Method and apparatus for embedding-aware vector quantization and transmission
The dynamic adaptive codebook design and task-driven compression strategy in wireless communication systems address the inefficiencies of traditional methods by adapting to embedding vector changes, ensuring accurate and efficient compression and semantic preservation.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-12-26
- Publication Date
- 2026-04-09
AI Technical Summary
Existing vector quantization methods for embedding information in wireless communication systems fail to adapt to the dynamic changes in dimensions and precision requirements of embedding vectors, leading to inefficiencies and loss of semantic features.
A dynamic adaptive codebook design and task-driven compression strategy that adjusts codebook size and codeword allocation based on embedding distribution and precision, incorporating an effectiveness quality indicator (EQI) for real-time adaptation.
Enhances compression efficiency by preserving critical semantic features and accurately reflecting user preferences in real-time, improving the effectiveness of applications like real-time recommendation systems.
Smart Images

Figure CN2024142688_09042026_PF_FP_ABST
Abstract
Description
METHOD AND APPARATUS FOR EMBEDDING-AWARE VECTOR QUANTIZATION AND TRANSMISSIONCROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims the benefit of U.S. Provisional Application Serial No. 63 / 702,001 filed on October 1, 2024, the entire contents of which are hereby incorporated by reference in its entirety.TECHNICAL FIELD
[0002] The application relates generally to wireless communications, and more specifically to methods, apparatuses and systems for embedding-aware vector quantization and transmission.BACKGROUND
[0003] As artificial intelligence (AI) applications become increasingly widespread, AI services generate a vast amount of embedding information that needs to be transmitted over wireless networks. Embedding information is typically composed of a set of continuous real-valued numbers, which are obtained through training processes and approximated in computers as floating-point numbers. The dimension of each embedding vector (i.e., the length of the vector) determines its complexity and capability. To better capture features, these dimensions are often quite high, such as 768, 1024, or even 12288 dimensions like in GPT-3. These high-dimensional vectors lead to a massive amount of data, placing a significant burden on wireless networks.SUMMARY
[0004] One or more implementations of the present application provide communication methods and communication apparatuses. The techniques described in the application can improve the performance of embedding-aware vector quantization and transmission in wireless communication systems.
[0005] According to a first aspect, a method is provided. The method includes transmitting embedding codebook information (ECI) , where the ECI indicates one or more embedding codebooks. The method further includes transmitting or receiving encoded embedding information, where the encoded embedding information is based on the ECI.
[0006] With reference to the first aspect, in some implementations, the method further includes receiving an embedding codebook confirmation (ECC) , where the ECC indicates a first embedding codebook belonging to the one or more embedding codebooks, where the encoded embedding information is based on the first embedding codebook.
[0007] With reference to the first aspect, in some implementations, the ECI includes at least one of the following for each of the one or more embedding codebooks: an identifier; a size; a modality; a machine learning model identifier; dimension; precision; a description; expansion support; or an application type.
[0008] With reference to the first aspect, in some implementations, the ECI indicates codewords for each of the one or more embedding codebooks.
[0009] With reference to the first aspect, in some implementations, the ECI is carried in at least one of a higher layer signaling or a physical layer signaling.
[0010] With reference to the first aspect, in some implementations, the ECI includes a first portion carried in a first higher layer signaling and a second portion carried in a second higher layer signaling, the first portion includes a first set of codewords for the one or more embedding codebooks, and the second portion includes a second set of codewords for the one or more embedding codebooks.
[0011] With reference to the first aspect, in some implementations, the method further includes encoding embedding information using the first embedding codebook, where the embedding information includes one or more embedding vectors.
[0012] With reference to the first aspect, in some implementations, the method further includes decoding the encoded embedding information using the first embedding codebook, where the decoded embedding information indicates one or more embedding vectors.
[0013] With reference to the first aspect, in some implementations, the method further includes transmitting an EQI, where the EQI is determined based on the encoded embedding information.
[0014] With reference to the first aspect, in some implementations, the method further includes transmitting an ECU, where the ECU indicates a second embedding codebook or a change to the first embedding codebook.
[0015] With reference to the first aspect, in some implementations, the change to the first embedding codebook indicates at least one of: one or more codewords to be removed from the first embedding codebook; one or more codewords to be added to the first embedding codebook; one or more codewords to be replaced in the first embedding codebook; or a change to a codeword length.
[0016] With reference to the first aspect, in some implementations, the second embedding codebook is from the one or more embedding codebooks.
[0017] With reference to the first aspect, in some implementations, the second embedding codebook is different from the one or more embedding codebooks, and the ECU indicates codewords for the second embedding codebook.
[0018] With reference to the first aspect, in some implementations, the ECU is determined based on at least one of: a distribution of received embedding information; a distribution of transmitted embedding information; a distribution of to-be-transmitted embedding information; or an EQI determined based on received embedding information; a CQI; or a received EQI.
[0019] According to a second aspect, a method is provided. The method includes receiving ECI, where the ECI indicates one or more embedding codebooks. The method further includes transmitting an ECC, where the ECC indicates a first embedding codebook belonging to the one or more embedding codebooks.
[0020] With reference to the second aspect, in some implementations, the ECI includes at least one of the following for each of the one or more embedding codebooks: an identifier; a size; a modality; a machine learning model identifier; dimension; precision; a description; expansion support; or an application type.
[0021] With reference to the second aspect, in some implementations, the ECI indicates codewords for each of the one or more embedding codebooks.
[0022] With reference to the second aspect, in some implementations, the ECI is carried in at least one of a higher layer signaling or a physical layer signaling.
[0023] With reference to the second aspect, in some implementations, the ECI includes a first portion carried in a first higher layer signaling and a second portion carried in a second higher layer signaling, the first portion includes a first set of codewords for the one or more embedding codebooks, and the second portion includes a second set of codewords for the one or more embedding codebooks.
[0024] With reference to the second aspect, in some implementations, the method further includes encoding embedding information using the first embedding codebook, where the embedding information includes one or more embedding vectors; and transmitting the encoded embedding information.
[0025] With reference to the second aspect, in some implementations, the method further includes receiving encoded embedding information; and decoding the encoded embedding information using the first embedding codebook, where the decoded embedding information indicates one or more embedding vectors.
[0026] With reference to the second aspect, in some implementations, the method further includes transmitting an EQI, where the EQI is determined based on the encoded embedding information.
[0027] With reference to the second aspect, in some implementations, the method further includes receiving an ECU, where the ECU indicates a second embedding codebook or a change to the first embedding codebook.
[0028] With reference to the second aspect, in some implementations, the change to the first embedding codebook indicates at least one of: one or more codewords to be removed from the first embedding codebook; one or more codewords to be added to the first embedding codebook; one or more codewords to be replaced in the first embedding codebook; or a change to a codeword length.
[0029] With reference to the second aspect, in some implementations, the second embedding codebook is from the one or more embedding codebooks.
[0030] With reference to the second aspect, in some implementations, the second embedding codebook is different from the one or more embedding codebooks, and the ECU indicates codewords for the second embedding codebook.
[0031] With reference to the second aspect, in some implementations, the ECU is determined based on at least one of: a distribution of received embedding information; a distribution of transmitted embedding information; a distribution of to-be-transmitted embedding information; or an EQI determined based on received embedding information; a CQI; or a received EQI.
[0032] According to a third aspect, an apparatus is provided. The apparatus is configured to perform the method according to the first aspect or one or more implementations of the first aspect, or the second aspect or one or more implementations of the second aspect.
[0033] According to a fourth aspect, an apparatus is provided. The apparatus includes: a transmitting unit configured to transmit ECI, where the ECI indicates one or more embedding codebooks; and a communication unit configured to transmit or receive encoded embedding information, where the encoded embedding information is based on the ECI.
[0034] According to a fifth aspect, an apparatus is provided. The apparatus includes: a receiving unit configured to receive ECI, where the ECI indicates one or more embedding codebooks; and a transmitting unit configured to transmit an ECC, where the ECC indicates a first embedding codebook from the one or more embedding codebooks.
[0035] According to a sixth aspect, an apparatus is provided. The apparatus includes: one or more processors; and an interface circuit configured to transmit ECI, where the ECI indicates one or more embedding codebooks; and transmit or receive encoded embedding information, where the encoded embedding information is based on the ECI.
[0036] According to a seventh aspect, an apparatus is provided. The apparatus includes: one or more processors; and an interface circuit configured to receive ECI, where the ECI indicates one or more embedding codebooks; and transmit an ECC, where the ECC indicates a first embedding codebook from the one or more embedding codebooks.
[0037] With reference to the sixth aspect or the seventh aspect, in some implementations, the interface circuit includes one or more transceivers.
[0038] According to an eighth aspect, an apparatus is provided. The apparatus includes one or more processors and one or more memories. The one or more memories store instructions which, when executed by the one or more processors, cause the apparatus to perform the method according to the first aspect or one or more implementations of the first aspect, or the second aspect or one or more implementations of the second aspect.
[0039] According to a ninth aspect, a communication system is provided. The communication system includes a first apparatus configured to perform the method according to the first aspect or one or more implementations of the first aspect. The communication system further includes a second apparatus configured to perform the method according to the second aspect or one or more implementations of the second aspect.
[0040] According to a tenth aspect, a non-transitory computer-readable storage medium is provided. The non-transitory computer-readable storage medium has instructions stored thereon which, when executed by an apparatus, cause the apparatus to perform the method according to the first aspect or one or more implementations of the first aspect, or the second aspect or one or more implementations of the second aspect.
[0041] According to an eleventh aspect, a computer program product is provided. The computer program product stores instructions which, when executed, cause an apparatus to perform the method according to the first aspect or one or more implementations of the first aspect, or the second aspect or one or more implementations of the second aspect.BRIEF DESCRIPTION OF THE DRAWINGS
[0042] FIG. 1 illustrates a schematic illustration of an example communication system.
[0043] FIG. 2 illustrates another example communication system.
[0044] FIG. 3 illustrates an example of an apparatus wirelessly communicating with another apparatus in a communication system.
[0045] FIG. 4 illustrates an example apparatus.
[0046] FIG. 5 illustrates another example apparatus.
[0047] FIG. 6 illustrates an example procedure for a dynamic adaptive codebook design.DETAILED DESCRIPTION
[0048] In some implementations, vector compression techniques include vector quantization and compression coding. Vector quantization is mainly used for dimensionality reduction; it reduces storage requirements and computational complexity by mapping high-dimensional data to a discrete set of codewords. This technique has been widely applied in fields such as signal processing, image compression (e.g., joint photographic experts group (JPEG) ) , and audio compression (e.g., moving picture experts group (MPEG) audio layer-3 (MP3) ) . Compression coding further reduces data size by efficiently encoding the data, typically using statistical-based methods such as entropy coding (e.g., Huffman coding) or arithmetic coding. However, these techniques primarily focus on the data values themselves and may overlook the semantic information and contextual relationships captured in embedding vectors, potentially leading to the loss of important features. Their codebook design and codeword allocation strategies may not be well-suited for the characteristics of embedding information, thus reducing compression efficiency.
