-truth channel feature vector corresponds to the aforementioned "channel feature vector related to training data collection." This ground-truth channel feature vector is the true value that the AI / ML model output most wants to approximate.

[0078] For example, during the inference phase, the terminal device generates a compressed channel feature vector, which is, for example, a precoding matrix indication (PMI), and is included in the feedback CSI, which corresponds to the aforementioned "channel state information (CSI) for downlink scheduling".

[0079] For example, during the performance monitoring phase, the terminal device reports the ground-truth channel feature vector. The network device calculates the difference between the reconstructed channel feature vector and the ground-truth channel feature vector, and then obtains the monitoring performance of the AI / ML model. Here, the ground-truth channel feature vector corresponds to the "channel feature vector related to performance monitoring data collection" mentioned above. This ground-truth channel feature vector is the true value that the AI / ML model output most hopes to approximate.

[0080] In some embodiments, channel feature vectors can be reported based on a codebook. This codebook can be a legacy codebook or an enhanced legacy codebook. For example, channel feature vectors related to training data collection and / or performance monitoring data collection can be reported based on a legacy codebook or an enhanced legacy codebook. Alternatively, channel feature vectors can also be reported based on non-codebooks.

[0081] In some embodiments, during operation 302, the terminal device may explicitly send the first information. For example, the terminal device may send the first information via signaling. The data may contain one or more layers of channel feature vectors or channel state information, where the layer index and / or layer sorting information indicates the sequence number of the feature value corresponding to each layer of channel feature vector or channel state information in the data among all feature values.

[0082] In some instances of operation 302, the data is sent together with the first information.

[0083] In other examples of operation 302, the data and the first information are sent separately, and the first information is associated with the data.

[0084] In some examples of operation 302, the data is sent via Layer 1 signaling or non-Layer 1 signaling, and the first information is sent via channel state information reporting.

[0085] For example, the first information is transmitted through Part I of the channel state information reporting, wherein the maximum layer number of the data is Y_max, and the length of the information field used to carry the first information is:

[0086] or Or Y_max × Y_max.

[0087] For example, the first information is transmitted through Part II of the channel state information reporting, wherein the rank value of the channel state information reporting is X, and X may have a maximum value of X_max. The length of the information field used to carry the first information is:

[0088] or Or X×X, or

[0089] or Or X×X_max.

[0090] When the data includes the channel feature vector related to the training data collection or the channel feature vector related to the performance monitoring data collection, and the channel state information (CSI): the terminal device sends at least one of the first information corresponding to the channel feature vector related to the training data collection or the channel feature vector related to the performance monitoring data collection and the first information corresponding to the channel state information (CSI) to the network device.

[0091] In other embodiments, during operation 302, the terminal device may implicitly send the first information.

[0092] For example, the terminal device sends the data through a predefined layer order or a layer order determined by the terminal device; or, the terminal device sends the data based on the layer order configured by the network device.

[0093] In some examples, when the network device configures two or more layer sortings for the terminal device, the terminal device can select one of the configured two or more layer sortings to send the data, and the terminal device sends information to the network device to report the selected layer sorting information.

[0094] In some examples, after the artificial intelligence or machine learning (AI / ML) model for channel state information (CSI) feedback is activated, the terminal device determines the layer ordering, and the transmission of channel state information for downlink scheduling maintains the layer ordering unchanged; and / or

[0095] Once the artificial intelligence or machine learning (AI / ML) model used for channel state information (CSI) feedback is activated, the transmission of channel feature vectors related to performance monitoring data collection maintains the same layer order as the layer order for transmitting channel state information used for downlink scheduling.

[0096] In some instances, where the data includes channel feature vectors associated with training data collection or channel feature vectors associated with performance monitoring data collection, and channel state information (CSI) for downlink scheduling: at least one of the layer ordering corresponding to the channel feature vectors and the layer ordering corresponding to the channel state information (CSI) is predefined or configured by the network device.

[0097] All embodiments of this application are applicable to one-sided models, two-sided models, terminal device-side models, and network device-side models.

[0098] The present application will now be further described in conjunction with different embodiments. In the embodiments described below, the layer index / layer sorting related information corresponds to the first information of operation 302. UE can represent a terminal device, and NW can represent a network device.

[0099] Example 1

[0100] Example 1 describes the training data collection phase.

[0101] In one embodiment, for training data collection in the spatiotemporal frequency domain CSI compression sub-use case, the terminal device receives configuration information (CSI-RS configuration information, CSI reporting configuration information) from the network, obtains the feature vector of the wireless channel through channel measurement, and reports the training data (the obtained feature vector). The reporting of training data can be performed via Layer 1 signaling (e.g., UCI) or non-Layer 1 signaling (e.g., Layer 3 RRC). During the collection and reporting of training data, the terminal device implicitly or explicitly reports layer index / layer ordering related information, that is, the mapping relationship between the feature vector and the layer.

[0102] The reporting method is as follows: the UE reports the layer index / layer sort of each sample via signaling.

[0103] The implicit reporting methods are: reporting through a predefined layer order on the UE and NW sides; or, the NW configures the layer order to the UE through signaling, and the UE reports training data based on the configured layer order.

