Compression of hybrid automatic repeat request acknowledgement codebook

Abstract

A method includes receiving, by a user equipment from a network node, information indicating at least one parameter for performing compression of a hybrid automatic repeat request acknowledgement (HARQ-ACK) codebook; performing, based at least on the information and at least one HARQ-ACK codebook compression model, compression of the HARQ-ACK codebook; monitoring operation of the at least one HARQ-ACK codebook compression model; and transmitting, to the network node, the compressed HARQ-ACK codebook.

Description

Technical Field

[0001] This description relates to wireless communication. Background Technology

[0002] A communication system can be a facility that enables communication between two or more nodes or devices (such as fixed or mobile communication devices). Signals can be carried on wired or wireless carriers.

[0003] An example of a cellular communication system is the architecture being standardized by the 3rd Generation Partnership Project (3GPP). Recent developments in this area are often referred to as the Long Term Evolution (LTE) of Universal Mobile Telecommunications System (UMTS) radio access technology. EUTRA (Evolved UMTS Terrestrial Radio Access) is the air interface for 3GPP's LTE upgrade path for mobile networks. In LTE, base stations or access points (APs) (also known as enhanced node APs (eNBs)) provide radio access within a coverage area or cell. In LTE, mobile devices or mobile stations are referred to as User Equipment (UEs). LTE has incorporated numerous improvements and developments. Various aspects of LTE continue to be improved.

[0004] The development of 5G New Radio (NR) is part of the ongoing evolution of mobile broadband to meet the requirements of 5G, similar to the early evolution of 3G and 4G wireless networks. In addition to mobile broadband, 5G is also designed for emerging use cases. The goal of 5G is to deliver significant improvements in wireless performance, which can include new levels of data rates, latency, reliability, and security. 5G NR can also be expanded to efficiently connect massive Internet of Things (IoT) networks and can provide new types of mission-critical services. For example, ultra-reliable low-latency communication (URLLC) devices may require high reliability and very low latency. 6G and other networks are also under development. Summary of the Invention

[0005] In some aspects, the technology described herein relates to an apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: receive information from a network node indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; perform compression of a HARQ-ACK codebook based at least on the information and at least one HARQ-ACK codebook compression model; monitor the operation of the at least one HARQ-ACK codebook compression model; and transmit the compressed HARQ-ACK codebook to the network node.

[0006] In some aspects, the technology described herein relates to an apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: send information to a user equipment indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; monitor the operation of at least one HARQ-ACK codebook compression model; and receive the compressed HARQ-ACK codebook from the user equipment.

[0007] In some aspects, the technology described herein relates to an apparatus comprising components for performing: receiving information from a network node indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; performing compression of a HARQ-ACK codebook based at least on the information and at least one HARQ-ACK codebook compression model; monitoring the operation of at least one HARQ-ACK codebook compression model; and transmitting the compressed HARQ-ACK codebook to the network node.

[0008] In some aspects, the technology described herein relates to an apparatus comprising components for performing: sending information to a user equipment indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; monitoring the operation of at least one HARQ-ACK codebook compression model; and receiving the compressed HARQ-ACK codebook from the user equipment.

[0009] In some aspects, the techniques described herein relate to a method comprising: receiving information from a network node by a user equipment, the information indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; performing compression of a HARQ-ACK codebook based at least on the information and at least one HARQ-ACK codebook compression model; monitoring the operation of at least one HARQ-ACK codebook compression model; and sending the compressed HARQ-ACK codebook to the network node.

[0010] In some aspects, the techniques described herein relate to a method comprising: sending information from a network node to a user equipment indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; monitoring the operation of at least one HARQ-ACK codebook compression model; and receiving the compressed HARQ-ACK codebook from the user equipment.

[0011] In some aspects, the technology described herein relates to an apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: receive from a network node information associated with a machine learning (ML)-based compression algorithm for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; perform compression of the HARQ-ACK codebook based at least on the information and the ML-based compression algorithm; and transmit the compressed HARQ-ACK codebook to the network node.

[0012] In some aspects, the technology described herein relates to an apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: send to a user equipment information associated with a machine learning (ML)-based compression algorithm for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; and receive the compressed HARQ-ACK codebook from the user equipment.

[0013] In some aspects, the technology described herein relates to an apparatus comprising components for performing: receiving from a network node information associated with a machine learning (ML)-based compression algorithm for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of the following: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; performing compression of the HARQ-ACK codebook based at least on the information and the ML-based compression algorithm; and transmitting the compressed HARQ-ACK codebook to the network node.

[0014] In some aspects, the technology described herein relates to an apparatus comprising components for performing: sending information associated with a machine learning (ML)-based compression algorithm to a user equipment for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of the following: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; and receiving the compressed HARQ-ACK codebook from the user equipment.

[0015] In some aspects, the techniques described herein relate to a method comprising: receiving, by a user equipment, information associated with a machine learning (ML)-based compression algorithm from a network node, the ML-based compression algorithm being used to perform compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of the following: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; performing compression of the HARQ-ACK codebook based at least on the information and the ML-based compression algorithm; and transmitting the compressed HARQ-ACK codebook to the network node.

[0016] In some aspects, the techniques described herein relate to a method comprising: a network node sending information associated with a machine learning (ML)-based compression algorithm to a user equipment, the ML-based compression algorithm being used to perform compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of the following: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; and receiving the compressed HARQ-ACK codebook from the user equipment.

[0017] For each instance method in the example methods, other example embodiments are provided or described, including: components for performing any of the example methods; a non-transitory computer-readable storage medium including instructions stored thereon, which, when executed by at least one processor, are configured to cause a computing system to perform any of the example methods; and an apparatus including at least one processor and at least one memory, the at least one memory including computer program code, the at least one memory and the computer program code being configured, together with the at least one processor, to cause the apparatus to perform at least any of the example methods.

[0018] Details of one or more examples in the embodiments are set forth in the accompanying drawings and the following description. Further features will be apparent from the description and drawings, and from the claims. Attached Figure Description

[0019] Figure 1 This is a block diagram of wireless network 130.

[0020] Figure 2 It is a flowchart illustrating the operation of a device (e.g., the device may be a UE or user equipment, or other device).

[0021] Figure 3 It is a flowchart illustrating the operation of a device (e.g., a network node, gNB, eNB, or other device).

[0022] Figure 4 It is a flowchart illustrating the operation of a device (e.g., the device may be a UE or user equipment, or other device).

[0023] Figure 5 It is a flowchart illustrating the operation of a device (e.g., a network node, gNB, eNB, or other device).

[0024] Figure 6 This is a flowchart illustrating one aspect of an example embodiment.

[0025] Figure 7A This is a diagram illustrating a framework of one aspect according to an example embodiment.

[0026] Figure 7B This is a diagram illustrating one aspect of an example embodiment.

[0027] Figure 8 This is a diagram illustrating an example encoder and decoder architecture based on a transformation model.

[0028] Figure 9This is a block diagram of a wireless station or node (e.g., UE, user equipment, AP, BS, eNB, gNB, RAN node, network node, TRP, or other node) 1300 according to an example embodiment. Detailed Implementation

[0029] It should be understood that although the terms "first," "second," etc., preceding the noun(s) may be used herein to describe various elements, these elements should not be limited by these terms. These words are used only to distinguish one element from another, and they do not restrict the order of the noun(s). For example, without departing from the scope of the exemplary embodiments, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0030] As used herein, unless otherwise expressly stated, “responding to A” does not indicate that the step is performed immediately after “A” occurs, and one or more intermediate steps may be included.

[0031] Figure 1 This is a block diagram of wireless network 130. Figure 1 In the wireless network 130, user equipment 131, 132, 133, and 135 (which may also be referred to as mobile stations (MS) or user equipment (UE)) can connect to (and communicate with) base station 134, which may also be referred to as access point (AP), enhanced NodeB (eNB), gNB, or RAN (Radio Access Network) node. BS (or AP) 134 provides radio coverage within cell 136, including to user equipment (or UE) 131, 132, 133, and 135. BS 134 is also connected to core network 150 via N2 or NG interface 151. Although only four user equipment (or UE) are shown as connected to or attached to one BS 134, any number of user equipment and / or BSs can be provided.

[0032] At least some of the functionality of a BS (e.g., NG-RAN, gNB, Access Point (AP), Base Station (BS), or (e)NodeB (eNB), RAN node) can also be performed by any node, server, or host, which can be operatively coupled to a transceiver (such as a remote wireless head). For example, some functions of a BS can be performed at least partially in a central / centralized unit (CU) and / or distributed unit (DU). Therefore, a 5G network architecture can be based on a so-called CU / DU split. A gNB-CU (central node) can control multiple spatially separate gNB-DUs, which at least function as transmit / receive (Tx / Rx) nodes. However, in some embodiments, a gNB-DU (also referred to as a DU) can include, for example, a Radio Link Control (RLC) layer, a Media Access Control (MAC) layer, and a Physical (PHY) layer, while a gNB-CU (also referred to as a CU) can include layers above the RLC layer, such as a Packet Data Convergence Protocol (PDCP) layer, a Radio Resource Control (RRC) layer, and an Internet Protocol (IP) layer. Other functional splits are also possible.

[0033] According to the illustrative example, a radio access network (RAN) can be part of a mobile telecommunications system. The RAN may include one or more BSs or RAN nodes implementing radio access technologies, for example, to allow one or more UEs to have access to a network or core network (CN). Thus, for example, the RAN (RAN nodes, such as BSs or gNBs) may reside between one or more user equipments or UEs and the core network. According to the example embodiment, each RAN node (e.g., BS, eNB, gNB, CU / DU…) or BS may provide one or more wireless communication services via the RAN node to one or more UEs or user equipments, for example, to allow the UEs to have wireless access to the network. Each RAN node or BS may perform or provide wireless communication services, such as allowing the UE or user equipment to establish a wireless connection to the RAN node, and to send data to one or more UEs and / or receive data from one or more UEs. For example, after establishing a connection to the UE, the RAN node or network node (e.g., BS, eNB, gNB, CU / DU…) may forward data received from the network or core network to the UE, and / or forward data received from the UE to the network or core network. RAN nodes or network nodes (e.g., BS, eNB, gNB, CU / DU, etc.) can perform various other radio functions or services, such as broadcasting control information (e.g., system information or on-demand system information) to UEs, paging UEs when data to be delivered to them exists, assisting UEs in inter-cell handovers, scheduling resources for uplink data transmission from (multiple) UEs and downlink data transmission to (multiple) UEs, and sending configuration information to configure one or more UEs. Some examples of one or more functions that a RAN node or BS can perform are provided.

[0034] User equipment or user node (user terminal, user equipment (UE), mobile terminal, handheld wireless device, etc.) can refer to portable computing devices, including wireless mobile communication devices operating with or without a subscriber identification module (SIM), including but not limited to the following types of devices: mobile station (MS), mobile phone, cellular phone, smartphone, personal digital assistant (PDA), handheld device, device using a wireless modem (alarm or measuring device, etc.), laptop and / or touchscreen computer, tablet computer, phablet, gaming terminal, laptop computer, vehicle, drone, sensor, and multimedia device, as an example, or any other wireless device. It should be understood that user equipment can also be (or may include) an almost entirely uplink-only device, an example of which is a camera or camcorder that uploads images or video clips to the network. Additionally, user node can include user equipment (UE), user device, mobile terminal, mobile station, mobile node, subscriber equipment, subscriber node, subscriber terminal, or other user node. For example, a user node can be used to communicate wirelessly with one or more network nodes (e.g., gNB, eNB, BS, AP, CU, DU, CU / DU) and / or with one or more other user nodes, regardless of the technology or radio access technology (RAT).

[0035] In 5G (which may be referred to as New Radio (NR)) (as an illustrative example), the core network 150 may be referred to as the 5G core network (5GC), which may include Access and Mobility Management Functions (AMF). For example, the AMF may include the following functions (e.g., some of the AMF functions may be supported in a single instance of the AMF): termination of the RAN control plane (CP) interface (N2), termination of the Non-Access Stratum (NAS) (or N1), NAS encryption and integrity protection, registration management, connection management, reachability management, mobility management, lawful interception, etc. The 5GC may also include Session Management Functions (SMF), which may include one or more of the following functions (one or more of the SMF functions may be supported in a single instance of the SMF): session management (e.g., session establishment, modification, and release, including tunnel maintenance between User Plane Functions (UPF) and BS 134), IP address allocation and management (including optional authorization), selection and control of (multiple) UPFs, configuration of traffic steering at the UPFs to route traffic to the correct destination, etc. In LTE (as an illustrative example), the core network 150 may be referred to as the evolved packet core (EPC), which may include a mobility management entity (MME) that can handle or assist user equipment mobility / handover between BSs; one or more gateways that can forward data and control signals between the BS and the packet data network or the Internet; and other control functions or blocks.

[0036] Furthermore, the technologies described in this paper can be applied to various types of user equipment or data service types, or to user equipment with applications running on it, which may be of different data service types. New radio (5G) developments can support multiple different applications or multiple different data service types, such as, for example: Machine-Type Communication (MTC), Enhanced Machine-Type Communication (eMTC), Internet of Things (IoT), and / or Narrowband IoT user equipment, Enhanced Mobile Broadband (eMBB), and Ultra-Reliable Low-Latency Communication (URLLC). Many applications associated with these new 5G (NR) technologies may typically require higher performance than previous wireless networks.