[0049] Furthermore, depending on different application scenarios or even different points in time within the same scenario, the dimensions and precision requirements of embedding information may vary. For example, in natural language processing (NLP) tasks such as reading comprehension, higher-dimensional embedding vectors may be needed to capture more semantic information, while in short-text or specific tasks like keyword extraction, lower-dimensional embeddings might suffice. The vector quantization methods mentioned above usually employ fixed codebook sizes and codeword allocation strategies, making them less flexible in the face of such diversity and dynamic changes. For instance, in real-time recommendation systems, user interests and behaviors vary over time. If the quantization method cannot adjust its codebook size and codeword allocation strategy, it may fail to effectively reflect users' latest preferences, affecting the accuracy and effectiveness of recommendations. Additionally, embeddings themselves contain complex semantic information and multidimensional features, and for different tasks, only a small part of the embedding information might be relevant while the rest may be redundant for the task at hand. The compression coding methods mentioned above rely heavily on statistical properties of the data, but embeddings require encoding methods that focus on task-related semantic content to improve compression efficiency and reduce semantic loss. Therefore, traditional vector compression techniques often show limitations in addressing the diversity and dynamic changes in demands.
[0050] Correspondingly, a vector compression and transmission scheme tailored for embeddings is provided, which divides compression into data compression and semantic compression. Specifically, data compression consists of dimension compression and precision compression, while semantic compression includes task-related compression and semantic consistency compression. Data compression and semantic compression complement each other, where dimension compression in the data compression reduces related features, providing a more effective basis for task-related compression, and good precision compression helps better preserve semantic consistency. In the present disclosure, unless otherwise specified, the terms “embedding, ” “embeddings, ” “embedding information, ” and “embedding data” can be used interchangeably.
[0051] In summary, the proposed scheme may include at least one of the following.
[0052] 1. Dynamic Adaptive Codebook Design. Based on data compression and semantic compression, a dynamically adjustable codebook and codeword allocation strategy is introduced for embeddings that correspond to slowly varying data. Unlike vector quantization mentioned above, this approach considers both the distribution of embeddings and the precision requirements of different scenarios, enabling the compression algorithm to flexibly adapt to changes in the dimensions of the embedding information and the specific needs of each application. This dynamic adaptation mechanism effectively addresses the diversity and real-time fluctuations in embedding data, ensuring both accuracy and efficiency in compression across various contexts.
[0053] 2. Task-Driven Compression Strategy. A task-driven compression approach is adopted, which focuses on analyzing the core semantic information in the embedding vectors related to the task objectives. By emphasizing the efficient encoding of these key pieces of information, this approach differs from the compression methods mentioned above by effectively filtering out redundant information. This ensures that the compression process does not lose critical semantic features, thereby enhancing compression efficiency.
[0054] 3. Enhanced Real-Time Adaptability. Utilizing the effectiveness quality indicator (EQI) metric, the encoding strategy can be rapidly adjusted in response to dynamic data changes. For instance, in real-time recommendation systems, the codebook and encoding strategy are updated in real time to accurately reflect users' latest interests and behaviors, thereby improving the accuracy and effectiveness of recommendations.
[0055] The details of one or more implementations of the subject matter of this present disclosure are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages of the subject matter will become apparent from the description, the drawings, and the claims.
[0056] FIG. 1 is a schematic illustration of an example communication system according to an implementation of the present disclosure, there is shown a communication system 100 that includes a radio access network (RAN) 120, one or more communication electronic devices (EDs) 110a, 110b, 110c, 110d, 110e, 110f, 110g, 110h, 110i, 110j (collectively referred to as 110) , a core network 130, a Public Switched Telephone Network (PSTN) 140, the Internet 150, and other networks 160. The RAN 120 may include, but is not limited to, a future generation RAN, or a legacy RAN such as, but not limited to, 5th generation (5G) , 4th generation (4G) , 3rd generation (3G) or 2nd generation (2G) radio access network. The RAN 120 may be, for example, an Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (E-UTRAN) , a NextGen RAN (NG RAN) , or some other type of RAN. Examples of RAN 120 based on the evolution of telecommunications standards include, but is not limited to, GSM (Global System for Mobile Communications) and CDMA (Code Division Multiple Access) for 2G, UMTS (Universal Mobile Telecommunications System) based on WCDMA (Wideband Code Division Multiple Access) and CDMA2000 for 3G, LTE (Long-Term Evolution) and WiMAX (Worldwide Interoperability for Microwave Access) for 4G, and NR (New Radio) for 5G. In some implementations, the RAN 120 may use any radio access technology (RAT) in the wireless interface between the one or more EDs 110 and the RAN 120. In some implementations, the term “radio access” may refer to the future generation air interface standards which may include both terrestrial networks (TNs) and non-terrestrial networks (NTNs) . These networks will be described in greater detail below in conjunction with various implementations. The one or more communication EDs 110 (also referred to as “user equipment” ) are configured to connect (e.g., communicatively couple) with each other or to one or more network nodes 170a, 170b (collectively referred to as 170) in the RAN 120. The core network (CN) 130 is a part of the communication system 100 and comprises network nodes (e.g., 170a, 170b) which provide support for the network features and telecommunication services. In some implementations, the CN 130 may be dependent on the RAT used in the communication system 100. In other implementations, the CN 130 may be access-agnostic, i.e., the CN 130 may be independent of the RAT used in the communication system 100. There are different types of CN 130, for different 3GPP system generations. For example, the CN 130 is the Evolved Packet Core (EPC) in 4G, also known as the Evolved Packet System (EPS) . In another example, the CN 130 is the 5G Core (5GC) which was developed as part of the 5G System (5GS) . The CN 130 also enables integration of different 3GPP and non-3GPP access types. In some implementations and referring to FIG. 1, the CN 130 also provides the interface towards external networks that may include the PSTN 140, the Internet 150, and other networks 160 in the communication system 100.
[0057] In general, the communication system 100 facilitates interaction between multiple wireless or wired elements. The communication system 100 may transmit different types of content, such as voice, data, video, and / or text, through different transmission methods such as, but not limited to, broadcast, multicast, groupcast, and unicast. Additionally, the communication system 100 operates by allocating and / or sharing resources, such as carrier spectrum bandwidth, among its constituent elements.
[0058] The communication system 100 may provide a wide range of communication services and applications including, but not limited to, Enhanced Mobile Broadband (eMBB) services, Ultra-Reliable Low-Latency Communication (URLLC) services, Massive Machine Type Communication (mMTC) services, Integrated Sensing And Communication (ISAC) , immersive communication, Ultra-massive Machine-Type Communication (uMTC) , hyper reliable and low-latency communication, ubiquitous connectivity, integrated AI and communication, and other services that can be provided by a future generation communication system. The communication system 100 may provide other services and applications such as, but not limited to, earth monitoring, remote sensing, passive sensing and positioning, navigation and tracking, autonomous delivery and mobility and the like.
[0059] The communication system 100 may include a terrestrial communication system (or network) and / or a non-terrestrial communication system (or network) . The communication system 100 may provide a high degree of availability and robustness through a joint operation of the terrestrial communication system and the non-terrestrial communication system. For example, integrating a non-terrestrial communication system (or components thereof) into a terrestrial communication system can result in a heterogeneous network comprising multiple layers. The heterogeneous network may achieve better overall performance through efficient multi-link joint operation, more flexible functionality sharing, and faster physical layer link switching between terrestrial networks and non-terrestrial networks. The terrestrial communication system and the non-terrestrial communication system could be considered as sub-systems of the communication system 100.
[0060] FIG. 2 illustrates another example communication system 100 according to an implementation of the present disclosure. The communication system 100 includes EDs 110a, 110b, 110c, 110d (collectively referred to as ED 110) , RANs 120a, 120b, one or more CNs 130, a PSTN 140, the Internet 150, and other networks 160. Additionally, the communication system 100 may also include a non-terrestrial network (NTN) 120c. The RANs 120a and120b may include network nodes 170a and 170b respectively. Examples of network nodes 170a, 170b include base stations, which can be generally referred to as terrestrial network (TN) devices or terrestrial transmit and receive points (T-TRPs) 170a and 170b (collectively referred to as 170) . In this context, the terms "TRP" and "base station" are used interchangeably unless otherwise specified. For simplicity, this disclosure primarily refers to network nodes as base stations; however, unless explicitly stated otherwise, references to TRP are considered non-limiting and interchangeable. The T-TRPs 170a, 170b may be base stations mounted on a building or tower. In one implementation, the NTN 120c includes a RAN node such as a base station 172, which may be generally referred to as an NTN device, a non-terrestrial node, a non-terrestrial network device, a non-terrestrial base station, or a non-terrestrial transmit and receive point (NT-TRP) 172.
[0061] In some implementations, the NT-TRP 172 is not attached to the ground, for example, as in the case of an airborne base station. An airborne base station may be implemented using communication equipment supported or carried by a flying device. For example, a flying device may include, but is not limited to, an airborne platform (such as a blimp or an airship) , balloon, drone (such as quadcopter) , and other types of aerial vehicles. In some implementations, an airborne base station may be supported or carried by an unmanned aerial system (UAS) or an unmanned aerial vehicle (UAV) , such as a drone. An airborne base station may be a moveable or mobile base station that can be flexibly deployed in different locations to meet network demand. A satellite base station is another example of a non-terrestrial base station. A satellite base station may be implemented using communication equipment supported or carried by a satellite. A satellite base station may also be referred to as an orbiting base station. High altitude platforms are yet another example of non-terrestrial base stations, including international mobile telecommunication base stations.
[0062] As referred to herein, and unless specified otherwise, a “TRP” may also refer to a T-TRP or an NT-TRP, a “T-TRP” may also refer to a “TN TRP” , and an “NT-TRP” may also refer to an “NTN TRP” . The NTN 120c may be considered a RAN, sharing operational aspects with RANs 120a, 120b. The NTN 120c may include at least one NTN device and at least one corresponding terrestrial network device. The at least one NTN device may function as a transport layer device and the at least one corresponding terrestrial network device may function as a RAN node, communicating with the ED 110 via the NTN device. Additionally, there may be an NTN gateway on the ground (referred to as a terrestrial network device) that also functions as a transport layer device facilitating communication with both the NTN device and the RAN node. The RAN node may communicate with the ED 110 via the NTN device and the NTN gateway. In some implementations, the NTN gateway and the RAN node may be located within the same device.
