Method and apparatus for evaluating semantic data quality: effectiveness quality indicator (EQI) and EQI-based adaptive transmission
The introduction of an EQI metric addresses the lack of comprehensive quality evaluation in semantic data transmission, optimizing data representation and transmission parameters for improved reliability and efficiency in AI applications.
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 wireless communication systems lack a comprehensive metric to evaluate the quality of semantic data transmission, particularly in AI applications, as channel quality indicators (CQI) focus solely on signal transmission quality without considering the semantic content of the data.
Introduce an Effectiveness Quality Indicator (EQI) metric to assess the quality of semantic data transmission, which measures semantic similarity, information completeness, and task relevance, allowing dynamic optimization of data representation, length, precision, and transmission parameters for improved efficiency.
EQI enhances the performance of AI applications by ensuring effective and reliable transmission of semantic information, optimizing modulation, coding schemes, and transmission power settings.
Smart Images

Figure CN2024142691_09042026_PF_FP_ABST
Abstract
Description
METHOD AND APPARATUS FOR EVALUATING SEMANTIC DATA QUALITY: EFFECTIVENESS QUALITY INDICATOR (EQI) AND EQI-BASED ADAPTIVE TRANSMISSIONCROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims the benefit of U.S. Provisional Application Serial No. 63 / 701,992 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 system for evaluating semantic data quality.BACKGROUND
[0003] In some transmission schemes, data is represented as a bit stream of 0s and 1s, and the physical layer does not understand the content (also called as meaning) of the data; it only ensures reliable transmission based on different quality of service (QoS) levels. To ensure reliable transmission, channel coding, cyclic redundancy check (CRC) , Hybrid Automatic Repeat reQuest (H-ARQ) retransmission mechanisms and transmission power control scheme are introduced.
[0004] The 3rd generation partnership project (3GPP) 5th generation (5G) New Radio (NR) standards use channel quality indicator (CQI) to evaluate the quality of wireless channels, primarily based on physical layer parameters such as signal strength and noise levels. The gNB selects appropriate modulation and coding schemes (MCS) and transmission power based on the CQI information reported by the UE to ensure reliable communication.SUMMARY
[0005] 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 semantic data quality evaluation in wireless communication systems.
[0006] According to a first aspect, a method is provided. The method includes receiving first embedding data. The method further includes determining an embedding quality indicator based on the first embedding data.
[0007] With reference to the first aspect, in some implementations, the method further includes determining an embedding adjustment based on the embedding quality indicator; and transmitting the embedding adjustment.
[0008] With reference to the first aspect, in some implementations, the method further includes transmitting the embedding quality indicator.
[0009] With reference to the first aspect, in some implementations, the method further includes receiving second embedding data, where the second embedding data includes an embedding adjustment.
[0010] With reference to the first aspect, in some implementations, the method further includes receiving information indicating an embedding quality measurement method.
[0011] With reference to the first aspect, in some implementations, the method further includes transmitting a response to the information indicating the embedding quality measurement method, wherein determining the embedding quality indicator includes determining the embedding quality indicator based on the first embedding data and the embedding quality measurement method.
[0012] With reference to the first aspect, in some implementations, the embedding quality measurement method indicates a weighted combination of at least one of: a first metric measuring a relevance level of embedding data with respect to a target task; a second metric measuring a level of information completeness of embedding data with respect to the target task; a third metric measuring content consistency between semantic content of current embedding data and semantic content of historic embedding data; or a fourth metric measuring a similarity between embedding data and an embedding reference.
[0013] With reference to the first aspect, in some implementations, the embedding quality indicator is in one of the following formats: a numerical value; a scale indicator; a direction indicator indicating whether to increase or decrease an embedding quality; or a description in natural language.
[0014] With reference to the first aspect, in some implementations, the embedding quality indicator is carried in a physical layer signaling.
[0015] With reference to the first aspect, in some implementations, the embedding adjustment includes a change to at least one of the following embedding parameters: an embedding length; an embedding precision level; a channel coding scheme for embedding; or a compression scheme for embedding.
[0016] With reference to the first aspect, in some implementations, determining the embedding adjustment includes: determining the embedding adjustment based on the embedding quality indicator and a channel quality indicator (CQI) .
[0017] According to a second aspect, a method is provided. The method includes transmitting first embedding data. The method further includes obtaining information indicating an embedding quality indicator.
[0018] With reference to the second aspect, in some implementations, obtaining the information indicating the embedding quality indicator includes: receiving the embedding quality indicator.
[0019] With reference to the second aspect, in some implementations, the method further includes determining an embedding adjustment based on the embedding quality indicator; and transmitting second embedding data based on the embedding adjustment.
[0020] With reference to the second aspect, in some implementations, the method further includes transmitting information indicating an embedding quality measurement method; and receiving a response to the information indicating the embedding quality measurement method.
[0021] With reference to the second aspect, in some implementations, the embedding quality measurement method indicates a weighted combination of at least one of: a first metric measuring a relevance level of embedding data with respect to a target task; a second metric measuring a level of information completeness of embedding data with respect to the target task; a third metric measuring content consistency between semantic content of current embedding data and semantic content of historic embedding data; or a fourth metric measuring a similarity between embedding data and an embedding reference.
[0022] With reference to the second aspect, in some implementations, the embedding quality indicator is in one of the following formats: a numerical value; a scale indicator; a direction indicator indicating whether to increase or decrease an embedding quality; or a description in natural language.
[0023] With reference to the second aspect, in some implementations, the embedding quality indicator is carried in a physical layer signaling.
[0024] With reference to the second aspect, in some implementations, the embedding adjustment includes a change to at least one of the following embedding parameters: an embedding length; an embedding precision level; a channel coding scheme for embedding; or a compression scheme for embedding.
[0025] With reference to the second aspect, in some implementations, determining the embedding adjustment includes: determining the embedding adjustment based on the embedding quality indicator and a channel quality indicator (CQI) .
