Generating channel state information (CSI) reports using artificial intelligence models

Abstract

A user equipment (UE) includes a transceiver and a processor configured to receive a configuration of channel state information (CSI) reporting characteristics from a network via the transceiver. The CSI report characteristic includes one or more of a maximum size of a CSI report payload, a maximum number of bits per layer or rank, a neural network (NN) identification (ID), or an expected CSI report content type. The processor is configured to generate a CSI report according to the received CSI report characteristics for transmission to the network via the transceiver.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This Patent Cooperation Treaty patent application claims priority to U.S. non-provisional patent application No. 17 / 958,207, filed on September 30, 2022, and entitled “Generation of a Channel State Information (CSI) Reporting Using an Artificial Intelligence Model,” the contents of which are incorporated herein by reference in their entirety. Technical Field

[0003] The present application generally relates to wireless communication systems, including methods and systems for channel state information (CSI) feedback using artificial intelligence (AI) models. Background Art

[0004] Wireless mobile communication technologies use various standards and protocols to send data between network devices (e.g., base stations) and wireless communication devices. Wireless communication system standards and protocols may include, for example, the 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE) (e.g., 4G), 3GPP New Radio (NR) (e.g., 5G), and the IEEE 802.11 standard for wireless local area networks (WLANs) (commonly referred to within industry organizations as WLANs). ).

[0005] As envisioned by 3GPP, different wireless communication system standards and protocols may use various radio access networks (RANs) to communicate between network equipment of the RAN (which may also sometimes be referred to as RAN nodes, network nodes, or simply nodes) and wireless communication devices referred to as user equipment (UE). 3GPP RANs may include, for example, Global System for Mobile Communications (GSM), Enhanced Data Rates for GSM Evolution (EDGE) RAN (GERAN), Universal Terrestrial Radio Access Network (UTRAN), Evolved Universal Terrestrial Radio Access Network (E-UTRAN), and / or Next Generation Radio Access Network (NG-RAN).

[0006] Each RAN may use one or more radio access technologies (RATs) for communication between network equipment and UEs. For example, GERAN implements GSM and / or EDGE RATs, UTRAN implements Universal Mobile Telecommunications System (UMTS) RATs or other 3GPP RATs, E-UTRAN implements LTE RATs (sometimes referred to as LTE), and NG-RAN implements NR RATs (sometimes referred to herein as 5G RATs, 5G NR RATs, or simply NR). In some deployments, E-UTRAN may also implement NR RATs. In some deployments, NG-RAN may also implement LTE RATs.

[0007] The network equipment used by the RAN may correspond to the RAN. An example of an E-UTRAN network equipment is an Evolved Universal Terrestrial Radio Access Network (E-UTRAN) Node B (also commonly denoted as an evolved Node B, enhanced Node B, eNodeB, or eNB). An example of an NG-RAN network equipment is a Next Generation Node B (sometimes also referred to as a gNodeB or gNB).

[0008] The RAN provides communication services together with external entities through its connection with the Core Network (CN). For example, E-UTRAN may utilize the Evolved Packet Core (EPC) and NG-RAN may utilize the 5G Core Network (5GC). BRIEF DESCRIPTION OF THE DRAWINGS

[0009] To easily identify the discussion of any particular element or action, the most significant digit(s) in a reference number refers to the drawing number that first introduces the element.

[0010] Figure 1 An example wireless communication system is shown in accordance with embodiments described herein.

[0011] Figure 2 Various example formats of CSI reports generated by a user equipment (UE) based on CSI reporting characteristics including a maximum size of a CSI report payload according to embodiments described herein are illustrated.

[0012] Figure 3 An example method of generating a CSI report according to embodiments described herein is illustrated.

[0013] Figure 4 Various example formats of CSI reports generated by a UE based on CSI reporting characteristics including a maximum size of a CSI report payload and a maximum number of bits per layer or rank in a CSI report according to embodiments described herein are illustrated.

[0014] Figure 5AVarious example formats of CSI reports generated by a UE that does not support puncturing in CSI reports according to the embodiments described herein are illustrated.

[0015] Figure 5B Various example formats of CSI reports generated by a UE supporting puncturing in CSI reporting according to the embodiments described herein are illustrated.

[0016] Figure 6 An example flow diagram illustrating operations that may be performed by a user equipment (UE) according to embodiments described herein.

[0017] Figure 7 An example format of a CSI report generated based on channel-based feedback according to embodiments described herein is illustrated.

[0018] Figure 8 An example flow diagram illustrating operations that may be performed by a network device of a RAN according to embodiments described herein.

[0019] Fig. 9 An example architecture of a wireless communication system according to embodiments disclosed herein is illustrated.

[0020] Fig.10 A system for performing signaling between a wireless device and a network device according to embodiments disclosed herein is illustrated. DETAILED DESCRIPTION

[0021] Various embodiments in the present disclosure relate to methods and systems for generating channel state information (CSI) feedback (or CSI compression feedback or CSI report) based on an artificial intelligence (AI) model. CSI feedback based on an AI model can reduce overhead, improve accuracy, and improve channel prediction. Currently, for CSI feedback, AI models can be trained according to various frameworks, including type 1 (joint training of bilateral AI models at a single entity (e.g., UE or network)), type 2 (joint training of bilateral AI models at UE and network), and type 3 (separate training at the network and UE, where the UE generates a CSI report and the network performs CSI reconstruction).

[0022] As described in the present disclosure, joint training may include training a model for generating CSI reports on the UE side and a model for reconstruction on the network side in the same loop for forward propagation and backward propagation. In addition, joint training may be performed using a single node or across multiple nodes, for example, it may be performed using gradient exchange between nodes. Separate training may include sequentially training a model on the UE side and a model on the network side, where the UE side or network side model may be trained first, or may be performed in parallel. In addition to Type 1, Type 2 and / or Type 3, other frameworks not mentioned in the present disclosure may also be used.

[0023] Various embodiments in the present disclosure describe generating CSI reports based on various configurations (e.g., payload size of CSI reports, format of CSI reports, etc.) for CSI report generation based on precoder matrix index (PMI) feedback and / or channel feedback. As described herein, generating a CSI report may include determining a channel quality indicator (CQI) and / or a rank indicator (RI). The CQI and / or RI in the CSI report is used to select a transmission layer for transmission in a downlink (DL) direction.