[0063] A base station 170 (also referred to as a TRP as stated above) is a network element within a radio access network responsible for radio transmission and reception in one or more cells to or from the ED (such as a user equipment) . In different implementations, the base station 170 may also be known as a base transceiver station (BTS) , a radio base station, a network node, a network device, a device on the network side, a transmit / receive node, a Node B, an evolved NodeB (eNodeB or eNB) , a Home eNodeB, a next Generation NodeB (gNB) , a transmission point (TP) , a site controller, an access point (AP) , a wireless router, a relay station, a terrestrial node, a terrestrial network device, a terrestrial base station, a non-terrestrial node, a non-terrestrial network device, a non-terrestrial base station, and a positioning node, among other possibilities. The base station 170 may be a macro base station (BS) , a pico BS, a relay node, a donor node, or combinations thereof. When the base station 170 performs (or is configured to perform) a method described herein, it may be interpreted as the base station itself, one or more modules (or units) in the base station, a circuit or chip, or a combination thereof, performing the method. For example, the circuit or chip may include a modem chip, also referred to as a baseband chip, a system on chip (SoC) including a modem core, a system in package (SIP) chip, and the like, and may be responsible for one or more communication functions within the base station.
[0064] The EDs 110a-110d and TRPs 170a-170b, 172 are examples of communication equipment configured to implement some or all of the operations and / or implementations described herein. The T-TRP 170a forms part of the RAN 120a, which may include other TRPs, and / or other devices. Also, the TRP 170b forms part of the RAN 120b, which may include other TRPs, and / or devices. Each TRP 170a, 170b may transmit and / or receive wireless signals within a particular geographic region or area, sometimes referred to as a “cell” or a “coverage area” . The TRPs 170a-170b may be responsible for allocating and / or configuring resources and transmission and / or reception in a set of cell (s) . A cell is a radio network object that can be uniquely identified by a cell identification that is broadcasted over a geographical region or area from base stations associated with the cell. A cell can work in either FDD or TDD mode. A cell may be further divided into cell sectors, and a base station 170a-170b may, for example, employ one or more transceivers to provide services to one or more sectors. Some implementations may include pico or femto cells if supported by the radio access technology. In some implementations, one or more transceivers could be used for each cell, such as with Multiple-Input Multiple-Output (MIMO) technology. The number of RANs 120a-120b shown is merely an example. Any number of RANs may be contemplated when designing the communication system 100.
[0065] A base station may be a single element, as shown in the figures, or multiple elements distributed throughout the corresponding RAN, or otherwise configured. In some implementations, a plurality of RAN nodes coordinate to assist the ED 110 in implementing radio access, and different RAN nodes separately implement and handle different functions of the base station. For example, the RAN node may be a central unit (CU) , a distributed unit (DU) , a CU-control plane (CP) , a CU-user plane (UP) , or a radio unit (RU) etc. The CU and the DU may be separately deployed, or included within the same element (i.e., a baseband unit (BBU) ) . The RU may be included in a radio frequency device or a radio frequency unit (i.e., a remote radio unit (RRU) , an active antenna unit (AAU) , or a remote radio head (RRH) ) . In different systems, the CU (or the CU-CP and the CU-UP) , the DU, or the RU may be known by different names, but their functions are understood by a person skilled in the art. For example, in an open radio access network (ORAN) system, a CU may be referred to as an open CU (O-CU) , a DU may be referred to as an open DU (O-DU) , and a CU-CP may be referred to as an open CU-CP (O-CU-CP) . The CU-UP may also be referred to as an open CU-UP (O-CU-UP) , and the RU may also be referred to as an open RU (O-RU) . Any one of the CU (or the CU-CP, or the CU-UP) , the DU, and the RU may be implemented using a software module, a hardware module, or a combination of a software module and a hardware module.
[0066] Furthermore, communication between different devices / apparatuses in various implementations of this disclosure may refer to direct communication (that is, without the need of forwarding by another device / apparatus) or may refer to communication (s) between different devices / apparatuses via another device / apparatus (that is, requiring forwarding by another device / apparatus) . Alternatively, such communication (s) may involve one functional unit inside a device / apparatus using another functional unit within the device / apparatus to communicate with another device / apparatus. In other words, phrases such as "sending (or transmitting) information to... (an ED or a base station) " in this disclosure may be understood as a destination endpoint of the information being an ED or a base station, including, sending / transmitting information directly or indirectly to an ED or a base station. Similarly, phrases like "receiving information from... (an ED or a base station) " may be understood as a source endpoint of the information being an ED or a base station, including directly or indirectly receiving information from an ED or a base station. Between the source endpoint that sends the information and the destination endpoint, necessary processing such as, but not limited to, format conversion, digital-to-analog conversion, amplification, and filtering may be performed on the information. However, the destination endpoint may understand valid information from the source endpoint. A similar understanding applies to other descriptions in this disclosure without reiterating details already described. In the present disclosure, the terms "send" and "transmit" may be used interchangeably in different implementations of this disclosure.
[0067] The ED 110 is used to connect people, objects, machines, and other entities. The ED 110 may be widely used in various scenarios including, but not limited to, cellular communications, device-to-device (D2D) , vehicle to everything (V2X) , peer-to-peer (P2P) , machine-to-machine (M2M) , MTC, internet of things (IoT) , virtual reality (VR) , augmented reality (AR) , mixed reality (MR) , metaverse, digital twin, industrial control, self-driving, remote medical, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, drones, robots, remote sensing, passive sensing, positioning, navigation and tracking, and autonomous delivery and mobility.
[0068] Each ED 110 represents any suitable end user device for wireless operation and may include such devices (or may be referred to as, but not limited to) a user equipment (UE) or a user device or a terminal device, a wireless transmit / receive unit (WTRU) , a mobile station, a fixed or mobile subscriber unit, a cellular telephone, a station (STA) , an MTC device, a personal digital assistant (PDA) , a smartphone, a laptop, a computer, a tablet, a wireless sensor, a consumer electronics device, a smart book, a vehicle, a car, a truck, a bus, a train, or an IoT device, wearable devices (such as a watch, a pair of glasses, head mounted equipment, etc. ) , an industrial device, or an apparatus (such as a module, modem, or chip) in the foregoing devices, among other possibilities. Future generation EDs 110 may be referred to by other terms. When an ED 110 performs (or is configured to perform) a method described herein, it may be interpreted as the ED itself, one or more modules (or units) in the ED, a circuit or chip, or a combination thereof, performing the method. For example, the circuit or chip may include a modem chip, also referred to as a baseband chip, a system on chip (SoC) including a modem core, or a system in package (SIP) chip, and the like, and may be responsible for one or more communication functions in the ED.
[0069] Each ED 110 connected to TRPs 170a-170b, and / or TRPs 172 can be dynamically or semi-statically turned-on (i.e., established, activated, or enabled) , turned-off (i.e., released, deactivated, or disabled) and / or configured in response to one of more of:connection availability and connection necessity.
[0070] Any ED 110 may be alternatively or additionally configured to interface, access, or communicate with any of the TRPs 170a, 170b and 172, the Internet 150, the CN 130, the PSTN 140, the other networks 160, or any combination thereof. In some examples, the ED 110a may communicate an uplink (UL) and / or downlink (DL) transmission over a terrestrial air interface 190a with station-TRP 170a. In some examples, the EDs 110a, 110b, 110c, and 110d may also communicate directly with one another via one or more sidelink (SL) air interfaces 190b. In some examples, the EDs 110a, 110d may communicate using an UL and / or DL transmission over a non-terrestrial air interface 190c with NT-TRP 172.
[0071] An air interface (such as, for example, 190a, 190b, 190c) generally includes a number of components and associated parameters that collectively specify how a transmission is to be sent and / or received over a wireless communications link between two or more communicating devices such as EDs and base station (s) . For example, an air interface may include one or more components defining the waveform (s) , frame structure (s) , multiple access scheme (s) , protocol (s) , coding scheme (s) and / or modulation scheme (s) for conveying information (such as, data) over a wireless communications link. The air interfaces 190a and 190b may use similar communication technology, that may include any suitable radio access technology.
[0072] The non-terrestrial air interface 190c can enable communication between the EDs 110a, 110d and one or more NT-TRPs 172 via a wireless link or simply a link. In some examples, the link is a dedicated connection for unicast transmission, a connection for broadcast transmission, or a connection between a group of EDs 110 and one or more NT-TRPs 172 for multicast transmission.
[0073] The TRPs 170a-170b, 172 may communicate with one another over one or more air interfaces 190e, 190f using wireless communication links (such as radio frequency (RF) , microwave, infrared (IR) , etc. ) or wired communication links. The air interfaces 190e, 190f may utilize any suitable radio access technology, and may be substantially similar to the air interfaces 190a, 190c over which the EDs 110a-110d communicate with one or more of the TRP 170a-170b, 172 or they may be substantially different. For example, the communication system 100 may implement one or more channel access methods, such as Time Division Multiple Access (TDMA) , Frequency Division Multiple Access (FDMA) , Code Division Multiple Access (CDMA) , Single Carrier Frequency Division Multiple Access (SC-FDMA) , Low Density Signature Multicarrier Code Division Multiple Access (LDS-MC-CDMA) , Non-Orthogonal Multiple Access (NOMA) , Pattern Division Multiple Access (PDMA) , Lattice Partition Multiple Access (LPMA) , Resource Spread Multiple Access (RSMA) , and Sparse Code Multiple Access (SCMA) .
[0074] The RANs 120a and 120b are in communication with the CN 130 to provide the EDs 110a 110b, and 110c with various services such as voice, data, multimedia, and other services. The RANs 120a and 120b and / or the CN 130 may be in direct or indirect communication with one or more other RANs (not shown) , which may or may not be directly served by the CN 130, and may employ different radio access technologies from RAN 120a and / or RAN 120b. The CN 130 may also serve as a gateway access between (i) the RANs 120a and 120b and / or the EDs 110a 110b, and 110c, and (ii) other networks (such as the PSTN 140, the Internet 150, and the other networks 160) . In addition, some or all of the EDs 110a 110b, and 110c may include functionality for communicating with different wireless networks over different wireless links using different wireless technologies and / or protocols. For example, the EDs 110a 110b, and 110c communicate using different cellular communications protocols, such as, but not limited to, a Global System for Mobile Communications (GSM) protocol, a code-division multiple access (CDMA) network protocol, a Push-to-Talk (PTT) protocol, a PTT over Cellular (POC) protocol, a Universal Mobile Telecommunications System (UMTS) protocol, a 3GPP Long Term Evolution (LTE) protocol, a fifth generation (5G) protocol, a New Radio (NR) protocol, and the like. Instead of wireless communication (or in addition thereto) , the EDs 110a 110b, and 110c may communicate using wired communication channels to a service provider or switch (not shown) , and / or to the Internet 150. The PSTN 140 may include circuit switched telephone networks for providing plain old telephone service (POTS) . The Internet 150 may include a network of computers and subnets (intranets) or both, and incorporate protocols, such as internet protocol (IP) , transmission control protocol (TCP) , user datagram protocol (UDP) . EDs 110a 110b, and 110c may be multimode devices capable of operation according to multiple radio access technologies, and may incorporate one or more transceivers necessary to support such technologies and / or functions.
