Data transceiving method and apparatus

Abstract

Embodiments of the present application provide a data transceiving method and apparatus. The method comprises: a terminal device receives, from a network device, a data set used for training an AI / ML model / function, and / or the terminal device transmits, to the network device, the data set used for training the AI / ML model / function, wherein the AI / ML model / function is used for channel state information (CSI) compression.

Description

Data transceiving method and apparatus TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of communication technology. BACKGROUND

[0002] In NR Rel-18, artificial intelligence / machine learning (AI / ML) over the air interface is studied. AI / ML can be used for the following use cases: Channel State Information (CSI) feedback enhancement, beam management, positioning enhancement. CSI feedback enhancement can include CSI prediction, CSI compression; beam management can include spatial beam prediction (BM case-1), temporal beam prediction (BM case-2); positioning enhancement can include direct positioning, AI / ML assisted positioning.

[0003] In some sub-use cases, a two-sided model can be used, i.e., the AI / ML model is at the terminal device side and at the network device side. In other sub-use cases, a one-sided model can be used, i.e., the AI / ML model is at the terminal device side or at the network device side. For CSI feedback enhancement, the AI / ML model can be at the terminal device side and at the network device side (may be referred to as two-sided model).

[0004] It should be noted that the above introduction to the technical background is only for the convenience of clearly and completely describing the technical solutions of the present application, and for the convenience of understanding by those skilled in the art. The above technical solutions cannot be considered as known to those skilled in the art merely because they are described in the background section of the present application.

[0005] SUMMARY

[0006] The inventors have found that the terminal device and / or the network device can use AI / ML functionality / model for CSI compression, and a data set for training the AI / ML model / functionality needs to be used. However, how to transceive the data set between the terminal device and the network device and / or how to define the format of the data set, there is no specific solution at present.

[0007] To solve at least one of the above problems, embodiments of the present application provide a data transceiving method and apparatus.

[0008] According to an aspect of embodiments of the present application, a data transceiving method is provided, comprising:

[0009] receiving, by a terminal device, a data set for training an AI / ML model / functionality from a network device; and / or

[0010] The terminal device sends a set of data for training the AI / ML model / function to the network device.

[0011] The AI / ML model / function is used for channel state information compression (CSI compression).

[0012] According to another aspect of embodiments of the present application, a data transceiving apparatus is provided, comprising:

[0013] a receiver that receives a set of data for training the AI / ML model / function from a network device; and / or

[0014] a transmitter that sends a set of data for training the AI / ML model / function to the network device.

[0015] The AI / ML model / function is used for channel state information compression (CSI compression).

[0016] According to another aspect of embodiments of the present application, a data transceiving method is provided, comprising:

[0017] a network device sends a set of data for training the AI / ML model / function to a terminal device; and / or

[0018] The network device receives a set of data for training the AI / ML model / function from the terminal device.

[0019] The AI / ML model / function is used for channel state information compression (CSI compression).

[0020] According to another aspect of embodiments of the present application, a data transceiving apparatus is provided, comprising:

[0021] a transmitter that sends a set of data for training the AI / ML model / function to a terminal device; and / or

[0022] a receiver that receives a set of data for training the AI / ML model / function from the terminal device.

[0023] The AI / ML model / function is used for channel state information compression (CSI compression).

[0024] According to another aspect of embodiments of the present application, a communication system is provided, comprising:

[0025] a terminal device that receives a set of data for training the AI / ML model / function from a network device, and / or, sends a set of data for training the AI / ML model / function to the network device.

[0026] a network device that transmits a data set for training an AI / ML model / function to a terminal device, and / or receives a data set for training an AI / ML model / function from the terminal device;

[0027] wherein the AI / ML model / function is used for channel state information compression (CSI compression).

[0028] One of the beneficial effects of the embodiments of the present application is that a data set for training an AI / ML model / function is exchanged between a terminal device and a network device, and the AI / ML model / function is used for CSI compression. Thus, the CSI compression based on the AI / ML model / function can be better implemented, and the signaling overhead and latency can be reduced.

[0029] Specific embodiments of the application are disclosed herein, and represented in the accompanying drawings, illustrating the principles of the application in a manner that can be employed by those skilled in the art. It is understood that the embodiments of the application are not limited in scope to the specific embodiments disclosed. Numerous modifications, alterations, and equivalents can be apparent to one of skill in the art in view of the principles of the application as disclosed in the appended claims and the following detailed description.

[0030] Features described and / or illustrated with respect to one implementation can be used in the same or similar manner in one or more other implementations, in combination with or in place of features in other implementations, or in place of other features.

[0031] It should be emphasized that the term "comprises / comprising" when used in this specification is taken to mean the presence of stated features, integers, steps or components but not the exclusion of one or more other features, integers, steps, components or groups thereof. BRIEF DESCRIPTION OF DRAWINGS

[0032] Elements and features depicted with respect to one drawing or implementation of the application can be combined with elements and features depicted with respect to one or more other drawings or implementations. Also, in the drawings, like reference numerals designate corresponding parts throughout the several views, and can be used to designate like components in more than one implementation.