[0026] 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.
[0027] According to a fourth aspect, an apparatus is provided. The apparatus includes: a receiving unit configured to receive first embedding data; and a processing unit configured to determine an embedding quality indicator based on the first embedding data.
[0028] According to a fifth aspect, an apparatus is provided. The apparatus includes: a transmitting unit configured to transmit first embedding data; and a processing unit configured to obtain information indicating an embedding quality indicator.
[0029] According to a sixth aspect, an apparatus is provided. The apparatus includes: one or more processors; and an interface circuit configured to receive first embedding data.
[0030] According to a seventh aspect, an apparatus is provided. The apparatus includes an interface circuit configured to transmit first embedding data; : one or more processors configured to obtain information indicating an embedding quality indicator.
[0031] With reference to the sixth aspect or the seventh aspect, in some implementations, the interface circuit includes one or more transceivers.
[0032] According to an eighth aspect, an apparatus is provided. The apparatus includes one or more processors coupled with 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.
[0033] 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.
[0034] According to a tenth aspect, a non-transitory computer-readable storage medium is provided. The non-transitory computer-readable storage 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.
[0035] According to an eleventh aspect, a computer program product is provided. The computer program product comprises 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
[0036] FIG. 1 illustrates a schematic illustration of an example communication system.
[0037] FIG. 2 illustrates another example communication system.
[0038] FIG. 3 illustrates an example of an apparatus wirelessly communicating with another apparatus in a communication system.
[0039] FIG. 4 illustrates an example apparatus.
[0040] FIG. 5 illustrates another example apparatus.
[0041] FIG. 6 illustrates an example negotiation procedure.
[0042] FIG. 7 illustrates another example negotiation procedure.
[0043] FIG. 8 illustrates an example procedure for embedding data transmission.
[0044] FIG. 9 illustrates another example procedure for embedding data transmission.DETAILED DESCRIPTION
[0045] With the rise of artificial intelligence (AI) , the transmission of data related to AI is becoming increasingly significant in wireless communications. Some types of AI-related data, such as semantic data, can exhibit characteristics that are quite different from other data. Given that embeddings are a common representation of semantic data, embedding data is taken as an example when some implementations are described in the present disclosure. However, it is understood that such implementations are not intended to be construed in a limiting sense, and that the described techniques are equally applicable to semantic data using any other representations.
[0046] Embeddings can map high-dimensional data into lower-dimensional vectors, preserving semantic and structural features. In the present disclosure, unless otherwise specified, the terms “embedding, ” “embeddings, ” “embedding information, ” and “embedding data” can be used interchangeably. Embeddings can be created using trained models and have one or more of the following key characteristics.
[0047] 1. Vector representation. Embeddings can be used to convert data like sentences or images into vectors that retain essential features of the original data.
[0048] 2. Model dependency. Different models can produce different embeddings suited to specific tasks.
[0049] 3. Distance measurement. Metrics like Euclidean distance or cosine similarity can be used to measure embedding similarity.
[0050] 4. Semantic comparison. Comparison of complex data formats through vector distances and similarities can be allowed.
[0051] Transmitting embeddings in a meaningful way over the lower layers (for example, physical layer and Medium Access Control (MAC) layer) can offer several benefits. Therefore, a metric to represent the effectiveness of embedding transmission is needed.
[0052] With the development of AI technologies, semantic data (such as embeddings) will emerge as a new type of data transmitted over communication systems. Semantic data, due to its distinct characteristics compared to traditional data, offers numerous advantages when transmitted at lower layers in a content-aware manner (e.g., its content and meaning are known to lower layer) . Channel quality indicator (CQI) focuses solely on signal transmission quality at the physical layer, neglecting the semantic content of the transmitted information. This limitation prevents CQI from accurately reflecting the quality of semantic data transmission in AI applications.
[0053] Accordingly, an Effectiveness Quality Indicator (EQI) scheme is provided in this application. EQI is a new metric specifically designed to evaluate the quality of semantic data transmitted over wireless communication channels.
[0054] The EQI measures effectiveness quality of semantic data representation, such as semantic similarity, information completeness, task relevance, etc. EQI can provide a more comprehensive assessment of semantic data transmission quality. EQI could be expressed in various forms, including numerical numbers, rating scales, directional indicators, or descriptive human language. The calculation of EQI can be adjusted based on the specific needs of downstream tasks and the communication system requirement. EQI can allow both a Generation NodeB (gNB) and a user equipment (UE) to dynamically optimize the length and precision of semantic data in order to achieve more efficient and effective transmission of semantic information.
[0055] The proposed EQI metric offers one or more of several significant advantages. It provides a flexible measurement tailored to semantic data representation. By combining EQI and CQI feedback, the gNB and the UE can select appropriate semantic representation (e.g., length, precision, and compression method) , modulation and coding scheme (MCS) , and transmission power settings, improving transmission effectiveness and reliability. Ultimately, EQI enhances the performance of AI applications by ensuring the effective transmission of semantic information.
[0056] 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.
[0057] 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.
[0058] 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.
[0059] 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.
[0060] 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.
[0061] 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.
[0062] 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.
[0063] 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.
[0064] 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.
[0065] 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.
[0066] 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.
[0067] 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.
[0068] 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.
[0069] 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.
[0070] 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.
[0071] 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.
[0072] 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.
[0073] 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.
[0074] 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) .
[0075] 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.
[0076] 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) .
[0077] 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.
[0078] 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.
[0079] 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.
[0080] 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.
[0081] 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.
[0082] 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.
[0083] 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) .
[0084] 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.
[0085] 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.
[0086] 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.
[0087] 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.
[0088] 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.
[0089] 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.
[0090] The apparatus 320 and / or the apparatus 310 may include other components, not shown or described herein for the sake of clarity.
[0091] 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.
[0092] 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.
[0093] 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.
[0094] 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.
[0095] 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) .