[0104] Figure 4(A) is a schematic diagram showing the reporting layer index / layer sorting. Figure 4(B) is a schematic diagram showing the implicit reporting layer index / layer sorting.

[0105] For explicit reporting, this layer index / ranking information can be reported together with the collected training data (e.g., codebook, or real channel feature vectors), or it can be reported separately and then associated with the collected training dataset. In one example, the layer index / ranking information could indicate the rank of the feature value corresponding to the feature vector among all feature values.

[0106] The training data may contain feature vectors from some or all layers, with each layer's feature vector corresponding to a single feature value. For example, in a 4Rx (4 receive) MIMO (Multiple-Input Multiple-Output) system, there are a total of 4 layers of channel feature vectors. The training data may only collect feature vectors from 3 layers, and the layer index or layer sorting information indicates the order of the feature values ​​(i.e., 3 feature values) of these 3 layer channel feature vectors among the feature values ​​(i.e., 4 feature values) of the 4 layer channel feature vectors.

[0107] In the first scenario of this embodiment, the terminal device reports layer index / layer ranking information via display signaling. For example, when the Rank value of the collected data sample is 3, the terminal device needs to report 3 layer feature vectors. The first feature vector corresponds to the feature vector of layer 3, the second feature vector corresponds to the feature vector of layer 1, and the third feature vector corresponds to the feature vector of layer 2. In this case, the terminal device needs to report the mapping relationship between the feature vectors and the layers (3,1,2), as shown in Figure 5. Different training data samples (e.g., training data samples collected at different times) may have the same or different layer indexes / layer rankings.

[0108] In this embodiment, training data can be reported via Layer 1 signaling or non-Layer 1 signaling. When training data is reported using Layer 1 signaling (e.g., Uplink Control Information (UCI)), the layer index / layer sort can be fed back through CSI reporting, for example, through Part I of CSI reporting or through Part II of CSI reporting.

[0109] For Part I, which provides feedback on layer index / ranking information, it is necessary to introduce new reporting data or reuse legacy reporting data. Assuming the maximum number of layers is Y_max (e.g., the maximum Rank value supported by the communication system, network configuration, or data collection), the length of the indicator field for layer index / ranking information can have the following values:

[0110] For each feature vector index, its length is

[0111] The possible permutations of Y eigenvectors are the factorial of Y;

[0112] For each feature vector, Y_max×Y_max uses a bitmap to indicate its layer index / layer order.

[0113] For Part II, which provides feedback on layer index / ranking information, it is still necessary to introduce new reporting data or reuse legacy reporting data. Assuming the reported Rank value is X, and X can potentially take the value X_max, the length of the indicator field for the layer index / ranking information can be as follows:

[0114] For each feature vector index, its length is

[0115] Given X eigenvectors, the possible permutations are the factorial of X.

[0116] For each feature vector, X×X uses a bitmap to indicate its layer index / layer order.

[0117] in

[0118] X×X_max.

[0119] In the second scenario of this embodiment, the standard predefines the layer ordering. The UE reports training data based on the predefined layer index / ordering, implicitly reporting layer index / ordering information to the network device. For example, the mapping between reported feature vectors and layers is predetermined in ascending order. When the rank value is X, the first feature vector in the reported feature vectors corresponds to layer 1, the second feature vector corresponds to layer 2, ..., and the Xth feature vector corresponds to layer X. Alternatively, the mapping between reported feature vectors and layers is predetermined in descending order. When the rank value is X, the first feature vector in the reported feature vectors corresponds to layer X, the second feature vector corresponds to layer X-1, ..., and the Xth feature vector corresponds to layer 1.

[0120] In the third scenario of this embodiment, the network device configures layer ordering to the terminal device via signaling (e.g., RRC), and the terminal device reports training data based on the configured layer ordering. The network can configure one or more layer ordering methods to the terminal. When multiple layer ordering methods exist, the UE reports which specific layer ordering was used for collecting training data. For different training data samples, the layer ordering may be the same or different.

[0121] In this embodiment, the reporting of training data (e.g., ground truth channel feature vectors) can be based on legacy codebooks or enhanced legacy codebooks.

[0122] This embodiment is applicable to the following scenarios:

[0123] Layer-specific AI / ML models or functions;

[0124] Layer common AI / ML model or functionality;

[0125] Rank-common AI / ML models or functions;

[0126] Rank-specific AI / ML model or functionality.

[0127] Example 2

[0128] Example 2 describes the inference phase of an AI / ML model or function.

[0129] In one embodiment, for inference data collection in the spatiotemporal frequency domain CSI compression sub-use case, the terminal device receives configuration information (CSI-RS configuration information, CSI reporting configuration information) from the network, obtains the CSI of the wireless channel through channel measurement, and then compresses and reports the CSI. The compressed CSI is fed back to the network device via Layer 1 signaling or non-Layer 1 signaling. During the CSI reporting process, the terminal device implicitly or explicitly reports layer index / layer ordering related information, that is, it feeds back the mapping relationship between PMI and layers.

[0130] The reporting method is as follows: the UE reports the layer index / layer sort for each CSI feedback via signaling.

[0131] The implicit reporting method is to report CSI through a predefined layer order, or the NW configures the layer order to the UE through signaling, and the UE reports CSI based on the configured layer order.