[0033] FIG. 1 is a schematic diagram of a communication system according to an embodiment of the present application;

[0034] FIG. 2 is a schematic diagram of using AI / ML for CSI compression according to an embodiment of the present application;

[0035] FIG. 3 is a schematic diagram of a data exchange method according to an embodiment of the present application;

[0036] FIG. 4 is an example diagram of a data set with one rank value according to an embodiment of the present application;

[0037] FIG. 5 is an example diagram of layer indexing information according to an embodiment of the present application;

[0038] FIG. 6 is an example diagram of a data set with multiple rank values according to an embodiment of the present application;

[0039] FIG. 7 is an example diagram of a data set with multiple data sample groups according to an embodiment of the present application;

[0040] FIG. 8 is a schematic diagram of a data transceiving method according to an embodiment of the present application;

[0041] FIG. 9 is a schematic diagram of a data transceiving apparatus according to an embodiment of the present application;

[0042] FIG. 10 is a schematic diagram of a data transceiving apparatus according to an embodiment of the present application;

[0043] FIG. 11 is a schematic diagram of a terminal device according to an embodiment of the present application;

[0044] FIG. 12 is a schematic diagram of a network device according to an embodiment of the present application. DETAILED DESCRIPTION

[0045] The foregoing and other features of the present application will become apparent to those skilled in the art upon consideration of the following description of specific embodiments of the present application, which are offered by way of illustration only. In the description of the embodiments of the present application, specific terminology is employed for the sake of clarity. However, the application is not intended to be limited to the specific embodiments described, but rather, is intended to include all modifications, equivalents, and alternatives that fall within the scope of the appended claims.

[0046] In the embodiments of the present application, the terms "first", "second", and the like are used to distinguish different elements, but do not indicate the spatial arrangement or the time sequence of the elements, and the elements should not be limited by these terms. The term "and / or" includes any one and all combinations of the associated listed terms. The terms "comprise", "include", "have", and the like are intended to mean the presence of the stated features, elements, components, or elements, but do not exclude the presence or addition of one or more other features, elements, components, or elements.

[0047] In the embodiments of the present application, the singular forms "a", "an", and "the" include the plural forms, and should be broadly understood as "one" or "one kind" rather than the meaning of "one"; in addition, the term "said" should be understood as including both singular and plural forms, unless the context clearly indicates otherwise. In addition, the term "according to" should be understood as "at least partially according to", and the term "based on" should be understood as "at least partially based on", unless the context clearly indicates otherwise.

[0048] In embodiments of the present application, the term "communication network" or "wireless communication network" can refer to a network that complies with any communication standard, such as Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), etc.

[0049] Also, the communication between devices in a communication system can be in accordance with any phase of communication protocol, such as can include but is not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G, and 5G, New Radio (NR), future 6G, etc., and / or other communication protocols known currently or to be developed in the future.

[0050] In embodiments of the present application, the term "network device" refers to a device that accesses a terminal device to a communication network and provides services for the terminal device in a communication system, for example. The network device can include but is 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.

[0051] Among them, the base station can include but is not limited to: Node B (NodeB or NB), evolved Node B (eNodeB or eNB), and 5G base station (gNB), IAB donor, etc., in addition to remote radio head (RRH), remote radio unit (RRU), relay or low-power node (such as femto, pico, etc.). Also, the term "base station" can include some or all functions of them, and each base station can provide communication coverage for 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.

[0052] In the embodiments of the present application, the term "user equipment" (UE) or "terminal equipment" (TE) refers to, for example, a device that accesses a communication network through a network device and receives network services. The terminal equipment can be fixed or mobile, and can also be referred to as a mobile station (MS), a terminal, a subscriber station (SS), an access terminal (AT), a station, and the like.

[0053] The terminal equipment can include, but is not limited to, the following devices: a cellular phone, a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a machine type communication device, a laptop computer, a cordless phone, a smart phone, a smart watch, a digital camera, and the like.

[0054] For another example, in an Internet of Things (IoT) scenario or the like, the terminal equipment can also be a machine or device that performs monitoring or measurement, and can include, but is not limited to, the following devices: a machine type communication (MTC) terminal, a vehicle-mounted communication terminal, a device-to-device (D2D) terminal, a machine-to-machine (M2M) terminal, and the like.

[0055] In addition, the term "network side" or "network device side" refers to the side of the network, which can be a certain base station or can include one or more network devices as described above. The term "user side" or "terminal side" or "terminal equipment side" refers to the side of the user or terminal, which can be a certain UE or can include one or more terminal devices as described above. In this document, "device" can refer to a network device or a terminal device unless otherwise specified.

[0056] The following describes the scenarios of the embodiments of the present application by way of examples, but the present application is not limited thereto.

[0057] FIG. 1 is a schematic diagram of a communication system according to an embodiment of the present application, which schematically illustrates a case taking a terminal equipment and a network device as an example. As shown in FIG. 1, the communication system 100 can include a network device 101 and terminal equipments 102 and 103. For simplicity, FIG. 1 only takes two terminal equipments and one network device as an example for illustration, but the embodiments of the present application are not limited thereto.

[0058] In the embodiments of the present application, the network device 101 and the terminal devices 102, 103 can perform existing services or future implementable service transmission. For example, these services can include, but are not limited to, enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0059] It is worth noting that FIG. 1 shows that both terminal devices 102, 103 are within the coverage of the network device 101, but the present application is not limited thereto. Both terminal devices 102, 103 can be outside the coverage of the network device 101, or one terminal device 102 is within the coverage of the network device 101 while the other terminal device 103 is outside the coverage of the network device 101.