[0096] 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.
[0097] 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.
[0098] 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.
[0099] 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.
[0100] 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.
[0101] 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.
[0102] 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.
[0103] 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.
[0104] 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) .
[0105] 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.
[0106] CQI is a critical parameter in modern wireless communication systems, such as LTE and 5G networks. It serves as a measure of the quality of the communication channel between a UE and a base station (for example, eNodeB or gNB) . The CQI value is derived from the signal-to-noise ratio (SNR) on the wireless channel and provides a snapshot of the channel’s condition at a specific point in time.
[0107] In the 5G system, the UE can continuously measure the channel quality and report CQI value to the base station. CQI value can range from 0 to 31 with a higher CQI value indicating a better channel quality. Based on the reported CQI, the base station can select an appropriate MCS and transmission power in order to achieve the maximum data throughput given the current channel condition.
[0108] There can be many benefits of using CQI.
[0109] 1. Optimized data rate. CQI enables the selection of the best MCS based on current channel conditions and maximizes the data throughput.
[0110] 2. Enhanced network efficiency. By adjusting transmission power according to CQI, networks can reduce interference and improve spectral efficiency.
[0111] 3. Improved QoS. Dynamic adjustments based on CQI ensure consistent and reliable communication, even in varying channel conditions.
[0112] Embedding, as a type of semantic data, is used to represent semantic data in the following discussion.
[0113] Embeddings are a fundamental concept in machine learning and natural language processing (NLP) . Embedding is a method to represent data, such as words, images, videos, or even entire documents, as vectors in a continuous vector space. This representation captures the semantic meaning of the data, making it easier for machine learning models and AI tasks to process and understand.
[0114] Embeddings are numerical representations of objects. For example, in the context of text, an embedding might represent a word or a sentence as a vector of elements. These vectors are designed so that similar objects have similar representations. For instance, the words “girl” and “boy” might have similar embeddings because they share related meanings.
[0115] Embeddings are typically created using AI models. These models are trained on large datasets to learn the relationships between different objects. During training, the model adjusts the embeddings so that objects with similar meanings are close to each other in the vector space. Popular techniques for creating embeddings include Word2Vec, GloVe, contrastive language-image pre-training (CLIP) , bidirectional encoder representations from transformer (BERT) , etc.
[0116] Embeddings have a wide range of applications in machine learning and NLP. The following are some examples.
[0117] 1. Semantic Search. Embeddings can be used to improve search engines by understanding the meaning behind search queries and matching them with relevant documents.
[0118] 2. Clustering. By representing data as embeddings, it becomes easier to group similar items together. This is useful in tasks like customer segmentation.
[0119] 3. Recommendation systems. Embeddings can help recommend products or content by finding items that are similar to what a user has liked in the past.
[0120] 4. Machine translation. Embeddings can capture the meaning of sentences, making it easier to translate text from one language to another.
[0121] Embeddings are a powerful tool in the field of machine learning, enabling models to understand and process complex data. By converting objects into numerical representations, embeddings make it possible to perform tasks like semantic search, clustering, and recommendation with greater accuracy and efficiency.
[0122] However, for AI applications, particularly those involving semantic data (e.g., embedding) , relying solely on CQI for resource allocation is insufficient. Besides channel quality, the effectiveness of the transmitted information is also critical. For example, as an embedding is for a downstream task, if the embedding format is not appropriately chosen, increasing the transmission power, selecting a higher MCS, or performing more retransmissions, still cannot ensure the successful completion of the downstream task. Merely identifying that the embedding effectiveness is not sufficient, and modifying the embedding itself can lead to better accomplishing the downstream task.
[0123] In some implementations, embedding is a new type of data transmitted in lower layers (e.g., physical and MAC layers) .
[0124] Embeddings are techniques for mapping high-dimensional data into lower-dimensional vector spaces, aiming to retain the semantic and structural features of the original data through vector representations. This mapping is typically achieved through trained models, allowing key features of the data to be expressed compactly in a lower-dimensional space. Specifically, embeddings can have one or more of the following characteristics.
[0125] 1. Vector Representation. Embedding techniques convert data from high-dimensional spaces (such as word, sentences, images, video, paragraph or other complex data) into lower-dimensional vectors. These vectors preserve the semantic information of the data in the high-dimensional space, enabling relationships and features to be represented through the distance and direction of the vectors. For example, in sentence embeddings, entire sentences or paragraphs are represented as fixed-length vectors, capturing the overall meaning so that sentences with similar themes or meanings are closer in vector space. This supports tasks such as text classification, sentiment analysis, or information retrieval. In image embeddings, images are converted into low-dimensional vectors that retain the primary features and content of the images, making image retrieval, classification, and recognition tasks more efficient.
[0126] 2. Model dependency. Different models and methods generate different embeddings. Each embedding technique (such as BERT, CLIP) is based on specific algorithms and training strategies, and processes data in various formats. As a result, the generated vector representations can differ. Each embedding method is suited to particular tasks and data types, affecting how the model represents the data.
[0127] 3. Distance measurement. In embedding space, distances between vectors are commonly used to measure the similarity between data points. Common distance metrics include Euclidean distance, cosine similarity, etc. These metrics help determine the relative relationships between data objects in the lower-dimensional space. For instance, in text processing, cosine similarity between words can reflect their semantic similarity.
[0128] 4. Semantic quantification and comparison. Traditional comparisons of language, image, and audio data can be challenging to quantify directly due to their complex and high-dimensional nature, and varied data formats. Embedding techniques map these different data formats into vector space, allowing comparisons and analyses of semantic features through vector distances and similarities. This approach overcomes the difficulties of direct comparisons found in traditional methods.
[0129] Embedding can be represented by a vector. Each element within this vector could be represented by a floating-point number.
[0130] Embedding data can have one or more of the following interesting properties.