[0037] The Internet of Things (IoT) can refer to a growing group of objects that can have internet or network connectivity, enabling them to send and receive information from other network devices. For example, many sensor-type applications or devices can monitor physical conditions or states and, for instance, send reports to servers or other network devices when events occur. Machine-type communication (MTC, or machine-to-machine communication) can be characterized by fully automated data generation, exchange, processing, and execution between intelligent machines, with or without human intervention. Enhanced Mobile Broadband (eMBB) can support much higher data rates than currently available in LTE.

[0038] Ultra-Reliable Low-Latency Communication (URLLC) is a new type of data service, or a new application scenario, that can be supported for new radio (5G) systems. This enables emerging new applications and services, such as industrial automation, autonomous driving, vehicle safety, and e-health services. Through illustrative examples, 3GPP aims to provide [equipment / services] corresponding to 10 [unclear - possibly 5G]. -5 The reliability of a connection is affected by low block error rate (BLER) and U-Plane (user / data plane) latency of up to 1 ms. Therefore, for example, URLLC user equipment / UEs may require significantly lower block error rates and lower latency than other types of user equipment / UEs (with or without requirements for simultaneous high reliability). Thus, for example, a URLLC UE (or URLLC application on a UE) may require much shorter latency compared to an eMBB UE (or an eMBB application running on a UE).

[0039] The technologies described in this document can be applied to a variety of wireless technologies or wireless networks, such as 5G (New Radio (NR)), cmWave and / or mmWave band networks, IoT, MTC, eMTC, eMBB, URLLC, 6G, etc., or any other wireless network or wireless technology. These example networks, technologies, or data service types are provided only as illustrative examples.

[0040] In Hybrid Automatic Repeat Request (HARQ) based on codebooks, feedback can be organized into a predefined structure called a codebook (CB), where ACK / NACK information for multiple downlink transmissions can be represented. This method enables efficient feedback in scenarios with multiple PDSCH (Physical Downlink Shared Channel) receptions. The ACK / NACK codebook content is also known as the Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook and is particularly advantageous in systems with high traffic or large-scale data transmission because it reduces the overhead associated with sending separate ACK / NACK bits for each transmission. This feedback mechanism is compatible with features such as retransmission based on code block groups (CBGs), where multiple code blocks in a transport block can be selectively acknowledged or retransmitted. However, when a communication system relies on codebook-based HARQ-ACK transmissions, the size of the HARQ-ACK codebook can lead to additional overhead in signaling between the UE and network nodes (e.g., base stations, gNBs, eNBs, etc.), thereby degrading the performance of the communication system.

[0041] Various types of HARQ-ACK codebooks can be utilized. For example, a Type 1 HARQ-ACK codebook, for which the size is determined semi-statically based on the RRC configuration; a Type 2 HARQ-ACK codebook, for which the codebook size changes dynamically; or an enhanced Type 2 or Type 3 HARQ-ACK codebook, for which the size is determined based on the RRC configuration, and can be used in conjunction with a Type 1 or Type 2 HARQ-ACK codebook.

[0042] Type 1 HARQ-ACK codebooks can be semi-static, meaning their structure is determined by pre-configured parameters and does not depend on dynamic changes at the physical layer. This makes them less demanding on network nodes, and they can report feedback for all downlink allocations, which may already point to uplink slots used for HARQ-ACK feedback. Type 3 HARQ-ACK codebooks are sometimes referred to as single-shot HARQ-ACK codebooks triggered by network nodes and contain the current state of all UE HARQ stop and wait buffers.

[0043] The example implementation enables enhanced communication system performance by reducing the HARQ-ACK codebook size, while maintaining the required attributes of the gNB infrastructure and the ability to detect lost downlink allocations.

[0044] In the example, the UE may receive information from a network node (e.g., gNB, base station, eNB, etc.) specifying at least one parameter for performing compression of the HARQ-ACK codebook. For example, the UE may receive information as part of Radio Resource Control (RRC) signaling and / or messages. As another example, the UE may receive information as part of Non-Access Stratum (NAS) signaling (e.g., registration acceptance message, UE configuration update command, service acceptance message, etc.). As yet another example, the UE may receive information from a network node as part of a Media Access Control (MAC) CE, system information, etc.

[0045] In the examples, the UE can perform compression of the HARQ-ACK codebook. For example, the UE can perform compression based on at least one parameter specifying the parameters used to perform HARQ-ACK codebook compression and at least one HARQ-ACK codebook compression model. In some examples, the UE can monitor the operation of at least one HARQ-ACK codebook compression model. For example, the UE can monitor at least one HARQ-ACK codebook compression model to ensure that the compression is efficient and the compression error is within an acceptable range under dynamic channel conditions. In some examples, the UE can send the compressed HARQ-ACK codebook to the network node. Compression can be performed by the UE as part of its encoder function. At least one HARQ-ACK codebook compression model can be used by the network node as part of decoding the compressed HARQ-ACK codebook.

[0046] Therefore, according to the example, the UE can receive an instruction from the gNB to activate HARQ-ACK codebook compression based on at least one HARQ-ACK codebook compression model. When the UE determines to send a HARQ-ACK codebook, the UE can then perform compression of the HARQ-ACK codebook and send the compressed HARQ-ACK codebook to the gNB. The HARQ-ACK codebook compression process may include training, execution, and maintenance phases for at least one HARQ-ACK codebook compression model / algorithm. The process may also include monitoring the operation of at least one HARQ-ACK codebook compression model. For example, monitoring can be performed by the UE based on an instruction from the gNB. At least one monitoring result can then be provided to the gNB, and the gNB can update at least one HARQ-ACK codebook compression model.

[0047] Therefore, when the example embodiment is implemented, the HARQ-ACK codebook size is reduced because compression is performed based on at least one HARQ-ACK codebook compression model. Additionally, the signaling overhead of the network and gNB infrastructure can be reduced.

[0048] Figure 2This is a flowchart illustrating the operation of an apparatus (e.g., a UE, user equipment, or other apparatus). Operation 210 includes the user equipment receiving information from a network node specifying at least one parameter for performing compression of the Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook. For example, the user equipment or UE may receive information as part of RRC signaling, NAS signaling, MAC-CE, System Information Block (SIB), etc. Operation 220 includes performing HARQ-ACK codebook compression based at least on the information and at least one HARQ-ACK codebook compression model. Operation 230 includes monitoring the operation of at least one HARQ-ACK codebook compression model. Operation 240 includes sending the compressed HARQ-ACK codebook to the network node.

[0049] Figure 3 This is a flowchart illustrating the operation of a device (e.g., a network node, gNB, eNB, or other device). Operation 310 includes the network node sending information to the user equipment specifying at least one parameter for performing compression of the Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook. Operation 320 includes monitoring at least one HARQ-ACK codebook compression model. Operation 330 includes receiving the compressed HARQ-ACK codebook from the user equipment.

[0050] about Figure 2 and Figure 3 The method described herein may further include at least one measurement configuration for performing at least one measurement. For example, at least one measurement may be configured to monitor the operation of at least one HARQ-ACK codebook compression model. Monitoring the operation of at least one HARQ-ACK codebook compression model may include at least one of the following: performing at least one measurement associated with at least one HARQ-ACK codebook compression model; determining at least one monitoring result for at least one HARQ-ACK codebook compression model based on the at least one measurement associated with at least one HARQ-ACK codebook compression model, for example, the monitoring result may be associated with at least one measurement configuration; and determining whether to update the at least one HARQ-ACK codebook compression model based on the determination of the at least one monitoring result. For example, performing at least one measurement associated with model operation may be performed during the training phase or the inference phase, or during the collection of input and output data for at least one HARQ-ACK codebook compression model. Updating at least one HARQ-ACK codebook compression model may be associated with parameters used to perform HARQ-ACK codebook compression. Furthermore, the update may indicate whether HARQ-ACK codebook compression is performed.

[0051] about Figure 2 and Figure 3The method described herein allows the UE to send to a network node (e.g., sending information that may be part of the training phase of a model, or performed during the configuration phase, execution phase, or maintenance phase) at least one of the following: a HARQ-ACK codebook; a compressed HARQ-ACK codebook; information indicating the differences between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; monitoring results for at least one HARQ-ACK codebook compression model based on at least one measurement associated with at least one HARQ-ACK codebook compression model; or information about at least one HARQ-ACK codebook compression model. For example, the sending may be via (or as part thereof) at least one of RRC signaling, or uplink control information (UCI), NAS signaling, etc. The UE may receive an instruction to configure HARQ-ACK codebook compression. For example, the instruction to configure HARQ-ACK codebook compression may indicate, activate, or enable HARQ-ACK codebook compression. The UE may receive an update of information indicating at least one parameter for performing HARQ-ACK codebook compression. In other words, the network can determine information to update at least one parameter used to perform compression of the HARQ-ACK codebook based on a comparison of the transmitted HARQ-ACK codebook and the compressed HARQ-ACK codebook, or based on information indicating the differences between the HARQ-ACK codebook and the compressed HARQ-ACK codebook.

[0052] As an implementation example, the UE can receive messages that may include information elements (e.g., RRC). In this example, signaling including information elements for activating, deactivating, and / or configuring HARQ-ACK codebook compression can be transmitted to, for example... PhysicalCellGroupConfig This is achieved by adding new parameters, and these new parameters can be called, for example... pdsch-HARQ- ACK-CodebookList , pdsch-HARQ-ACK-Compression , pdsch-HARQ-ACK-Compression- SecondaryPUCCHGroup and / or pdsch-HARQ-ACK-Compression-Training . pdsch-HARQ-ACK-CodebookList is a configuration list for one or more HARQ-ACK codebooks, pdsch-HARQ-ACK-Compression enables the HARQ-ACK codebook compression algorithm, and pdsch-HARQ-ACK-Compression-SecondaryPUCCHGroup enables the HARQ-ACK codebook compression algorithm for the secondary PUCCH group (if configured).

[0053] about Figure 2 and Figure 3The method described herein, wherein at least one parameter for performing HARQ-ACK codebook compression may include at least one of the following: information about at least one HARQ-ACK codebook compression model. For example, information about at least one HARQ-ACK codebook compression model may include: an identifier (e.g., model ID) of at least one HARQ-ACK codebook compression model; a physical downlink control channel (PDCCH) aggregation level; at least one scheduling instance; at least one scheduling constraint; or redundancy information, etc.

[0054] about Figure 2 and Figure 3 The method described herein may include at least one of the following: bundling multiple HARQ-ACK bits; bitmap encoding of HARQ-ACK; run-length encoding (RLE), for example, a data compression technique that can store repeated data values ​​as single values ​​and counts; or Burrows-Wheeler transform (BWT), etc.

[0055] about Figure 2 and Figure 3 The method described herein allows at least one HARQ-ACK codebook compression model to be based on a machine learning (ML) algorithm. For example, the ML algorithm may be based on an ML model configured on at least one of the UE and / or network nodes.

[0056] The term "model" can refer to the relationship between inputs and outputs learned from training data, and thus, after training, a corresponding output can be generated for a given input. In the example, the model can be trained on a training dataset for one configuration, and then the model can perform inference (e.g., one or more inferences and / or one or more outputs) on datasets from the same or different configurations.

[0057] about Figure 2 and Figure 3 The methods described herein, including ML algorithms or ML models, may include at least one of the following: an input, which may include a HARQ-ACK codebook; and a quality indicator, for example, a PDCCH aggregation level. For example, the quality indicator may be configured by the network node. The ML algorithm or ML model may also include a variable-length input, which may include a HARQ-ACK codebook and variable-length padding for training bits. The ML algorithm or ML model may include an output. For example, the output may include at least one of a compressed HARQ-ACK codebook on the encoder side or a reconstructed HARQ-ACK codebook on the decoder side. For example, encoding and / or decoding functions may be implemented on both the UE and / or the network node.

[0058] about Figure 2 and Figure 3 The method described herein may also include a source of HARQ-ACK (or HARQ-ACK bits) in the HARQ-ACK codebook as input. For example, the source may indicate that the negative ACK (NACK) was caused by a PDCCH decoding error, a PDCCH monitoring interruption, or a Physical Downlink Shared Channel (PDSCH) decoding error, PDSCH monitoring error, etc. For example, the source may be a cause value (e.g., a predetermined hexadecimal value, binary value, etc.) indicating the cause of the NACK.

[0059] about Figure 2 and Figure 3 The method described herein allows the compressed HARQ-ACK codebook to be configured by network nodes to be either fixed in length or variable in length.

[0060] about Figure 2 and Figure 3 The method described herein, at least one HARQ-ACK codebook compression model may include encoding and decoding functions. These encoding and / or decoding functions may be performed on at least one of the UE or network nodes (e.g., gNB, base station, etc.).

[0061] about Figure 2 and Figure 3 The method described herein allows the UE to receive from a network node at least one of the following: information on at least one HARQ-ACK codebook compression model; an indication of an ML model for the at least one HARQ-ACK codebook compression model, etc. For example, the ML model may include at least one of the following: linear regression; logistic regression; decision tree; support vector machine (SVM) algorithm; Naive Bayes algorithm; K-nearest neighbors (KNN) algorithm; K-means; random forest algorithm; dimensionality reduction algorithm, etc.