[0060] In the embodiments of the present application, the higher layer signaling can be, for example, radio resource control (RRC) signaling; for example, referred to as RRC message, for example, including MIB, system information, dedicated RRC message; or referred to as RRC IE. The higher layer signaling can also be, for example, MAC (Medium Access Control) signaling; or referred to as MAC CE. However, the present application is not limited thereto.

[0061] FIG. 2 is a schematic diagram of CSI compression using AI / ML according to an embodiment of the present application, which schematically illustrates the operation of CSI compression using AI / ML (two-sided model). On the terminal device side, the terminal device measures the reference signal (for example, CSI-RS) to obtain the wireless channel information. Then, the terminal device can further obtain the eigen vector of the wireless channel, which is used as the input of the terminal device side AI / ML model / function, i.e., the input of the encoder, to compress the CSI. The terminal device reports / transmits the output of the encoder to the network device side. On the network device side, the received CSI feedback is used as the input of the network device side AI / ML model / function, i.e., the input of the decoder. After decompression, the output of the decoder is the reconstructed CSI.

[0062] The above illustrates the AI / ML-based CSI compression in a schematic manner, and the present application is not limited thereto. In addition, the above-mentioned embodiments can be part of the embodiments of the present application, can be applicable to the present application, and can be combined with one or more of the following embodiments.

[0063] In Rel-19, the following options are determined for the co-training of CSI compression with a double-sided model:

[0064] Option 1: Fully standardized reference model (structure + parameters);

[0065] Option 2: Standardized data set;

[0066] Option 3: Standardized reference model structure + exchange of parameters between the NW side and the UE side;

[0067] Option 4: Standardized data / data set format + exchange of data sets between the NW side and the UE side;

[0068] Option 5: Standardized model format + exchange of reference models between the NW side and the UE side.

[0069] However, there is currently no specific solution for how to transmit the data set between the terminal device and the network device and how to define the format of the data set.

[0070] In the embodiments of the present application, one or more AI / ML models can be configured and run in the network device and / or the terminal device. The AI / ML model can be used for various signal processing functions of wireless communication, such as CSI prediction, CSI compression, beam prediction, positioning management, etc.; the present application is not limited thereto.

[0071] Embodiments of the first aspect

[0072] The embodiments of the present application provide a data transmission method, which is described from the terminal device side.

[0073] FIG. 3 is a schematic diagram of a data transmission method according to an embodiment of the present application. As shown in FIG. 3, the method includes:

[0074] 301, the terminal device receives a data set for training an AI / ML model / function from a network device; and / or

[0075] 302, the terminal device sends a data set for training an AI / ML model / function to the network device;

[0076] Wherein, the AI / ML model / function is used for channel state information compression (CSI compression).

[0077] It is notable that the above Fig. 3 only schematically illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the operations can be appropriately adjusted, and furthermore, some operations can be added or some operations can be removed. A person skilled in the art can appropriately modify based on the above description, and the present application is not limited to the above Fig. 3.

[0078] In some embodiments, the functionality refers to an AI / ML feature / feature group enabled by a configuration, wherein the configuration is supported based on a condition indicated by a UE capability.

[0079] For example, the AI / ML functionality can be one or more functionalities, or, can be one or more logical models, or, can be one or more sub- functionalities, or, can be one or more features, or, can be one or more feature groups.

[0080] For another example, the functionality can be spatial beam prediction using AI / ML, or, can be time beam prediction using AI / ML, or, can be CSI prediction using AI / ML, or, can be direct positioning using AI / ML, or, can be AI / ML assisted positioning, etc.

[0081] In some embodiments, the AI / ML functionality / model can be used for CSI compression.

[0082] For convenience of description, the CSI compression based on AI / ML functionality / model is referred to as model inference or inference operation, the training data collection based on AI / ML functionality / model is referred to as training data collection (the training data collection can also use a non-AI / ML manner), and the performance monitoring based on AI / ML functionality / model is referred to as performance monitoring.

[0083] In some embodiments, the data set includes one or more data samples; the format of the data set and / or the data samples is predefined.

[0084] For example, for CSI compression with a bilateral model, a data set for training can be exchanged between a network device side (e.g., gNB) and a terminal device side (e.g., UE). The data set can be transmitted from the network device side to the terminal device side, or the data set can be transmitted from the terminal device side to the network device side. The data set can contain multiple data samples.

[0085] In some embodiments, the data samples are one or more combinations of:

[0086] encoder input data and decoder output data;

[0087] encoder input data and encoder output data;

[0088] encoder output data and decoder output data;

[0089] encoder input data, encoder output data, and decoder output data.

[0090] For example, the data samples can be one or more tuples of:

[0091] {encoder input data, decoder output data};

[0092] {encoder input data, encoder output data};

[0093] {encoder output data, decoder output data};

[0094] {encoder input data, encoder output data, decoder output data}.

[0095] For example, the encoder input data can be target CSI, the encoder output data can be the same as the decoder input data, which can be CSI feedback, and the decoder output can be reconstructed target CSI. With the above data, CSI compression can be performed using AI / ML; details about AI / ML can also be referred to related art.

[0096] In some embodiments, the data set is based on a raw channel or based on a codebook; and the data set includes or is associated with indication information indicating whether the data set is based on a raw channel or based on a codebook.

[0097] For example, the data set for training can be based on raw channel, i.e., the target CSI is raw channel.