[0131] 1. Different elements in an embedding vector may correspond to different features. For certain downstream tasks, some features are irrelevant, so the corresponding elements might be less critical. Therefore, for a certain downstream task, puncturing (remove or zeros out) some elements from embedding representation will not have significant influence on the task performance.
[0132] 2. The same features can be represented at different elements within an embedding vector. Essentially, embeddings encode features in a way that allows it to be expressed across various elements. Therefore, for a certain downstream task, embedding compression is possible. For example, puncturing (removing or zeros out) some elements from embedding representation will not have significant influence on the task performance. But retaining all the elements of embedding will increase the task performance.
[0133] 3. In embedding space, vectors that are close to each other typically convey similar information. Therefore, minor transmission errors might not significantly impact downstream tasks. Therefore, minor errors introduced in embeddings will not have a significant influence on the task performance. This means that channel coding may not be needed when channel status is very good (CQI is high) .
[0134] 4. There are specialized training methods for embedding generation that can produce a series of embeddings with different lengths to represent the similar meanings. Longer embedding can capture and express more detailed features. One example of the nested embedding is embedding training by Matryoshka representation learning. Therefore, for a certain downstream task, effective communication is not about the length, longer embeddings are not always better. For example, in a recommendation system, shorter embeddings might be sufficient to capture user requirements and provide accurate recommendations. These shorter embeddings can effectively distill the essential features needed to understand user requirement and user preference. However, longer embeddings might incorporate too many features, which could overwhelm the system and lead to confusion. This excess information can dilute the relevance of the recommendations, ultimately resulting in less clear and less accurate suggestions.
[0135] 5. Each element in an embedding vector can be represented by a floating-point number. Different levels of precision (such as 64-bit floating, 32-bit floating, 16-bit floating, or only using 4-bit to represent each element) can convey similar features with higher precision likely representing more detailed features. This is similar to the example discussed earlier about embedding length. Higher precision is not always better, it just needs to be sufficient. For downstream tasks, it’s also not about providing as many features as possible. Instead, the goal is to provide just enough features to meet the requirements of the downstream task. Sometimes, overloading the system with excessive features can lead to inefficiencies and confusion, ultimately hindering performance rather than enhancing it.
[0136] 6. For the bit representation of a floating-point number of each element, the transmission quality requirements vary depending on the position. For example, the exponent part demands higher transmission quality. If there is an error in the exponent part, the value of the entire element can deviate significantly. However, if there is an error in the least significant bit (LSB) of the mantissa, the entire element might still be usable. Therefore, in physical layer transmission, it is possible to selectively use channel coding to protect certain positions rather than all positions. This selective approach allows for more efficient use of resources by focusing error correcting efforts on the most critical parts of the data. By doing so, the system can maintain low latency, high performance and reliability without the overhead of protecting every single bit, which can be unnecessary and resource-intensive.
[0137] 7. For many real-time applications, the latency of embedding transmission is a crucial factor.
[0138] 8. In real-time tasks, if an embedding transmission error is detected, it is often more practical to discard the error data rather than retransmit it, and simply transmit new data.
[0139] 9. The ultimate goal of embeddings can be to serve downstream tasks. As long as the downstream tasks can accept the given expression of embeddings (e.g., length, compression, and precision) , the transmission can be considered successful.
[0140] In some implementations, embedding is a type of intermediate data that only AI can understand. Humans may need AI to translate embeddings into textual information for comprehension. For example, by asking questions from different perspectives, humans can extract various pieces of information from the embedding.
[0141] Furthermore, different embeddings can be quickly compared to measure their similarity. This allows for a rapid assessment of whether embeddings are related or unrelated.
[0142] Based on the above discussion, the effectiveness of embeddings can be crucial for downstream tasks. In some implementations, embeddings are not always better when they are longer or more precise; they just need to be sufficient for the downstream task. The environment is constantly changing, and the requirements of some downstream tasks can change rapidly too, especially those with high latency demands. Therefore, the ability to quickly adjust the expression of embeddings and their channel coding methods can be highly beneficial for task execution.
[0143] Consequently, transmitting embeddings directly as known and interpretable data (e.g., content-aware) at the lower layer is essential, which is also referred to as content-aware transmission of embedding. It offers one or more of the following benefits.
[0144] Error tolerance: The inherent characteristics of embeddings provide a certain level of error tolerance. Therefore, in some cases, it is feasible to transmit embeddings without channel coding, simplifying the transmission process.
[0145] Efficiency: Embeddings that represent the same entity or concept could have variable lengths and different precision. If the lower layer can understand the difference in different representations, it will significantly simplify the embedding data transmission and reduce both the amount of data transmitted and the latency.
[0146] Error handling: Transmission errors introduced by the channel in embeddings may be acceptable. Since the physical layer has a better understanding of channel conditions, it can more quickly adjust both the embedding representation itself and the transmission method.
[0147] Adaptive transmission: CQI mechanisms can only adjust the transmission method (such as Modulation and Coding Scheme, MCS) and transmission power, but not the data. However, channel quality directly affects embedding data attributes (such as length and precision) . Thus, if the physical layer directly understands embeddings, it can more effectively adjust both the embedding data expression itself and the transmission method.
[0148] The embedding mentioned above is just an example to illustrate semantic data. All the analysis and explanations are applicable to other types of semantic data as well.
[0149] Due to the significant differences between embedding data and other data types, it can be essential to treat embeddings as a new data type in communication systems. It’s necessary to redesign the lower layer (e.g., physical layer and MAC layer) to accommodate both the characteristics of embedding data expression itself and the methods of transmitting it (such as MCS) . The goal is to ensure that embedding data transmission is more effective and with lower latency, while also guaranteeing the reliable transmission of the semantics to meet the requirements of downstream tasks.
[0150] Traditional CQI mechanisms focus solely on the quality of the physical layer signal, neglecting the semantic content of the transmitted information. This approach fails to accurately reflect the transmission quality of embedding information in AI applications. Given the crucial role that embedding information plays in the parsing and execution of AI tasks, existing evaluation metrics need to be improved.