[0024] Reference will now be made specifically to the representative embodiments / aspects shown in the accompanying drawings. The following description is not intended to limit the embodiments to a preferred embodiment. On the contrary, it is intended to cover alternatives, combinations, modifications and equivalents that may be included within the spirit and scope of the embodiments defined by the appended claims.

[0025] Figure 1 An example wireless communication system according to the embodiments described herein is shown. Figure 1 As shown, the wireless communication system 100 may include a network device 102, a network device 104, and a user equipment (UE) 106. The UE 106 may be communicatively coupled to the network device 102 and / or the network device 104 to send data in an uplink (UL) direction and / or receive data in a downlink (DL) direction. In some embodiments, the network devices 102 and 104 may be eNb, eNodeB, gNodeB, or access point (AP) in a radio access network (RAN), and may support one or more radio access technologies, such as 4G, 5G, 5G New Radio (5G NR), etc. The UE 106 may be a phone, a smart phone, a tablet, a smart watch, an Internet of Things (IoT), a vehicle, etc.

[0026] The CSI report describes the state of the channel. The UE may send a CSI report as feedback to the network device. The CSI report may include several parameters, such as a channel quality indicator (CQI), a precoding matrix indicator (PMI) with different codebook sets, and a rank indicator (RI). The UE may use a channel state information reference signal (CSI-RS) to measure the CSI feedback and generate a CSI report. Upon receiving the CSI report, the network device may schedule data transmission in the DL direction on a specific transmission layer.

[0027] In some embodiments, performance monitoring for CSI feedback may be performed using a bilateral model on the UE side and on the network side. The UE may generate a CSI report based on performance monitoring using an AI model. The UE may generate a CSI report based on a configuration of a CSI report received from a network device (or a configuration of a CSI report characteristic), and send the CSI report to the network device. As a non-limiting example, the configuration of the CSI report characteristic may include one or more of the following: a maximum size of a CSI report payload, a maximum number of bits per layer or rank, a neural network (NN) identifier (ID) (or an ID of an AI model), and / or an expected CSI report content type. The NN ID identifies a specific AI model used by the UE for performance monitoring. Different AI models may be configured for each layer or rank for performance monitoring. Alternatively, the same AI model may be configured for each layer or rank for performance monitoring.

[0028] Figure 2 Various example formats of CSI reports generated by a user equipment (UE) based on a CSI report configuration according to an embodiment described herein are illustrated, the CSI report configuration including a maximum size of a CSI report payload. For example, a network device may configure the UE for a configuration of a CSI report characteristic including a maximum size (e.g., max) of a CSI report payload. The network device may also configure the UE so that there are an equal number of bits in the CSI report payload for each layer or rank. Therefore, the UE may select an AI model having an AI encoder function that generates CSI reports with equal payloads for each layer or rank. In other words, the UE may select an AI model having an AI encoder function that generates a CSI report output of a size less than max / N for each layer or rank. In Figure 2 , diagram 200 shows various example formats of CSI reports.

[0029] The CSI reporting format for a UE configured with a maximum size of CSI report and an equal number of bits per layer or rank may be Figure 2202. A CSI report 202 having a maximum size of a CSI report and an equal number of bits per layer or rank may include an RI 202a, a CQI 202b, an NN ID 202c, and an encoder output 202d for a first layer (or layer 1). In some embodiments, and as a non-limiting example, the UE may train and / or use the same AI model for all layers or ranks, and the NNID (or AI model ID) of the AI ​​model may be included in the CSI report as 202c. However, if a different AI model is trained and / or used for each layer or rank, the NN ID corresponding to the second layer or rank may be included in the CSI report as 202e. Therefore, the NN ID of the AI ​​model associated with the second layer or rank may be optional. The CSI report 202 may include an encoder output 202f for a second layer (or layer 2). Even though not shown in the CSI report 202, the encoder output 202f for the second layer may be followed by the NN ID of the AI ​​model associated with the third layer or rank (if a different AI model is trained and / or used for the third layer or rank) and the encoder output for the third layer (or layer 3), etc. The encoder output 202d for the first layer (or layer 1), the encoder output 202f for the second layer (or layer 2) may have the same size. In addition, the total size of the CSI report payload including the RI 202a, the CQI 202b, the NN ID 202c, the encoder output 202d for the first layer, the NN ID 202e, the encoder output 202f for the second layer, etc. does not exceed the maximum size (e.g., max) of the CSI report payload configured by the network device.

[0030] In some embodiments, and as a non-limiting example, the network device may configure the UE for a configuration of a CSI report characteristic including a maximum size (e.g., max) of the CSI report payload. The network device may also configure the UE so that there are different numbers of bits in the CSI report payload of each layer or rank. Therefore, the UE may select a corresponding AI model corresponding to each layer or rank. The corresponding AI model for each layer or rank may have an AI encoder function that generates an encoder output for the layer or rank, which encoder output does not exceed the maximum size (e.g., max) of the CSI report payload when added to the AI ​​encoder function output of other layers or ranks. In addition, the AI ​​encoder function output for one layer or rank may be different from the AI ​​encoder function output for another layer or rank. In other words, if the maximum size of the CSI report payload is max, and for four layers or ranks, the UE may select four different AI models, wherein their AI encoder functions generate outputs K1, K2, K3, and K4 for layers 1 to 4, respectively, wherein the sum of K1, K2, K3, and K4 does not exceed the configured maximum size (e.g., max) of the CSI report payload.

[0031] The CSI reporting format for UEs configured with a maximum size of CSI report and a different number of bits per layer or rank may be specified in Figure 2 204. The CSI report 204 with the maximum size of the CSI report and different numbers of bits per layer or rank may include RI 204a, CQI 204b, NN ID 204c, and encoder output 204d for the first layer (or layer 1). The CSI report 204 may also include the NN ID corresponding to the second layer or rank as 204e. The CSI report 204 may include an encoder output 202f for the second layer (or layer 2). Even though not shown in the CSI report 204, the encoder output 202f for the second layer may be followed by the NN ID of the AI ​​model associated with the third layer or rank and the encoder output for the third layer (or layer 3), etc. The encoder output 204d for the first layer (or layer 1) and the encoder output 204f for the second layer (or layer 2) may have different sizes. Therefore, in addition to the encoder function output corresponding to each layer or rank, the CSI report 204 may also include RI, CQI per subband or wideband, and NN ID for each layer or rank.