[0062] about Figure 2 and Figure 3 The method described herein allows the UE to receive an instruction from a network node to deactivate (e.g., disable) compression of the HARQ-ACK codebook.

[0063] about Figure 2 and Figure 3The method described herein allows the UE to send a capability indication associated with HARQ-ACK codebook compression to the network node. For example, the capability indication may include an indication of HARQ-ACK codebook compression capability, an indication of supported HARQ-ACK codebook compression models for HARQ-ACK codebook compression, and an indication of support for one or more ML models used for HARQ-ACK codebook compression. For example, the UE may send the capability indication as part of (or via) at least one of RRC signaling, RRC messages, NAS signaling, NAS messages, etc.

[0064] about Figure 2 and Figure 3 The method described herein allows the UE to receive an indication to monitor the operation of at least one HARQ-ACK codebook compression model. Monitoring the operation of at least one HARQ-ACK codebook compression model can be based on this indication.

[0065] about Figure 2 and Figure 3 The method described herein specifies that information indicating at least one parameter for performing compression of the HARQ-ACK codebook is received as part of at least one of RRC signaling, RRC messages, MAC-CE transmissions, NAS signaling, NAS messages, etc.

[0066] Alternatively or concurrently, example embodiments enable enhanced communication system performance by reducing the HARQ-ACK codebook size. To reduce the HARQ-ACK codebook size, the UE and / or gNB may employ an ML-based compression algorithm or model. HARQ-ACK codebook compression reduces the size of uplink transmissions while maintaining the necessary attributes required by the gNB infrastructure and the ability to detect lost downlink allocations.

[0067] In the example, the UE can receive information associated with a machine learning (ML)-based compression algorithm from a network node, which is used to perform compression of the Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook. For example, the UE can receive information as part of RRC signaling and / or messages. As another example, the UE can receive information as part of NAS signaling (e.g., registration accept message, UE configuration update command, service accept message, etc.). As yet another example, the UE can receive information as part of MAC-CE transmissions, system information (broadcast), etc., from a network node. Compression of the HARQ-ACK codebook can be performed based on this ML-based compression algorithm. The ML-based compression algorithm can include: inputs to the ML-based compression algorithm. For example, the inputs can include an indication of the reason for NACK in the HARQ-ACK codebook, a quality indicator, etc. The ML-based compression algorithm can include outputs that can include the compressed HARQ-ACK codebook. The UE can perform compression of the HARQ-ACK codebook. For example, performing compression of the HARQ-ACK codebook can be based at least on the information associated with the ML-based compression algorithm and the ML-based compression algorithm itself. The UE can send the compressed HARQ-ACK codebook to the network node.

[0068] Therefore, when the example embodiment is implemented according to an ML-based compression algorithm, the HARQ-ACK codebook size is reduced because compression is performed based on the ML-based compression algorithm or model. Additionally, the signaling overhead of the network and gNB infrastructure is reduced.

[0069] Figure 4 This is a flowchart illustrating the operation of an apparatus (e.g., which may be a UE or user equipment, or other apparatus). Operation 410 includes the user equipment receiving information associated with a machine learning (ML)-based compression algorithm from a network node (e.g., as part of RRC signaling, NAS signaling, MAC-CE transmission, SIB, etc.), the ML-based compression algorithm being used to perform compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of the following: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook. Operation 420 includes performing compression of the HARQ-ACK codebook based at least on the information and the ML-based compression algorithm. Operation 430 includes sending the compressed HARQ-ACK codebook to the network node.

[0070] Figure 5This is a flowchart illustrating the operation of an apparatus (e.g., a network node, gNB, eNB, or other apparatus). Operation 510 includes the network node sending information associated with a machine learning (ML)-based compression algorithm to the user equipment, the ML-based compression algorithm being used to perform compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of the following: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook. Operation 520 includes receiving the compressed HARQ-ACK codebook from the user equipment.

[0071] about Figure 4 and Figure 5 The method described herein may include at least one measurement configuration for performing at least one measurement. For example, at least one measurement may be configured to be used to train an ML-based compression algorithm.

[0072] about Figure 4 and Figure 5 The method described herein allows the UE to send at least one of the following to the network node: a HARQ-ACK codebook; a compressed HARQ-ACK codebook; information indicating the differences between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; information about an ML-based compression algorithm, etc. For example, the transmission may be via at least one of RRC signaling or UCI. The UE may receive an instruction to configure (e.g., activate, enable, etc.) the compression of the HARQ-ACK codebook. In the example, the network may determine to configure the compression of the HARQ-ACK codebook based on comparing the sent HARQ-ACK codebook with the compressed HARQ-ACK codebook, or based on information indicating the differences between the HARQ-ACK codebook and the compressed HARQ-ACK codebook.

[0073] about Figure 4 and Figure 5The method described herein, for performing HARQ-ACK codebook compression, may include information on an ML-based compression algorithm that includes at least one of the following: an identifier for the ML-based compression algorithm; information on the loss function of the ML-based compression algorithm (e.g., binary cross-entropy); information on the transformation model of the ML-based compression algorithm (e.g., a neural network that learns context and thus meaning by tracking relationships in sequence data (such as words in a sentence); information on the encoding algorithm of the ML-based compression algorithm; information on the decoding algorithm of the ML-based compression algorithm; the physical downlink control channel (PDCCH) aggregation level; at least one scheduling instance; at least one scheduling constraint; redundancy information, etc. For example, the ML-based compression algorithm may be based on different types of ML models, which can be any transformation model, autoencoder, or long short-term memory (LSTM) model, possessing the property of being able to account for patterns that evolve over time. These patterns may be related to the scheduling instances used (Time Domain Resource Allocation (TDRA) rows), which may adjust according to changes in channel quality. These patterns may also be related to scheduling constraints, meaning that not all TDRA rows can be used simultaneously (or it is impossible for them to be used simultaneously). If more than one HARQ-ACK codebook is reported that spans the same downlink time slot due to the K1 vector, a pattern related to redundancy of the time slot indicated in the codebook may occur. For example, if the maximum K1 is 16 time slots, two HARQ-ACK codebooks within these 16 time slots may point to the same time slot, thus generating redundancy information.

[0074] about Figure 4 and Figure 5 The method described herein, wherein the ML-based compression algorithm may be at least partially based on a compression algorithm that may include at least one of the following: bundling multiple HARQ-ACK bits; bitmap coding of HARQ-ACK, run-length coding (RLE), Burrows-Wheeler transform (BWT), etc. For example, the ML-based compression algorithm may be based on an ML model configured on at least one of the UE and / or network nodes.

[0075] about Figure 4 and Figure 5 The method described herein may further include at least one of the following as input to the ML-based compression algorithm: a HARQ-ACK codebook, and / or a variable-length input, which may include a HARQ-ACK codebook and variable-length padding for training bits. Padding for training bits may include the process of adding extra bits (e.g., zeros) to the end of the data sequence used to train the ML model, ensuring that all data inputs are of the same length. This may be necessary for efficient processing in the ML model, especially when the original data lengths differ.

[0076] about Figure 4 and Figure 5 The method described herein allows the quality indicator to include the PDCCH aggregation level, and the indication of the cause of NACK in the HARQ-ACK codebook can specify the source of the HARQ-ACK in the HARQ-ACK codebook. For example, the source of the HARQ-ACK can indicate that the NACK was caused by a Physical Downlink Control Channel (PDCCH) decoding error or a Physical Downlink Shared Channel (PDSCH) error. The aggregation level (AL) can specify the number of Control Channel Elements (CCEs) that can be used for downlink control information (DCI) transmission. AL can be 1, 2, 4, or 8. For example, an AL of 2 can indicate that the PDCCH carrier will consist of 2 CCEs. Each CCE can include 6 Resource Element Groups (REGs), and a REG can be equal to 72 Resource Elements (Res).

[0077] about Figure 4 and Figure 5 The method described herein produces a HARQ-ACK codebook of fixed length.

[0078] about Figure 4 and Figure 5 The method described herein, wherein the ML-based compression algorithm may include encoding and decoding functions performed on at least one of the UE or network nodes.

[0079] about Figure 4 and Figure 5 The method described herein allows the UE to receive at least one of the following from a network node: information about an ML-based compression algorithm, an indication of an ML model for the ML-based compression algorithm, etc. For example, the ML model may include at least one of the following: linear regression, logistic regression, decision tree, support vector machine (SVM) algorithm, Naive Bayes algorithm, K-nearest neighbors (KNN) algorithm, K-means, random forest algorithm, or dimensionality reduction algorithm, etc.

[0080] about Figure 4 and Figure 5 The method described herein allows the UE to receive an instruction from the network node to deactivate the compression of the HARQ-ACK codebook.

[0081] about Figure 4 and Figure 5 The method described herein allows the UE to monitor the operation of an ML-based compression algorithm and perform model training based on the monitoring results.

[0082] about Figure 4 and Figure 5The method described herein allows the UE to monitor the operation of an ML-based compression algorithm. The UE can send the monitoring results to the network node. The UE can receive updates to the information regarding the ML-based compression algorithm. For example, updates can be based on the monitoring results; if the monitoring results indicate unsatisfactory results, the network node can determine to update the information regarding the ML-based compression algorithm. For example, monitoring can include or be performed as part of model training, where the monitoring results can be used to train the model.

[0083] about Figure 4 and Figure 5 The method described herein allows the UE to send a capability indication associated with HARQ-ACK codebook compression to the network node. For example, the capability indication may include at least one of the following: an indication of HARQ-ACK codebook compression capability; an indication of supported compression algorithms for HARQ-ACK codebook compression; an indication of support for one or more ML-based algorithms used for HARQ-ACK codebook compression; an indication of support for one or more ML models used for HARQ-ACK codebook compression; etc. For example, the transmission of the capability indication may be performed between the UE and the network node as part of at least one of RRC signaling, NAS signaling, etc.

[0084] about Figure 4 and Figure 5 The method described herein allows information based on the ML compression algorithm to be received as part of at least one of RRC signaling / messages, MAC-CE transmissions, NAS signaling / messages, etc.

[0085] Figure 6 This is a flowchart illustrating aspects of an example embodiment. The flowchart comprises three parts: Part A: Algorithm configuration; Part B: Execution of the compression process; and Part C: Maintenance of the compression component.

[0086] about Figure 6In the flowchart, in Part A (Configuration Part), a network node (e.g., gNB) can facilitate the configuration, provisioning, and alignment / training of the encoder and decoder between the UE and the gNB. If configured, this may involve the UE sending both compressed and uncompressed HARQ-ACK codebooks to allow the network node to align its decoders. Additionally, more than one instance of the HARQ-ACK codebook compression algorithm can be implemented, for example, one instance per UE vendor, or one instance per network node vendor or configuration (e.g., one instance best suited for indoor, outdoor, or a combination thereof). As another example, each component in more than one instance of the HARQ-ACK codebook compression algorithm can be associated with an identifier so that it can be identified, monitored, and changed as needed. At step A1, the UE can receive from the gNB the configuration, TDRA table, K1 vector, etc., in the DCI format to be monitored. The K1 vector size can indicate which timing options are feasible from downlink slots to uplink slots (where HARQ-ACK feedback will be sent). HARQ-ACK feedback can be generated based on all feasible downlink slots that can theoretically be pointed to the indicated uplink slot. At step A2, the UE can receive a configuration of the HARQ-ACK codebook feedback type (e.g., Type-1) from the gNB. The HARQ-ACK codebook (e.g., Type-1) may include a predefined bit pattern corresponding to an ACK or NACK for each PDSCH timing on which the UE can receive packets. Each bit in the codebook may represent a combined state of PDCCH detection and specific transport block decoding. At step A3, the UE can receive an indication to enable HARQ-ACK codebook (e.g., Type-1) compression and / or training. For example, the indication may include information specifying at least one parameter for performing HARQ-ACK codebook compression. At step A4, the UE can generate the HARQ-ACK codebook. At step A5, the UE can perform HARQ-ACK codebook compression. For example, the UE can perform compression based on information indicating at least one parameter for compressing the HARQ-ACK codebook and / or at least one HARQ-ACK codebook compression model. At step A6, the UE can send the (uncompressed) HARQ-ACK codebook and the compressed HARQ-ACK codebook to the gNB. At step A7, the gNB can perform training on a HARQ-ACK codebook (e.g., Type-1) compression algorithm, encoder, and / or decoder. The gNB can perform training based on the received (uncompressed) HARQ-ACK codebook and the compressed HARQ-ACK codebook. At step A8, the gNB can send an indication to enable the HARQ-ACK codebook (e.g., Type-1). For example, the indication may include an update of information indicating at least one parameter for performing HARQ-ACK codebook compression.

[0087] about Figure 6 In the flowchart, in part B, for example, during the execution phase, the UE may apply encoding when it has already generated a HARQ-ACK codebook, and then send the compressed HARQ-ACK codebook instead of the original (uncompressed) HARQ-ACK codebook. At step B1, the UE may then receive scheduling information from the gNB regarding the PDSCH for HARQ-ACK feedback. At step B2, the UE may generate a HARQ-ACK codebook. At step B3, the UE may perform compression of the HARQ-ACK codebook. For example, the UE may perform compression based at least on information specifying at least one parameter used for performing HARQ-ACK codebook compression and / or at least one HARQ-ACK codebook compression model. At step B4, the UE may send the compressed HARQ-ACK codebook to the gNB. At step B5, the gNB may decode the HARQ-ACK codebook and reconstruct the HARQ-ACK codebook.