[0151] CQI is a parameter and metric that measures the channel quality between the gNB and UE, reflecting the transmission quality of the wireless signal, such as signal strength, noise level, and interference. Traditional communication systems allocate resources like bandwidth, power, and time slots based on CQI quality and current Quality of Service (QoS) requirements.
[0152] However, for AI applications, especially those involving semantic data (e.g., embeddings) , relying solely on CQI to allocate resources may be insufficient. Besides channel quality, the effectiveness of the information carried in each transmission is also critical. For instance, in the case of a very simple downstream task, short embeddings with low precision might be sufficient to meet the requirements. In such scenarios, there is no need to opt for longer and higher precision embeddings. On the other hand, for a complex downstream task, short and low precision embeddings would not yield good performance. In these cases, it is advisable to choose longer embeddings with higher precision. To elaborate further, the choice of embedding length and precision is crucial and should be tailored to the specific needs of the task at hand. Simple tasks, such as basic text classification or sentiment analysis, often do not require extensive detail and can perform adequately with shorter embeddings. Conversely, more complex tasks, such as machine translation, question answering, or detailed content generation, demand a higher level of detail and accuracy. In these instances, longer embeddings with higher precision are necessary to capture the nuanced information and intricate patterns within the data. This ensures that the model can perform at its best, providing accurate and reliable results.
[0153] Therefore, the effectiveness quality indicator (EQI) is introduced to evaluate semantic data. EQI is a new metric that assesses the quality of semantic data to reflect the effectiveness of the transmitted information. EQI focuses more on the semantic similarity, information completeness, and task relevance of the received semantic data, providing a more accurate reflection of the effectiveness of embedding transmissions.
[0154] In summary, EQI can allow for adjustment of embedding data expression. In some implementations, combining CQI and EQI allows for the adjustment of both the embedding data expression and embedding data transmission methods.
[0155] Given the distinct nature of semantic data (e.g., embeddings) compared to the data typically handled by current wireless communication systems, embeddings can be treated as a new type of data for transmission. The base station (e.g., gNB) or terminals can obtain the raw content of the semantic data during transmission and interpret its meaning.
[0156] EQI (Effectiveness Quality Indicator) is a metric used to measure the effectiveness of semantic information expression. It can be assessed by, for example, the semantic similarity, information completeness, and task relevance of semantic data (such as embeddings) after it has been transmitted through the channel. EQI can be measured and reported by both the user equipment (UE) and the gNB.
[0157] Based on the received EQI feedback, both the UE and the gNB can dynamically adjust the length, puncture scheme, precision, and other factors of the semantic data to achieve more efficient and reliable embedding information transmission.
[0158] EQI measures the effectiveness quality of the transmitted embeddings. It helps the sender in adjusting subsequent embedding. The calculation of EQI can include one or more of the following aspects.
[0159] 1. Relevance to target task. Task-specific evaluation metric can be used to assess the performance of embeddings. The evaluation metric includes accuracy, precision, recall, F1-score, etc. For example, in a classification task, if none of the categories has a significantly higher probability than the others, it indicates that the classification is ambiguous. This suggests that the model is not confidently distinguishing between the categories, leading to a less clear-cut classification and a lower EQI value. In the mentioned example, there are many methods to transmit the ambiguous level of classification to a numerical value, such as by applying a sigmoid function or softmax function.
[0160] 2. Information completeness. Information completeness can be crucial for several types of tasks, particularly those that rely heavily on nuanced and comprehensive data representations. Downstream task performance could be used to evaluate it. For example, in an information retrieval task, if the user feels like the results haven’ t covered all his requirements, it means a better embedding needs to be used to represent the full spectrum of meanings and contexts of search queries. In this case, a lower EQI value will be given. There are many simple criteria to convert user feedback into numerical expressions or provide directions for future adjustments. For example, the term “UP” could indicate the need for more precise embedding representations.
[0161] 3. Content consistency. In certain scenarios, semantic content changes slowly. Using statistical algorithms to compare the current semantic content with previously collected data could be used. If the embedding content remains consistent with historical data after the comparison, the EQI value will be higher, indicating high information transmission effectiveness. Significant changes in content over time, such as shifts in topic or context, will reduce the EQI value, reflecting potential information anomalies or abrupt changes.
[0162] 4. Reference check. A target embedding vector can be predefined for a certain task. By computing similarity measures (such as cosine similarity or Euclidean distance) between received embedding and target embedding, an EQI measure is obtained. A higher similarity score can indicate higher relevance and higher EQI value, and vice versa.
[0163] Each of the points mentioned above can be expanded to get a numerical calculation method for EQI calculation. They can also be expanded to get direction indication or descriptive language for EQI adjustment indication in the future. In practical EQI calculations, a single point may be focused on, or the values derived from different points may be combined, weighting them proportionally to produce a final EQI value.
[0164] In the system, UE and gNB can negotiate and align on the EQI calculation method. For instance, if more emphasis is placed on task relevance, the weight of the “relevance to target task” parameter in the EQI calculation can be increased while reducing the weight of “content consistency. ”
[0165] EQI can be expressed in various forms, and the following show some examples.
[0166] Numerical value: EQI can be expressed as a numerical value, which is derived based on the calculation of EQI mentioned above.
[0167] Rating scale: EQI can be expressed as a rating scale, such as 32 levels ranging from 0 to 31. A higher value indicates better effectiveness quality.
[0168] Direction indicator: EQI can be expressed using adjustment directions, such as “UP” to indicate the need to increase effectiveness quality and “DOWN” to decrease effectiveness quality.
[0169] Descriptive language: EQI can be described by human language. For example, "Suitable for the task, but higher precision would be better" .
[0170] For embedding data, the following parameters can be adjusted, length of embedding, compression scheme of embedding, precision of embedding, and channel coding scheme for the embedding.