[0098] For another example, the data set for training can be based on codebook, i.e., the target CSI is eigenvector of raw channel.

[0099] For yet another example, in the data set for training, information (indicating information) whether it is based on raw channel or codebook can be included in the data set, for example, the indicating information can be an indicator indicating whether it is based on raw channel or codebook.

[0100] In some embodiments, the data set includes one or more data samples for the same rank; and the data set includes or associates information of the rank.

[0101] For example, the data set for training includes data samples with the same rank value. In addition, the data set can contain (explicitly) information of the rank value, for example, the data set contains an indicator indicating the rank value, or the data set contains the rank value.

[0102] For another example, the data set for training includes data samples with the same rank value. In addition, the data set can associate (implicitly) information of the rank value, for example, the identification (ID) of the data set is associated with the corresponding rank value.

[0103] FIG. 4 is an example diagram of a data set with one rank value according to an embodiment of the present application. As shown in FIG. 4, the data set contains the rank value (rank X), and the data set for training includes data samples (data sample#1, …, data sample#N) with the same rank value.

[0104] In some embodiments, the data sample includes or associates layer indexing information, which indicates the mapping between the eigen vector of the data sample and the layer.

[0105] FIG. 5 is an example diagram of layer indexing information according to an embodiment of the present application. As shown in FIG. 5, for example, for each data sample, the layer indexing information is contained in the data sample, and the layer indexing indicates the mapping between the eigen vector and the layer.

[0106] In some embodiments, the data set comprises a plurality of data samples for different ranks; and each data sample comprises or is associated with information of a corresponding rank.

[0107] FIG. 6 is an example diagram of a data set with multiple rank values according to an embodiment of the present application. As shown in FIG. 6, the data set contains multiple rank values (rank X1, …, rank XN), and the data set for training comprises data samples (data sample #1, …, data sample #N) with corresponding rank values, e.g., data sample #1 corresponds to rank X1, …, data sample #N corresponds to rank XN.

[0108] In some embodiments, the data sample comprises or is associated with layer indexing information, which indicates a mapping between an eigen vector of the data sample and a layer.

[0109] For example, for each data sample, the layer indexing information is contained in the data sample, and the layer indexing indicates the mapping between the eigen vector and the layer.

[0110] In some embodiments, the data set comprises a plurality of data samples for different ranks; the plurality of data samples are included in one or more data sample groups, and the data samples in one data sample group correspond to the same rank.

[0111] In some embodiments, different data sample groups correspond to different ranks, or different data sample groups correspond to the same rank; each data sample group comprises or is associated with information of a corresponding rank.

[0112] FIG. 7 is an example diagram of a data set with multiple data sample groups according to an embodiment of the present application. As shown in FIG. 7, the data set contains multiple data sample groups (data sample group #1, …), each of which comprises multiple data samples (data sample #1, …), and each data sample group corresponds to a rank value. For example, data sample group #1 corresponds to rank X1, ….

[0113] In some embodiments, the data samples comprise or are associated with layer indexing information indicating a mapping between eigen vectors and layers of the data samples.

[0114] For example, for each data sample, layer indexing information is included in the data sample, the layer indexing indicating a mapping between eigen vectors and layers.

[0115] In some embodiments, adjacent data samples in the data set correspond to consecutive time instances.

[0116] For example, for CSI compression with a bilateral model, adjacent data samples in the training data set are from consecutive time instances.

[0117] In some embodiments, the time interval between two consecutive time instances corresponding to adjacent data samples in the data set is the same.

[0118] The data set comprises or is associated with information of the time interval.

[0119] For example, in the data set, the time interval between two consecutive time instances corresponding to two adjacent data samples is the same. Information of the time interval can be included in the data set. For example, the information of the time interval can be represented by a CSI-RS period.

[0120] In some embodiments, the data set comprises a plurality of data samples based on a plurality of time intervals; the plurality of data samples are included in one or more data sample groups, and the data samples in one data sample group have the same time interval.

[0121] In some embodiments, the time interval between data samples is the same for different data sample groups, or the time interval between data samples is different for different data sample groups.

[0122] For example, the data set can contain data samples based on multiple time intervals, e.g., multiple CSI-RS periods. The data set can include one or more data sample groups. The time intervals (or CSI-RS periods) between data samples within one data sample group are the same. For different data sample groups, the time intervals (or CSI-RS periods) between data samples can be the same or can also be different.

[0123] In some embodiments, the data sample includes an association ID indicating a condition / configuration of the terminal device and / or the network device.

[0124] For example, the association ID indicates a condition / configuration on the gNB side and / or a condition or configuration on the UE side.

[0125] In some embodiments, the data set includes one or more data samples for one association ID; and the data set includes or associates information of the association ID.

[0126] For example, the data set for training includes data samples with the same association ID, i.e., only one association ID is included in the data set.

[0127] In some embodiments, the data set includes multiple data samples for multiple association IDs; the multiple data samples are included in one or more data sample groups, and one data sample group corresponds to one association ID.

[0128] For example, the data set for training includes data samples with multiple association IDs. The data set can include one or more data sample groups, and one data sample group is associated with one association ID.

[0129] In some embodiments, the data set for training the AI / ML model / function is compressed.

[0130] For example, in the data set, the data samples can be based on Float32 format. Alternatively, the terminal device and / or the network device can compress the data set to reduce overhead. For example, Int8 or Int16 is used to represent the floating point part of the data.