[0132] For explicit reporting, this layer index / ranking information can be reported together with the CSI, or it can be reported separately and then associated with the reporting CSI. In one example, the layer index / ranking information can indicate the rank of the feature value corresponding to the PMI among all features.

[0133] In the first scenario of this embodiment, the terminal device reports layer index / layer ranking information via display signaling. For example, when the Rank value of the collected data sample is 3, the terminal device needs to report 3 layers of PMIs. The first PMI is the feature vector of layer 3, the second PMI corresponds to the feature vector of layer 1, and the third PMI corresponds to the feature vector of layer 2. In this case, the terminal device needs to report the mapping relationship between PMIs and layers as (3,1,2), as shown in Figure 6. For different inference operations (e.g., model inference at different times), the layer index / layer ranking of the PMIs may be the same or different.

[0134] In this embodiment, the PMI is reported via Layer 1 signaling (e.g., UCI), and the layer index / layer ranking can be fed back together with the CSI report. For example, the layer index / layer ranking is fed back in Part I of the CSI report, or the layer index / layer ranking is fed back in Part II of the CSI report.

[0135] For Part I, which provides feedback on layer index / ranking information, new reporting data needs to be introduced or legacy reporting data needs to be reused. Assuming the maximum number of layers is Y_max (e.g., the maximum Rank value supported by the communication system or the maximum data collection), the length of the indicator field for layer index / ranking information can have the following values:

[0136] For each feature vector index, its length is

[0137] The possible permutations of Y eigenvectors are the factorial of Y;

[0138] For each feature vector, Y_max×Y_max uses a bitmap to indicate its layer index / layer sort.

[0139] For Part II, which provides feedback on the layer index / ranking information, it is still necessary to introduce new reporting data or reuse legacy reporting data. Assume the reported Rank value is X, and the maximum possible value of X is X0. max Then, the length of the indicator field for the layer index / layer sorting information can be as follows:

[0140] For each feature vector index, its length is

[0141] Given X eigenvectors, the possible permutations are the factorial of X.

[0142] For each feature vector, X×X uses a bitmap to indicate its layer index / layer order.

[0143] in

[0144] X×X_max.

[0145] In the second scenario of this embodiment, the standard predefines the layer ordering. The UE reports the CSI based on the predetermined layer index / ordering, implicitly reporting the layer index / ordering information of the PMI to the network device. For example, the mapping between the reported PMI and layers is predetermined in ascending order. When the rank value is X, in the reported feature vector, the first PMI corresponds to layer 1, the second PMI corresponds to layer 2, ..., and the Xth PMI corresponds to layer X. Alternatively, the mapping between the reported PMI and layers is predetermined in descending order. When the rank value is X, in the reported PMI, the first PMI corresponds to layer X, the second PMI corresponds to layer X-1, ..., and the Xth PMI corresponds to layer 1.

[0146] In the third scenario of this embodiment, the network device configures layer ordering to the terminal device via signaling (e.g., RRC), and the terminal device performs CSI feedback based on the configured layer ordering. The network can configure one or more layer ordering methods to the terminal. When multiple layer ordering methods exist, the UE reports which specific layer ordering was used for CSI reporting. For different CSI reports, the layer ordering may be the same or different.

[0147] In the fourth scenario of this embodiment, for spatiotemporal frequency domain CSI compression, the UE does not report the layer index / layer order information of PMI to the network device. When the AI / ML model is activated, the layer order of PMI reported by the UE is determined by the UE itself, and the layer order of PMI remains unchanged in subsequent CSI feedback.

[0148] This embodiment is applicable to the following scenarios:

[0149] Layer-specific AI / ML models or functions;

[0150] Layer common AI / ML model or functionality;

[0151] Rank-common AI / ML models or functions;

[0152] Rank-specific AI / ML model or functionality.

[0153] Example 3

[0154] Example 3 describes the performance monitoring phase for AI / ML models or functions.

[0155] In this embodiment, for data collection for performance monitoring of the spatiotemporal frequency domain CSI compression sub-use case, the terminal device receives configuration information (CSI-RS configuration information, CSI reporting configuration information) from the network, obtains the ground-truth channel feature vector of the wireless channel through channel measurement, and reports the ground-truth channel feature vector for NW-side model performance monitoring. The reporting of the ground-truth channel feature vector can be performed through Layer 1 signaling (e.g., UCI) or non-Layer 1 signaling (e.g., Layer 3 Radio Resource Control (RRC) signaling). During the collection and reporting of the ground-truth channel feature vector, the terminal device implicitly or explicitly reports layer index / layer ordering related information, that is, the mapping relationship between the ground-truth channel feature vector and the layer:

[0156] The reporting method is as follows: the UE reports the layer index / layer sort of each sample via signaling.

[0157] The implicit reporting method is as follows: the UE and NW side report through a predefined layer order; or, the NW configures the layer order to the UE through signaling, and the UE reports performance monitoring data based on the configured layer order.

[0158] For explicit reporting, this layer index / ranking information can be reported along with the collected performance monitoring data, or it can be reported separately and then associated with the collected performance monitoring dataset. In one example, the layer index / ranking information can indicate the rank of the eigenvalue corresponding to the ground truth channel feature vector among all eigenvalues.