[0088] about Figure 6 In the flowchart, in part C, for example, during the maintenance phase, the network can monitor the operation and operating conditions of at least one HARQ-ACK codebook compression model (e.g., performance where feasible), and can determine whether any adjustments to the at least one HARQ-ACK codebook compression model are needed. For example, the gNB can determine which different instances of the at least one HARQ-ACK codebook compression model are activated or used (e.g., an algorithm or model more suitable for the conditions). As another example, the gNB can determine to disable the process, causing the UE to send an uncompressed HARQ-ACK codebook instead of a compressed one. Therefore, at step C1, the gNB can monitor the performance of the at least one HARQ-ACK codebook compression model. For example, the at least one HARQ-ACK codebook compression model can be identified by a model identifier (e.g., HARQ-ACK codebook compression model ID X). At step C2, the gNB can determine that a new model or algorithm is needed. Then, at step C3, the gNB can send configuration information for the new HARQ-ACK codebook compression model (e.g., HARQ-ACK codebook compression model ID Y). At step C4, the gNB can determine whether to deactivate HARQ-ACK codebook compression. For example, the UE can determine that compression of the HARQ-ACK codebook is not needed. Then, at step C5, the gNB can send an indication to disable or deactivate HARQ-ACK codebook compression.

[0089] Figure 7A This is a diagram illustrating the framework of aspects according to an example embodiment. Figure 7AThe architecture for HARQ-ACK codebook compression described herein may include an encoder on the UE side and a decoder on the gNB side. The compression algorithm takes the HARQ-ACK codebook as input and outputs a compressed HARQ-ACK codebook. The compressed HARQ-ACK codebook can be transmitted to the gNB via the channel. The gNB can feed the compressed HARQ-ACK codebook to the decoder and reconstruct the (original) HARQ-ACK codebook. The framework may also include management functions for the encoder (which the gNB can use to configure the UE to have an encoder component), and management functions and maintenance procedures for the decoder component (monitoring, configuring another encoder component, activation / deactivation of the compression process). An additional component that can further improve system performance is an adaptive module. The adaptive module can estimate state parameters from channel measurements and provide these state parameters as input to the encoder module and / or decoder module.

[0090] Figure 7B This diagram illustrates aspects of an example embodiment. The HARQ-ACK codebook compression algorithm can be an ML-based compression algorithm. In this case, the algorithm can be trained using... Figure 7BThe architecture described herein is used for execution. ML-based compression algorithms can employ (based on) ML models. ML model types can be, for example, any transformation, autoencoder, or Long Short-Term Memory (LSTM) model, which can consider (or observe) patterns evolving over time. For example, a pattern can correspond to the scheduling instances (TDRA lines) used, which can adapt to channel conditions as channel quality changes. Another example of a pattern can correspond to scheduling constraints. For example, not all TDRA lines can be used simultaneously (or it is impossible for them to be used simultaneously). Furthermore, a pattern can correspond to redundancy in the slots indicated in the codebook. Redundancy can occur if more than one HARQ-ACK codebook spanning the same downlink slot is reported due to the K1 vector. In this example, if the maximum K1 is 16 slots, two HARQ-ACK codebooks within these 16 slots can point to the same slot, thus generating redundant information. For example, ML models or ML-based compression algorithms can be designed to provide a fixed-size compressed HARQ-ACK codebook as part of the output. This makes codebook detection more robust and reduces the need for configurations across different PUCCH resource sets. Another element of ML models or ML-based compression algorithms is the loss function (such as binary cross-entropy). The loss function can be designed to balance compression gain and the probability of reconstruction errors, particularly erroneous ACKs and erroneous NACKs. Erroneous ACKs and / or erroneous NACKs can cause retransmissions not to occur when they are needed, or they can cause retransmissions to occur even when they are not needed. An example of a loss function can be based on binary cross-entropy. Binary cross-entropy can be a measure used to evaluate the performance of classification models in ML-based binary classification tasks.

[0091] Figure 8This is a diagram illustrating an example encoder and decoder architecture based on a transformation model. This example encoder and decoder architecture uses a transformation model that is designed to take the (raw) HARQ-ACK codebook and an auxiliary quality indicator as input. The quality indicator can be a PDCCH aggregation level. In this example, the two inputs can be represented as a variable-length binary vector and an integer value for the quality indicator. These two inputs can be provided to an input layer, which is then fully connected to the two hidden layers (layer 1 and layer 2) in the encoder in this example, and then fully connected to a bottleneck layer that effectively performs compression of the HARQ-ACK codebook. The output of the bottleneck layer can be quantized for transmission via the air interface (or radio channel) between the UE and the gNB. The representation of the quantized layer of the bottleneck layer can no longer represent a binary ACK / NACK sequence, but instead a cue, which can be used to reconstruct the compressed HARQ-ACK codebook in the decoder. At the gNB, the decoder can receive the quantized bottleneck layer output and parse the received output through two hidden layers (layers 3 and 4 in this example) before reaching the representation layer. At the representation layer, the compressed HARQ-ACK codebook can be requantized to form a reconstructed HARQ-ACK codebook.

[0092] about Figure 8 The picture and Figure 2 As described in section 7, the source of the HARQ-ACK (bits) in the codebook can also be included as input to the encoder to indicate that the source of the NACK is a PDCCH decoding error, or a PDSCH decoding error, etc. This source can be relevant because it provides information about the robustness of both the PDCCH and PDSCH. Capturing the source in the compression algorithm can be done by expanding or creating a copy of the entry set (of the same length as the HARQ-ACK codebook with the erroneous source), and then feeding this copy to the compression algorithm. The bottleneck layer may also require some modifications to carry more information, for example, by slightly lengthening it or by making it explicit by utilizing the indication of the main error source. Providing the source to the compression algorithm can help the gNB determine whether adjustments to the PDCCH or PDSCH should be made when an error occurs.

[0093] about Figure 8 The picture and Figure 2 In the method described in section 7, the length of the compressed HARQ-ACK codebook can be fixed and determined by a standard implementation configurable by network nodes or by a deterministic algorithm (e.g., a fixed length per carrier).

[0094] about Figure 8 The picture and Figure 2In the methods described in section 7, at least one HARQ-ACK codebook compression model or ML-based compression algorithm can be specified as a two-sided training process, for example, performed on the UE side and / or the network node side.

[0095] Figure 9 This is a block diagram of a wireless station or node (e.g., UE, user equipment, AP, BS, eNB, gNB, RAN node, network node, TRP, or other node) 1300 according to an example embodiment. The wireless station 1300 may include, for example, one or more (e.g., such as...) Figure 9 The two RF (radio frequency) or wireless transceivers 1302A and 1302B shown herein include a transmitter for transmitting signals and a receiver for receiving signals. The wireless station also includes a processor 1304 or control unit / entity (controller 1308) for executing instructions or software and controlling the transmission and reception of signals, and a memory 1306 for storing data and / or instructions. The processor 1304 may also perform decisions or determinations, generate frames, packets, or messages for transmission, decode received frames or messages for further processing, and other tasks or functions described herein. The processor 1304 (which may be a baseband processor) may, for example, generate messages, packets, frames, or other signals for transmission via the wireless transceiver 1302 (1302A or 1302B). The processor 1304 may control the transmission of signals or messages via the wireless network and may control the reception of signals or messages via the wireless network (e.g., after being down-converted by the wireless transceiver 1302). Processor 1304 may be programmable and capable of executing software or other instructions stored in memory or other computer media to perform one or more of the tasks and functions described above. Processor 1304 may be (or may include) hardware, programmable logic, a programmable processor executing software or firmware, and / or any combination thereof. For example, using other terminology, processor 1304 and transceiver 1302 may be considered together as a wireless transmitter / receiver system.

[0096] Additionally, refer to Figure 9 The controller 1308 (or processor 1304) can execute software and instructions, and can provide overall control for station 1300, and can provide... Figure 9 Other systems, not shown, provide control, such as controlling input / output devices (e.g., a display, a keyboard), and / or can execute software for one or more applications that may be provided on the wireless station 1300, such as, for example, an email program, an audio / video application, a word processor, a voice call application, or other applications or software.

[0097] Additionally, a storage medium containing the stored instructions may be provided, which, when executed by a controller or processor, may cause the processor 1304 or other controller or processor to perform one or more of the functions or tasks described above.

[0098] According to another example embodiment, the RF or (multiple) wireless transceivers 1302A / 1302B can receive signals or data and / or transmit or emit signals or data. The processor 1304 (and possibly the transceivers 1302A / 1302B) can control the RF or wireless transceivers 1302A or 1302B to receive, transmit, broadcast, or emit signals or data.

[0099] For each instance method in the example methods, an example embodiment is provided or described, including: an apparatus (e.g., Figure 9 (1300 in the text), the device includes components for performing any method (e.g., Figure 9 The processor 1304, RF transceiver 1302A and / or 1302B, and / or memory 1306; a non-transitory computer-readable storage medium (e.g., Figure 9 The memory 1306 in the storage medium includes instructions stored thereon, which are executed by at least one processor. Figure 9 When the processor 1304 in the system executes, it is configured to cause the computing system (e.g., Figure 9 (1300 in the middle) executes any example method; and a device (e.g., Figure 9 (1300 in the middle), the device includes at least one processor (e.g., Figure 9 The processor 1304 in the memory and at least one memory (e.g., Figure 9 The at least one memory (1306) includes computer program code, and the at least one memory (1306) and the computer program code are configured, together with at least one processor (1304), such that the device (e.g., 1300) performs at least any one of the example methods.

[0100] Embodiments of the various technologies described herein can be implemented in digital electronic circuit systems, or in computer hardware, firmware, software, or a combination thereof. Embodiments can be implemented as computer program products, i.e., computer programs tangibly embodied in an information carrier (e.g., in a machine-readable storage device or in a propagating signal) for execution or control of their operation by a data processing apparatus (e.g., a programmable processor, a computer, or multiple computers). Embodiments can also be provided on a computer-readable medium or a computer-readable storage medium, which may be a non-transitory medium. Embodiments of the various technologies may also include embodiments provided via transient signals or media, and / or program and / or software embodiments downloadable via the Internet or (multiple) other networks (wired and / or wireless networks). Additionally, embodiments can also be provided via machine-type communication (MTC) and via the Internet of Things (IoT).

[0101] As used herein, the term “circuit system” or “circuit” refers to all of the following: (a) a hardware circuit implementation only (such as an implementation in an analog and / or digital circuit system only); and (b) a combination of circuitry and software (and / or firmware), such as (if applicable): (i) a combination of (multiple) processors; or (ii) a portion of (multiple) processors / software including (multiple) digital processors, software, and (multiple) memories, which work together to enable a device to perform various functions; and (c) a circuit, such as (multiple) microprocessors or portions thereof, which require software or firmware to operate, even if the software or firmware is not physically present. This definition of “circuit system” applies to all uses of the term in this application. As another example, as used herein, the term “circuit system” will also cover an implementation of a processor (or multiple processors) or a portion thereof and its accompanying software and / or firmware. For example, and if applicable to a particular claim element, the term “circuit system” will also cover a baseband integrated circuit or application processor integrated circuit for a mobile phone, or a similar integrated circuit in a server, cellular network device, or another network device.

[0102] Computer programs can be in the form of source code, object code, or some intermediate form, and can be stored on some carrier, distribution medium, or computer-readable medium, which can be any entity or device capable of carrying the program. Examples of such carriers include recording media, computer memory, read-only memory, photoelectric and / or electrical carrier signals, telecommunication signals, and software distribution packages. Depending on the required processing power, a computer program can be executed on a single electronic digital computer or can be distributed among multiple computers.

[0103] Furthermore, embodiments of the various techniques described herein can utilize cyber-physical systems (CPS) (systems that control collaborative computing elements of physical entities). CPS enables embodiments and uses of a large number of interconnected ICT devices (sensors, actuators, processors, microcontrollers, etc.) embedded in physical objects in different locations. Mobile cyber-physical systems are a subclass of cyber-physical systems in which the physical systems involved possess inherent mobility. Examples of mobile physical systems include mobile robots and electronic devices transported by humans or animals. The proliferation of smartphones has increased interest in the field of mobile cyber-physical systems. Therefore, various embodiments of the techniques described herein can be provided via one or more of these techniques.

[0104] Computer programs (such as the aforementioned computer programs) can be written in any programming language, including compiled or interpreted languages, and can be deployed in any form, including as standalone programs, or as modules, components, subroutines, or other units or parts thereof adapted to a computing environment. Computer programs can be deployed to be executed on a single computer, or on multiple computers at a single site, or distributed across multiple sites and interconnected via a communication network.

[0105] The method steps can be executed by one or more programmable processors that execute a computer program or portions thereof to perform a function by manipulating input data and generating output. The method steps can also be executed by special-purpose logic circuitry (e.g., an FPGA (Field-Programmable Gate Array) or an ASIC (Application-Specific Integrated Circuit)), and the apparatus can also be implemented as special-purpose logic circuitry.