[0032] In some embodiments, the network (or network device) may not configure the number of bits per layer, and the UE may determine whether to generate CSI reports with equal or different numbers of bits per layer or rank, and / or a maximum number of bits per layer, based on the UE specific implementation. Thus, the UE may have maximum or better control over the AI ​​model selection, where the limit on the maximum payload size of the generated CSI report fits within the physical uplink control channel (PUCCH) format.

[0033] In some embodiments, the UE may be configured with a list of NN IDs by a network device, for example via radio resource control (RRC) signaling. The NN ID in the CSI report may be an index of an NN ID in the configured NN ID list to reduce the payload size of the CSI report. If the NN ID list is configured to include 8 NN IDs, the NN ID field in the CSI report may, for example, have 3 bits.

[0034] In some embodiments, and as a non-limiting example, the network device may configure the UE for a configuration of CSI reporting characteristics including a maximum size (e.g., max) of the CSI report payload. The network device may also configure the UE so that there are the same or different number of bits in the CSI report payload for each layer or rank. The UE may select one or more AI models as described above, which may generate a CSI report payload that does not exceed the maximum size (e.g., max) of the CSI report payload, and the encoder function output for each layer or rank is the same or different than that configured by the network device. The UE may be further configured to generate a CSI report with truncation. Thus, if the UE supports truncation, the UE may indicate the actual number of bits and / or the number of truncation bits in the CSI report. For CSI reports with different number of bits per layer or rank with truncation, Figure 2 206. The CSI report 206 may include RI 206a, CQI 206b, NN ID 206c, and encoder output 206d for the first layer (or layer 1). The CSI report 206 may also include punctured bits 206e, followed by encoder output 206f for the second layer (or layer 2). Even though not shown in the CSI report 204, the encoder output 202f for the second layer may be followed by punctured bits and encoder output for the third layer (or layer 3), etc. The encoder output 206d for the first layer (or layer 1) and the encoder output 206f for the second layer (or layer 2) may have different sizes.

[0035] Figure 3 An example method of generating a CSI report according to an embodiment described herein is illustrated. As shown in the example method 300, at 302, the UE may determine the RI based on a channel state information reference signal (CSI-RS) measurement. The RI suggests the number of multiple-input multiple-output (MIMO) layers of a multiple-input multiple-output (MIMO) system. As a non-limiting example, a conventional method based on a wideband covariant matrix may be used to determine the RI. However, other methods and / or matrices may also be used.

[0036] At 304, the UE may determine the number of bits per layer or rank based on the RI determined at 302 (e.g., using Figure 4 As used herein Figure 2 As described above, the UE may be configured by the network device for the number of bits per layer or rank, and the UE may use the Figure 2 The UE may select one or more AI models (or one or more AI encoder functions) as described above, and execute (or run) the selected one or more encoder functions. Based on the output generated by executing the selected one or more encoder functions, at 308, the UE may generate a CSI report. Figure 2As shown, the generated CSI report may include RI, CQI per subband and / or broadband, encoder output (or AI model output) for each layer or rank, and / or one or more NN IDs. If the UE supports puncturing, the CSI report may also include puncturing bits and / or the position of puncturing bits in the CSI report.

[0037] Figure 4 Various example formats of CSI reports generated by a UE based on CSI reporting characteristics according to the embodiments described herein are illustrated, and the CSI reporting characteristics include the maximum size of the CSI report payload and the maximum number of bits per layer or rank in the CSI report. For example, the network device may configure the UE for a configuration of a CSI reporting characteristic including the maximum size (e.g., max) of the CSI report payload. The network device may also configure the UE for the maximum number of bits in the CSI report payload for each layer or rank. Therefore, the UE may select an AI model with an AI encoder function based on the RI. In other words, the UE may select an AI model with an AI encoder function corresponding to each layer or rank.

[0038] exist Figure 4 In the illustrated diagram 400, various CSI report formats corresponding to different RIs are shown. CSI report 402 may correspond to an RI of 1 and include RI 402a, CQI 402b, NN ID 402c, and encoder function output 402d for layer 1. The UE may select an AI model with an encoder function that outputs a maximum number of bits equal to or less than the configured maximum number of bits per layer or rank. CSI report 404 may correspond to an RI of 2 and include RI 404a, CQI 404b, NN ID 404c, and encoder function output 404d for layer 1. CSI report 404 may also include NN ID 404e corresponding to the second layer and encoder function output 404f for layer 2. Therefore, when compared to the CSI report payload for an RI of 1, the CSI report payload size may be almost twice as large. For an RI of 3 or 4, and the UE may select a corresponding AI model for each layer or rank, where the encoder output for each layer or rank has the same or different number of bits. The CSI report 406 may correspond to an RI of 3 and include an RI 406a, a CQI 406b, an NN ID 406c, and an encoder function output 406d for layer 1. The CSI report 406 may also include an NN ID 406e corresponding to the second layer and an encoder function output 406f for layer 2. The CSI report 406 may also include an NN ID 406g corresponding to the third layer and an encoder function output 406h for layer 3.

[0039] Figure 5AVarious example formats of CSI reports generated by a UE that does not support truncation in CSI reports according to the embodiments described herein are illustrated. Specifically, the various example formats of CSI reports generated by the UE and shown in diagram 500a correspond to CSI report characteristics including a maximum size of a CSI report payload and a configured NN ID for each layer or rank. Based on the inference capability and / or memory / storage capability (or capacity) of the UE, the UE may be configured for the same NN ID for all layers or ranks, or for different NN IDs for each layer or rank.