[0171] The length of embedding may be adjusted. During a training phase, embeddings of different lengths can be trained to represent the same information. Longer embeddings will capture more detailed features. Shorter embeddings will capture less detailed features.
[0172] For example, by using Matryoshka representation learning, information could be represented by embeddings with different granularities. This approach allows a single embedding (this embedding could be shortened to different lengths) to adapt to the requirement of various downstream tasks. In tasks like ImageNet classification, if shorter embeddings can’ t achieve good performance, longer embeddings which can capture more detailed features could be used to achieve higher accuracy. In large-scale retrieval systems, such as those used in search engines, if longer embeddings can’ t meet the latency requirement, shorter embeddings could be used to speed up the retrieval process without a substantial loss in performance. For tasks with limited data, like few-shot classification, if shorter embeddings can’ t achieve a good result, longer embeddings could be used to improve accuracy by capturing more nuanced information.
[0173] The compression scheme of embedding may be adjusted. Embedding vectors can be compressed by many methods such as principal component analysis (PCA) , singular value decomposition (SVD) or puncturing.
[0174] Taking “puncturing” as an example, embedding vectors can be “punctured, ” which typically means selectively zeroing out or removing certain elements of the vectors. This can be very useful for various purposes, such as reducing the dimensionality of the vector or focusing on specific features. For example, if an embedding vector has 6 elements and represents a sentence, this vector can be “punctured” by zeroing out certain elements in the vector (such as the 1st or 5th element) , the punctured embedding vector can still be used in downstream tasks but with a reduced focus on elements that have been zeroed out.
[0175] Puncturing can help reduce the size of embedding, making transmission more efficient without significantly losing important information.
[0176] The precision of embedding may be adjusted. In the context of embedding, element precision refers to the numerical accuracy of each element within the embedding vector. This precision can vary, typically represented in terms of floating-point formats like 32-bit, 16-bit, 8-bit or higher or lower bits.
[0177] Higher precision is generally used in scenarios where accuracy is critical, such as financial analysis and high-stakes machine learning tasks. It can provide more accurate and detailed representations, which can improve the performance of AI tasks, especially in tasks requiring fine-grained distinctions.
[0178] Lower precision is commonly used in scenarios where latency is critical or environments with limited resources, such as real-time inference and edge computing. Lower precision can enable faster processing and handle larger datasets.
[0179] For example, in tasks like medical diagnosis, if lower precision can’ t achieve good performance, higher precision embedding is needed to ensure it captures all necessary details. In tasks like recommendation systems, if higher precision can’ t meet the latency requirement, a lower precision representation of embedding will be used to provide quick suggestions without significant loss of performance.
[0180] The channel coding scheme may be adjusted. From a physical layer perspective, the channel coding scheme can also be adjusted to protect only specific parts of the embedding bit stream. For instance, it might be chosen to protect only the exponential bits or the exponential bits along with a portion of the mantissa bits. This selective protection approach allows channel coding schemes to focus error correction resources on the most critical parts of the data, thereby enhancing efficiency and performance.
[0181] To achieve more effective information transmission, the gNB can use EQI to dynamically adjust embedding content including embedding length, embedding precision, embedding compression scheme and channel coding scheme. In the following analysis, a high EQI value means good effectiveness of embedding, and a low EQI value means bad effectiveness of embedding.
[0182] High EQI values can mean that the current embedding length, embedding precision and embedding compression scheme are good and have already achieved good performance in downstream tasks. Shorter embedding length, lower embedding precision, higher compression scheme (e.g., puncturing more elements) or protecting fewer bits in channel coding could be tried in the future transmission.
[0183] Low EQI values can mean that the current embedding length, embedding precision and embedding compression scheme are not good enough and cannot achieve good performance in downstream tasks. Longer embedding length, higher embedding precision, lower embedding compression scheme, or protecting more bits in channel coding may need to be used in the future transmission.
[0184] In some conditions, EQI and CQI could be considered together to dynamically adjust embedding content and embedding transmission method. MCS, transmission power, and resource allocation can be adjusted based on the received CQI, and embedding length, embedding precision and embedding compression scheme can be adjusted based on EQI feedback. In some implementations, the factors affected by EQI may be adjusted first and then the factors affected by CQI can be adjusted. In some implementations, the factors affected by CQI may be adjusted first and then the factors affected by EQI can be adjusted. In some implementations, the factors affected by EQI or CQI may be adjusted together (also referred to as mixed adjustment) . The following are examples of mixed adjustment.
[0185] High EQI and High CQI: A high CQI means the channel status is very good. A high EQI means effectiveness of embedding is very good. This is a very ideal situation. In this condition, a higher modulation scheme, protecting less bits in channel coding, lowering coding rate or decreasing power to keep data rates may be used, meanwhile decreasing embedding length, decreasing embedding precision or increasing compression scheme for more efficient transmission.
[0186] Low EQI but High CQI: A high CQI means the channel status is very good. A low EQI means the effectiveness of embedding is not good. Since CQI is high, low EQI is not caused by errors introduced in transmission. In this condition, increasing embedding length, increasing embedding precision or decreasing embedding compression may be used to add more features for downstream tasks.
[0187] High EQI but Low CQI: A low CQI means the channel status is not that good and may introduce a lot of errors to EQI transmission. But a high EQI is still possible, which means the transmitted embedding includes more than required features for downstream tasks. At least one of protecting more bits in channel coding scheme, decreasing MCS, increasing power or adding redundancy or retransmit may be used to ensure reliable transmission, while decreasing embedding length, decreasing embedding precision or increasing compression to alleviate system burden.
[0188] Low EQI and Low CQI: In this condition, low EQIs may be caused by poor channel conditions. In this condition, ensuring reliable transmission may be used first by using at least one of adopting a conservative approach, protecting all bits in channel coding scheme, lowering MCS or increasing transmission power. Then increasing embedding length, increasing embedding precision and decreasing embedding compression to improve embedding effectiveness may be used.