[0159] In the first scenario of this embodiment, the terminal device reports layer index / layer ranking information via display signaling. For example, when the Rank value of the collected ground truth data sample is 3, the terminal device needs to report three layers of ground truth channel feature vectors. The first ground truth channel feature vector corresponds to the channel feature vector of layer 3, the second ground truth channel feature vector corresponds to the channel feature vector of layer 1, and the third ground truth channel feature vector corresponds to the channel feature vector of layer 2. In this case, the terminal device needs to report the mapping relationship (3,1,2) between the ground truth channel feature vectors and layers, as shown in Figure 7. Different performance monitoring data samples (e.g., performance monitoring data samples collected at different times) may have the same or different layer indexes / layer rankings.

[0160] In this embodiment, performance monitoring data can be reported via Layer 1 signaling or non-Layer 1 signaling. When Layer 1 signaling (e.g., UCI) is used to report performance monitoring data (e.g., ground truth channel feature vectors), the layer index / layer sorting can be fed back through CSI reporting. For example, it can be fed back through Part I of CSI reporting, or through Part II of CSI reporting.

[0161] For Part I, which provides feedback on layer index / ranking information, new reporting data needs to be introduced or legacy reporting data needs to be reused. Assuming the maximum number of layers is Y_max (e.g., the maximum Rank value supported by the communication system or the maximum data collection Rank value), the length of the indicator field for layer index / ranking information can have the following values:

[0162] For each channel feature vector index, its length is

[0163] The possible permutations of the Y channel feature vectors are the factorial of Y.

[0164] For each channel feature vector, Y_max×Y_max uses a bitmap to indicate its layer index / layer order.

[0165] For Part II, which provides feedback on the layer index / ranking information, it is still necessary to introduce new reporting data or reuse legacy reporting data. Assume the reported Rank value is X, and the maximum possible value of X is X0. max Then, the length of the indicator field for the layer index / layer sorting information can be as follows:

[0166] For each channel feature vector index, its length is

[0167] The possible permutations of the X channel feature vectors are the factorial of X;

[0168] For each channel feature vector, a bitmap is used to indicate its layer index / layer order.

[0169] in

[0170] X×X_max.

[0171] In the second scenario of this embodiment, the standard predefines the layer ordering. The UE reports performance monitoring data based on the predefined layer index / ordering, implicitly reporting layer index / ordering information to the network device. For example, the mapping between reported channel feature vectors and layers is predetermined in ascending order. When the rank value is X, the first channel feature vector in the reported channel feature vectors corresponds to layer 1, the second channel feature vector corresponds to layer 2, ..., and the Xth channel feature vector corresponds to layer X. Alternatively, the mapping between reported channel feature vectors and layers is predetermined in descending order. When the rank value is X, the first channel feature vector in the reported channel feature vectors corresponds to layer X, the second channel feature vector corresponds to layer X-1, ..., and the Xth channel feature vector corresponds to layer 1.

[0172] In the third scenario of this embodiment, the network device configures layer ordering to the terminal device via signaling (e.g., RRC), and the terminal device reports performance monitoring data based on the configured layer ordering. The network can configure one or more layer ordering methods to the terminal. When multiple layer ordering methods exist, the UE reports which specific layer ordering was used to collect performance monitoring data. For different performance monitoring data, the layer ordering may be the same or different.

[0173] In the third scenario of this embodiment, for performance monitoring of spatiotemporal frequency domain CSI compression, the UE does not report the layer index / layer ordering information of the ground truth channel feature vector to the network device. When the AI / ML model is triggered to report ground truth, the layer ordering of the ground truth channel feature vector remains consistent with the layer ordering of the PMI during the inference phase.

[0174] In this embodiment, the reporting of ground truth channel feature vectors can be based on legacy codebooks or enhanced legacy codebooks.

[0175] This embodiment is applicable to the following scenarios:

[0176] Layer-specific AI / ML models or functions;

[0177] Layer common AI / ML model or functionality;

[0178] Rank-common AI / ML models or functions;

[0179] Rank-specific AI / ML model or functionality.

[0180] Example 4

[0181] Example 4 illustrates the case where both the performance monitoring stage and the model inference stage exist for AI / ML models or functions.

[0182] In this embodiment, when the network device performs performance monitoring for spatiotemporal frequency domain CSI compression, the UE needs to report the ground truth channel feature vector and its layer index / layer ordering information. The layer index / layer ordering information can be reported to the network device explicitly or implicitly, and can be reported separately or together with the ground truth channel feature vector.

[0183] When network devices perform performance monitoring, in addition to reporting ground truth channel feature vectors, AI / ML models also need to report CSI for inference. The layer index / layer ranking information of PMI in CSI can also be reported to the network device explicitly or implicitly. The layer index / layer ranking information can be reported separately or together with the ground truth channel feature vector.

[0184] In the first option, both the layer index / sort of the ground truth channel feature vector and the layer index / sort of PMI / CSI are reported to the network device. These two layer indices / sorts can be the same or different.

[0185] In the second option, only one layer index / layer sorting information is reported to the network device (that is, one layer index / layer sorting information is defaulted). The network device considers this layer index / layer sorting to be both the ground truth channel feature vector and the PMI / CSI.