[0040] The CSI report 502 may correspond to an RI of 1 and include an RI 502a, a CQI 502b, and an encoder function output 502c for layer 1. The UE may select an AI model with an encoder function whose output is equal to or less than the maximum number of bits of the maximum number of bits per layer or rank configured. The CSI report 504 may correspond to an RI of 2 and include an RI 504a, a CQI 504b, and an encoder function output 504c for layer 1. The CSI report 504 may also include an encoder function output 504d for layer 2. The CSI report 506 may correspond to an RI of 3 and include an RI 506a, a CQI 506b, and an encoder function output 506c for layer 1. The CSI report 506 may also include an encoder function output 506d for layer 2 and an encoder function output 506e for layer 3. Therefore, the CSI report payload is determined based on the determined RI, or the CSI report payload size increases as the RI increases. In other words, the CSI report payload scales with the RI.

[0041] Figure 5B Various example formats of CSI reports generated by a UE supporting truncation in CSI reports according to the embodiments described herein are illustrated. Specifically, the various example formats of CSI reports generated by the UE and shown in diagram 500b correspond to CSI reporting characteristics including a maximum size of a CSI report payload and a configured NN ID for each layer or rank. Based on the inference capability and / or memory / storage capability (or capacity) of the UE, the UE may be configured for the same NN ID for all layers or ranks, or for different NN IDs for each layer or rank.

[0042] The CSI report 508 may correspond to an RI of 1 and include RI 508a, CQI 508b, and encoder function output 508c for layer 1. The UE may select an AI model with an encoder function that outputs a maximum number of bits equal to or less than the configured maximum number of bits per layer or rank. Since the RI is 1, the CSI report 508 may correspond to an RI of 1. Figure 5A502 in the CSI report is not different. CSI report 510 may correspond to an RI of 2 and include RI 510a, CQI 510b and encoder function output 510c for layer 1. CSI report 510 may also include encoder function output 510d for layer 2. Based on the puncturing configuration configured by the network device, the UE may include puncturing bits in the CSI report. The puncturing configuration may be received by the UE using RRC signaling. As a non-limiting example, when the RI is 2, the puncturing configuration may not indicate that the puncturing bits are included. Therefore, as shown in CSI report 510, the puncturing bits may not be included in the CSI report. CSI report 512 may correspond to an RI of 3 and include RI 512a, CQI 512b and encoder function output 512c for layer 1. CSI report 512 may also include puncturing bits according to the puncturing configuration, which is shown as 512d and 512f of encoder function outputs for separating different layers or ranks. The CSI report 512 may thus include an encoder function output 512e for layer 2 and an encoder function output 512g for layer 3. In some implementations, the UE may not be configured with a puncturing configuration, and the UE may include puncturing bits having a puncturing bit size that is selected or determined in such a way that the payload size of the CSI report does not exceed the configured maximum size of the CSI report payload.

[0043] Figure 6 An example flow chart illustrating operations that may be performed by a user equipment (UE) according to an embodiment described herein. As shown in flow chart 600, at 602, the UE may receive a configuration of CSI reporting characteristics from a network (or network device). The CSI reporting characteristics may include one or more of the following: a maximum size of a CSI report payload, a maximum number of bits per layer or rank, an NN ID (corresponding to one or more layers or ranks), and an expected CSI report content type. As a non-limiting example, the CSI reporting characteristics may be specified to include a list of NN IDs and / or a specific NN ID corresponding to each layer or rank. The expected CSI report content type may indicate to the UE whether the CSI report includes a PMI-based CSI output or a channel-based CSI output. Using Figure 7 The CSI reporting format according to the channel-based CSI output is described.

[0044] As a non-limiting example, a PMI-based CSI output may have a PMI-based CSI output that does not require a spatial or frequency domain transform. The UE may perform an eigenvector calculation and select an AI model (or AI encoder function) based on the calculated eigenvector as input. Alternatively, a PMI-based CSI output may have a PMI-based CSI output that requires a spatial and / or frequency domain transform. The UE may perform a domain transform based on a maximum spatial basis transform configuration and / or a maximum frequency domain transform configuration, and select an AI model (or AI encoder function) based on the performed domain transform as input.

[0045] In some embodiments, and as a non-limiting example, for PMI-based CSI report generation, if the CSI reconstruction model is unknown at the UE, or the UE does not have the ability to perform CSI reconstruction model inference due to processing complexity or delay constraints, the CQI can be a subband CQI based on an ideal eigenvector. Alternatively, in the case where the UE knows the CSI reconstruction model and has the ability to perform reconstruction model inference within the CSI processing time limit, the CQI can be a subband CQI based on a quantized PMI (such as a CSI reconstruction model output). The CQI subband can be configured to be wider than the PMI subband. Alternatively, the CQI can be wideband.

[0046] In some embodiments, and as a non-limiting example, the channel-based CSI output may have a channel-based CSI output that does not require a spatial or frequency domain transform. The UE may perform an AI encoder function based on a CSI-RS measurement configuration received from the network (or network device). Alternatively, the channel-based CSI output may have a channel-based CSI output that requires a spatial and / or frequency domain transform. The UE may perform a domain transform based on a spatial basis transform configuration and / or a frequency domain transform configuration, and select an AI model (or AI encoder function) based on the domain transform performed as input.

[0047] Other aspects of the CSI reporting characteristics are described in detail in this disclosure, and therefore, those details are not repeated for the sake of brevity.At 604, the UE may generate a CSI report based on the CSI reporting characteristics and send to the network (or network device).

[0048] Figure 7 An example format of a CSI report generated based on channel-based feedback according to embodiments described herein is illustrated. Figure 2 , Figure 4 , Figure 5A and / or Figure 5BThe CSI report format shown is based on a PMI-based CSI output. The CSI report format 700 may correspond to a CSI report format based on channel-based feedback. The CSI report for channel-based feedback may include a CQI 702 and an encoder function output 704 for channel feedback. As a non-limiting example, the payload size of the CSI report and / or the NN ID (of the encoder function to be used) may be configured by the network (or networking device). The CSI report payload size (or encoder output channel feedback size) may not be based on the RI, but may be determined based on the number of transmit or receive antenna ports at the UE.

[0049] In some embodiments, for channel-based CSI report generation, the CQI may be a subband CQI assuming open-loop MIMO, and the CQI may reflect the level of inter-cell interference. Additionally or alternatively, the CQI may be a subband CQI based on a complete (or ideal) eigenvector. The CQI subband may be configured to be wider than the channel feedback subband size. In some embodiments, the CQI may be wideband.