[0189] In some implementations, the modules used in the EQI and CQI based adaptive transmission can include one or more gNBs and one or more UEs.
[0190] The gNB (s) can be responsible for controlling and managing the wireless network, including scheduling, resource allocation, and transmission power control. For example, the gNB receives EQI and CQI information reported by the UE and adjusts the embedding expression (e.g., embedding length, embedding precision and embedding compression method) and the embedding transmission method (e.g., channel coding scheme including how many bits to protect in embedding data, MCS, power and resource allocation) . The gNB is also responsible for negotiating and aligning the EQI definition with the UE and computing the downlink EQI to report back to the UE.
[0191] The UE (s) can receive embedding information sent by the gNB, compute the EQI based on the received information, and report this EQI back to the gNB. The UE also participates in the process of aligning the EQI definition and reports traditional CQI information, while receiving uplink EQI sent by the gNB and adjusting its embedding expression.
[0192] In some implementations, the following channels may be used to fulfill the functions mentioned above. For example, a physical uplink control channel (PUCCH) is used to transmit uplink EQI, CQI information, and EQI definitions. Simultaneously, a physical downlink control channel (PDCCH) can handle the transmission of downlink EQI information. This approach optimizes the use of current channel resources, facilitating the implementation and management of EQI within the existing network framework.
[0193] In some implementations, PUCCH can be used for the UE to transmit control information to the gNB, including downlink EQI and CQI.
[0194] In some implementations, PDCCH can be used for the gNB to transmit control information to the UE, including uplink EQI.
[0195] In some implementations, Physical Downlink Shared Channel (PDSCH) can be used for the gNB to transmit data information to the UE, including embedding data.
[0196] In some implementations, the Medium Access Control (MAC) Layer can be responsible for controlling access to the shared channel by multiple UEs and conducting data transmission based on the gNB's scheduling instructions.
[0197] In some implementations, a new channel could be introduced to improve the performance. As semantic data and embedding technologies advance, future networks may introduce dedicated physical channels specifically designed for the transmission of semantic embeddings or other types of semantic data. In this evolving scenario, EQI will be enhanced by integrating CQI metrics to evaluate not only the correlation and integrity of the semantic content but also the overall quality of the communication channel. This integration will facilitate more precise and efficient communication, significantly improving network performance and user experience in future network environments.
[0198] The procedures for the EQI and CQI based adaptive transmission may include one or more of gNB initiated negotiation procedure of EQI, UE initiated negotiation procedure of EQI, embedding data transmission from UE to gNB, and embedding data transmission from gNB to UE.
[0199] FIG. 6 shows an example negotiation procedure 600, which illustrates a gNB initiated negotiation procedure for EQI. The procedure 600 can be performed by a UE (e.g., the ED 110 of FIGS. 1-2) and a gNB (e.g., the network node 170 of FIGS. 1-2).
[0200] In some implementations, the calculation of EQI can be highly dependent on the nature of the downstream tasks. Therefore, different downstream tasks may require different methods for calculating EQI. For example, the weighting of various factors (e.g., relevance to a target task, information completeness, content consistency, etc. ) might differ depending on the specific requirements of each task. This means that the importance assigned to each factor in the EQI calculation can vary, ensuring that the embeddings are optimized for the particular characteristics and demands of the downstream task.
[0201] In some implementations, before embedding data transmission from the UE to the gNB, the gNB can initiate negotiation and alignment of the EQI calculation method with the UE.
[0202] For example, as shown in FIG. 6, the procedure 600 includes the following steps.
[0203] At 602, the gNB sends information indicating an embedding quality measurement method to the UE. Accordingly, the UE receives the information indicating the embedding quality measurement method from the gNB. The embedding quality measurement method can be used to determine or measure an embedding quality indicator. The embedding quality indicator is a metric used to measure the effectiveness of semantic information expression. In some implementations, the embedding quality indicator includes an Effectiveness Quality Indicator (EQI) described in the present disclosure. In some implementations, the embedding quality measurement method can also be referred to as an EQI measurement method. The embedding quality measurement method can include weightings of different factors (e.g., relevance to a target task, information completeness, content consistency, and reference check) as described above.
[0204] In some implementations, the embedding quality measurement method indicates a weighted combination of at least one of:a first metric measuring a relevance level of embedding data with respect to a target task; a second metric measuring a level of information completeness of embedding data with respect to the target task; a third metric measuring content consistency between semantic content of current embedding data and semantic content of historic embedding data; or a fourth metric measuring a similarity between embedding data and an embedding reference (e.g., as described above with reference to the calculation of EQI) . In some implementations, the weighted combination includes an average or an evenly weighted combination of two or more of these metrics. Alternatively, the weighted combination can be only one of these metrics. In other words, only one of these metrics is selected, assigning zero weights to the other unselected metrics.
[0205] At 604, the UE transmits a response to the information indicating the embedding quality measurement method to the gNB. Accordingly, the gNB receives the response to the information indicating the embedding quality measurement method from the UE. In other words, the UE can confirm the reception of the embedding quality measurement method (e.g., the EQI measurement method) at 604.
[0206] In some implementations (for example, when the UE does not support the embedding quality measurement method) , the response can include a suggestion to use another embedding quality measurement method. The gNB can transmit a message to the UE to indicate whether the gNB accepts the embedding quality measurement method proposed by the UE.
[0207] FIG. 7 shows an example negotiation procedure 700, which illustrates a UE initiated negotiation procedure for EQI. The procedure 700 can be performed by a UE (e.g., the ED 110 of FIGS. 1-2) and a gNB (e.g., the network node 170 of FIGS. 1-2) .
[0208] In some implementations, before embedding data transmission from the gNB to the UE, the UE can initiate negotiation and alignment of the EQI calculation method with the gNB.
[0209] For example, as shown in FIG. 7, the procedure 700 includes the following steps.