[0106] For example, processors suitable for executing computer programs include both general-purpose microprocessors and special-purpose microprocessors, as well as any type of digital computer, chip, or chipset containing one or more processors. Typically, the processor receives instructions and data from read-only memory or random access memory, or both. Computer components may include at least one processor for executing instructions and one or more memory devices for storing instructions and data. Typically, a computer may also include one or more mass storage devices (e.g., magnetic disks, magneto-optical disks, or optical disks) for storing data, or operatively coupled thereto to receive data or transfer data to or from them, or both. Information carriers suitable for embodying computer program instructions and data include all forms of non-volatile memory, such as semiconductor memory devices like EPROMs, EEPROMs, and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and CD-ROMs and DVD-ROMs. Processors and memory may be complemented by or integrated into a special-purpose logic circuit system.

[0107] To provide interaction with the user, embodiments can be implemented on a computer with a display device (such as a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to the user, and a user interface (such as a keyboard and pointing device, e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any form, including sound, speech, or tactile input.

[0108] The embodiments can be implemented in a computing system that includes backend components (e.g., as a data server), or middleware components (e.g., an application server), or frontend components (e.g., a client computer with a graphical user interface or a web browser through which a user can interact with the embodiments), or any combination of such backend, middleware, or frontend components. The components can be interconnected by digital data communications of any form or medium, such as a communication network. Examples of communication networks include local area networks (LANs) and wide area networks (WANs), such as the Internet.

[0109] While certain features of the described embodiments have been illustrated herein, many modifications, substitutions, alterations, and equivalents will now occur to those skilled in the art. Therefore, it should be understood that the appended claims are intended to cover all such modifications and alterations falling within the true spirit of the various embodiments.

[0110] Some examples will be described.

[0111] Example 1. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: receive information from a network node indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; perform compression of a HARQ-ACK codebook based at least on the information and at least one HARQ-ACK codebook compression model; monitor the operation of the at least one HARQ-ACK codebook compression model; and transmit the compressed HARQ-ACK codebook to the network node.

[0112] Example 2. The apparatus according to Example 1, wherein: the information further includes at least one measurement configuration for performing at least one measurement; and the at least one measurement is configured to be used to monitor the operation of at least one HARQ-ACK codebook compression model.

[0113] Example 3. According to the apparatus of Example 2, the operation of monitoring at least one HARQ-ACK codebook compression model includes at least one of the following: performing at least one measurement associated with at least one HARQ-ACK codebook compression model; determining at least one monitoring result for at least one HARQ-ACK codebook compression model based on at least one measurement associated with at least one HARQ-ACK codebook compression model; or determining whether to update at least one HARQ-ACK codebook compression model based on determining at least one monitoring result.

[0114] Example 4. An apparatus according to any one of Examples 1 to 3, wherein the apparatus is further configured to perform: sending to a network node at least one of the following: a HARQ-ACK codebook; a compressed HARQ-ACK codebook; information indicating the difference between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; at least one monitoring result for at least one HARQ-ACK codebook compression model based on at least one measurement associated with at least one HARQ-ACK codebook compression model; or information for at least one HARQ-ACK codebook compression model, wherein the sending is via at least one of Radio Resource Control (RRC) signaling or Uplink Control Information (UCI); and wherein the apparatus is further configured to perform at least one of the following: receiving an instruction to configure compression of the HARQ-ACK codebook; or receiving an update of information indicating at least one parameter for performing compression of the HARQ-ACK codebook.

[0115] Example 5. An apparatus according to any one of Examples 1 to 4, wherein at least one parameter for performing compression of the HARQ-ACK codebook includes at least one of the following: information on at least one HARQ-ACK codebook compression model, the information including an identifier of at least one HARQ-ACK codebook compression model; physical downlink control channel (PDCCH) aggregation level; at least one scheduling instance; at least one scheduling constraint; or redundancy information.

[0116] Example 6. An apparatus according to any one of Examples 1 to 5, wherein at least one HARQ-ACK codebook compression model includes at least one of the following: bundling multiple HARQ-ACK bits; bitmap encoding of HARQ-ACK; run-length encoding (RLE); or Burrows-Wheeler transform (BWT).

[0117] Example 7. An apparatus according to any one of Examples 1 to 6, wherein at least one HARQ-ACK codebook compression model is based on a machine learning (ML) algorithm, and wherein the ML algorithm is based on an ML model configured on at least one of the user equipment or the network node.

[0118] Example 8. An apparatus according to Example 7, wherein the ML algorithm includes at least one of the following: an input including a HARQ-ACK codebook; a quality indicator including a PDCCH aggregation level, wherein the quality indicator is configured by a network node; a variable-length input including a HARQ-ACK codebook and variable-length padding for training bits; or an output including at least one of a compressed HARQ-ACK codebook on the encoder side or a reconstructed HARQ-ACK codebook on the decoder side.

[0119] Example 9. The apparatus according to Example 8, wherein the input further includes a source of HARQ-ACK in the HARQ-ACK codebook, wherein the source indicates that the negative ACK (NACK) is caused by a PDCCH decoding error, a PDCCH monitoring interruption or a Physical Downlink Shared Channel (PDSCH) decoding error, or a PDSCH monitoring error.

[0120] Example 10. An apparatus according to any one of Examples 1 to 9, wherein the compressed HARQ-ACK codebook is configured by the network node to be fixed in length or variable in length.

[0121] Example 11. An apparatus according to any one of Examples 1 to 10, wherein at least one HARQ-ACK codebook compression model includes encoding and decoding functions performed on at least one of the user equipment or the network node.

[0122] Example 12. An apparatus according to any one of Examples 1 to 11, wherein the apparatus is further configured to perform receiving from the network node at least one of the following: information of at least one HARQ-ACK codebook compression model; or an instruction for an ML model for at least one HARQ-ACK codebook compression model, wherein the ML model includes at least one of the following: linear regression; logistic regression; decision tree; support vector machine (SVM) algorithm; Naive Bayes algorithm; K-nearest neighbors (KNN) algorithm; K-means; random forest algorithm; or dimensionality reduction algorithm.

[0123] Example 13. An apparatus according to any one of Examples 1 to 12, wherein the apparatus is further configured to perform an instruction to receive compression of the HARQ-ACK codebook from a network node.

[0124] Example 14. An apparatus according to any one of Examples 1 to 13, wherein the apparatus is further configured to send to a network node at least one of the following: an indication of HARQ-ACK codebook compression capability; an indication of a supported HARQ-ACK codebook compression model for HARQ-ACK codebook compression; or an indication of support for one or more ML models for HARQ-ACK codebook compression, wherein the sending is via at least one of RRC signaling or Non-Access Stratum (NAS) signaling.

[0125] Example 15. An apparatus according to any one of Examples 1 to 14, wherein the apparatus is further configured to perform an instruction to receive and monitor at least one HARQ-ACK codebook compression model, and wherein the operation of monitoring at least one HARQ-ACK codebook compression model is based on the instruction.

[0126] Example 16. An apparatus according to any one of Examples 1 to 15, wherein information specifying at least one parameter for performing compression of the HARQ-ACK codebook is received as part of at least one of: Radio Resource Control (RRC) signaling; Media Access Control (MAC) Control Unit (MAC-CE); or Non-Access Stratum (NAS) signaling.

[0127] Example 17. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: send information to a user equipment indicating information about at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; monitor the operation of at least one HARQ-ACK codebook compression model; and receive the compressed HARQ-ACK codebook from the user equipment.

[0128] Example 18. The apparatus according to Example 17, wherein: the information further includes at least one measurement configuration for performing at least one measurement; and the at least one measurement is configured to be used to monitor the operation of at least one HARQ-ACK codebook compression model.

[0129] Example 19. The apparatus of Example 18, wherein the operation of monitoring at least one HARQ-ACK codebook compression model includes at least one of the following: performing at least one measurement associated with at least one HARQ-ACK codebook compression model; determining at least one monitoring result for at least one HARQ-ACK codebook compression model based on at least one measurement associated with at least one HARQ-ACK codebook compression model; or determining whether to update at least one HARQ-ACK codebook compression model based on determining at least one monitoring result.

[0130] Example 20. An apparatus according to any one of Examples 17 to 19, wherein the apparatus is further configured to perform: receiving from a user equipment at least one of the following: a HARQ-ACK codebook; a compressed HARQ-ACK codebook; information indicating the difference between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; at least one monitoring result for at least one HARQ-ACK codebook compression model based on at least one measurement associated with at least one HARQ-ACK codebook compression model; or information for at least one HARQ-ACK codebook compression model, wherein receiving is performed via at least one of Radio Resource Control (RRC) signaling or Uplink Control Information (UCI); and wherein the apparatus is further configured to perform at least one of the following: sending an instruction to configure compression of the HARQ-ACK codebook; or sending an update of information indicating at least one parameter for performing compression of the HARQ-ACK codebook.

[0131] Example 21. An apparatus according to any one of Examples 17 to 20, wherein at least one parameter for performing compression of the HARQ-ACK codebook includes at least one of the following: information on at least one HARQ-ACK codebook compression model, the information including an identifier of at least one HARQ-ACK codebook compression model; physical downlink control channel (PDCCH) aggregation level; at least one scheduling instance; at least one scheduling constraint; or redundancy information.

[0132] Example 22. An apparatus according to any one of Examples 17 to 22, wherein at least one HARQ-ACK codebook compression model includes at least one of the following: bundling multiple HARQ-ACK bits; bitmap encoding of HARQ-ACK; run-length encoding (RLE); or Burrows-Wheeler transform (BWT).

[0133] Example 23. An apparatus according to any one of Examples 17 to 22, wherein at least one HARQ-ACK codebook compression model is based on a machine learning (ML) algorithm, and wherein the ML algorithm is based on an ML model configured on at least one of the user equipment or the network node.

[0134] Example 24. An apparatus according to Example 23, wherein the ML algorithm includes at least one of the following: an input including a HARQ-ACK codebook; a quality indicator including a PDCCH aggregation level, wherein the quality indicator is configured by a network node; a variable-length input including a HARQ-ACK codebook and variable-length padding for training bits; or an output including at least one of a compressed HARQ-ACK codebook on the encoder side or a reconstructed HARQ-ACK codebook on the decoder side.

[0135] Example 25. The apparatus according to Example 24, wherein the input further includes a source of HARQ-ACK in the HARQ-ACK codebook, wherein the source indicates that the negative ACK (NACK) is caused by a PDCCH decoding error, a PDCCH monitoring interruption or a Physical Downlink Shared Channel (PDSCH) decoding error, or a PDSCH monitoring error.

[0136] Example 26. An apparatus according to any one of Examples 17 to 25, wherein the compressed HARQ-ACK codebook is configured by the network node to be fixed in length or variable in length.

[0137] Example 27. An apparatus according to any one of Examples 17 to 26, wherein at least one HARQ-ACK codebook compression model includes encoding and decoding functions performed on at least one of the user equipment or the network node.

[0138] Example 28. An apparatus according to any one of Examples 17 to 26, wherein the apparatus is further configured to send to a user equipment at least one of the following: information on at least one HARQ-ACK codebook compression model; or an instruction for an ML model for at least one HARQ-ACK codebook compression model, wherein the ML model includes at least one of the following: linear regression; logistic regression; decision tree; support vector machine (SVM) algorithm; Naive Bayes algorithm; K-nearest neighbors (KNN) algorithm; K-means; random forest algorithm; or dimensionality reduction algorithm.

[0139] Example 29. An apparatus according to any one of Examples 17 to 28, wherein the apparatus is further configured to perform an instruction to send to a user equipment the compression of the HARQ-ACK codebook to be deactivated.

[0140] Example 30. An apparatus according to any one of Examples 17 to 29, wherein the apparatus is further configured to receive from a user equipment at least one of the following: an indication of HARQ-ACK codebook compression capability; an indication of a supported HARQ-ACK codebook compression model for HARQ-ACK codebook compression; or an indication of support for one or more ML models for HARQ-ACK codebook compression, wherein the receiving is via at least one of RRC signaling or Non-Access Stratum (NAS) signaling.

[0141] Example 31. An apparatus according to any one of Examples 17 to 30, wherein the apparatus is further configured to perform the transmission of information for monitoring at least one HARQ-ACK codebook compression model, and wherein the monitoring of at least one HARQ-ACK codebook compression model is based on the instruction.

[0142] Example 32. An apparatus according to any one of Examples 17 to 31, wherein information specifying at least one parameter for performing compression of the HARQ-ACK codebook is transmitted as part of at least one of: Radio Resource Control (RRC) signaling; Media Access Control (MAC) Control Unit (MAC-CE); or Non-Access Stratum (NAS) signaling.

[0143] Example 33. An apparatus comprising components for performing: receiving information from a network node, the information indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; performing compression of a HARQ-ACK codebook based at least on the information and at least one HARQ-ACK codebook compression model; monitoring the operation of at least one HARQ-ACK codebook compression model; and transmitting the compressed HARQ-ACK codebook to the network node.

[0144] Example 34. An apparatus comprising components for performing: sending information to a user equipment indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; monitoring the operation of at least one HARQ-ACK codebook compression model; and receiving the compressed HARQ-ACK codebook from the user equipment.

[0145] Example 35. A method comprising: receiving information from a network node by a user equipment, the information indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; performing compression of a HARQ-ACK codebook based at least on the information and at least one HARQ-ACK codebook compression model; monitoring the operation of at least one HARQ-ACK codebook compression model; and sending the compressed HARQ-ACK codebook to the network node.

[0146] Example 36. According to the method of 35, wherein: the information further includes at least one measurement configuration for performing at least one measurement; and the at least one measurement is configured to be used to monitor the operation of at least one HARQ-ACK codebook compression model.