[0050] Figure 8 An example flow chart illustrating operations that may be performed by a network device of a RAN according to an embodiment described herein is illustrated. As shown in flowchart 800, at 802, a network device (e.g., a base station) may send a configuration of a CSI reporting characteristic to a UE. The CSI reporting characteristic may include one or more of the following: a maximum size of a CSI report payload, a maximum number of bits per layer or rank, an NN ID (corresponding to one or more layers or ranks), and an expected CSI report content type. As a non-limiting example, it may be specified that the CSI reporting characteristic may include a list of NN IDs and / or a specific NN ID corresponding to each layer or rank. The expected CSI report content type may indicate to the UE whether the CSI report includes a PMI-based CSI output or a channel-based CSI output. At 804, the network device may receive from the UE a CSI report generated by the UE according to the sent CSI reporting characteristic. Since the generation of CSI reports of various formats based on the CSI reporting characteristics sent at 802 is described in detail in the present disclosure, those details are not repeated for brevity.

[0051] Embodiments contemplated herein include an apparatus having means for performing one or more elements of method 600 or 800. In the context of method 600, the apparatus may be, for example, an apparatus of a UE (such as wireless device 1002 as a UE, as described herein). In the context of method 600, the apparatus may be, for example, an apparatus of a network device (such as network device 1020, as described herein).

[0052] Embodiments contemplated herein include one or more non-transitory computer-readable media storing instructions that, when executed by one or more processors of an electronic device, cause the electronic device to perform one or more elements of method 600 or 800. In the context of method 600, the non-transitory computer-readable medium may be, for example, a memory of a UE (such as memory 1006 of wireless device 1002 as a UE, as described herein). In the context of method 800, the non-transitory computer-readable medium may be, for example, a memory of a network device (such as memory 1024 of network device 1020, as described herein).

[0053] Embodiments contemplated herein include an apparatus having logical components, modules, or circuits for performing one or more elements of method 600 or 800. In the context of method 600, the apparatus may be, for example, an apparatus of a UE (such as wireless device 1002 as a UE, as described herein). In the context of method 800, the apparatus may be, for example, an apparatus of a network device (such as network device 1020, as described herein).

[0054] Embodiments contemplated herein include an apparatus having one or more processors and one or more computer-readable media that use or store instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more elements of method 600 or 800. In the context of method 600, the apparatus may be, for example, an apparatus of a UE (such as wireless device 1002 as a UE, as described herein). In the context of method 800, the apparatus may be, for example, an apparatus of a network device (such as network device 1020, as described herein).

[0055] Embodiments contemplated herein include a signal as described in or in connection with one or more elements of method 600 or 800 .

[0056] Embodiments contemplated herein include a computer program or computer program product having instructions, wherein execution of the program by a processor causes the processor to perform one or more elements of the method 600 or 800. In the context of the method 600, the processor may be a processor of a UE (such as the processor 1004 of the wireless device 1002 as a UE, as described herein), and the instructions may be located, for example, in the processor and / or on a memory of the UE (such as the memory 1006 of the wireless device 1002 as a UE, as described herein). In the context of the method 800, the processor may be a processor of a network device (such as the processor 1022 of the network device 1020, as described herein), and the instructions may be located, for example, in the processor and / or on a memory of the network device (such as the memory 1024 of the network device 1020, as described herein).

[0057] Fig. 9 An example architecture of a wireless communication system 900 according to an embodiment disclosed herein is illustrated. The description provided below is for an example wireless communication system 900 operating in conjunction with the LTE system standard and / or the 5G or NR system standard provided in the 3GPP technical specifications.

[0058] like Fig. 9 As shown, wireless communication system 900 includes UE 902 and UE 904 (although any number of UEs may be used). In this example, UE 902 and UE 904 are illustrated as smartphones (e.g., handheld touch screen mobile computing devices capable of connecting to one or more cellular networks), but may also include any mobile or non-mobile computing device configured for wireless communication.

[0059] UE 902 and UE 904 may be configured to be communicatively coupled to RAN 906. In an embodiment, RAN 906 may be NG-RAN, E-UTRAN, etc. UE 902 and UE 904 utilize connections (or channels) (shown as connection 908 and connection 910, respectively) with RAN 906, where each connection (or channel) includes a physical communication interface. RAN 906 may include one or more base stations, such as base station 912 and base station 914, to implement connection 908 and connection 910.

[0060] In this example, connection 908 and connection 910 are air interfaces that enable such communicative coupling and may conform to the RAT used by the RAN 906 , such as, for example, LTE and / or NR.

[0061] In some embodiments, UE 902 and UE 904 may also communicate data directly via side link interface 916. UE 904 is shown as being configured to access an access point (shown as AP 918) via connection 920. As an example, connection 920 may include a local wireless connection, such as a connection conforming to any IEEE 802.11 protocol, wherein AP 918 may include In this example, AP 918 may be connected to another network (eg, the Internet) without going through CN 924.

[0062] In an embodiment, UE 902 and UE 904 may be configured to communicate with each other or with base station 912 and / or base station 914 over a multi-carrier communication channel using orthogonal frequency division multiplexing (OFDM) communication signals according to various communication techniques, such as, but not limited to, orthogonal frequency division multiple access (OFDMA) communication techniques (e.g., for downlink communication) or single carrier frequency division multiple access (SC-FDMA) communication techniques (e.g., for uplink and ProSe or sidelink communication), although the scope of the embodiments is not limited in this respect. The OFDM signal may include multiple orthogonal subcarriers.

[0063] In some embodiments, all or part of the base station 912 or the base station 914 may be implemented as one or more software entities running on a server computer as part of a virtual network. In addition, or in other embodiments, the base station 912 or the base station 914 may be configured to communicate with each other via the interface 922. In an embodiment where the wireless communication system 900 is an LTE system (e.g., when the CN 924 is an EPC), the interface 922 may be an X2 interface. The X2 interface may be defined between two or more base stations (e.g., two or more eNBs, etc.) connected to the EPC and / or between two eNBs connected to the EPC. In an embodiment where the wireless communication system 900 is an NR system (e.g., when the CN 924 is a 5GC), the interface 922 may be an Xn interface. The Xn interface is defined between two or more base stations (e.g., two or more gNBs, etc.) connected to the 5GC, between the base station 912 (e.g., gNB) and the eNB connected to the 5GC, and / or between two eNBs connected to the 5GC (e.g., CN 924).