[0075] In addition, the communication system 100 may comprise a sensing agent (not shown) to manage the sensed data from ED 110 and / or any one of TRPs 170a, 170b, 172. In one implementation, the sensing agent may be part of any one of TRPs 170a, 170b, 172. In another implementation, the sensing agent is a separate node that can communicate with the CN 130 and / or the RAN 120 (such as any one of TRPs 170a, 170b, 172) .
[0076] FIG. 3 is a schematic illustration showing an apparatus 310 wirelessly communicating with another apparatus 320 within a communication system (e.g., the communication system 100) according to an implementation of the present disclosure. The apparatus 310 may be an electronic device (such as ED 110) . The apparatus 320 may be a network node (e.g., the network node 170) such as T-TRP 170 or an NT-TRP 172. Although only one apparatus 310, and one apparatus 320 are shown in the figure, the number of apparatus 310 and / or number of apparatus 320 can vary, potentially including one or more of each. For example, a single ED 110 may be served by a single T-TRP 170 (or a single NT-TRP 172) , or by multiple T-TRPs 170 (or multiple NT-TRPs 172) . Similarly, a single ED 110 may be served by one or more T-TRPs 170 and one or more NT-TRPs 172. Similarly, a single T-TRP 170 (or a single NT-TRP 172) may serve one or more EDs 110.
[0077] The apparatus 310 may include one or more processors 210. For clarity and to avoid overcrowding the illustration, only a single processor 210 is illustrated. The apparatus 310 may further include a transmitter 201 and a receiver 203 coupled to one or more antennas 204. For clarity, only a single antenna 204 is illustrated. One, some, or all of the antennas 204 may alternatively be panels. In some implementations, the transmitter 201 and the receiver 203 are separate from each other. In other implementations, the transmitter 201 and the receiver 203 may be integrated into a single unit, for example, as a transceiver. The transceiver is configured to modulate data or other content for transmission by the one or more antennas 204 or a network interface controller (NIC) . The transceiver may also be configured to demodulate data or other content received by the one or more antennas 204. A transceiver may include any suitable structure for generating signals for wireless or wired transmission and / or for processing signals received through wireless or wired communication. Each antenna 204 includes any suitable structure for transmitting and / or receiving wireless or wired signals. The apparatus 310 may include a memory 208. In some implementations, the apparatus 310 may include multiple memories 208. Only a single transmitter 201, receiver 203, processor 210, memory 208, and antenna 204 is illustrated for simplicity, but the apparatus 310 may include one or more other components. In some implementations of the present disclosure, the transceiver (or transmitter 201 and / or receiver 203) may be viewed as an interface circuit.
[0078] The memory 208 is configured to store instructions used to perform operations described herein. The memory 208 may also be configured to store data that is used, generated, or collected by the apparatus 310. For example, the memory 208 can store software instructions or modules configured to implement some or all of the functionalities and / or operations described herein and that which are executed by the one or more processors 210.
[0079] The apparatus 310 may further include one or more input / output devices (not shown) or interfaces. The input / output devices or interfaces facilitate interaction with a user or other devices in the network. Each input / output device or interface includes suitable components for facilitating transmission of information to a user and reception of information from a user, and for various network interface communications. Such components may include, but are not limited to, a speaker, microphone, keypad, keyboard, display, touch screen, and the like.
[0080] The processor 210 may be configured to perform (or control the apparatus 310 to perform) operations (or methods) described herein as being performed by the apparatus 310. For example, the processor 210 performs or controls the apparatus 310 to perform the operations of: a) receiving one or more transport blocks (TBs) , b) using a resource for decoding at least one of the received TBs, c) releasing the resource for decoding another of the received TBs, and / or d) receiving configuration information configuring a resource. Specifically, the operations may include tasks related to: preparing a transmission for UL transmission to the apparatus 320, processing DL transmissions received from the apparatus 320, and handling SL transmission to and from another apparatus 310. Processing operations related to preparing a transmission for UL transmission may include operations such as, but not limited to, encoding, modulating, transmit beamforming, and generating symbols for transmission. Processing operations related to processing DL transmissions may include operations such as, but not limited to, receive beamforming, demodulating and decoding received symbols. Processing operations related to processing SL transmissions may include operations such as, but not limited to, transmit / receive beamforming, modulating / demodulating and encoding / decoding symbols. Depending upon the implementation, a DL transmission may be received by the receiver 203, possibly using receive beamforming, and the processor 210 may extract signaling from the DL transmission (such as by detecting and / or decoding the signaling) . An example of signaling may be a reference signal transmitted by the apparatus 320. In some implementations, the processor 210 implements the transmit beamforming and / or the receive beamforming based on the indication of beam direction, such as beam angle information (BAI) , received from the apparatus 320. In some implementations, the processor 210 may be configured to perform operations relating to network access (such as initial access) and / or downlink synchronization, which includes operations for detecting a synchronization sequence, decoding and obtaining the system information, and the like. In some implementations, the processor 210 may perform channel estimation, such as using a reference signal received from the apparatus 320.
[0081] Although not illustrated, in some implementations, the processor 210 may either be a part of the transmitter 201 or a part of the receiver 203 or a part of both the transmitter 201 and the receiver 203. Although not illustrated, in some implementations, the memory 208 may be a part of the processor 210.
[0082] The processor 210, along with the processing components of the transmitter 201 and the receiver 203 may each be implemented by one or more processors that may the same or different. These processors are configured to execute instructions stored in a memory (such as in the memory 208) .
[0083] The apparatus 320 includes one or more processors 260 (only one processor 260 is illustrated) . The apparatus 320 may further include one or more transmitters 252 and one or more receivers 254 coupled to one or more antennas 256. Only a single antenna 256 is illustrated to avoid clutter in the illustration. One, some, or all of the antennas 256 may alternatively be panels. In some implementations, the transmitter 252 and the receiver 254 are separate from each other. In other implementations, the transmitter 252 and the receiver 254 may be integrated into a single unit such as, for example, as a transceiver. The apparatus 320 may further include a memory 258. In some implementations, the apparatus 320 may include multiple memories 258. The apparatus 320 may further include a scheduler 253. Only a single transmitter 252, receiver 254, processor 260, memory 258, antenna 256 and scheduler 253 are illustrated for simplicity, however the apparatus 320 may include one or more other components. In the present disclosure, in some implementations, the transceiver (or transmitter 252 and / or receiver254) may be viewed as an interface circuit.
[0084] In some implementations, various components of the apparatus 320 may be distributed. For example, some of the modules of the apparatus 320 may be located remotely from the equipment housing the antennas 256 for the apparatus 320 (and therefore can also be viewed as one or more nodes) . These modules, which can be considered as one or more nodes, may be coupled to the equipment that houses the antennas 256 over a communication link (not shown) , sometimes referred to as front haul, such as the Common Public Radio Interface (CPRI) . Therefore, in some implementations, the term apparatus 320 may also refer to network-side nodes that perform processing operations such as, but not limited to, determining the location of the apparatus 310, resource allocation (scheduling) , message generation, and encoding / decoding, and that which are not necessarily part of the equipment that houses the antennas 256 of the apparatus 320. The nodes may also be coupled to other apparatuses 320. In some implementations, the apparatus 320 may actually be a plurality of nodes that are operating together to serve the apparatus 310, such as through the use of coordinated multipoint transmissions, or through the use of an ORAN system as described above in the disclosure.
[0085] The processor 260 is configured to perform operations including those related to: preparing a transmission for DL transmission to the apparatus 310, processing an UL transmission received from the apparatus 310, preparing a transmission for backhaul transmission to another apparatus 320, and processing a transmission received over backhaul from another apparatus 320. Processing operations related to preparing a transmission for DL or backhaul transmission may include operations such as, but not limited to, encoding, modulating, precoding (such as MIMO precoding) , transmit beamforming, and generating symbols for transmission. Processing operations related to processing received transmissions in the UL or over backhaul may include operations such as, but not limited to, receive beamforming, demodulating received symbols, and decoding received symbols. The processor 260 may also be configured to perform operations relating to network access (such as initial access) and / or DL synchronization, such as generating the content of synchronization signal blocks (SSBs) , generating the system information, and the like. In some implementations, the processor 260 is further configured to generate an indication of beam direction, such as BAI, which may be scheduled for transmission by the scheduler 253 which will be described below. In some implementations, the processor 260 implements the transmit beamforming and / or receive beamforming based on beam direction information (such as BAI) received from another apparatus 320. The processor 260 is configured to perform other network side processing operations described herein, such as, but not limited to, determining the location of the apparatus 310, determining where to deploy another apparatus 320, and the like. In some implementations, the processor 260 may generate signaling data, to configure one or more parameters of the apparatus 310 and / or one or more parameters of another apparatus 320. Any signaling data generated by the processor 260 is sent by the transmitter 252. In some implementations, the apparatus 320 implements physical layer processing. In some implementations, the apparatus 320 may perform higher layer functions such as those at the Medium Access Control (MAC) or Radio Link Control (RLC) layers in addition to physical layer processing. In the apparatus 320, the scheduler 253 may be coupled to the processor 260 or integrated within the processor 260. In some implementations, the scheduler 253 may be integrated within the apparatus 320 or may be operated separately from the apparatus 320. The scheduler 253 may schedule UL, DL, SL, and / or backhaul transmissions, including issuing scheduling grants and / or configuring scheduling-free (such as “configured grant” ) resources.
[0086] The apparatus 320 may further include a memory 258 that is configured to store instructions for performing the operations described herein. The memory 258 may also store data that is used, generated, or collected by the apparatus 320. For example, the memory 258 can store software instructions or modules configured to implement some or all of the functionalities and / or implementations described herein and that which are executed by the processor 260.
[0087] Although not illustrated, the processor 260 may be implemented as part of the transmitter 252 and / or a part of the receiver 254. Although not illustrated, in some implementations, the processor 260 may implement the scheduler 253 and the memory 258 may be implemented as part of the processor 260.
[0088] The processor 260, the scheduler 253, the processing components of the transmitter 252, and the processing components of the receiver 254 may each be implemented by the same or different processors that are configured to execute instructions stored in a memory, such as in the memory 258.
[0089] The apparatus 320 and / or the apparatus 310 may include other components, not shown or described herein for the sake of clarity.
[0090] Note that the term “signaling” , as used herein, may alternatively be referred to as control signaling, control message, control information, or message for simplicity. Signaling between a base station (such as the TRP 170a. 170b, 172) and a UE or sensing device (such as ED 110) , or signaling between a different UE or sensing device (such as between ED 110a and ED 110b) may be carried in physical layer signaling (also called as dynamic signaling) , which is transmitted in a physical layer control channel. For DL, the physical layer signaling may be known as downlink control information (DCI) which is transmitted in a physical downlink control channel (PDCCH) . For UL, the physical layer signaling may be known as uplink control information (UCI) which is transmitted in a physical uplink control channel (PUCCH) . For SL, signaling between different UEs or sensing devices (such as between ED 110a and ED 110b) may be known as SL control information (SCI) which is transmitted in a physical sidelink control channel (PSCCH) . Signaling may be carried in a higher layer (such as higher than physical layer) signaling, which is transmitted in a physical layer data channel, such as in a physical downlink shared channel (PDSCH) for downlink signaling, in a physical uplink shared channel (PUSCH) for uplink signaling, and in a physical sidelink shared channel (PSSCH) for SL signaling. Higher layer signaling may also be called static signaling, or semi-static signaling. The higher layer signaling may include radio resource control (RRC) protocol signaling or media access control -control element (MAC-CE) signaling. Signaling may be included in a combination of physical layer signaling and higher layer signaling.