[0186] In the third option, the layer index / sorting information of the ground truth channel feature vector and the layer index / sorting information of PMI / CSI are predefined by the standard. In this case, the UE reports the layer index / sorting information implicitly. These two predefined layer index / sorting information (i.e., the layer index / sorting information of the ground truth channel feature vector and the layer index / sorting information of PMI / CSI) can be the same or different.

[0187] In the fourth option, the ground truth channel feature vector and the layer index / layer order of PMI / CSI are either predefined or configured by NW. Both the ground truth channel feature vector and the layer index / layer order of PMI / CSI need to be reported according to the predefined or configured information.

[0188] This embodiment is applicable to the following scenarios:

[0189] Layer-specific AI / ML models or functions;

[0190] Layer common AI / ML model or functionality;

[0191] Rank-common AI / ML models or functions;

[0192] Rank-specific AI / ML model or functionality.

[0193] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0194] The above embodiments of this application can be used in at least one of the following scenarios, or in other scenarios.

[0195] Second aspect of the embodiments

[0196] This application provides a method for receiving information, applied to a network device, which corresponds to the method in the first aspect of the embodiment. The contents that are the same as those in the first aspect of the embodiment will not be repeated.

[0197] Figure 8 is a schematic diagram of a method for receiving information according to an embodiment of the second aspect of this application. As shown in Figure 8, from the network device (NW) side, the method includes:

[0198] 801: Sends Channel State Information Reference Signal (CSI-RS) to terminal equipment; and

[0199] 802: Receive data related to Channel State Information (CSI) sent by the terminal device, as well as first information, wherein the first information is information related to the layer index and / or layer order of the data.

[0200] In some embodiments, the data includes at least one of the following:

[0201] Channel feature vectors are used for channel state information (CSI) in downlink scheduling.

[0202] In some embodiments, the channel feature vector is a channel feature vector associated with the collection of training data; and / or

[0203] The channel feature vector is a channel feature vector related to the collection of performance monitoring data.

[0204] In some embodiments, the channel feature vector is reported based on a codebook or a non-codebook.

[0205] In some embodiments, the network device receives the first information via signaling.

[0206] In some embodiments, the data includes one or more layers of channel feature vectors or channel state information, and the layer index and / or layer sorting related information are used to indicate the arrangement number of the feature value corresponding to each layer of channel feature vector or channel state information in the data among all feature values.

[0207] In some embodiments, the data is received together with the first information; or

[0208] The data and the first information are received separately, and the first information is associated with the data.

[0209] In some embodiments, the data is received via Layer 1 signaling or non-Layer 1 signaling.

[0210] The first information is received via channel state information reporting.

[0211] In some embodiments, the first information is received through Part I of the channel state information reporting, the maximum number of layers of the data is Y_max, and the length of the information field used to carry the first information is:

[0212] or Or Y_max × Y_max.

[0213] In some embodiments, the first information is received via Part II of the channel state information reporting.

[0214] The rank value of the channel state information reported is X, and the maximum possible value of X is X. max The length of the information field used to carry the first information is:

[0215] or Or X×X, or

[0216] or in Or X×X_max.

[0217] In some embodiments, where the data includes the channel feature vector associated with the training data collection or the channel feature vector associated with the performance monitoring data collection, and the channel state information (CSI),

[0218] The network device receives at least one of the first information corresponding to the channel feature vector related to training data collection or the channel feature vector related to performance monitoring data collection, and the first information corresponding to the channel state information (CSI) sent by the terminal device.

[0219] In some embodiments, the network device receives the data through a predefined layer ordering or a layer ordering determined by the terminal device; or

[0220] The network device receives the data based on the layer order configured for the terminal device by the network device.

[0221] In some embodiments, when the network device configures two or more layer sorting methods for the terminal device...

[0222] The network device receives the data sent by the terminal device from one of the configured layer sorting methods selected from the two or more layer sorting methods.

[0223] Furthermore, the network device receives information from the terminal device regarding the layer order for reporting the selected layer.

[0224] In some embodiments, after the artificial intelligence or machine learning (AI / ML) model for channel state information (CSI) feedback is activated, the layer ordering is determined by the terminal device, and the reception of channel state information for downlink scheduling maintains the layer ordering unchanged; and / or

[0225] Once the artificial intelligence or machine learning (AI / ML) model for channel state information (CSI) feedback is activated, the reception of channel feature vectors related to performance monitoring data collection maintains the same layer order as the layer order for the reception of channel state information used for downlink scheduling.

[0226] In some embodiments, where the data includes channel feature vectors related to training data collection or channel feature vectors related to performance monitoring data collection, and channel state information (CSI) for downlink scheduling,

[0227] At least one of the layer order corresponding to the channel feature vector and the layer order corresponding to the channel state information (CSI) is predefined or configured by the network device.

[0228] Third aspect of the embodiments

[0229] This application provides an apparatus for transmitting information. This apparatus may be, for example, a terminal device, or one or more components or parts configured on the terminal device. It corresponds to the method applied to the terminal device side in the first aspect embodiment, and the content identical to that in the first aspect embodiment will not be repeated.