[0064] The RAN 906 is shown communicatively coupled to the CN 924. The CN 924 may include one or more network elements 926 configured to provide various data and telecommunication services to customers / subscribers (e.g., UE 902 and users of UE 904) connected to the CN 924 via the RAN 906. The components of the CN 924 may be implemented in one physical device or separate physical devices including components for reading and executing instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium).

[0065] In an embodiment, CN 924 may be an EPC, and RAN 906 may be connected to CN 924 via an S1 interface 928. In an embodiment, S1 interface 928 may be divided into two parts: an S1 user plane (S1-U) interface that carries service data between base station 912 or base station 914 and a serving gateway (S-GW); and an S1-MME interface that is a signaling interface between base station 912 or base station 914 and a mobility management entity (MME).

[0066] In an embodiment, CN 924 may be a 5GC, and RAN 906 may be connected to CN 924 via an NG interface 928. In an embodiment, NG interface 928 may be divided into two parts: an NG user plane (NG-U) interface, which carries service data between base station 912 or base station 914 and a user plane function (UPF); and an S1 control plane (NG-C) interface, which is a signaling interface between base station 912 or base station 914 and an access and mobility management function (AMF).

[0067] Generally, the application server 930 may be an element that provides applications that use Internet Protocol (IP) bearer resources with the CN 924 (e.g., packet-switched data services). The application server 930 may also be configured to support one or more communication services (e.g., VoIP sessions, group communication sessions, etc.) for the UE 902 and UE 904 via the CN 924. The application server 930 may communicate with the CN 924 via an IP communication interface 932.

[0068] Fig.10 A system 1000 for performing signaling 1038 between a wireless device 1002 and a network device 1020 according to an embodiment disclosed herein is illustrated. The system 1000 may be part of a wireless communication system as described herein. The wireless device 1002 may be, for example, a UE of a wireless communication system. The network device 1020 may be, for example, a base station (e.g., an eNB or a gNB) of a wireless communication system.

[0069] The wireless device 1002 may include one or more processors 1004. The processor 1004 may execute instructions to perform various operations of the wireless device 1002, as described herein. The processor 1004 may include one or more baseband processors implemented using, for example, a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a controller, a field programmable gate array (FPGA) device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.

[0070] The wireless device 1002 may include a memory 1006. The memory 1006 may be a non-transitory computer-readable storage medium that stores instructions 1008 (which may include, for example, instructions executed by the processor 1004). The instructions 1008 may also be referred to as program code or a computer program. The memory 1006 may also store data used by the processor 1004 and results computed by the processor.

[0071] The wireless device 1002 may include one or more transceivers 1010, which may include radio frequency (RF) transmitter and / or receiver circuitry that uses an antenna 1012 of the wireless device 1002 to facilitate signaling (e.g., signaling 1038) to and / or from the wireless device 1002 with other devices (e.g., network device 1020) in accordance with a corresponding RAT.

[0072] The wireless device 1002 may include one or more antennas 1012 (e.g., one, two, four, or more). For implementations with multiple antennas 1012, the wireless device 1002 may take advantage of the spatial diversity of these multiple antennas 1012 to transmit and / or receive multiple different data streams on the same time-frequency resources. This behavior may be referred to as, for example, multiple-input multiple-output (MIMO) behavior (referring to multiple antennas used at each of the transmitting device and the receiving device to implement this aspect). MIMO transmission by the wireless device 1002 may be implemented based on precoding (or digital beamforming) applied at the wireless device 1002, which multiplexes the data streams across the antennas 1012 based on known or assumed channel characteristics, so that each data stream is received with appropriate signal strength relative to the other streams and at a desired location in the spatial domain (e.g., the location of the receiver associated with the data stream). Certain embodiments may use a single-user MIMO (SU-MIMO) approach (where data streams are all directed to a single receiver) and / or a multi-user MIMO (MU-MIMO) approach (where separate data streams may be directed to separate (different) receivers in different locations in the spatial domain).

[0073] In certain embodiments with multiple antennas, the wireless device 1002 may implement analog beamforming techniques whereby the phases of signals transmitted by antennas 1012 are relatively adjusted such that the (joint) transmissions of antennas 1012 are directional (this is sometimes referred to as beam steering).

[0074] The wireless device 1002 may include one or more interfaces 1014. The interfaces 1014 may be used to provide input to or output from the wireless device 1002. For example, a wireless device 1002 that is a UE may include an interface 1014, such as a microphone, a speaker, a touch screen, buttons, etc., to allow a user of the UE to provide input and / or output to the UE. Other interfaces of such a UE may consist of transmitters, receivers, and other circuits (e.g., in addition to the transceiver 1010 / antenna 1012 already described), which allow communication between the UE and other devices and may be performed according to known protocols (e.g., etc.) to perform the operation.

[0075] The wireless device 1002 may include one or more CSI measurement and reporting modules 1016 (in Fig.10 1016). The CSI measurement and reporting module 1016 may be implemented via hardware, software, or a combination thereof. For example, the CSI measurement and reporting module 1016 may be implemented as a processor, circuit, and / or instructions 1008 stored in the memory 1006 and executed by the processor 1004. In some examples, the CSI measurement and reporting module 1016 may be integrated within the processor 1004 and / or the transceiver 1010. For example, the CSI measurement and reporting module 1016 may be implemented by a combination of software components (e.g., executed by a DSP or a general purpose processor) and hardware components (e.g., logic gates and circuits) within the processor 1004 or the transceiver 1010.

[0076] The CSI measurement and reporting module 1016 may be used in various aspects of the present disclosure, such as Figures 1 to 8 The CSI measurement and reporting module 1016 may be configured, for example, to configure CSI measurement and reporting and send one or more CSI reports to another device (eg, to the network device 1020).

[0077] The network device 1020 may include one or more processors 1022. The processor 1022 may execute instructions to perform various operations of the network device 1020, as described herein. The processor 1022 may include one or more baseband processors implemented using, for example, a CPU, a DSP, an ASIC, a controller, an FPGA device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.