[0131] Embodiments of the present application can be applied to CSI compression in space and frequency domain (SF compression), and can also be applied to CSI compression in time domain, space domain and frequency domain (TSF compression), wherein both the UE side and the gNB side can use historical CSI information. Embodiments of the present application can also be applied to CSI compression plus CSI prediction, wherein the CSI prediction is performed on the UE side. The present application is not limited to the above scenarios.

[0132] The above embodiments are only illustrative of the embodiments of the present application, but the present application is not limited thereto, and can be appropriately modified on the basis of the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0133] As can be seen from the above embodiments, a data set for training an AI / ML model / function for CSI compression is transceived between a terminal device and a network device. Thus, CSI compression based on an AI / ML model / function can be implemented, and signaling overhead and latency can be reduced.

[0134] Embodiments of the second aspect

[0135] The embodiments of the present application provide a data transceiving method, which is described from the network device side. The embodiments of the second aspect can be combined with the embodiments of the first aspect, and the same content as the embodiments of the first aspect will not be described again.

[0136] FIG. 8 is a schematic diagram of a data transceiving method according to an embodiment of the present application. As shown in FIG. 8, the method comprises:

[0137] 801, the network device sends a data set for training an AI / ML model / function to the terminal device; and / or

[0138] 802, the terminal device receives the data set for training the AI / ML model / function from the network device.

[0139] The AI / ML model / function is used for channel state information compression (CSI compression).

[0140] It is worth noting that the above FIG. 8 only illustrates the embodiments of the present application, but the present application is not limited thereto. For example, the execution order between the operations can be appropriately adjusted, and in addition, some operations can be added or some operations can be reduced. Those skilled in the art can appropriately modify the above content, and the present application is not limited to the above FIG. 8.

[0141] In some embodiments, the data set comprises one or more data samples; the format of the data set and / or the data sample is predefined.

[0142] In some embodiments, the data sample is one or more combinations of:

[0143] encoder input data and decoder output data;

[0144] encoder input data and encoder output data;

[0145] encoder output data and decoder output data;

[0146] encoder input data, encoder output data and decoder output data.

[0147] In some embodiments, the data set is based on raw channel or based on codebook; and the data set includes or associates indication information for indicating whether the data set is based on raw channel or based on codebook.

[0148] In some embodiments, the data set includes one or more data samples for the same rank; and the data set includes or associates information of the rank.

[0149] In some embodiments, the data sample includes or associates layer indexing information indicating mapping between eigen vector of the data sample and layer.

[0150] In some embodiments, the data set includes multiple data samples for different ranks; and each data sample includes or associates information of the corresponding rank.

[0151] In some embodiments, the data sample includes or associates layer indexing information indicating mapping between eigen vector of the data sample and layer.

[0152] In some embodiments, the data set includes multiple data samples for different ranks; the multiple data samples are included in one or more data sample groups, and data samples in one data sample group correspond to the same rank.

[0153] In some embodiments, different data sample groups correspond to different ranks, or, different data sample groups correspond to the same rank;

[0154] Each data sample group includes or associates information of the corresponding rank.

[0155] In some embodiments, the data sample includes or associates layer indexing information indicating mapping between eigen vector of the data sample and layer.

[0156] In some embodiments, adjacent data samples in the data set correspond to consecutive time instances.

[0157] In some embodiments, a time interval between two consecutive time instances corresponding to adjacent data samples in the data set is the same.

[0158] The data set includes or is associated with information of the time interval.

[0159] In some embodiments, the data set includes a plurality of data samples based on a plurality of time intervals; the plurality of data samples are included in one or more data sample groups, and data samples in one data sample group have the same time interval.

[0160] In some embodiments, the time interval between data samples is the same for different data sample groups, or the time interval between data samples is different for different data sample groups.

[0161] In some embodiments, the data samples include an association ID for indicating a condition / configuration of the terminal device and / or the network device.

[0162] In some embodiments, the data set includes one or more data samples for one association ID; and the data set includes or is associated with information of the association ID; and / or

[0163] The data set includes a plurality of data samples for a plurality of association IDs; the plurality of data samples are included in one or more data sample groups, and one data sample group corresponds to one association ID.

[0164] In some embodiments, the network device compresses the data set for training the AI / ML model / function.

[0165] In some embodiments, the network device can send configuration information, etc. to the terminal device. The network device can receive feedback information and / or report information sent by the terminal device. For example, the terminal device can report inference results and / or performance monitoring results and / or training data collection results to the network device, and the present application is not limited thereto.

[0166] The above embodiments are only illustrative of the embodiments of the present application, but the present application is not limited thereto, and can be appropriately modified on the basis of the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0167] As can be seen from the above embodiments, a data set for training an AI / ML model / function for CSI compression is transceived between a terminal device and a network device. Thus, CSI compression based on an AI / ML model / function can be implemented, and signaling overhead and latency can be reduced.

[0168] Embodiments of the third aspect

[0169] The embodiments of the present application provide a data transceiving apparatus. The apparatus can be a terminal device, or one or more components or assemblies configured in the terminal device. The same content as the embodiments of the first and second aspects will not be described again.

[0170] FIG. 9 is a schematic diagram of a data transceiving apparatus according to an embodiment of the present application. As shown in FIG. 9, the data transceiving apparatus 900 according to an embodiment of the present application includes a receiver 901 and a transmitter 902, and can further include a processor 903.