[0230] Figure 9 is a schematic diagram of an information sending device according to an embodiment of this application. As shown in Figure 9, the information sending device 900 includes a first processing unit 901, which controls the terminal device to perform the following operations:

[0231] The terminal device acquires data related to Channel State Information (CSI); and

[0232] The terminal device sends the data and first information to the network device, wherein the first information is information related to the layer index and / or layer sorting of the data.

[0233] In some embodiments, the data includes at least one of the following:

[0234] Channel feature vectors are used for channel state information (CSI) in downlink scheduling.

[0235] In some embodiments, the channel feature vector is a channel feature vector associated with the collection of training data; and / or

[0236] The channel feature vector is a channel feature vector related to the collection of performance monitoring data.

[0237] In some embodiments, the channel feature vector is reported based on a codebook or a non-codebook.

[0238] In some embodiments, the terminal device sends the first information via signaling.

[0239] In some embodiments, the data includes one or more layers of channel feature vectors or channel state information, and the layer index and / or layer sorting related information are used to indicate the arrangement number of the feature value corresponding to each layer of channel feature vector or channel state information in the data among all feature values.

[0240] In some embodiments, the data is sent together with the first information; or

[0241] The data and the first information are sent separately, and the first information is associated with the data.

[0242] In some embodiments, the data is transmitted via Layer 1 signaling or non-Layer 1 signaling.

[0243] The first information is transmitted via channel state information reporting.

[0244] In some embodiments, the first information is transmitted via Part I of the channel state information reporting.

[0245] The maximum number of layers in the data is Y_max, and the length of the information field used to carry the first information is:

[0246] or Or Y_max × Y_max.

[0247] In some embodiments, the first information is transmitted via Part II of the channel state information reporting.

[0248] The rank value of the channel state information reported is X, and X may have a maximum value of X_max. The length of the information field used to carry the first information is:

[0249] or Or X×X, or

[0250] or in or

[0251] X×X_max.

[0252] In some embodiments, where the data includes the channel feature vector associated with the training data collection or the channel feature vector associated with the performance monitoring data collection, and the channel state information (CSI),

[0253] The terminal device sends at least one of the first information corresponding to the channel feature vector related to training data collection or the channel feature vector related to performance monitoring data collection, and the first information corresponding to the channel state information (CSI) to the network device.

[0254] In some embodiments, the terminal device sends the data through a predefined layer ordering or a layer ordering determined by the terminal device; or

[0255] The terminal device sends the data based on the layer ordering configured in the network device.

[0256] In some embodiments, when the network device configures two or more layer sorting methods for the terminal device...

[0257] The terminal device selects one of the two or more hierarchical sorting methods configured to send the data.

[0258] Furthermore, the terminal device sends information to the network device to report the selected layer order information.

[0259] In some embodiments, after the artificial intelligence or machine learning (AI / ML) model for channel state information (CSI) feedback is activated, the terminal device determines the layer ordering, and the transmission of channel state information for downlink scheduling maintains the layer ordering unchanged; and / or

[0260] Once the artificial intelligence or machine learning (AI / ML) model used for channel state information (CSI) feedback is activated, the transmission of channel feature vectors related to performance monitoring data collection maintains the same layer order as the layer order for transmitting channel state information used for downlink scheduling.

[0261] In some embodiments, where the data includes channel feature vectors related to training data collection or channel feature vectors related to performance monitoring data collection, and channel state information (CSI) for downlink scheduling,

[0262] At least one of the layer order corresponding to the channel feature vector and the layer order corresponding to the channel state information (CSI) is predefined or configured by the network device.

[0263] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0264] It is worth noting that the above description only covers the components or modules relevant to this application, but this application is not limited thereto. The device 900 may also include other components or modules; for details regarding these components or modules, please refer to related technologies.

[0265] Furthermore, for simplicity, Figure 9 only illustrates the connection relationships or signal flow between the various components or modules, but those skilled in the art should understand that various related technologies such as bus connections can be used. The aforementioned components or modules can be implemented using hardware facilities such as processors, memory, transmitters, and receivers; this application does not limit this implementation.

[0266] Fourth aspect of the embodiment

[0267] This application provides an apparatus for receiving information. This apparatus may be, for example, a network device, or one or more components or parts configured within a network device. It corresponds to the method applied to the network device side in the second aspect of the embodiment, and the content identical to that in the second aspect of the embodiment will not be repeated.

[0268] Figure 10 is a schematic diagram of an information receiving device according to an embodiment of this application. As shown in Figure 10, the information receiving device 1000 includes a second processing unit 1001, which controls the network device to perform the following operations:

[0269] Sending Channel State Information Reference Signal (CSI-RS) to terminal equipment; and

[0270] The terminal device receives channel state information (CSI) related data and first information, wherein the first information is information related to the layer index and / or layer order of the data.

[0271] In some embodiments, the data includes at least one of the following:

[0272] Channel feature vectors are used for channel state information (CSI) in downlink scheduling.

[0273] In some embodiments, the channel feature vector is a channel feature vector associated with the collection of training data; and / or

[0274] The channel feature vector is a channel feature vector related to the collection of performance monitoring data.

[0275] In some embodiments, the channel feature vector is reported based on a codebook or a non-codebook.

[0276] In some embodiments, the network device receives the first information via signaling.