[0078] The network device 1020 may include a memory 1024. The memory 1024 may be a non-transitory computer-readable storage medium that stores instructions 1026 (which may include, for example, instructions executed by the processor 1022). The instructions 1026 may also be referred to as program code or a computer program. The memory 1024 may also store data used by the processor 1022 and results calculated by the processor.

[0079] The network device 1020 may include one or more transceivers 1028, which may include RF transmitter and / or receiver circuits that use the antenna 1030 of the network device 1020 to facilitate signaling (e.g., signaling 1038) to and / or from the network device 1020 with other devices (e.g., wireless device 1002) according to the corresponding RAT.

[0080] The network device 1020 may include one or more antennas 1030 (e.g., one, two, four, or more). In embodiments with multiple antennas 1030, the network device 1020 may perform MIMO, digital beamforming, analog beamforming, beam steering, etc. as described.

[0081] The network device 1020 may include one or more interfaces 1032. The interface 1032 may be used to provide input to or output from the network device 1020. For example, the network device 1020 as a base station may include an interface 1032 consisting of a transmitter, a receiver, and other circuits (e.g., in addition to the transceiver 1028 / antenna 1030 already described), which enables the base station to communicate with other equipment in the core network and / or enables the base station to communicate with external networks, computers, databases, etc., for the purpose of operating, managing, and maintaining the base station or other equipment that can be operably connected to the base station.

[0082] The network device 1020 may include one or more CSI report configuration modules 1034 (in Fig.10 1022). The CSI report configuration module 1034 may be implemented via hardware, software, or a combination thereof. For example, the CSI report configuration module 1034 may be implemented as a processor, circuit, and / or instructions 1026 stored in the memory 1024 and executed by the processor 1022. In some examples, the CSI report configuration module 1034 may be integrated within the processor 1022 and / or the transceiver 1028. For example, the CSI report configuration module 1034 may be implemented by a combination of software components (e.g., executed by a DSP or a general purpose processor) and hardware components (e.g., logic gates and circuits) within the processor 1022 or the transceiver 1028.

[0083] The CSI report configuration module 1034 is used in various aspects of the present disclosure, such as Figures 1 to 8 The CSI report configuration module 1034 may configure a CSI report to be sent by another device (eg, the wireless device 1002).

[0084] For one or more embodiments, at least one of the components set forth in one or more of the foregoing figures may be configured to perform one or more operations, techniques, processes, and / or methods as described herein. For example, a baseband processor as described herein in conjunction with one or more of the foregoing figures may be configured to operate according to one or more of the examples set forth herein. For another example, circuits associated with a UE, a base station, a network element, etc. as described above in conjunction with one or more of the foregoing figures may be configured to operate according to one or more of the examples set forth herein.

[0085] Unless otherwise expressly stated, any of the above embodiments may be combined with any other embodiment (or combination of embodiments). The foregoing description of one or more specific implementations provides illustration and description, but is not intended to be exhaustive or to limit the scope of the embodiments to the precise form disclosed. In view of the above teachings, modifications and variations are possible or can be obtained from the practice of various embodiments.

[0086] Embodiments and implementations of the systems and methods described herein may include various operations that may be embodied in machine executable instructions to be executed by a computer system. A computer system may include one or more general or special purpose computers (or other electronic devices). A computer system may include hardware components that include specific logic components for performing operations; or may include a combination of hardware, software, and / or firmware.

[0087] It should be appreciated that the systems described herein include descriptions of specific embodiments. These embodiments may be combined into a single system, partially combined into other systems, separated into multiple systems, or otherwise divided or combined. In addition, it is contemplated that parameters, attributes, aspects, etc. of another embodiment may be used in one embodiment. For clarity, these parameters, attributes, aspects, etc. are described only in one or more embodiments, and it should be appreciated that these parameters, attributes, aspects, etc. may be combined with or substituted for parameters, attributes, aspects, etc. of another embodiment unless expressly stated herein.

[0088] It is understood that the use of personally identifiable information should be subject to privacy policies and practices that are generally recognized to meet or exceed industry or government requirements for maintaining user privacy. Specifically, personally identifiable information data should be managed and processed to minimize the risk of unintentional or unauthorized access or use, and the nature of the authorized use should be clearly stated to users.

[0089] Although the foregoing has been described in considerable detail for the sake of clarity, it will be apparent that certain changes and modifications may be made without departing from the principles of the invention. It should be noted that there are many alternative ways to implement both the processes and the apparatus described herein. Therefore, the embodiments of the present invention should be regarded as illustrative rather than restrictive, and the specification is not limited to the details given herein, but may be modified within the scope and equivalents of the appended claims.

Claims

1. A user equipment (UE), comprising: Transceiver; and A processor, the processor being configured to: receiving, via the transceiver, from a network, a configuration of channel state information (CSI) reporting characteristics, the configuration of the CSI reporting characteristics comprising one or more of the following: Maximum size of CSI report payload; The maximum number of bits per level or rank; Neural Network (NN) Identification (ID); or The type of content expected in CSI reports; as well as Based on the received configuration of CSI reporting characteristics, a CSI report is generated for transmission to the network via the transceiver.

2. The UE according to claim 1, wherein: The configuration of the CSI reporting characteristics includes the expected CSI report content type; and The expected CSI report content type includes a Precoder Matrix Indicator (PMI) based CSI output or a channel based CSI output.

3. The UE according to claim 1, wherein: The configuration of the CSI report characteristics includes the expected CSI report content type; The expected CSI report content type is a Precoder Matrix Indicator (PMI) based CSI output without spatial or frequency domain transformation; The processor is configured to: Perform eigenvector calculations; as well as selecting an artificial intelligence (AI) model based on the feature vector as input; and The feature vector is based on the performed feature vector calculation.

4. The UE according to claim 1, wherein: The configuration of the CSI report characteristics includes the expected CSI report content type; The expected CSI report content type is a Precoder Matrix Indicator (PMI) based CSI output with a spatial basis or a frequency domain basis; as well as The processor is configured to: performing a domain transform based on the spatial basis or the frequency domain basis; and An artificial intelligence (AI) model is selected based on the performed domain transformation as input.