[0091] It should be noted that in the present disclosure, “information” , when different from “message” , may be carried within a single message, or may be carried in multiple separate messages.
[0092] FIG. 4 illustrates an example apparatus 410 according to an implementation of the present disclosure. The apparatus 410 may be a communication device or an apparatus implemented in a communication device such as the ED 110 or the TRPs 170a, 170b, 172. For example, the apparatus 410 implemented in an ED may be an integrated circuit, which in some instances may be referred to as a chip, a modem, a modem chip, a baseband chip, or a baseband processor. In some implementations, one or more integrated circuits can be packaged into a system-on-chip, a system-in-package, or a multi-chip module. The apparatus 410 can include one or more integrated circuits and other discrete components. In some implementations, the apparatus 410 may be a module within the ED 110, or within the apparatus 310. In some implementations, the apparatus 410 may be a module within one of the TRPs 170a, 170b, 172, or the apparatus 320.
[0093] In an example, the apparatus 410 may include one or more processors / processor cores 411, and an interface circuit 412. The apparatus 410 may further include a memory 413. The one or more processors 411 are configured to process signals and execute one or more communication protocols. The memory 413 is configured to store at least a part of the corresponding computer program instructions and / or data. In an example, the one or more processors 411 execute the computer program instructions stored in the memory 413 to implement related operations (for example, inputting, outputting, receiving, and transmitting) in the method implementations disclosed herein. In some implementations, the memory 413 being configured to store the corresponding computer program instructions and / or data may mean that the memory 413 is configured to store all of the corresponding computer program instructions and / or data for execution by the one or more processors 411. In some implementations, the memory 413 being configured to store the corresponding computer program instructions and / or data may mean that the memory 413 is configured to store a part of the corresponding computer program instructions and / or data. For example, the part of the corresponding computer program instructions and / or data may include computer program instructions and / or data that need to be currently executed by the one or more processors 411. Thus, the memory 413 may store different parts of computer program instructions and / or data for a plurality of times for the one or more processors 411 to perform related operations in the method implementations disclosed herein. As a communication interface, the interface circuit 412 is configured to implement communication with another component. For example, the interface circuit 412 may communicate a signal with another apparatus or system, such as a radio frequency processing apparatus or another processor. The signal may include or carry information intended as a payload, such as user data, control information, etc. The signal may also include or carry information useful to a receiver, but not necessarily as a payload, such as a pilot signal or reference signal. Communicating the signal may include transmitting the signal to another component or device. Communicating the signal may additionally or alternatively include receiving the signal from another component or device. Transmitting the signal may include outputting the signal to a component or device that is directly or indirectly coupled to the interface circuit 412. Receiving the signal may include inputting or obtaining the signal from a component or device that is directly or indirectly coupled to the interface circuit 412. In some implementations, to reduce a load of the one or more processors, a baseband signal processing circuit 414 may be also disposed to implement processing of at least a part of baseband signals, including signal demodulation, modulation, encoding, decoding, or the like.
[0094] The apparatus 410 may be the processor 210 (or 260) within the apparatus 310 (or 320) , in some scenarios, or may be included within the processor 210 (or 260) within the apparatus 310 (or 320) in some scenarios. The apparatus 410 may be a baseband chip or may include a baseband chip. In some implementations, the apparatus 410 may be independently packaged into a chip. In some implementations, the apparatus 310 (or 320) includes different types of chips. The apparatus 410 may be packaged into a processor chip (for example, an SoC chip or an SIP chip) with the different types of chips. In some implementations, the apparatus 410 may be packaged into a chip with some or all of circuits of a radio frequency processing system that may further be included in the apparatus 310 (or 320) .
[0095] FIG. 5 illustrates an example apparatus 510 according to an implementation of the present disclosure. The apparatus 510 may include corresponding modules or units configured to implement methods and / or implementations described herein. In some implementations, the apparatus 510 includes a processing unit 512 and a communication unit 513. In some implementations, the apparatus 510 may further include a storage unit 511 configured to store apparatus program code (or instructions) and / or data.
[0096] The apparatus 510 may be an ED side apparatus, for example, an ED or a module in an ED, or a circuit or a chip responsible for a communication function in an ED. In some implementations, apparatus 510 may be the apparatus 310. The processing unit 512 may be the processor 210. The communication unit 513 may comprise a receiving unit and / or a transmitting unit. The receiving unit and / or the transmitting unit may be the transmitter 201 and / or the receiver 203 respectively. The storage unit 511 may be the memory 208.
[0097] The apparatus 510 may be a base station side apparatus, for example, a base station or a module in a base station, or a circuit or a chip responsible for a communication function in a base station. In some implementations, apparatus 510 may be apparatus 320. The processing unit 512 may be the processor 260 (the scheduler 253 may also be included) . The communication unit 513 may comprise a receiving unit and / or a transmitting unit. The receiving unit and / or the transmitting unit may be the transmitter 252 and / or the receiver 254 respectively. The storage unit 511 may be the memory 258.
[0098] In some implementations, when the apparatus 510 is an ED 110 or a module in an ED 110, a function of the apparatus 510 may be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system on chip (SoC) chip or an SIP chip that includes a modem core. A function of the communication unit 513 may be implemented by a transceiver circuit.
[0099] In some implementations, when the apparatus 510 is a circuit or a chip that is responsible for a communication function in an ED 110, such as a modem chip, a system on chip (SoC) chip or an SIP chip that includes a modem core, a function of the processing unit 512 may be implemented by a circuit system within the chip which includes one or more processors. A function of the communication unit 513 may be implemented by an interface circuit or a data transceiver circuit on the chip.
[0100] It may be understood that the units in the apparatus 510 may be logical or functional. Each function may correspond to one functional unit, or two or more functions may be integrated into a single functional unit. In actual implementation, all or some of the units may be integrated into a single physical entity, or may be distributed across different physical entities. In addition, the functional units may be implemented in the form of hardware, software, or a combination of hardware and software. Whether a function is implemented in the form of hardware or software depends on particular applications and design constraint conditions of the technical solutions. A person skilled in the art may use different methods to implement the described functions for specific applications, but it should not be considered that the implementation goes beyond the scope of this disclosure.
[0101] In an example, a functional unit in any one of the apparatuses may be configured as one or more integrated circuits for implementing the methods disclosed herein, for example, as one or more application-specific integrated circuits (application-specific integrated circuits, ASICs) , one or more central processing units (CPUs) , one or more microprocessors or microprocessor units (MPUs) , one or more microcontrollers or microcontroller units (MCUs) , one or more digital signal processors (DSPs) , one or more field programmable gate arrays (FPGAs) , or a combination of these.
[0102] In an example, the storage unit 511 may include a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, and / or a register.
[0103] A processor may be referred to as a processor system, an application processor, a baseband processor, a processor circuit, or a processor core. The processor may include one or a combination of one or more central processing units (CPUs) , one or more digital signal processors (DSPs) , one or more microprocessors (microprocessor units, MPUs) , one or more microcontrollers (microcontroller units, MCUs) , one or more graphics processing units (GPUs) , one or more field programmable gate arrays (FPGAs) , one or more artificial intelligence processors (AI processors) , or one or more neural network processing units (NPUs) .
[0104] Memory or a storage unit may include one or more of the following storage media: a random access memory (RAM) , a static random access memory (static RAM, SRAM) , a dynamic random access memory (dynamic RAM, DRAM) , a phase-change memory (PCM) , a resistive random access memory (resistive RAM, ReRAM) , a magnetoresistive random access memory (magnetoresistive RAM, MRAM) , a ferroelectric random access memory (ferroelectric RAM, FRAM) , a cache, a register, a read-only memory (ROM) , a flash memory (flash memory) , an erasable programmable read-only memory (erasable programmable ROM, EPROM) , a hard disk, and the like. In an example, computer program instructions used to execute implementations may be stored in a non-volatile memory, for example, at least a part of a memory or storage unit (for example, one or more of a ROM, a flash memory, an EPROM, or a hard disk) . When a terminal runs, a part or all of corresponding computer program instructions may be loaded to a memory that has a higher transmission speed with the processor, for example, at least a part of a memory or a storage unit (for example, one or more of a RAM, an SRAM, a DRAM, a PCM, a RERAM, an MRAM, a FRAM, a cache, or a register) , so that the processor executes the computer program instructions to perform the steps in the method implementations disclosed herein.
[0105] Some compression schemes for embedding are described below.
[0106] Embedding vector compression can be divided into two aspects: data compression and semantic compression. In some implementations, the goal of data compression is to reduce the burden of storage and transmission, while semantic compression focuses on preserving the key information and relevant semantics within the embedding vectors. By combining these two compression methods, the processing efficiency of embedding data can be improved while maintaining its semantic integrity and accuracy.
[0107] Unlike bit-stream data, the elements in embedding vectors are real numbers approximated by floating-point numbers, so data compression involves two key aspects dimension compression and precision compression.
[0108] a) Dimension Compression: By reducing the dimensions of the embedding vectors, data complexity and storage requirements are decreased while retaining essential feature information. Available example dimension compression methods include:
[0109] 1. Puncture: Puncture can remove redundant dimensions based on the distribution characteristics of embedding vectors to reduce data complexity.
[0110] 2. Shorten: Shorten can introduce nested structures or other mechanisms during training to ensure the integrity of key features during compression.
[0111] 3. PCA Dimensionality Reduction: PCA dimensionality reduction can use principal component analysis (PCA) to lower data dimensions while retaining primary information.
[0112] 4. Sampling: Sampling can select representative dimensions through random or systematic sampling of the embedding vectors.
[0113] b) Precision Compression: Precision compression can reduce the precision of floating-point numbers to further decrease storage space while aiming to retain data validity and detailed information. Common methods include generalized post-training quantization (GPTQ) , generalized gradient-based uniform quantization framework (GGUF) , adaptive weight quantization (AWQ) , etc.
[0114] Semantic compression can be further divided into task-driven compression and semantic consistency compression.
[0115] 1. Task-Driven Compression: Based on the target task, task-driven compression extracts task-relevant core semantic information from embeddings using methods such as knowledge distillation or contrastive learning.
[0116] 2. Semantic Consistency Compression: Semantic consistency compression focuses on maintaining the semantic consistency of the original data during compression. In addition to knowledge distillation and precision quantization, this approach can also compress semantic descriptions directly at the natural language level. For instance, semantic transformation and rewriting can convert detailed manuals or long articles into concise points or summaries while preserving the original semantic information.