[0147] Example 37. According to the method of Example 36, the operation of monitoring at least one HARQ-ACK codebook compression model includes at least one of the following: performing at least one measurement associated with at least one HARQ-ACK codebook compression model; determining at least one monitoring result for at least one HARQ-ACK codebook compression model based on at least one measurement associated with at least one HARQ-ACK codebook compression model; or determining whether to update at least one HARQ-ACK codebook compression model based on determining at least one monitoring result.

[0148] Example 38. A method according to any one of Examples 35 to 37, further comprising: sending to a network node at least one of the following: a HARQ-ACK codebook; a compressed HARQ-ACK codebook; information indicating the difference between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; at least one monitoring result for at least one HARQ-ACK codebook compression model based on at least one measurement associated with at least one HARQ-ACK codebook compression model; or information for at least one HARQ-ACK codebook compression model, wherein the sending is via at least one of Radio Resource Control (RRC) signaling or Uplink Control Information (UCI); and the method further comprising at least one of the following: receiving an instruction to configure compression of the HARQ-ACK codebook; or receiving an update of information indicating at least one parameter for performing compression of the HARQ-ACK codebook.

[0149] Example 39. A method according to any one of Examples 35 to 38, wherein at least one parameter for performing compression of the HARQ-ACK codebook includes at least one of the following: information on at least one HARQ-ACK codebook compression model, the information including an identifier of at least one HARQ-ACK codebook compression model; physical downlink control channel (PDCCH) aggregation level; at least one scheduling instance; at least one scheduling constraint; or redundancy information.

[0150] Example 40. According to the method of any one of Examples 35 to 39, wherein at least one HARQ-ACK codebook compression model includes at least one of the following: bundling multiple HARQ-ACK bits; bitmap encoding of HARQ-ACK; run-length encoding (RLE); or Burrows-Wheeler transform (BWT).

[0151] Example 41. The method of any one of Examples 35 to 40, wherein at least one HARQ-ACK codebook compression model is based on a machine learning (ML) algorithm, and wherein the ML algorithm is based on an ML model configured on at least one of the user equipment or the network node.

[0152] Example 42. According to the method of Example 41, wherein the ML algorithm includes at least one of the following: an input including a HARQ-ACK codebook; a quality indicator including a PDCCH aggregation level, wherein the quality indicator is configured by a network node; a variable-length input including a HARQ-ACK codebook and variable-length padding for training bits; or an output including at least one of a compressed HARQ-ACK codebook on the encoder side or a reconstructed HARQ-ACK codebook on the decoder side.

[0153] Example 43 follows the method of Example 42, wherein the input also includes a source of HARQ-ACK in the HARQ-ACK codebook, wherein the source indicates that the negative ACK (NACK) is caused by a PDCCH decoding error, a PDCCH monitoring interruption or a Physical Downlink Shared Channel (PDSCH) decoding error, or a PDSCH monitoring error.

[0154] Example 44. The method of any one of Examples 35 to 43, wherein the compressed HARQ-ACK codebook is configured by the network node to be fixed in length or variable in length.

[0155] Example 45. According to any one of Examples 35 to 44, wherein at least one HARQ-ACK codebook compression model includes encoding and decoding functions performed on at least one of the user equipment or the network node.

[0156] Example 46. The method according to any one of Examples 35 to 45 further includes receiving from the network node at least one of the following: information on at least one HARQ-ACK codebook compression model; or an indication of an ML model for at least one HARQ-ACK codebook compression model, wherein the ML model includes at least one of the following: linear regression; logistic regression; decision tree; support vector machine (SVM) algorithm; Naive Bayes algorithm; K-nearest neighbors (KNN) algorithm; K-means; random forest algorithm; or dimensionality reduction algorithm.

[0157] Example 47. The method according to any one of Examples 35 to 46 further includes receiving an instruction from the network node to deactivate the compression of the HARQ-ACK codebook.

[0158] Example 48. The method according to any one of Examples 35 to 46 further includes sending to the network node at least one of the following: an indication of HARQ-ACK codebook compression capability; an indication of a supported HARQ-ACK codebook compression model for HARQ-ACK codebook compression; or an indication of support for one or more ML models for HARQ-ACK codebook compression, wherein the sending is via at least one of RRC signaling or Non-Access Stratum (NAS) signaling.

[0159] Example 49. The method according to any one of Examples 35 to 48 further includes receiving an instruction to monitor the operation of at least one HARQ-ACK codebook compression model, and wherein the monitoring of the operation of at least one HARQ-ACK codebook compression model is based on the instruction.

[0160] Example 50. According to any one of Examples 35 to 49, information specifying at least one parameter for performing compression of the HARQ-ACK codebook is received as part of at least one of: Radio Resource Control (RRC) signaling; Media Access Control (MAC) Control Unit (MAC-CE); or Non-Access Stratum (NAS) signaling.

[0161] Example 51. A method comprising: sending information from a network node to a user equipment indicating at least one parameter for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; monitoring the operation of at least one HARQ-ACK codebook compression model; and receiving the compressed HARQ-ACK codebook from the user equipment.

[0162] Example 52. According to the method of Example 51, wherein: the information further includes at least one measurement configuration for performing at least one measurement; and at least one measurement is configured to be used to monitor the operation of at least one HARQ-ACK codebook compression model.

[0163] Example 53. According to the method of Example 52, the operation of monitoring at least one HARQ-ACK codebook compression model includes at least one of the following: performing at least one measurement associated with at least one HARQ-ACK codebook compression model; determining at least one monitoring result for at least one HARQ-ACK codebook compression model based on at least one measurement associated with at least one HARQ-ACK codebook compression model; or determining whether to update at least one HARQ-ACK codebook compression model based on determining at least one monitoring result.

[0164] Example 54. A method according to any one of Examples 51 to 53, further comprising: receiving from a user equipment at least one of the following: a HARQ-ACK codebook; a compressed HARQ-ACK codebook; information indicating the difference between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; at least one monitoring result for at least one HARQ-ACK codebook compression model based on at least one measurement associated with at least one HARQ-ACK codebook compression model; or information for at least one HARQ-ACK codebook compression model, wherein at least one of Radio Resource Control (RRC) signaling or Uplink Control Information (UCI) is received; and the method further comprises at least one of the following: sending an instruction to configure compression of the HARQ-ACK codebook; or sending an update of information indicating at least one parameter for performing compression of the HARQ-ACK codebook.

[0165] Example 55. A method according to any one of Examples 51 to 54, wherein at least one parameter for performing compression of the HARQ-ACK codebook includes at least one of the following: information on at least one HARQ-ACK codebook compression model, the information including an identifier of at least one HARQ-ACK codebook compression model; physical downlink control channel (PDCCH) aggregation level; at least one scheduling instance; at least one scheduling constraint; or redundancy information.

[0166] Example 56. According to the method of any one of Examples 51 to 55, wherein at least one HARQ-ACK codebook compression model includes at least one of the following: bundling multiple HARQ-ACK bits; bitmap encoding of HARQ-ACK; run-length encoding (RLE); or Burrows-Wheeler transform (BWT).

[0167] Example 57. The method of any one of Examples 51 to 56, wherein at least one HARQ-ACK codebook compression model is based on a machine learning (ML) algorithm, and wherein the ML algorithm is based on an ML model configured on at least one of the user equipment or the network node.

[0168] Example 58. According to the method of Example 57, wherein the ML algorithm includes at least one of the following: an input including a HARQ-ACK codebook; a quality indicator, wherein the quality indicator includes a PDCCH aggregation level, wherein the quality indicator is configured by a network node; a variable-length input, the variable-length input including a HARQ-ACK codebook and variable-length padding for training bits; or an output, wherein the output includes at least one of a compressed HARQ-ACK codebook on the encoder side or a reconstructed HARQ-ACK codebook on the decoder side.

[0169] Example 59. The method of Example 58, wherein the input also includes a source of HARQ-ACK in the HARQ-ACK codebook, wherein the source indicates that the negative ACK (NACK) is caused by a PDCCH decoding error, a PDCCH monitoring interruption or a Physical Downlink Shared Channel (PDSCH) decoding error, or a PDSCH monitoring error.

[0170] Example 60. The method of any one of Examples 51 to 59, wherein the compressed HARQ-ACK codebook is configured by the network node to be fixed in length or variable in length.

[0171] Example 61. According to any one of Examples 51 to 60, wherein at least one HARQ-ACK codebook compression model includes encoding and decoding functions performed on at least one of the user equipment or the network node.

[0172] Example 62. The method according to any one of Examples 51 to 61 further includes sending to the user equipment at least one of the following: information on at least one HARQ-ACK codebook compression model; or an indication of an ML model for at least one HARQ-ACK codebook compression model, wherein the ML model includes at least one of the following: linear regression; logistic regression; decision tree; support vector machine (SVM) algorithm; Naive Bayes algorithm; K-nearest neighbors (KNN) algorithm; K-means; random forest algorithm; or dimensionality reduction algorithm.

[0173] Example 63. The method according to any one of Examples 51 to 62 further includes sending an instruction to the user equipment to deactivate the compression of the HARQ-ACK codebook.

[0174] Example 64. The method according to any one of Examples 51 to 63 further includes receiving from the user equipment at least one of the following: an indication of HARQ-ACK codebook compression capability; an indication of a supported HARQ-ACK codebook compression model for HARQ-ACK codebook compression; or an indication of support for one or more ML models for HARQ-ACK codebook compression, wherein at least one of RRC signaling or Non-Access Stratum (NAS) signaling is received.

[0175] Example 65. The method according to any one of Examples 51 to 64 further includes sending information for monitoring the operation of at least one HARQ-ACK codebook compression model, and wherein monitoring the operation of at least one HARQ-ACK codebook compression model is based on the instruction.

[0176] Example 66. According to any one of Examples 51 to 65, information specifying at least one parameter for performing compression of the HARQ-ACK codebook is transmitted as part of at least one of: Radio Resource Control (RRC) signaling; Media Access Control (MAC) Control Unit (MAC-CE); or Non-Access Stratum (NAS) signaling.

[0177] Example 67. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: receive from a network node information associated with a machine learning (ML)-based compression algorithm for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of: an indication of the cause of a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; perform compression of the HARQ-ACK codebook based at least on the information and the ML-based compression algorithm; and transmit the compressed HARQ-ACK codebook to the network node.

[0178] Example 68. The apparatus according to Example 67, wherein: the information further includes at least one measurement configuration for performing at least one measurement; and the at least one measurement is configured to be used to train an ML-based compression algorithm.

[0179] Example 69. An apparatus according to Example 67 or 68, wherein the apparatus is further configured to perform: sending to a network node at least one of the following: a HARQ-ACK codebook; a compressed HARQ-ACK codebook; information indicating the difference between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; or information based on an ML-based compression algorithm, wherein the sending is via at least one of Radio Resource Control (RRC) signaling or Uplink Control Information (UCI); and receiving an instruction to configure the compression of the HARQ-ACK codebook.

[0180] Example 70. An apparatus according to any one of Examples 67 to 69, wherein the information of the ML-based compression algorithm for performing compression of the HARQ-ACK codebook includes at least one of the following: an identifier of the ML-based compression algorithm; information of the loss function of the ML-based compression algorithm; information of the transformation model of the ML-based compression algorithm; information of the encoding algorithm of the ML-based compression algorithm; information of the decoding algorithm of the ML-based compression algorithm; physical downlink control channel (PDCCH) aggregation level; at least one scheduling instance; at least one scheduling constraint; or redundancy information.

[0181] Example 71. An apparatus according to any one of Examples 67 to 70, wherein the ML-based compression algorithm is at least partially based on a compression algorithm comprising at least one of the following: bundling multiple HARQ-ACK bits; bitmap encoding of HARQ-ACK; run-length encoding (RLE); or Burrows-Wheeler transform (BWT).

[0182] Example 72. An apparatus according to any one of Examples 67 to 71, wherein the ML-based compression algorithm is based on an ML model configured on at least one of the user equipment or the network node.

[0183] Example 73. The apparatus according to Example 72, wherein the input to the ML-based compression algorithm further includes at least one of the following: a HARQ-ACK codebook; or a variable-length input comprising a HARQ-ACK codebook and variable-length padding for training bits.

[0184] Example 74. An apparatus according to any one of Examples 67 to 73, wherein: the indication of the cause of NACK in the HARQ-ACK codebook indicates the source of HARQ-ACK in the HARQ-ACK codebook, wherein the source of HARQ-ACK indicates that the NACK is caused by a Physical Downlink Control Channel (PDCCH) decoding error or a Physical Downlink Shared Channel (PDSCH) error; and the quality indicator includes the PDCCH aggregation level.

[0185] Example 75. An apparatus according to any one of Examples 67 to 74, wherein the compressed HARQ-ACK codebook is of fixed length.

[0186] Example 76. An apparatus according to any one of Examples 67 to 75, wherein the ML-based compression algorithm includes encoding and decoding functions performed on at least one of the user equipment or the network node.

[0187] Example 77. An apparatus according to any one of Examples 67 to 76, wherein the apparatus is further configured to perform receiving from the network node at least one of the following: information on an ML-based compression algorithm; or an instruction for an ML model for an ML-based compression algorithm, wherein the ML model includes at least one of the following: linear regression; logistic regression; decision tree; support vector machine (SVM) algorithm; Naive Bayes algorithm; K-nearest neighbors (KNN) algorithm; K-means; random forest algorithm; or dimensionality reduction algorithm.