5. The UE according to claim 1, wherein: The configuration of the CSI report characteristics includes the expected CSI report content type; The expected CSI report content type is a channel-based CSI output without spatial or frequency domain transform; and The processor is configured to: receiving a CSI reference signal (CSI-RS) measurement configuration; and An artificial intelligence (AI) encoder function is performed based on the received CSI-RS measurement configuration.

6. The UE according to claim 1, wherein: The configuration of the CSI report characteristics includes the expected CSI report content type; The expected CSI report content type is a channel-based CSI output having a spatial basis or a frequency domain basis; as well as The processor is configured to: performing a domain transform based on the spatial basis or the frequency domain basis; and An AI encoder function that performs an artificial intelligence (AI) model based on the performed domain transformation as input; The CSI report also includes a channel quality indicator (CQI), the CQI is per subband (subband CQI) or per wideband (wideband CQI); The sub-band CQI is based on an ideal eigenvector.

7. The UE according to claim 1, wherein: The configuration of the CSI reporting characteristics includes the maximum size of the CSI report payload and the expected CSI report content type; The expected CSI report content type is a CSI output based on a Precoder Matrix Indicator (PMI); and To generate the CSI report, the processor is configured to: Determine the rank indicator (RI) based on CSI reference signal (CSI-RS) measurements, The CSI-RS measurement is performed based on a CSI-RS measurement configuration; Based on the determined RI, selecting an AI encoder function of a corresponding artificial intelligence (AI) model for each layer or rank; executing the selected AI encoder function to generate an AI output corresponding to each layer or rank; and The CSI report is generated, wherein the CSI report includes the RI, a channel quality indicator (CQI), the AI ​​output, or an AI model identifier (ID) of the corresponding AI model for each layer or rank.

8. The UE according to claim 7, wherein: using a wideband covariance matrix to determine the RI; and selecting the AI ​​encoder function of the corresponding AI model for each layer or rank based on the number of bits per layer or rank in the CSI report; and The selected AI encoder function corresponding to the first layer or rank is different from the selected AI encoder function corresponding to the second layer or rank.

9. The UE according to claim 7, wherein: selecting the AI ​​encoder function of the corresponding AI model for each layer or rank based on the number of bits per layer or rank in the CSI report; The number of bits per layer or rank is an equal number of bits per layer or rank; The total number of layers or ranks is N; The maximum size of the CSI report payload is max; and The output size of the selected AI encoder function is (max / N).

10. The UE according to claim 7, wherein: selecting the AI ​​encoder function of the corresponding AI model for each layer or rank based on the number of bits per layer or rank in the CSI report; The number of bits per layer or rank is a different number of bits per layer or rank; The total number of layers or ranks is N; and The combined output size of the selected AI encoder functions corresponding to each layer or rank is less than the maximum size of the CSI report payload.

11. The UE according to claim 7, wherein: selecting the AI ​​encoder function of the corresponding AI model for each layer or rank based on the number of bits per layer or rank in the CSI report; The selected AI encoder functions corresponding to each layer or rank are the same; and The CSI report also includes one or more punctuation bits separating the AI ​​encoder function output for each layer or rank in the CSI report.

12. The UE according to claim 7, wherein: selecting the AI ​​encoder function of the corresponding AI model for each layer or rank based on the number of bits per layer or rank in the CSI report; The selected AI encoder functions corresponding to each layer or rank are the same; and The size of the one or more punctuations output by the AI ​​encoder function that separate each layer or rank in the CSI report is configured by the network or determined by the UE to fit the maximum size of the CSI report payload.

13. The UE according to claim 7, wherein: selecting the AI ​​encoder function of the corresponding AI model for each layer or rank based on the number of bits per layer or rank in the CSI report; The selected AI encoder functions corresponding to each layer or rank are the same; and When punctuation for separating AI encoder function outputs for different layers or ranks in the CSI report is not configured at the UE or is not supported by the UE, the AI ​​encoder output corresponding to each layer or rank is scaled based on the RI.

14. The UE according to claim 7, wherein: The processor is configured to: Training the corresponding AI model for each layer or rank; and The corresponding AI models of each layer or rank are the same or different.

15. The UE according to claim 7, wherein: The CQI is per subband (subband CQI) or per wideband (wideband CQI); The subband CQI is based on an ideal eigenvector or a quantized PMI; and The AI ​​model ID of the corresponding AI model of each layer or rank is indexed and configured at the UE using radio resource control (RRC) signaling.

16. The UE according to claim 7, wherein: The received configuration of CSI reporting characteristics includes the maximum size of the CSI report payload and the maximum number of bits per layer in the CSI report; and The determined RI is 1 or 2, and the corresponding AI model has an encoder output with the maximum number of bits per layer or rank; or The determined RI is 3 or 4, and the corresponding AI model has an encoder output for each layer or rank, and the encoder output for each layer or rank has the same or different number of bits for each layer or rank.

17. A method comprising: Receiving, at a user equipment (UE), from a network, a configuration of channel state information (CSI) reporting characteristics, the configuration of the CSI reporting characteristics comprising one or more of the following: Maximum size of CSI report payload; The maximum number of bits per level or rank; Neural Network (NN) Identification (ID); or The type of content expected in CSI reports; as well as generating a CSI report for transmission to the network according to the received configuration of the CSI reporting characteristics; wherein, The expected CSI report content type is based on the CSI output of the channel.

18. The method of claim 17, wherein: The maximum size of the CSI report payload is determined based on the number of transmit or receive antenna ports at the UE.

19. A network device comprising: Transceiver; and A processor, the processor being configured to: Sending, via the transceiver, a configuration of a channel state information (CSI) reporting characteristic to a user equipment (UE), the configuration of the CSI reporting characteristic comprising one or more of the following: Maximum size of CSI report payload; The maximum number of bits per level or rank; Neural Network (NN) Identification (ID); or The type of content expected in CSI reports; as well as A CSI report generated by the UE according to the transmitted configuration of CSI reporting characteristics is received from the UE via the transceiver.

20. The network device according to claim 19, wherein: The expected CSI report content type includes a Precoder Matrix Indicator (PMI) based CSI output or a channel based CSI output.

Images