[0171] The receiver 901 receives a data set for training an AI / ML model / function from a network device; and / or

[0172] The transmitter 902 transmits the data set for training the AI / ML model / function to the network device.

[0173] The AI / ML model / function is used for channel state information compression (CSI compression).

[0174] In some embodiments, the data set includes one or more data samples; the format of the data set and / or the data samples is predefined.

[0175] In some embodiments, the data samples are one or more combinations of:

[0176] encoder input data and decoder output data;

[0177] encoder input data and encoder output data;

[0178] encoder output data and decoder output data;

[0179] encoder input data, encoder output data, and decoder output data.

[0180] In some embodiments, the data set is based on raw channel or based on codebook; and the data set includes or associates with indication information for indicating whether the data set is based on raw channel or based on codebook.

[0181] In some embodiments, the data set includes one or more data samples for the same rank; and the data set includes or associates with information of the rank.

[0182] In some embodiments, the data sample includes or associates with layer indexing information indicating mapping between eigen vector of the data sample and layer.

[0183] In some embodiments, the data set includes multiple data samples for different ranks; and each data sample includes or associates with information of the corresponding rank.

[0184] In some embodiments, the data sample includes or associates with layer indexing information indicating mapping between eigen vector of the data sample and layer.

[0185] In some embodiments, the data set includes multiple data samples for different ranks; the multiple data samples are included in one or more data sample groups, and data samples in one data sample group correspond to the same rank.

[0186] In some embodiments, different data sample groups correspond to different ranks, or, different data sample groups correspond to the same rank.

[0187] Each data sample group includes or associates with information of the corresponding rank.

[0188] In some embodiments, the data sample includes or associates with layer indexing information indicating mapping between eigen vector of the data sample and layer.

[0189] In some embodiments, adjacent data samples in the data set correspond to consecutive time instances.

[0190] In some embodiments, a time interval between two consecutive time instances corresponding to adjacent data samples in the data set is the same.

[0191] The data set comprises or is associated with information of the time interval.

[0192] In some embodiments, the data set comprises a plurality of data samples based on a plurality of time intervals; the plurality of data samples are included in one or more data sample groups, and data samples in one data sample group have the same time interval.

[0193] In some embodiments, the time interval between data samples is the same for different data sample groups, or the time interval between data samples is different for different data sample groups.

[0194] In some embodiments, the data samples comprise an association ID for indicating a condition / configuration of the terminal device and / or the network device.

[0195] In some embodiments, the data set comprises one or more data samples for one association ID; and the data set comprises or is associated with information of the association ID; and / or

[0196] The data set comprises a plurality of data samples for a plurality of association IDs; the plurality of data samples are included in one or more data sample groups, and one data sample group corresponds to one association ID.

[0197] In some embodiments, the processor 903 compresses the data set for training the AI / ML model / function.

[0198] The above various embodiments are only exemplarily described, but the present application is not limited thereto, and can be appropriately modified on the basis of the above various embodiments. For example, the above various embodiments can be used alone, or one or more of the above various embodiments can be combined.

[0199] It is worth noting that the above only describes the components or modules related to the present application, but the present application is not limited thereto. The data transceiver apparatus 900 can also include other components or modules, and the specific content of these components or modules can be referred to related technologies.

[0200] In addition, for the sake of simplicity, only the connection relationship or signal direction between each component or module is exemplarily shown in FIG. 9, but it should be clear to those skilled in the art that various related technologies such as bus connection can be adopted. Each component or module described above can be implemented by hardware facilities such as a processor, a memory, a transmitter, a receiver, etc.; the implementation of the present application is not limited thereto.

[0201] As can be seen from the above embodiments, the terminal device and the network device transceive a data set for training an AI / ML model / function for CSI compression. Thus, CSI compression based on the AI / ML model / function can be implemented, and signaling overhead and latency can be reduced.

[0202] Embodiments of the fourth aspect

[0203] The embodiments of the present application provide a data transceiving apparatus. The apparatus can be a network device, or one or more components or components configured in the network device. The same content as the embodiments of the first to third aspects will not be described again.

[0204] FIG. 10 is another schematic diagram of the data transceiving apparatus according to the embodiments of the present application. As shown in FIG. 10, the data transceiving apparatus 1000 includes a transmitter 1001 and a receiver 1002, and can further include a processor 1003.

[0205] The transmitter 1001 transmits, to a terminal device, a data set for training an AI / ML model / function; and / or

[0206] The receiver 1002 receives, from the terminal device, a data set for training an AI / ML model / function.

[0207] The AI / ML model / function is used for channel state information compression (CSI compression).

[0208] In some embodiments, the processor 1003 compresses the data set for training the AI / ML model / function.

[0209] The above embodiments are only exemplarily described, but the present application is not limited thereto, and appropriate modifications can be made on the basis of the above embodiments. For example, each of the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0210] It is worth noting that the above only describes the components or modules related to the present application, but the present application is not limited thereto. The data transceiver device 1000 can also include other components or modules, and the specific content of these components or modules can be referred to related technologies.

[0211] In addition, for the sake of simplicity, only the connection relationship or signal path between the various components or modules is exemplarily shown in FIG. 10, but those skilled in the art should understand that various related technologies such as bus connection can be used. The various components or modules described above can be implemented by hardware facilities such as processors, memories, transmitters, receivers, etc.; the present application is not limited thereto.