[0277] In some embodiments, the data includes one or more layers of channel feature vectors or channel state information, and the layer index and / or layer sorting related information are used to indicate the arrangement number of the feature value corresponding to each layer of channel feature vector or channel state information in the data among all feature values.

[0278] In some embodiments, the data is received together with the first information; or

[0279] The data and the first information are received separately, and the first information is associated with the data.

[0280] In some embodiments, the data is received via Layer 1 signaling or non-Layer 1 signaling.

[0281] The first information is received via channel state information reporting.

[0282] In some embodiments, the first information is received through Part I of the channel state information reporting, the maximum number of layers of the data is Y_max, and the length of the information field used to carry the first information is:

[0283] or Or Y_max × Y_max.

[0284] In some embodiments, the first information is received via Part II of the channel state information reporting.

[0285] The rank value of the channel state information reported is X, and X may have a maximum value of X_max. The length of the information field used to carry the first information is:

[0286] or Or X×X, or

[0287] or in or

[0288] X×X_max.

[0289] In some embodiments, where the data includes the channel feature vector associated with the training data collection or the channel feature vector associated with the performance monitoring data collection, and the channel state information (CSI),

[0290] The network device receives at least one of the first information corresponding to the channel feature vector related to training data collection or the channel feature vector related to performance monitoring data collection, and the first information corresponding to the channel state information (CSI) sent by the terminal device.

[0291] In some embodiments, the network device receives the data through a predefined layer ordering or a layer ordering determined by the terminal device; or

[0292] The network device receives the data based on the layer order configured for the terminal device by the network device.

[0293] In some embodiments, when the network device configures two or more layer sorting methods for the terminal device...

[0294] The network device receives the data sent by the terminal device from one of the configured layer sorting methods selected from the two or more layer sorting methods.

[0295] Furthermore, the network device receives information from the terminal device regarding the layer order for reporting the selected layer.

[0296] In some embodiments, after the artificial intelligence or machine learning (AI / ML) model for channel state information (CSI) feedback is activated, the layer ordering is determined by the terminal device, and the reception of channel state information for downlink scheduling maintains the layer ordering unchanged; and / or

[0297] Once the artificial intelligence or machine learning (AI / ML) model used for channel state information (CSI) feedback is activated, the reception of channel feature vectors related to performance monitoring data collection maintains the same layer order as the layer order of the reception of channel state information used for downlink scheduling.

[0298] In some embodiments, where the data includes channel feature vectors related to training data collection or channel feature vectors related to performance monitoring data collection, and channel state information (CSI) for downlink scheduling,

[0299] At least one of the layer order corresponding to the channel feature vector and the layer order corresponding to the channel state information (CSI) is predefined or configured by the network device.

[0300] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0301] It is worth noting that the above description only covers the components or modules relevant to this application, but this application is not limited thereto. The device 1000 may also include other components or modules; for details regarding these components or modules, please refer to related technologies.

[0302] Furthermore, for simplicity, Figure 10 only illustrates the connection relationships or signal flow between the various components or modules, but those skilled in the art should understand that various related technologies such as bus connections can be used. The aforementioned components or modules can be implemented using hardware facilities such as processors, memory, transmitters, and receivers; this application does not limit this implementation.

[0303] Fifth aspect of the embodiment

[0304] This application provides a communication system, including a terminal device and a network device.

[0305] For example, the structure of the communication system can be seen with reference to FIG1. ​​As shown in FIG1, the communication system 100 includes network device 101 and terminal devices 102 and 103. At least one of the terminal devices 102, 103 and network device 101 may have the configuration of the electronic device shown in FIG11.

[0306] Figure 11 is a schematic block diagram of the electronic device. As shown in Figure 11, the electronic device 1100 may include a processor 1110 and a memory 1120; the memory 1120 is coupled to the processor 1110. The memory 1120 can store various data; in addition, it also stores an information processing program 1130, and executes the program 1130 under the control of the processor 1110 to receive or send various information.

[0307] In one embodiment, processor 1110 may be configured to perform the methods in the first aspect embodiment and / or the methods in the second aspect embodiment.

[0308] Furthermore, as shown in Figure 11, the electronic device 1100 may also include a transceiver 1540 and an antenna 1550, etc.; the functions of the above components are similar to those in the prior art, and will not be described in detail here. It is worth noting that the electronic device 1100 does not necessarily include all the components shown in Figure 11; in addition, the electronic device 1100 may also include components not shown in Figure 11, which can be referred to in the prior art.

[0309] The apparatus and methods described above in this application can be implemented in hardware or in combination with software. This application relates to a computer-readable program that, when executed by a logic component, enables the logic component to implement the apparatus or components described above, or to implement the various methods or steps described above. This application also relates to storage media for storing the above programs, such as hard disks, magnetic disks, optical disks, DVDs, flash memory, etc.

[0310] The methods / apparatus described in conjunction with the embodiments of this application can be directly embodied in hardware, software modules executed by a processor, or a combination of both. For example, one or more and / or combinations of one or more functional block diagrams shown in the figures can correspond to various software modules in a computer program flow, or to various hardware modules. These software modules can correspond to the various steps shown in the figures, respectively. These hardware modules can be implemented, for example, using a field-programmable gate array (FPGA) to embed these software modules.