[0188] Example 78. An apparatus according to any one of Examples 67 to 77, wherein the apparatus is further configured to perform an instruction to receive compression of the HARQ-ACK codebook from the network node.

[0189] Example 79. An apparatus according to any one of Examples 67 to 78, wherein the apparatus is further caused to perform: monitoring the operation of an ML-based compression algorithm; and performing model training based on the monitoring results.

[0190] Example 80. An apparatus according to any one of Examples 67 to 79, wherein the apparatus is further configured to perform: monitoring the operation of the ML-based compression algorithm; sending the monitoring results to the network node; and receiving updates of information about the ML-based compression algorithm.

[0191] Example 81. An apparatus according to any one of Examples 67 to 80, wherein the apparatus is further configured to send to the network node at least one of the following: an indication of HARQ-ACK codebook compression capability; an indication of supported compression algorithms for HARQ-ACK codebook compression; an indication of support for one or more ML-based algorithms used for HARQ-ACK codebook compression; or an indication of support for one or more ML models used for HARQ-ACK codebook compression, wherein the sending is via at least one of RRC signaling or Non-Access Stratum (NAS) signaling.

[0192] Example 82. An apparatus according to any one of Examples 67 to 81, wherein information of an ML-based compression algorithm is received as part of at least one of: Radio Resource Control (RRC) signaling; Media Access Control (MAC) Control Unit (MAC-CE); or Non-Access Stratum (NAS) signaling.

[0193] Example 83. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: send to a user equipment information associated with a machine learning (ML)-based compression algorithm for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of: an indication of the cause of a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; and receive the compressed HARQ-ACK codebook from the user equipment.

[0194] Example 84. The apparatus according to Example 83, wherein: the information further includes at least one measurement configuration for performing at least one measurement; and the at least one measurement is configured to be used for training an ML-based compression algorithm.

[0195] Example 85. An apparatus according to Example 83 or 84, wherein the apparatus is further configured to perform: receiving from the user equipment at least one of the following: a HARQ-ACK codebook; a compressed HARQ-ACK codebook; information indicating the difference between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; or information of an ML-based compression algorithm, wherein receiving is performed via at least one of Radio Resource Control (RRC) signaling or Uplink Control Information (UCI); and transmitting an instruction to configure the compression of the HARQ-ACK codebook.

[0196] Example 86. An apparatus according to any one of Examples 83 to 85, wherein the information of the ML-based compression algorithm for performing compression of the HARQ-ACK codebook includes at least one of the following: an identifier of the ML-based compression algorithm; information of the loss function of the ML-based compression algorithm; information of the transformation model of the ML-based compression algorithm; information of the encoding algorithm of the ML-based compression algorithm; information of the decoding algorithm of the ML-based compression algorithm; physical downlink control channel (PDCCH) aggregation level; at least one scheduling instance; at least one scheduling constraint; or redundancy information.

[0197] Example 87. An apparatus according to any one of Examples 83 to 86, wherein the ML-based compression algorithm is at least partially based on a compression algorithm comprising at least one of the following: bundling multiple HARQ-ACK bits; bitmap encoding of HARQ-ACK; run-length encoding (RLE); or Burrows-Wheeler transform (BWT).

[0198] Example 88. An apparatus according to any one of Examples 83 to 87, wherein the ML-based compression algorithm is based on an ML model configured on at least one of the user equipment or network node.

[0199] Example 89. The apparatus according to Example 88, wherein the input to the ML-based compression algorithm further includes at least one of the following: a HARQ-ACK codebook; or a variable-length input comprising a HARQ-ACK codebook and variable-length padding for training bits.

[0200] Example 90. An apparatus according to any one of Examples 83 to 89, wherein: the indication of the cause of NACK in the HARQ-ACK codebook indicates the source of HARQ-ACK in the HARQ-ACK codebook, wherein the source of HARQ-ACK indicates that the NACK is caused by a Physical Downlink Control Channel (PDCCH) decoding error or a Physical Downlink Shared Channel (PDSCH) error; and the quality indicator includes the PDCCH aggregation level.

[0201] Example 91. An apparatus according to any one of Examples 83 to 90, wherein the compressed HARQ-ACK codebook is configured by the network node to be fixed in length or variable in length.

[0202] Example 92. An apparatus according to any one of Examples 83 to 91, wherein the ML-based compression algorithm includes encoding and decoding functions performed on at least one of the user equipment or the network node.

[0203] Example 93. An apparatus according to any one of Examples 83 to 92, wherein the apparatus is further configured to send to a user equipment at least one of the following: information on an ML-based compression algorithm; or an instruction for an ML model for an ML-based compression algorithm, wherein the ML model includes at least one of the following: linear regression; logistic regression; decision tree; support vector machine (SVM) algorithm; Naive Bayes algorithm; K-nearest neighbors (KNN) algorithm; K-means; random forest algorithm; or dimensionality reduction algorithm.

[0204] Example 94. An apparatus according to any one of Examples 83 to 93, wherein the apparatus is further configured to perform an instruction to send to a user equipment the compression of the HARQ-ACK codebook to be deactivated.

[0205] Example 95. An apparatus according to any one of Examples 83 to 94, wherein the apparatus is further configured to: monitor the operation of an ML-based compression algorithm; and perform model training based on the monitoring results.

[0206] Example 96. An apparatus according to any one of Examples 83 to 95, wherein the apparatus is further configured to perform: monitoring the operation of an ML-based compression algorithm; sending the monitoring results to a user equipment; and receiving updates to the information of the ML-based compression algorithm.

[0207] Example 97. An apparatus according to any one of Examples 83 to 96, wherein the apparatus is further configured to perform receiving from a user equipment at least one of the following: an indication of HARQ-ACK codebook compression capability; an indication of supported compression algorithms for HARQ-ACK codebook compression; an indication of support for one or more ML-based algorithms used for HARQ-ACK codebook compression; or an indication of support for one or more ML models used for HARQ-ACK codebook compression, wherein transmission is performed via at least one of RRC signaling or Non-Access Stratum (NAS) signaling.

[0208] Example 98. An apparatus according to any one of Examples 83 to 97, wherein information based on an ML compression algorithm is transmitted as part of at least one of: Radio Resource Control (RRC) signaling; Media Access Control (MAC) Control Unit (MAC-CE); or Non-Access Stratum (NAS) signaling.

[0209] Example 99. An apparatus comprising components for performing: receiving from a network node information associated with a machine learning (ML)-based compression algorithm for performing compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; performing compression of the HARQ-ACK codebook based at least on the information and the ML-based compression algorithm; and transmitting the compressed HARQ-ACK codebook to the network node.

[0210] Example 100. An apparatus comprising components for performing: sending information associated with a machine learning (ML)-based compression algorithm to a user equipment, the ML-based compression algorithm being used to perform compression of a hybrid automatic repeat request acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; and receiving the compressed HARQ-ACK codebook from the user equipment.

[0211] Example 101. A method comprising: receiving, by a user equipment, information associated with a machine learning (ML)-based compression algorithm from a network node, the ML-based compression algorithm being used to perform compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of: an indication of the cause of a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; performing compression of the HARQ-ACK codebook based at least on the information and the ML-based compression algorithm; and transmitting the compressed HARQ-ACK codebook to the network node.

[0212] Example 102. According to the method of Example 101, wherein: the information further includes at least one measurement configuration for performing at least one measurement; and the at least one measurement is configured to be used to train an ML-based compression algorithm.

[0213] Example 103. The method according to Example 101 or 102 further includes: sending to a network node at least one of the following: a HARQ-ACK codebook; a compressed HARQ-ACK codebook; information indicating the difference between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; or information based on an ML-based compression algorithm, wherein the sending is via at least one of Radio Resource Control (RRC) signaling or Uplink Control Information (UCI); and receiving an instruction to configure the compression of the HARQ-ACK codebook.

[0214] Example 104. According to the method of any one of Examples 101 to 103, the information of the ML-based compression algorithm used to perform compression of the HARQ-ACK codebook includes at least one of the following: an identifier of the ML-based compression algorithm; information of the loss function of the ML-based compression algorithm; information of the transformation model of the ML-based compression algorithm; information of the encoding algorithm of the ML-based compression algorithm; information of the decoding algorithm of the ML-based compression algorithm; physical downlink control channel (PDCCH) aggregation level; at least one scheduling instance; at least one scheduling constraint; or redundancy information.

[0215] Example 105. A method according to any one of Examples 101 to 104, wherein the ML-based compression algorithm is at least partially based on a compression algorithm comprising at least one of the following: bundling multiple HARQ-ACK bits; bitmap encoding of HARQ-ACK; run-length encoding (RLE); or Burrows-Wheeler transform (BWT).

[0216] Example 106. The method of any one of Examples 101 to 105, wherein the ML-based compression algorithm is based on an ML model configured on at least one of the user equipment or the network node.

[0217] Example 107. According to the method of Example 106, the input to the ML-based compression algorithm further includes at least one of the following: a HARQ-ACK codebook; or a variable-length input, which includes a HARQ-ACK codebook and variable-length padding for training bits.

[0218] Example 108. A method according to any one of Examples 101 to 107, wherein: the indication of the cause of NACK in the HARQ-ACK codebook indicates the source of HARQ-ACK in the HARQ-ACK codebook, wherein the source of HARQ-ACK indicates that the NACK is caused by a Physical Downlink Control Channel (PDCCH) decoding error or a Physical Downlink Shared Channel (PDSCH) error; and the quality indicator includes the PDCCH aggregation level.

[0219] Example 109. The method of any one of Examples 101 to 108, wherein the compressed HARQ-ACK codebook is of fixed length.

[0220] Example 110. The method of any one of Examples 101 to 109, wherein the ML-based compression algorithm includes encoding and decoding functions performed on at least one of the user equipment or the network node.

[0221] Example 111: The method according to any one of Examples 101 to 110 further includes receiving from the network node at least one of the following: information on an ML-based compression algorithm; or an indication of an ML model for an ML-based compression algorithm, wherein the ML model includes at least one of the following: linear regression; logistic regression; decision tree; support vector machine (SVM) algorithm; Naive Bayes algorithm; K-nearest neighbors (KNN) algorithm; K-means; random forest algorithm; or dimensionality reduction algorithm.

[0222] Example 112. The method according to any one of Examples 101 to 111 further includes receiving an instruction from the network node to deactivate compression of the HARQ-ACK codebook.

[0223] Example 113. The method according to any one of Examples 101 to 112 further includes: monitoring the operation of the ML-based compression algorithm; and performing model training based on the monitoring results.

[0224] Example 114. The method according to any one of Examples 101 to 113 further includes: monitoring the operation of the ML-based compression algorithm; sending the monitoring results to the network node; and receiving updates to the information of the ML-based compression algorithm.

[0225] Example 115. The method according to any one of Examples 101 to 114 further includes sending to the network node at least one of the following: an indication of HARQ-ACK codebook compression capability; an indication of supported compression algorithms for HARQ-ACK codebook compression; an indication of support for one or more ML-based algorithms used for HARQ-ACK codebook compression; or an indication of support for one or more ML models used for HARQ-ACK codebook compression, wherein the sending is via at least one of RRC signaling or Non-Access Stratum (NAS) signaling.

[0226] Example 116. The method according to any one of Examples 101 to 115, wherein information of the ML-based compression algorithm is received as part of at least one of: Radio Resource Control (RRC) signaling; Media Access Control (MAC) Control Unit (MAC-CE); or Non-Access Stratum (NAS) signaling.

[0227] Example 117. A method comprising: sending information associated with a machine learning (ML)-based compression algorithm to a user equipment from a network node, the ML-based compression algorithm being used to perform compression of a Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook, wherein the compression is performed based on the ML-based compression algorithm, wherein: the input to the ML-based compression algorithm includes at least one of the following: an indication of the reason for a negative acknowledgment (NACK) of the HARQ-ACK codebook; or a quality indicator; and the output of the ML-based compression algorithm includes the compressed HARQ-ACK codebook; and receiving the compressed HARQ-ACK codebook from the user equipment.

[0228] Example 118. According to the method of Example 117, wherein: the information further includes at least one measurement configuration for performing at least one measurement; and the at least one measurement is configured to be used to train an ML-based compression algorithm.

[0229] Example 119. The method according to Example 117 or 118 further includes: receiving from the user equipment at least one of the following: a HARQ-ACK codebook; a compressed HARQ-ACK codebook; information indicating the difference between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; or information of an ML-based compression algorithm, wherein receiving is via at least one of Radio Resource Control (RRC) signaling or Uplink Control Information (UCI); and sending an instruction to configure the compression of the HARQ-ACK codebook.

[0230] Example 120. According to the method of any one of Examples 117 to 119, the information of the ML-based compression algorithm used to perform compression of the HARQ-ACK codebook includes at least one of the following: an identifier of the ML-based compression algorithm; information of the loss function of the ML-based compression algorithm; information of the transformation model of the ML-based compression algorithm; information of the encoding algorithm of the ML-based compression algorithm; information of the decoding algorithm of the ML-based compression algorithm; physical downlink control channel (PDCCH) aggregation level; at least one scheduling instance; at least one scheduling constraint; or redundancy information.