[0117] Some compression applications for embeddings are described below.
[0118] In some implementations, data compression and semantic compression complement each other. In the data compression, dimension compression can reduce related features, providing a more effective basis for task-related compression, while good precision compression helps better preserve semantic consistency. The following design refers to the combination of both data compression and semantic compression.
[0119] In some implementations, a dynamic adaptive codebook design can be applied to data compression and / or semantic compression.
[0120] For example, raw data can be represented by multiple embedding vectors, which can be classified into two categories based on their variation: "slowly varying" and "rapidly varying. " For instance, in image processing, different regions of an image-such as the foreground and background-correspond to distinct embedding vectors. The overall embedding for the image is a combination of these vectors. Typically, the embeddings representing the background show minimal variation, while those for the foreground can fluctuate more dramatically. In the context of task processing, the descriptions, parameters, and results of tasks can similarly be represented by different embedding vectors. Generally, the embedding states for task parameters and results display more significant variation compared to the task descriptions. For example, during a task invocation, the task description tends to remain relatively stable, whereas the task parameters and results can vary considerably depending on the specifics of the task.
[0121] In some implementations, for embeddings that vary slowly, vector quantization techniques can significantly enhance data transmission efficiency. In these cases, the variations in vectors are relatively minor, suggesting that they tend to cluster in specific regions. To optimize data transmission for such embeddings, a dynamically adaptive codebook can be designed to handle the slowly varying embedding components. This approach involves identifying representative centroids (or codewords) for the vectors and mapping similar embedding vectors to the same codeword, thereby achieving effective data compression.
[0122] A gNB (in this application, a gNB is used as an example of a base station) can combine data compression and semantic compression techniques to adaptively adjust the size of the vector quantization codebook and allocate codewords based on the demands of different scenarios. For instance, depending on the specific requirements of various application contexts, it can utilize different precisions and codebook sizes. This adaptive mechanism effectively addresses the diversity and real-time fluctuations of embedding data, ensuring both accuracy and efficiency in compression across a range of application scenarios. For example, the gNB may adaptively adjust the size of the vector quantization codebook based on the embedding distribution and / or the application scenario requirements.
[0123] a. Based on the embedding distribution: When embedding information is concentrated in certain areas of the feature space, such as feature vectors in images or texts clustered in specific regions, a smaller codebook can be used to enhance the compression rate. For instance, applying the k-means algorithm to cluster these features and using the cluster centroids as codewords can effectively improve transmission and storage efficiency. It's important to note that even for embeddings corresponding to slowly varying components, the distribution may differ depending on the specifics of the model training. Conversely, when embedding information is dispersed across the feature space, with feature vectors spread over multiple areas, a larger codebook allows for finer-grained quantization, enabling a more accurate representation of these scattered features.
[0124] b. Based on the application scenarios requirements: For standardized template documents (such as contract templates or report templates) , which typically have fixed structures and content with variable content in specific sections, the precision requirements for embeddings are lower. Therefore, a smaller codebook can be used for compression to enhance storage and transmission efficiency. In contrast, autonomous driving systems may need to process substantial amounts of sensor data (such as light detection and ranging (LiDAR) and camera data) in real time for environmental perception and decision-making, thus higher precision quantization is essential. Even in slowly changing street scenes, there is still a significant demand for precision and the description of numerous features (such as the regularly changing traffic lights and the availability of parking spaces along the street) . This may necessitate the use of a larger codebook to ensure an accurate representation of the environmental data captured by sensors, thus enabling high-precision understanding of the environment and supporting effective decision-making.
[0125] Task-driven compression strategy can refer to an approach where the gNB focuses on task requirements by analyzing core semantic information related to the task objectives within embedding vectors, efficiently encoding these key pieces of information. This approach effectively filters out redundant information, ensuring that key semantic features are preserved, thus enhancing compression efficiency. Some examples are provided below.
[0126] Image Classification Tasks: In image classification, the gNB can analyze core features related to category recognition, such as shapes, colors, and textures in images. Key information is efficiently encoded, while background details or irrelevant texture information is ignored, improving classification accuracy and reducing data volume.
[0127] Obstacle Detection in Autonomous Driving: In autonomous driving systems, the gNB can analyze sensor data embeddings, focusing on features relevant to obstacle recognition, such as object shapes and distance information. Key information is efficiently encoded, while background or irrelevant data is ignored, improving obstacle detection accuracy and system response speed.
[0128] User Interest Prediction in Recommendation Systems: In recommendation systems, the gNB can analyze embedding vectors from user behavior data, focusing on core features related to user interests, such as browsing history and purchase records. These details are efficiently encoded to accurately predict user interests, while irrelevant user behaviors or data are compressed, enhancing personalization and effectiveness of the recommendation system.
[0129] Enhanced real-time adaptability is described below. Based on EQI and CQI metrics, as well as specific strategies and application needs, the gNB can rapidly adjust encoding strategies in response to dynamic data changes. By real-time monitoring and analyzing these metrics, the gNB can flexibly optimize encoding parameters to balance the quality of embedding data and compression efficiency. However, compression strategy design depends not only on EQI and CQI metrics but also on flexible adjustments based on specific scenarios.
[0130] For instance, in a temperature monitoring system, if the EQI drops due to sudden temperature changes, the encoding strategy needs to be adjusted based on the scenario. In an indoor environment, detecting a rapid increase in temperature might indicate a fire risk, additional encoding redundancy (e.g., entropy coding) may be necessary to ensure reliable transmission and prevent severe consequences from data loss or errors. Conversely, in an outdoor open area, such temperature changes might be caused by occasional transmission errors, allowing the system to reduce additional overhead to maintain transmission efficiency.
[0131] Embedding compression based efficient transmission is described below.
[0132] In the present disclosure, signaling design can be introduced to implement the dynamic adaptive codebook design mentioned above.
[0133] Modules to implement the dynamic adaptive codebook design may include one or more gNBs and one or more UEs.
[0134] The one or more gNBs can be responsible for generating and maintaining the embedding codebook, and dynamically adjusting the codebook size and codeword allocation strategy based on the distribution characteristics of the embeddings. The gNB also transmits the codebook information to the UE and negotiates and aligns the codebook used with the UE.
[0135] The one or more UEs can be responsible for receiving the codebook information transmitted by the gNB and using the codebook to compress and decompress embedding information. The UE also participates in the negotiation and alignment of the codebook.
[0136] In some implementations, an embedding codebook refers to a collection of codewords used to quantize embedding vectors into codeword indices. The codebook can be stored in either the gNB or the UE and can be updated dynamically.
[0137] In some implementations, a physical downlink control channel (PDCCH) is used for transmitting control information from the gNB to the UE, including codebook information and codebook update information.
[0138] In some implementations, a physical downlink shared channel (PDSCH) is used for transmitting data information from the gNB to the UE, including embedding information.
[0139] In some implementations, a physical uplink shared channel (PUSCH) is used for transmitting data information from the UE to the gNB, including embedding information.
[0140] The new signaling to implement the dynamic adaptive codebook design may include at least one of the following.
[0141] 1. Embedding Codebook Information (ECI) : The gNB can use ECI signaling to transmit codebook information to the UE, including codebook size, codewords, and codeword indices. For example, ECI signaling can be transmitted via RRC signaling or PDCCH signaling.
[0142] 2. Embedding Codebook Update (ECU) : The gNB can use ECU signaling to transmit codebook update information to the UE, such as adding codewords, deleting codewords, or updating codewords. For example, ECU signaling can be transmitted via RRC signaling or PDCCH signaling.
[0143] 3. Embedding codebook confirmation (ECC) : The UE can use ECC signaling to confirm the mutually supported codebook with gNB, ensuring that both parties agree on parameters such as size, codewords, and floating-point format. For example, ECI signaling can be transmitted via PUCCH signaling.
[0144] It is understood that RRC signaling can refer to signaling or information included in one or more RRC messages, and the PDCCH signaling can refer to signaling or information transmitted via PDCCH.
[0145] The data formats to implement the dynamic adaptive codebook design may include at least one of the following:
[0146] 1. Compressed embedding information: Compressed embedding information can represent embedding vectors using codeword indices. For example, a 128-dimensional embedding vector (slowly varying) compressed using a codebook with 256 codewords would only require 8 bits to represent.
[0147] 2. Codebook information: Codebook information can include codebook size, codewords, and codeword indices. Codewords can be represented using floating-point or fixed-point formats. The specific format can be chosen based on the precision requirements of the embedding and the computational capabilities of the hardware platform.
[0148] 3. Floating-point formats: Various floating-point formats can be used, such as institute of electrical and electronics engineers (IEEE) 754 single-precision (32-bit) , half-precision (16-bit) , or Bfloat16 format.
[0149] 4. Fixed-point formats: Fixed-point numbers can be used to represent embedding vectors, with precision controlled by adjusting the position of the decimal point.
[0150] FIG. 6 shows an example procedure 600 for a dynamic adaptive codebook design according to one or more aspects of the present disclosure. The procedure 600 can be performed by a UE 601 (e.g., the ED 110 of FIGS. 1-2) and a gNB 602 (e.g., the network node 170 of FIGS. 1-2) . While the procedure in FIG. 6 is described with reference to a UE and a gNB, this description is provided for illustrative purposes only and is not intended to be limiting. In practice, the procedure can be applied to other instances of network nodes and terminal devices or equivalents thereof. For example, the procedure can be applied between two gNBs, two UEs (e.g., two UEs communicating via one or more sidelinks) , a gNB and a distribution unit (DU) , a gNB and a control unit (CU) , two CUs, a CU to a DU, or two DUs. It is understood that steps or operations shown in the procedure are not exhaustive and that other operations can be performed as well before, after, or between any of the illustrated operations. Further, some of the steps or operations may be omitted, performed simultaneously, or performed in a different order than those shown in FIG. 6.
[0151] As shown in FIG. 6, the procedure 600 for the dynamic adaptive codebook design may include at least one of the following steps.
[0152] At 603, the gNB can initialize an embedding codebook, which can be either a pre-trained codebook or one trained based on collected embedding data.
[0153] At 604, the gNB can transmit embedding codebook information (ECI) to the UE. Accordingly, the UE can receive the ECI from the gNB. In other words, the gNB sends codebook information to the UE via ECI signaling. This may trigger the codebook negotiation between the gNB and the UE. In some implementations, the ECI can indicate one or more embedding codebooks. The ECI can include at least one of the following for each embedding codebook of the one or more embedding codebooks: an identifier of the embedding codebook; a size of the embedding codebook; a modality of the embedding codebook; a machine learning model identifier of the embedding codebook; dimension of the embedding codebook (e.g., codewords length) ; precision of the embedding codebook; a description of the embedding codebook; expansion support of the embedding codebook; or an application type of the embedding codebook. Tables I and II illustrate examples of the information of an embedding codebook included in the ECI.