[0212] As can be seen from the above embodiments, the terminal device and the network device transceive a data set for training an AI / ML model / function for CSI compression. Thus, CSI compression based on the AI / ML model / function can be achieved, and signaling overhead and latency can be reduced.

[0213] Embodiments of the fifth aspect

[0214] The embodiments of the present application also provide a communication system, which can be referred to FIG. 1, and the same content as the embodiments of the first to fourth aspects will not be repeated.

[0215] In some embodiments, the communication system 100 can at least include:

[0216] a terminal device, which receives a data set for training an AI / ML model / function from a network device, and / or transmits a data set for training an AI / ML model / function to the network device;

[0217] a network device, which transmits a data set for training an AI / ML model / function to a terminal device, and / or receives a data set for training an AI / ML model / function from the terminal device;

[0218] wherein the AI / ML model / function is used for channel state information compression (CSI compression).

[0219] The embodiments of the present application also provide a terminal device, but the present application is not limited thereto, and can also be other devices.

[0220] FIG. 11 is a schematic diagram of a terminal device according to an embodiment of the present application. As shown in FIG. 11, the terminal device 1100 can include a processor 1110 and a memory 1120; the memory 1120 stores data and programs and is coupled to the processor 1110. It is worth noting that this figure is exemplary; other types of structures can also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0221] For example, the processor 1110 can be configured to execute programs to implement the data transceiving method as described in the embodiments of the first aspect. For example, the processor 1110 can be configured to control: receiving, from a network device, a data set for training an AI / ML model / function; and / or transmitting, to the network device, the data set for training the AI / ML model / function; wherein the AI / ML model / function is for channel state information compression (CSI compression).

[0222] As shown in FIG. 11, the terminal device 1100 can further include a communication module 1130, an input unit 1140, a display 1150, and a power supply 1160. Functions of the above components are similar to those of the prior art, and will not be described here. It should be noted that the terminal device 1100 does not necessarily include all the components shown in FIG. 11, and the above components are not essential; in addition, the terminal device 1100 can include components not shown in FIG. 11, and reference can be made to the prior art.

[0223] Embodiments of the present application also provide a network device, which can be a base station for example, but the present application is not limited thereto, and can also be other network devices.

[0224] FIG. 12 is a schematic diagram of the network device according to an embodiment of the present application. As shown in FIG. 12, the network device 1200 can include a processor 1210 (such as a central processing unit CPU) and a memory 1220; the memory 1220 is coupled to the processor 1210. The memory 1220 can store various data; in addition, it also stores programs 1230 for information processing, and executes the programs 1230 under the control of the processor 1210.

[0225] For example, the processor 1210 can be configured to execute programs to implement the data transceiving method as described in the embodiments of the second aspect. For example, the processor 1210 can be configured to control: transmitting, to a terminal device, a data set for training an AI / ML model / function; and / or receiving, from the terminal device, the data set for training the AI / ML model / function; wherein the AI / ML model / function is for channel state information compression (CSI compression).

[0226] In addition, as shown in FIG. 12, the network device 1200 can further include a transceiver 1240, an antenna 1250, and the like; functions of the above components are similar to those of the prior art, and will not be described here. It should be noted that the network device 1200 does not necessarily include all the components shown in FIG. 12; in addition, the network device 1200 can include components not shown in FIG. 12, and reference can be made to the prior art.

[0227] The embodiments of the present application further provide a computer program, which, when executed in a terminal device, causes the terminal device to perform the data transceiving method according to the embodiments of the first aspect.

[0228] The embodiments of the present application further provide a storage medium storing a computer program, which causes a terminal device to perform the data transceiving method according to the embodiments of the first aspect.

[0229] The embodiments of the present application further provide a computer program, which, when executed in a network device, causes the network device to perform the data transceiving method according to the embodiments of the second aspect.

[0230] The embodiments of the present application further provide a storage medium storing a computer program, which causes a network device to perform the data transceiving method according to the embodiments of the second aspect.

[0231] The apparatuses and methods described above can be implemented by hardware, or by hardware combined with software. The present application relates to a computer readable program, which, when executed by a logic component, can cause the logic component to implement the apparatuses or constituent components described above, or to implement the various methods or steps described above. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, etc.

[0232] The methods / apparatuses described in connection with the embodiments of the present application can be directly embodied as hardware, software modules executed by a processor, or a combination of the two. For example, one or more of the functional blocks shown in the figures and / or a combination of one or more of the functional blocks can correspond to individual software modules of a computer program flow, or to individual hardware modules. These software modules can correspond to individual steps shown in the figures, respectively. These hardware modules can be implemented by, for example, fixing software modules using a field programmable gate array (FPGA).

[0233] The software modules can reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium can be coupled to the processor, such that the processor can read information from, and write information to, the storage medium; in the alternative, the storage medium can be integral to the processor. The processor and the storage medium can reside in an ASIC. The software modules can be stored in a memory of the mobile terminal, or in a memory card that can be inserted into the mobile terminal. For example, if the device (e.g., mobile terminal) employs a MEGA-SIM card or a flash memory device with a large capacity, the software modules can be stored in the MEGA-SIM card or the flash memory device.

[0234] One or more of the functional blocks described in the accompanying drawings and / or one or more combinations of the functional blocks can be implemented as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any appropriate combination thereof, for performing the functions described in this application. One or more of the functional blocks described in the accompanying drawings and / or one or more combinations of the functional blocks 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 conjunction with a DSP core, or any other such configuration.