[0231] Example 121. A method according to any one of Examples 117 to 120, wherein the ML-based compression algorithm is at least partially based on a compression algorithm comprising at least one of the following: bundling multiple HARQ-ACK bits; bitmap encoding of HARQ-ACK; run-length encoding (RLE); or Burrows-Wheeler transform (BWT).

[0232] Example 122. The method of any one of Examples 117 to 121, wherein the ML-based compression algorithm is based on an ML model configured on at least one of the user equipment or network node.

[0233] Example 123. According to the method of Example 122, the input to the ML-based compression algorithm further includes at least one of the following: a HARQ-ACK codebook; or a variable-length input, which includes a HARQ-ACK codebook and variable-length padding for training bits.

[0234] Example 124. A method according to any one of Examples 117 to 123, wherein: the indication of the cause of NACK in the HARQ-ACK codebook indicates the source of HARQ-ACK in the HARQ-ACK codebook, wherein the source of HARQ-ACK indicates that the NACK is caused by a Physical Downlink Control Channel (PDCCH) decoding error or a Physical Downlink Shared Channel (PDSCH) error; and the quality indicator includes the PDCCH aggregation level.

[0235] Example 125. The method of any one of Examples 117 to 124, wherein the compressed HARQ-ACK codebook is configured by the network node to be either fixed in length or variable in length.

[0236] Example 126. The method of any one of Examples 117 to 125, wherein the ML-based compression algorithm includes encoding and decoding functions performed on at least one of the user equipment or the network node.

[0237] Example 127. The method according to any one of Examples 117 to 126 further includes sending to the user equipment at least one of the following: information on an ML-based compression algorithm; or an instruction for an ML model for an ML-based compression algorithm, wherein the ML model includes at least one of the following: linear regression; logistic regression; decision tree; support vector machine (SVM) algorithm; Naive Bayes algorithm; K-nearest neighbors (KNN) algorithm; K-means; random forest algorithm; or dimensionality reduction algorithm.

[0238] Example 128. The method according to any one of Examples 117 to 127 further includes sending an instruction to the user equipment to deactivate the compression of the HARQ-ACK codebook.

[0239] Example 129. The method according to any one of Examples 117 to 128 further includes: monitoring the operation of the ML-based compression algorithm; and performing model training based on the monitoring results.

[0240] Example 130. The method according to any one of Examples 117 to 129 further includes: monitoring the operation of the ML-based compression algorithm; sending the monitoring results to the user equipment; and receiving updates to the information of the ML-based compression algorithm.

[0241] Example 131. The method according to any one of Examples 117 to 130 further includes receiving from the user equipment at least one of the following: an indication of HARQ-ACK codebook compression capability; an indication of supported compression algorithms for HARQ-ACK codebook compression; an indication of support for one or more ML-based algorithms used for HARQ-ACK codebook compression; or an indication of support for one or more ML models used for HARQ-ACK codebook compression, wherein transmission is made via at least one of RRC signaling or Non-Access Stratum (NAS) signaling.

[0242] Example 132. A method according to any one of Examples 117 to 131, wherein information based on an ML compression algorithm is transmitted as part of at least one of: Radio Resource Control (RRC) signaling; Media Access Control (MAC) Control Unit (MAC-CE); or Non-Access Stratum (NAS) signaling.

[0243] Example 133. A non-transitory computer-readable storage medium including instructions stored thereon, which, when executed by at least one processor, are configured to cause a computing system to perform a method according to any one of Examples 35 to 66.

[0244] Example 134. A computer program including instructions stored thereon for performing a method according to any one of Examples 35 to 66.

[0245] Example 135. An apparatus comprising components for performing a method according to any one of Examples 35 to 66.

[0246] Example 136. A non-transitory computer-readable storage medium including instructions stored thereon, which, when executed by at least one processor, are configured to cause a computing system to perform a method according to any one of Examples 101 to 132.

[0247] Example 137. A computer program including instructions stored thereon for performing a method according to any one of Examples 101 to 132.

[0248] Example 138. An apparatus comprising components for performing a method according to any one of Examples 101 to 132.

Claims

1. A device for communication, comprising: At least one processor; as well as At least one memory storing instructions that, when executed by the at least one processor, cause the device to perform at least the following: Receive information from a network node, the information specifying at least one parameter for compressing the HARQ-ACK codebook for performing hybrid automatic repeat request acknowledgment (HARQ-ACK); Based at least on the information and at least one HARQ-ACK codebook compression model, the compression of the HARQ-ACK codebook is performed; Monitor the operation of at least one HARQ-ACK codebook compression model; as well as The compressed HARQ-ACK codebook is sent to the network node.

2. The apparatus according to claim 1, wherein: The information also includes at least one measurement configuration for performing at least one measurement; and The at least one measurement is configured to be used to monitor the operation of the at least one HARQ-ACK codebook compression model.

3. The apparatus of claim 2, wherein the operation of monitoring the at least one HARQ-ACK codebook compression model comprises at least one of the following: Perform the at least one measurement associated with the at least one HARQ-ACK codebook compression model; Based on the at least one measurement associated with the at least one HARQ-ACK codebook compression model, at least one monitoring result for the at least one HARQ-ACK codebook compression model is determined; or Based on the determination of the at least one monitoring result, determine whether to update the at least one HARQ-ACK codebook compression model.

4. The apparatus according to any one of claims 1 to 3, wherein the apparatus is further caused to perform: Send at least one of the following to the network node: The HARQ-ACK codebook; The compressed HARQ-ACK codebook; Information indicating the differences between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; Based on at least one measurement associated with the at least one HARQ-ACK codebook compression model, and at least one monitoring result for the at least one HARQ-ACK codebook compression model; or The information of the at least one HARQ-ACK codebook compression model, wherein the transmission is via at least one of Radio Resource Control (RRC) signaling or Uplink Control Information (UCI); and The device is also configured to perform at least one of the following: Receive an instruction to configure the compression of the HARQ-ACK codebook; or Receive an update to the information specifying at least one parameter used to perform compression of the HARQ-ACK codebook.

5. The apparatus according to any one of claims 1 to 3, wherein the at least one parameter for performing compression of the HARQ-ACK codebook includes at least one of the following: Information of the at least one HARQ-ACK codebook compression model, the information including the identifier of the at least one HARQ-ACK codebook compression model; Physical downlink control channel (PDCCH) aggregation level; At least one scheduling instance; At least one scheduling constraint; or Redundant information.

6. The apparatus according to any one of claims 1 to 3, wherein the at least one HARQ-ACK codebook compression model comprises at least one of the following: Bundle multiple HARQ-ACK bits; Bitmap encoding of HARQ-ACK; Run-length encoding (RLE); or Burrows-Wheeler Transform (BWT) 7. The apparatus according to any one of claims 1 to 3, wherein the at least one HARQ-ACK codebook compression model is based on a machine learning (ML) algorithm, and wherein the ML algorithm is based on an ML model configured on at least one of the apparatus or the network node.

8. The apparatus of claim 7, wherein the ML algorithm comprises at least one of the following: Input, the input including a HARQ-ACK codebook; A quality indicator, wherein the quality indicator includes the PDCCH aggregation level, and wherein the quality indicator is configured by the network node; Variable-length input, which includes the HARQ-ACK codebook and variable-length padding for training bits; or The output includes at least one of a compressed HARQ-ACK codebook on the encoder side or a reconstructed HARQ-ACK codebook on the decoder side.

9. The apparatus of claim 8, wherein the input further comprises a source of HARQ-ACK in the HARQ-ACK codebook, wherein the source indicates that the negative ACK / NACK is caused by a PDCCH decoding error, a PDCCH monitoring interruption, or a Physical Downlink Shared Channel (PDSCH) decoding error, or a PDSCH monitoring error.

10. The apparatus according to any one of claims 1 to 3, wherein the compressed HARQ-ACK codebook is configured by the network node to be fixed in length or variable in length.

11. The apparatus according to any one of claims 1 to 3, wherein the at least one HARQ-ACK codebook compression model includes encoding and decoding functions performed on at least one of the apparatus or the network node.

12. The apparatus according to any one of claims 1 to 3, wherein the apparatus is further configured to receive at least one of the following from the network node: Information of at least one HARQ-ACK codebook compression model; or Instructions for an ML model used in the at least one HARQ-ACK codebook compression model, wherein the ML model includes at least one of the following: Linear regression; Logistic regression; Decision tree; Support Vector Machine (SVM) algorithm; Naive Bayes algorithm; K-Nearest Neighbors (KNN) algorithm; K-means; Random Forest algorithm; or Dimensionality reduction algorithm.

13. The apparatus according to any one of claims 1 to 3, wherein the apparatus is further configured to perform an instruction to receive from the network node to deactivate compression of the HARQ-ACK codebook.

14. The apparatus according to any one of claims 1 to 3, wherein the apparatus is further configured to send at least one of the following to the network node: Indicator of HARQ-ACK codebook compression capability; An indication of the supported HARQ-ACK codebook compression model used for compression of the HARQ-ACK codebook; or Indications for support for one or more ML models used for compression of the HARQ-ACK codebook. The transmission is carried out via at least one of RRC signaling or NAS signaling.

15. The apparatus according to any one of claims 1 to 3, wherein the apparatus is further configured to perform an instruction to receive and monitor the operation of the at least one HARQ-ACK codebook compression model, and wherein the operation of monitoring the at least one HARQ-ACK codebook compression model is based on the instruction.

16. The apparatus according to any one of claims 1 to 3, wherein information specifying at least one parameter for performing compression of the HARQ-ACK codebook is received as part of at least one of the following: Radio Resource Control (RRC) signaling; Media access control MAC control unit MAC-CE; or Non-access stratum (NAS) signaling.

17. An apparatus for communication, comprising: At least one processor; as well as At least one memory storing instructions that, when executed by the at least one processor, cause the device to perform at least the following: Send information to the user equipment, the information specifying at least one parameter for compressing the HARQ-ACK codebook for performing the Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK) codebook; Monitor the operation of at least one HARQ-ACK codebook compression model; as well as Receive the compressed HARQ-ACK codebook from the user equipment.

18. The apparatus of claim 17, wherein: The information also includes at least one measurement configuration for performing at least one measurement; and The at least one measurement is configured to be used for the operation of monitoring the at least one HARQ-ACK codebook compression model.

19. The apparatus of claim 18, wherein the operation of monitoring the at least one HARQ-ACK codebook compression model comprises at least one of the following: Perform the at least one measurement associated with the at least one HARQ-ACK codebook compression model; Based on the at least one measurement associated with the at least one HARQ-ACK codebook compression model, at least one monitoring result for the at least one HARQ-ACK codebook compression model is determined; or Based on the determination of the at least one monitoring result, determine whether to update the at least one HARQ-ACK codebook compression model.

20. The apparatus according to any one of claims 17 to 19, wherein the apparatus is further caused to perform: Receive at least one of the following from the user equipment: The HARQ-ACK codebook; The compressed HARQ-ACK codebook; Information indicating the differences between the HARQ-ACK codebook and the compressed HARQ-ACK codebook; Based on at least one measurement associated with the at least one HARQ-ACK codebook compression model, and at least one monitoring result for the at least one HARQ-ACK codebook compression model; or Information of the at least one HARQ-ACK codebook compression model, wherein the reception is via at least one of Radio Resource Control (RRC) signaling or Uplink Control Information (UCI); and The device is also configured to perform at least one of the following: Send an instruction to configure the compression of the HARQ-ACK codebook; or Send an update of the information specifying at least one parameter used to perform compression of the HARQ-ACK codebook.

21. The apparatus according to any one of claims 17 to 19, wherein the at least one parameter for performing compression of the HARQ-ACK codebook includes at least one of the following: Information of the at least one HARQ-ACK codebook compression model, the information including the identifier of the at least one HARQ-ACK codebook compression model; Physical downlink control channel (PDCCH) aggregation level; At least one scheduling instance; At least one scheduling constraint; or Redundant information.

22. The apparatus according to any one of claims 17 to 19, wherein the at least one HARQ-ACK codebook compression model comprises at least one of the following: Bundle multiple HARQ-ACK bits; Bitmap encoding of HARQ-ACK; Run-length encoding (RLE); or Burrows-Wheeler Transform (BWT) 23. The apparatus according to any one of claims 17 to 19, wherein the at least one HARQ-ACK codebook compression model is based on a machine learning (ML) algorithm, and wherein the ML algorithm is based on an ML model configured on at least one of the user equipment or the apparatus.

24. The apparatus of claim 23, wherein the ML algorithm comprises at least one of the following: Input, the input including a HARQ-ACK codebook; A quality indicator, wherein the quality indicator includes the PDCCH aggregation level, and wherein the quality indicator is configured by the device; Variable-length input, the variable-length input including the HARQ-ACK codebook and variable-length padding for training bits; or The output includes at least one of a compressed HARQ-ACK codebook on the encoder side or a reconstructed HARQ-ACK codebook on the decoder side.

25. A method for communication, comprising: The user equipment receives information from the network node, the information specifying at least one parameter for compressing the codebook for performing the Hybrid Automatic Repeat Request Acknowledgment (HARQ-ACK); Based at least on the information and at least one HARQ-ACK codebook compression model, the compression of the HARQ-ACK codebook is performed; Monitor the operation of at least one HARQ-ACK codebook compression model; as well as The compressed HARQ-ACK codebook is sent to the network node.

Images