[0154] In some implementations, the ECI can indicate codewords for each of the one or more embedding codebooks. For example, the ECI can include the codewords of an embedding codebook. Alternatively, the ECI can include indices or identifiers for the codewords of the embedding codebook, and the indices or identifiers can be used to map the codewords in a pre-defined mapping table.
[0155] In some implementations, the ECI is carried in at least one of a higher layer signaling or a physical layer signaling. For example, the ECI can be carried via PDCCH. Alternatively, the ECI may be transmitted through any suitable channel configured for ECI transmissions.
[0156] In some implementations, the ECI can include a first portion carried in a first higher layer signaling and a second portion carried in a second higher layer signaling. The first portion can include a first set of codewords for the one or more embedding codebooks, and the second portion can include a second set of codewords for the one or more embedding codebooks. For example, the first portion and the second portion can belong to a same embedding codebook. Alternatively, the first portion and the second portion can belong to different embedding codebooks.
[0157] At 605, the UE can transmit an embedding codebook confirmation (ECC) to the gNB. Accordingly, the gNB receives the ECC from the UE. The ECC can indicate a first embedding codebook from the one or more embedding codebooks. In other words, the UE can send confirmation information on the codebook via ECC. In this way, the gNB and UE negotiate and select a mutually supported codebook, such as one with the same size, codewords, and floating-point format by using steps 604 and 605.
[0158] At 606, the gNB can encode embedding information using the first embedding codebook. The embedding information comprises one or more embedding vectors. In other words, the gNB can perform data compression by using the agreed-upon codebook (e.g., the first embedding codebook) to compress embedding information, converting embedding vectors into codeword indices.
[0159] At 607, the gNB can transmit the encoded embedding information to the UE. Accordingly, the UE can receive the encoded embedding information from the gNB. The encoded embedding information is based on the ECI. For example, the encoded embedding information is determined by the gNB based on the first embedding codebook indicated by the ECI (e.g., at 606) . In other words, the gNB can transmit the compressed embedding information (codeword indices or coded embedding) to the UE (e.g., via PDSCH or any other suitable channel configured for transmission of embedding information) .
[0160] At 608, the UE can decode the encoded embedding information using the first embedding codebook. The decoded embedding information indicates one or more embedding vectors. In other words, the UE can perform data decompression by using the agreed-upon codebook (e.g., the first embedding codebook) to decompress the received codeword indices back into embedding vectors.
[0161] At 609, the gNB can transmit an embedding codebook update (ECU) to the UE. Accordingly, the UE can receive the ECU from the gNB. In other words, the gNB may perform codebook update by dynamically updating the codebook. The codebook update can be based on changes in the distribution of embedding information. The gNB can transmit the update information (e.g., the ECU at 609) to the UE via ECU signaling. Accordingly, the UE may update its local codebook upon receiving the update information. In some implementations, the ECU can be carried via PDCCH. Alternatively, the ECU may be transmitted through any suitable channel configured for updating the codebook.
[0162] In some implementations, the ECU indicates a second embedding codebook or a change to the first embedding codebook. The change to the first embedding codebook can indicate at least one of: one or more codewords to be removed from the first embedding codebook; one or more codewords to be added to the first embedding codebook; one or more codewords to be replaced in the first embedding codebook; or a change to a codeword length (e.g., changed from 32 bits to 64 bits) . In some implementations, the second embedding codebook is from the one or more embedding codebooks. Alternatively, the second embedding codebook is different from the one or more embedding codebooks, and the ECU indicates codewords for the second embedding codebook.
[0163] In some implementations, the ECU is determined based on at least one of: a distribution of received embedding information; a distribution of transmitted embedding information; a distribution of to-be-transmitted embedding information; or an effectiveness quality indicator (EQI) determined based on received embedding information; a channel quality indicator (CQI) ; or a received EQI.
[0164] In some implementations, the UE transmits compressed embedding information (codeword indices or coded embedding) to the gNB. For example, at 610, the UE can encode embedding information using the first embedding codebook. The embedding information comprises one or more embedding vectors. In other words, the UE can perform data compression by using the agreed-upon codebook (e.g., the first embedding codebook) to compress embedding information, converting embedding vectors into codeword indices.
[0165] At 611, the UE can transmit the encoded embedding information to the gNB. Accordingly, the gNB can receive the encoded embedding information from the UE. In some implementations, the UE can transmit the compressed embedding information (codeword indices or coded embedding) to the gNB via PUSCH (or any other suitable channel configured for transmission of embedding information) .
[0166] At 612, the gNB can decode the encoded embedding information using the first embedding codebook. The decoded embedding information indicates one or more embedding vectors. In other words, the gNB can perform data decompression by using the agreed-upon codebook (e.g., the first embedding codebook) to decompress the received codeword indices back into embedding vectors.
[0167] In some implementations, the gNB can transmit an effectiveness quality indicator (EQI) to the UE. The EQI can be determined (e.g., by the gNB) based on the encoded embedding information (e.g., the encoded embedding information received by the gNB at 611) .
[0168] In some implementations, the gNB can receive the EQI from the UE. The EQI can be determined (e.g., by the UE) based on the encoded embedding information (e.g., the encoded embedding information received by the UE at 607) .
[0169] In some implementations, multi-level vector quantization may be used for embedding compression. In this approach, the embedding vector can be decomposed into multiple sub-vectors based on the varying importance of features in each part. Each sub-vector is then subjected to vector quantization at different levels of precision. For example, critical features might use higher precision, while less important ones can use lower precision, allowing for a more efficient representation.
[0170] In some implementations, to achieve enhanced real-time adaptability, residual quantization can be employed for embedding compression. This technique quantifies the residual information, i.e., the difference between the original vector and the quantized vector. Focusing on compressing only the changing parts at each moment can further improve efficiency. For instance, in surveillance scenarios, only the areas of the frame that change significantly between frames can be encoded, reducing data redundancy.
[0171] In some implementations, an original embedding codebook can be designed as a full codebook of size (M1+M2) × N. The original codebook can be divided into a first codebook of size M1× N (e.g., the first M1× N portion of the full codebook) and a second codebook (e.g., the remaining M2× N portion of the full codebook) . During an initial communication phase, only a smaller portion of the codebook (e.g., the first M1× N portion) is activated by default. A receiver (e.g., the UE 601 of FIG. 6) can be pre-configured with knowledge of the complete codebook structure but decodes only the transmitted portion.
[0172] During a first phase, a transmitter (e.g., the gNB 602 of FIG. 6) can transmit the first M1× N codewords. The receiver can decode the data based solely on the initial portion of the codebook.
[0173] During a second phase, the transmitter and the receiver can perform an optional expansion of the codebook. For example, if the transmitter detects insufficient information richness or increased task complexity, it starts transmitting the extended codebook portion (e.g., the remaining M2× N) . The receiver combines both portions into the full codebook and decodes using the complete structure without requiring renegotiation.
[0174] Table I illustrates an example codebook that can be configured to support the described residual quantization based progressive codebook feature. Table I
[0175] As shown in Table I, the ECI (e.g., the ECI transmitted at 604 of FIG. 6) can include a header part and a data part. The header part can include one or more parameters including Model ID, Phase, Size, Dimension, and Precision. The data part can include indices for the transmitted codebook. The codebook in Table I can be used for an object detection task. In the first phase, simple edge features are transmitted. Then, in the second phase, more complex features are transmitted. The complex features include additional object categories as the detection progresses. In some implementations, the dimensions (e.g., 256 as shown in Table I) and precision (e.g., float 32 as shown in Table I) of the codewords in the first codebook and the second codebook can be the same.
[0176] During the first phase of the transmission, only the codewords from the first portion of the codebook are sent. For example, a header part of the ECI in the first phase can include “Model ID: 1, Phase: 1, Size: 512, Dimension: 256, Precision: float 32. ” A data part of the ECI in the first phase can include “105 (codeword C105) . ”
[0177] During the second phase of the transmission (also referred to as extended transmission) , the codewords from the remaining portion of the codebook are sent. For example, a header part of the ECI in the second phase can include “Model ID: 1, Phase: 2, Size: 512, Dimension: 256, Precision: float 32. ” A data part of the ECI in the second phase can include “728 (codeword C728) . ” The receiver can combine the two portions as: (C105, C728) . In some implementations, the ECI in the first phase can be transmitted at 604 of FIG. 6, and the ECI in the second phase can be transmitted as the ECU at 609 of FIG. 6.
[0178] Table II illustrates another example codebook that can be configured to support the described residual quantization based progressive codebook feature. Table II
[0179] As shown in Table II, the dimensions and precision of the codewords in the codebook may vary between the first phase and the second phase. The codebook in Table II can be used for semantic segmentation of images, where codewords describe region-specific features. Simple regions are encoded with basic attributes (e.g., average color) in low-dimensional and low-precision representations (e.g., the first codebook) , while complex regions include additional edge and texture features in high-dimensional and high-precision representations (e.g., the second codebook) .
[0180] During the first phase of the transmission, only the codewords from the first portion of the codebook are sent. For example, a header part of the ECI in the first phase can include “Model ID: 1, Phase: 1, Size: 256, Dimension: 256, Precision: float 16. ” A data part of the ECI in the first phase can include “205 (codeword C205) . ”
[0181] During the second phase of the transmission (also referred to as extended transmission) , the codewords from the remaining portion of the codebook are sent. For example, a header part of the ECI in the second phase can include “Model ID: 1, Phase: 2, Size: 1024, Dimension: 768, Precision: float 32. ” A data part of the ECI in the second phase can include “1080 (codeword C1080) . ” The receiver can combine the two portions as: (C205, C1080) . In some implementations, the ECI in the first phase can be transmitted at 604 of FIG. 6, and the ECI in the second phase can be transmitted as the ECU at 609 of FIG. 6.
[0182] In some implementations, entropy coding may be used for embedding compression. For example, entropy coding can be applied to compressed codeword indices using methods like Huffman coding or arithmetic coding, which helps to further reduce the overall data volume. This is particularly useful in scenarios where certain symbols occur more frequently, allowing for shorter representations.
[0183] In some implementations, joint codebook design may be used for embedding compression. This method allows for the handling of multiple related embedding information using a single joint codebook. For instance, by employing the same codebook for prompt information and its associated background information, compression efficiency can be significantly increased. This synergy minimizes redundancy and maximizes the information captured in the compressed format.
[0184] In the present disclosure, the terms “a” or “an” are defined to mean “at least one” , that is, these terms do not exclude a plural number of items, unless stated otherwise.
[0185] In the present disclosure, terms such as “substantially” , “generally” and “about” , which modify a value, condition or characteristic of a feature of an example embodiment, should be understood to mean that the value, condition or characteristic is defined within tolerances that are acceptable for the proper operation of the example embodiment for its intended application.
[0186] In the present disclosure, unless stated otherwise, the terms “connected” and “coupled” , and derivatives and variants thereof, refer herein to any structural or functional connection or coupling, either direct or indirect, between two or more elements. For example, the connection or coupling between the elements can be acoustical, mechanical, optical, electrical, thermal, logical, or any combinations thereof.