[0235] The application has been described above with the attachment to the specific embodiments, but it should be clear to those skilled in the art that these descriptions are exemplary and are not a limitation on the scope of protection of the application. Those skilled in the art can make various modifications and changes to the application according to the spirit and principles of the application, and these modifications and changes are also within the scope of the application.

[0236] With regard to the embodiments including the above embodiments, the following notes are also disclosed:

[0237] 1. A data transceiving method, comprising:

[0238] a terminal device receiving a set of data from a network device for training an AI / ML model / function; and / or

[0239] the terminal device sending a set of data to the network device for training an AI / ML model / function;

[0240] wherein the AI / ML model / function is for channel state information compression (CSI compression).

[0241] 2. A data transceiving method, comprising:

[0242] a network device sending a data set for training an AI / ML model / function to a terminal device; and / or

[0243] the network device receiving a data set for training an AI / ML model / function from the terminal device;

[0244] wherein the AI / ML model / function is used for channel state information compression (CSI compression).

[0245] 3. A terminal device comprising a memory and a processor, the memory storing a computer program, the processor being configured to execute the computer program to implement the data transceiving method of the appended item 1.

[0246] 4. A network device comprising a memory and a processor, the memory storing a computer program, the processor being configured to execute the computer program to implement the data transceiving method of the appended item 2.

[0247] 5. A computer program product comprising at least a computer program, the computer program being executed by a processor to cause a terminal device to execute the data transceiving method of the appended item 1.

[0248] 6. A computer program product comprising at least a computer program, the computer program being executed by a processor to cause a network device to execute the data transceiving method of the appended item 2.

Claims

1. A data transceiving apparatus, comprising: a receiver that receives a data set for training an AI / ML model / function from a network device; and / or a transmitter that transmits a data set for training an AI / ML model / function to the network device; wherein the AI / ML model / function is used for channel state information compression.

2. The apparatus of claim 1, wherein, The data set comprises one or more data samples; the format of the data set and / or the data samples is predefined.

3. The apparatus of claim 2, wherein, The data samples are one or more combinations of: encoder input data and decoder output data; encoder input data and encoder output data; encoder output data and decoder output data; encoder input data, encoder output data, and decoder output data.

4. The apparatus of claim 1, wherein, The data set is based on an original channel or based on a codebook; and the data set comprises or is associated with indication information indicating whether the data set is based on an original channel or based on a codebook.

5. The apparatus of claim 1, wherein, The data set comprises one or more data samples for a same rank; and the data set comprises or is associated with information of the rank.

6. The apparatus of claim 5, wherein, The data samples comprise or are associated with layer index information indicating a mapping between a feature vector of the data sample and a layer.

7. The apparatus of claim 1, wherein, The data set comprises multiple data samples for different ranks; and each data sample comprises or is associated with information of a corresponding rank.

8. The apparatus of claim 7, wherein, The data samples comprise or are associated with layer index information indicating a mapping between a feature vector of the data sample and a layer.

9. The apparatus of claim 1, wherein, The data set comprises multiple data samples for different ranks; the multiple data samples are included in one or more data sample groups, and the data samples in a data sample group correspond to a same rank.

10. The apparatus of claim 9, wherein, Different data sample groups correspond to different ranks, or different data sample groups correspond to a same rank; Each data sample group comprises or is associated with information of a corresponding rank.

11. The apparatus of claim 9, wherein, The data samples comprise or are associated with layer index information indicating a mapping between a feature vector of the data sample and a layer.

12. The apparatus of claim 1, wherein, Adjacent data samples in the data set correspond to consecutive time instances.

13. The apparatus of claim 12, wherein, The time interval between two consecutive time instances corresponding to adjacent data samples in the data set is the same; The data set comprises or is associated with information of the time interval.

14. The apparatus of claim 12, wherein, The data set comprises multiple data samples based on multiple time intervals; the multiple data samples are included in one or more data sample groups, and the data samples in a data sample group have the same time interval.

15. The apparatus of claim 14, wherein, For different data sample groups, the time interval between data samples is the same, or for different data sample groups, the time interval between data samples is different.

16. The apparatus of claim 1, wherein, The data samples comprise an association ID indicating a condition / configuration of a terminal device and / or a network device.

17. The apparatus of claim 16, wherein, The data set comprises one or more data samples for one association ID; and the data set comprises or is associated with information of the association ID; and / or The data set comprises a plurality of data samples for a plurality of association IDs; the plurality of data samples are included in one or more data sample groups, and one data sample group corresponds to one association ID.

18. The apparatus of claim 1, wherein, The apparatus further comprises: a processor that compresses the data set for training the AI / ML model / function.

19. A data transceiving apparatus comprising: a transmitter that transmits a data set for training an AI / ML model / function to a terminal device; and / or a receiver that receives a data set for training an AI / ML model / function from the terminal device; wherein the AI / ML model / function is for channel state information compression.

20. A communication system comprising: a terminal device that receives a data set for training an AI / ML model / function from a network device, and / or transmits a data set for training an AI / ML model / function to the network device; a network device that transmits a data set for training an AI / ML model / function to a terminal device, and / or receives a data set for training an AI / ML model / function from the terminal device; wherein the AI / ML model / function is for channel state information compression.

Images