[0311] The software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. A storage medium can be coupled to the processor, enabling the processor to read information from and write information to the storage medium; or the storage medium can be an integral part of the processor. The processor and storage medium can reside in an ASIC. The software module can be stored in the memory of a mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a high-capacity MEGA-SIM card or a high-capacity flash memory device, the software module can be stored in the MEGA-SIM card or the high-capacity flash memory device.

[0312] One or more and / or one or more combinations of functional blocks described in the figures can be implemented as a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, or any suitable combination thereof for performing the functions described in this application. One or more and / or one or more combinations of functional blocks described in FIG9 or FIG10 can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0313] The present application has been described above with reference to specific embodiments. However, those skilled in the art should understand that these descriptions are exemplary and not intended to limit the scope of protection of the present application. Those skilled in the art can make various modifications and variations to the present application based on its spirit and principles, and these modifications and variations are also within the scope of the present application.

Claims

1. A device for transmitting information, applied to a terminal device, characterized in that, The device includes a first processing unit, which controls the terminal device to perform the following operations: The terminal device acquires data related to Channel State Information (CSI); and The terminal device sends the data and first information to the network device, wherein the first information is information related to the layer index and / or layer sorting of the data.

2. The apparatus of claim 1, wherein, The data includes at least one of the following: Channel feature vectors are used for channel state information (CSI) in downlink scheduling.

3. The apparatus of claim 2, wherein, The terminal device sends the first information via signaling.

4. The apparatus of claim 3, wherein, The data is sent together with the first information; or The data and the first information are sent separately, and the first information is associated with the data.

5. The apparatus of claim 3, wherein, The data is sent via Layer 1 signaling or non-Layer 1 signaling. The first information is transmitted via channel state information reporting.

6. The apparatus of claim 5, wherein, The first information is transmitted through Part I of the channel state information reporting. The maximum number of layers in the data is Y_max, and the length of the information field used to carry the first information is: or Or Y_max × Y_max.

7. The apparatus of claim 5, wherein, The first information is transmitted through Part II of the channel state information reporting. The rank value of the channel state information reported is X, and X may have a maximum value of X_max. The length of the information field used to carry the first information is: or Or X×X, or or or X×X_max.

8. The apparatus of claim 3, wherein, When the data includes the channel feature vector related to the training data collection or the channel feature vector related to the performance monitoring data collection, and the channel state information (CSI), The terminal device sends at least one of the first information corresponding to the channel feature vector related to training data collection or the channel feature vector related to performance monitoring data collection, and the first information corresponding to the channel state information (CSI) to the network device.

9. The apparatus of claim 1, wherein, The terminal device sends the data through a predefined layer ordering or a layer ordering determined by the terminal device; or The terminal device sends the data based on the layer ordering configured in the network device.

10. The apparatus of claim 9, wherein, When the network device is configured with two or more layer sorting methods for the terminal device. The terminal device selects one of the two or more hierarchical sorting methods configured to send the data. Furthermore, the terminal device sends information to the network device via first instruction information to report the selected layer order information.

11. The apparatus of claim 9, wherein, After the artificial intelligence or machine learning (AI / ML) model for channel state information (CSI) feedback is activated, the terminal device determines the layer order, and the transmission of channel state information for downlink scheduling keeps the layer order unchanged. and / or Once the artificial intelligence or machine learning (AI / ML) model used for channel state information (CSI) feedback is activated, the transmission of channel feature vectors related to performance monitoring data collection maintains the same layer order as the layer order for transmitting channel state information used for downlink scheduling.

12. The apparatus of claim 9, wherein, In the case where the data includes channel feature vectors related to training data collection or channel feature vectors related to performance monitoring data collection, and channel state information (CSI) for downlink scheduling, At least one of the layer order corresponding to the channel feature vector and the layer order corresponding to the channel state information (CSI) is predefined or configured by the network device.

13. An apparatus for receiving information, applied to a network device, characterized in that, The device includes a second processing unit, which controls the network device to perform the following operations: Sending Channel State Information Reference Signal (CSI-RS) to terminal equipment; and The terminal device receives channel state information (CSI) related data and first information, wherein the first information is information related to the layer index and / or layer order of the data.

14. The apparatus of claim 13, wherein, The data includes at least one of the following: Channel feature vectors are used for channel state information (CSI) in downlink scheduling.

15. The apparatus of claim 14, wherein, The network device receives the first information via signaling.

16. The apparatus of claim 15, wherein, The data is received together with the first information; or The data and the first information are received separately, and the first information is associated with the data.

17. The apparatus of claim 15, wherein, The data is received via Layer 1 signaling or non-Layer 1 signaling. The first information is received via channel state information reporting.

18. The apparatus of claim 17, wherein, The first information is received through Part I of the channel state information report. The maximum number of layers in the data is Y_max, and the length of the information field used to carry the first information is: or Or Y_max × Y_max.

19. The apparatus of claim 17, wherein, The first information is received through Part II of the channel state information reporting. The rank value of the channel state information reported is X, and X may have a maximum value of X_max. The length of the information field used to carry the first information is: or Or X×X, or or or X×X_max.

20. The apparatus of claim 13, wherein, The network device receives the data through a predefined layer ordering or a layer ordering determined by the terminal device; or The network device receives the data based on the layer order configured for the terminal device by the network device.

Images