[0187] In the present disclosure, expressions such as “match” , “matching” and “matched” , including variants and derivatives thereof, are intended to refer herein to a condition in which two or more elements are either the same or within some predetermined tolerance of each other. That is, these terms are meant to encompass not only “exactly” or “identically” matching the two elements but also “substantially” , “approximately” or “subjectively” matching the two or more elements, as well as providing a higher or best match among a plurality of matching possibilities.
[0188] In the present disclosure, the expression “based on” is intended to mean “based at least partly on” , that is, this expression can mean “based solely on” or “based partially on” , and so should not be interpreted in a limited manner. More particularly, the expression “based on” could also be understood as meaning “depending on” , “representative of” , “indicative of” , “associated with” or similar expressions.
[0189] In the present disclosure, the terms "system" and "network" may be used interchangeably in different embodiments of this application. "At least one" means one or more, and " a plurality of" means two or more. The term "and / or" describes an association relationship of associated objects, and indicates that three relationships may exist. For example, A and / or B may indicate the following three cases: Only A exists, both A and B exist, and only B exists, where A and B may be singular or plural. The character " / " indicates an "or" relationship between associated objects. "At least one of the following items (pieces) " or a similar expression thereof indicates any combination of these items, including a single item (piece) or any combination of a plurality of items (pieces) . For example, "at least one of A, B, or C" includes: only A; only B; only C; A and B; A and C; B and C; or A, B, and C, and "at least one of A, B, and C" may also be understood as including: only A; only B; only C; A and B; A and C; B and C; or A, B, and C. In addition, unless otherwise specified, ordinal numbers such as "first" and "second" in embodiments of this application are used to distinguish between a plurality of objects, and are not used to limit a sequence, a time sequence, priorities, or importance of the plurality of objects.
[0190] A person skilled in the art should understand that embodiments of this application may be provided as a method, an apparatus (or system) , computer-readable storage medium, or a computer program product. Therefore, this application may use a form of a hardware-only embodiment, a software-only embodiment, or an embodiment with a combination of software and hardware. Moreover, this application may use a form of a computer program product that is implemented on one or more computer-usable storage media (including but not limited to a disk memory, an optical memory, and the like) that include computer-usable program code.
[0191] This application is described with reference to the flowcharts and / or block diagrams of the method, the device (system) , and the computer program product according to this application. It should be understood that computer program instructions may be used to implement each process and / or each block in the flowcharts and / or the block diagrams and a combination of a process and / or a block in the flowcharts and / or the block diagrams. The computer program instructions may be provided for a general-purpose computer, a dedicated computer, an embedded processor, or a processor of another programmable data processing device and enable a machine to execute the instructions. When executed by any computer or the processor of a programmable data processing device, the instructions cause the apparatus to implement specific functions as described in one or more procedures in the flowcharts and / or one or more blocks in the block diagrams. The computer program instructions may alternatively be stored in a computer-readable memory that can indicate a computer or another programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate an artifact that includes an instruction apparatus. The instruction apparatus implements a specific function in one or more procedures in the flowcharts and / or one or more blocks in the block diagrams.
[0192] The computer program instructions may alternatively be loaded onto a computer or another programmable data processing device, so that a series of operations and steps are performed on the computer or the other programmable data processing device, so that computer-implemented processing is generated. Therefore, the instructions executed on the computer or on another programmable device provide steps for implementing specific functions as described in one or more procedures in the flowcharts and / or one or more blocks in the block diagrams.
[0193] It is clear that a person skilled in the art can make various modifications and variations to this application without departing from the scope of this disclosure. This disclosure is intended to cover these modifications and variations of this application provided that they fall within the scope of protection defined by the following claims and their equivalent technologies.
Claims
A method comprising:transmitting embedding codebook information (ECI) , wherein the ECI indicates one or more embedding codebooks; andtransmitting or receiving encoded embedding information, wherein the encoded embedding information is based on the ECI.The method of claim 1, further comprising:receiving an embedding codebook confirmation (ECC) , wherein the ECC indicates a first embedding codebook, wherein the first embedding codebook belongs to the one or more embedding codebooks, and the encoded embedding information is based on the first embedding codebook.The method of claim 1 or claim 2, wherein the ECI comprises at least one of the following for each of the one or more embedding codebooks:an identifier;a size;a modality;a machine learning model identifier;dimension;precision;a description;expansion support; oran application type.The method of any one of claims 1-3, wherein the ECI indicates codewords for each of the one or more embedding codebooks.The method of any one of claims 1-4, wherein the ECI is carried in at least one of a higher layer signaling or a physical layer signaling.The method of any one of claims 1-5, wherein the ECI comprises a first portion carried in a first higher layer signaling and a second portion carried in a second higher layer signaling, the first portion comprises a first set of codewords for the one or more embedding codebooks, and the second portion comprises a second set of codewords for the one or more embedding codebooks.The method of any one of claims 2-6, further comprising:encoding embedding information using the first embedding codebook, wherein the embedding information comprises one or more embedding vectors.The method of any one of claims 2-6, further comprising:decoding the encoded embedding information using the first embedding codebook, wherein the decoded embedding information indicates one or more embedding vectors.The method of claim 8, further comprising:transmitting an effectiveness quality indicator (EQI) , wherein the EQI is determined based on the encoded embedding information.The method of any one of claims 2-9, further comprising:transmitting an embedding codebook update (ECU) , wherein the ECU indicates a second embedding codebook or a change to the first embedding codebook.The method of claim 10, wherein the change to the first embedding codebook indicates at least one of:one or more codewords to be removed from the first embedding codebook;one or more codewords to be added to the first embedding codebook;one or more codewords to be replaced in the first embedding codebook; ora change to a codeword length.The method of claim 10 or claim 11, wherein the second embedding codebook is from the one or more embedding codebooks.The method of any one of claims 10-12, wherein the second embedding codebook is different from the one or more embedding codebooks, and the ECU indicates codewords for the second embedding codebook.The method of any one of claims 10-13, wherein the ECU is determined based on at least one of:a distribution of received embedding information;a distribution of transmitted embedding information;a distribution of to-be-transmitted embedding information; oran effectiveness quality indicator (EQI) determined based on received embedding information;a channel quality indicator (CQI) ; ora received EQI.A method comprising:receiving embedding codebook information (ECI) , wherein the ECI indicates one or more embedding codebooks; andtransmitting an embedding codebook confirmation (ECC) , wherein the ECC indicates a first embedding codebook, wherein the first embedding codebook belongs to the one or more embedding codebooks.The method of claim 15, wherein the ECI comprises at least one of the following for each of the one or more embedding codebooks:an identifier;a size;a modality;a machine learning model identifier;dimension;precision;a description;expansion support; oran application type.The method of claim 15 or claim 16, wherein the ECI indicates codewords for each of the one or more embedding codebooks.The method of any one of claims 15-17, wherein the ECI is carried in at least one of a higher layer signaling or a physical layer signaling.The method of any one of claims 15-18, wherein the ECI comprises a first portion carried in a first higher layer signaling and a second portion carried in a second higher layer signaling, the first portion comprises a first set of codewords for the one or more embedding codebooks, and the second portion comprises a second set of codewords for the one or more embedding codebooks.The method of any one of claims 15-19, further comprising:encoding embedding information using the first embedding codebook, wherein the embedding information comprises one or more embedding vectors; andtransmitting the encoded embedding information.The method of any one of claims 15-20, further comprising:receiving encoded embedding information; anddecoding the encoded embedding information using the first embedding codebook, wherein the decoded embedding information indicates one or more embedding vectors.The method of claim 21, further comprising:transmitting an effectiveness quality indicator (EQI) , wherein the EQI is determined based on the encoded embedding information.The method of any one of claims 15-22, further comprising:receiving an embedding codebook update (ECU) , wherein the ECU indicates a second embedding codebook or a change to the first embedding codebook.The method of claim 23, wherein the change to the first embedding codebook indicates at least one of:one or more codewords to be removed from the first embedding codebook;one or more codewords to be added to the first embedding codebook;one or more codewords to be replaced in the first embedding codebook; ora change to a codeword length.The method of claim 23 or claim 24, wherein the second embedding codebook belongs to the one or more embedding codebooks.The method of any one of claims 23-25, wherein the second embedding codebook is different from the one or more embedding codebooks, and the ECU indicates codewords for the second embedding codebook.The method of any one of claims 23-26, wherein the ECU is determined based on at least one of:a distribution of received embedding information;a distribution of transmitted embedding information;a distribution of to-be-transmitted embedding information; oran effectiveness quality indicator (EQI) determined based on received embedding information;a channel quality indicator (CQI) ; ora received EQI.An apparatus, configured to perform the method of any one of claims 1-14 or any one of claims 15-27.An apparatus comprising:a transmitting unit configured to transmit embedding codebook information (ECI) , wherein the ECI indicates one or more embedding codebooks; anda communication unit configured to transmit or receive encoded embedding information, wherein the encoded embedding information is based on the ECI.An apparatus comprising:a receiving unit configured to receive embedding codebook information (ECI) , wherein the ECI indicates one or more embedding codebooks; anda transmitting unit configured to transmit an embedding codebook confirmation (ECC) , wherein the ECC indicates a first embedding codebook from the one or more embedding codebooks.An apparatus comprising:one or more processors; andan interface circuit configured to:transmit embedding codebook information (ECI) , wherein the ECI indicates one or more embedding codebooks; andtransmit or receive encoded embedding information, wherein the encoded embedding information is based on the ECI.An apparatus comprising:one or more processors; andan interface circuit configured to:receive embedding codebook information (ECI) , wherein the ECI indicates one or more embedding codebooks; andtransmit an embedding codebook confirmation (ECC) , wherein the ECC indicates a first embedding codebook from the one or more embedding codebooks.The apparatus of claim 31 or claim 32, wherein the interface circuit comprises one or more transceivers.An apparatus comprising:one or more processors coupled with one or more memories storing instructions which, when the instructions executed by the one or more processors, cause the apparatus to perform the method of any one of claims 1-14 or any one of claims 15-27.A communication system, wherein the communication system comprises a first apparatus configured to perform the method of any one of claims 1-14 and a second apparatus configured to perform the method of any one of claims 15-27.A non-transitory computer-readable storage medium storing instructions stored thereon which, when executed by an apparatus, cause the apparatus to perform the method of any one of claims 1-14 or any one of claims 15-27.A computer program product having instructions which, when executed, cause an apparatus to perform the method of any one of claims 1-14 or any one of claims 15-27.
Citation Information
Patent Citations
Channel state information reporting with basis expansion for advanced wireless communications systems
US20160072562A1
Embedding codebooks for resource optimization
US20190121884A1
Method and system for channel state information feedback using sub-codebook based trellis coded quantization
US20220360305A1
Generating compressed representations of video for efficient learning of video tasks
WO2023170069A1
Determining quantization information
WO2024031502A1