[0210] At 702, the UE sends information indicating an embedding quality measurement method to the gNB. Accordingly, the gNB receives the information indicating the embedding quality measurement method from the UE. In some implementations, the embedding quality measurement method can also be referred to as an EQI measurement method. The embedding quality measurement method can include weightings of different factors (e.g., relevance to a target task, information completeness, content consistency, and reference check) as described above.
[0211] At 704, the gNB transmits a response to the information indicating the embedding quality measurement method to the UE. Accordingly, the UE receives the response to the information indicating the embedding quality measurement method from the gNB. In other words, the gNB can confirm the reception of the embedding quality measurement method (e.g., the EQI measurement method) at 704. In some implementations (for example, when the gNB doesn’ t support the embedding quality measurement method) , the response can include a suggestion to use another embedding quality measurement method. The UE can transmit a message to the gNB to indicate whether the UE accepts the embedding quality measurement method proposed by the gNB.
[0212] FIG. 8 shows an example procedure 800 for embedding data transmission from a UE to a gNB. The procedure 800 can be performed by a UE (e.g., the ED 110 of FIGS. 1-2) and a gNB (e.g., the network node 170 of FIGS. 1-2) .
[0213] As shown in FIG. 8, the procedure 800 includes the following steps.
[0214] At 802, the UE transmits first embedding data to the gNB. Accordingly, the gNB receives the first embedding data from the UE. In some implementations, the UE transmits the first embedding data (e.g., embedding information) to the gNB via the PUSCH or a new dedicated embedding channel. In some implementations, the UE transmits the first embedding data to the gNB via any suitable channel (e.g., as described in the present disclosure) . In some implementations, the original embedding representation and transmission method can be defined by the gNB and communicated to the UE (e.g., before 802) .
[0215] The gNB can receive and decode the embedding information (e.g., from the first embedding data, not shown in FIG. 8) .
[0216] In some implementations, the gNB can determine an embedding quality indicator (e.g., an EQI) based on the first embedding data (not shown in FIG. 8) . The embedding quality indicator can take one of the following formats (e.g., as described above with reference to the various forms of EQI) : a numerical value; a scale indicator; a direction indicator indicating whether to increase or decrease an embedding quality; or a description in natural language.
[0217] Determining the embedding quality indicator can include determining the embedding quality indicator based on the first embedding data and an embedding quality measurement method. For example, the gNB can calculate an uplink EQI based on the received embedding information (e.g., determined from the first embedding data) and the agreed EQI calculation method. The embedding quality measurement method (e.g., the agreed EQI calculation method) can be determined, for example, according to the procedures described with reference to FIGS. 6-7. In some implementations, the gNB also calculates a CQI. For example, the CQI can include, but is not limited to, signal-to-noise ratio (SNR) , signal-to-interference-plus-noise ratio (SINR) , reference signal received quality (RSRQ) , reference signal received power (RSRP) , bit error rate (BER) , block error rate (BLER) , or any other suitable traditional CQIs. In some implementations, in the procedure 800, the gNB transmits the embedding quality indicator to the UE.For example, the embedding quality indicator is carried in a physical layer signaling.
[0218] At 804, the gNB can transmit an embedding adjustment to the UE. Accordingly, the UE can receive the embedding adjustment from the gNB. In some implementations, the embedding adjustment can be determined (e.g., by the gNB) based on the embedding quality indicator. In some implementations, the embedding adjustment can be determined (e.g., by the gNB) based on the embedding quality indicator and / or the CQI (e.g., as described above with reference to the mixed adjustment) . In some implementations, from the UE’s perspective, receiving the embedding adjustment (determined based on the embedding quality indicator) from the gNB can be considered as receiving information indicating the embedding quality indicator. In some other implementations, receiving the embedding quality indicator from the gNB can be considered as receiving information indicating the embedding quality indicator.
[0219] In some implementations, the embedding adjustment includes a change to at least one of the following embedding representation parameters: an embedding length, an embedding precision level, a channel coding scheme for embedding, or a compression scheme for embedding. In some implementations, the embedding adjustment can further include a change to the embedding transmission method. For example, the embedding adjustment can indicate a different channel to be used to carry the embedding data.
[0220] Thus, the gNB can adjust the uplink embedding representation and transmission method according to received EQI and CQI. The gNB can inform the UE of these adjustments (e.g., at 804) via a PDCCH channel or another broadcast or dedicated channel.
[0221] Accordingly, the UE receives the embedding adjustment (e.g., the new embedding representation and transmission method) indicated by the gNB (e.g., at 804) .
[0222] At 806, the UE transmits second embedding data to the gNB. The second embedding data can include the embedding adjustment. In some implementations, the second embedding data including the embedding adjustment means that at least one of an embedding representation parameter or an embedding transmission method (e.g., as described above) has changed. In some implementations, the UE applies the embedding adjustment (e.g., the new embedding representation and transmission method) indicated by gNB to determine embedding information (e.g., the second embedding data) and transmits embedding information to the gNB via the PUSCH or a new dedicated embedding channel.
[0223] FIG. 9 shows an example procedure 900 for embedding data transmission from a gNB to a UE. The procedure 900 can be performed by a UE (e.g., the ED 110 of FIGS. 1-2) and a gNB (e.g., the network node 170 of FIGS. 1-2) .
[0224] As shown in FIG. 9, the procedure 900 includes the following steps.
[0225] At 902, the gNB transmits first embedding data to the UE. Accordingly, the UE receives the first embedding data from the gNB. In some implementations, the gNB transmits the first embedding data (e.g., embedding information) to the UE via the PDSCH or a dedicated embedding channel. Alternatively, the first embedding data may be transmitted through any suitable downlink channel configured for embedding transmissions.
[0226] The UE can receive and decode the embedding information (not shown in FIG. 9) .
[0227] The UE can determine an embedding quality indicator (e.g., an EQI) based on the first embedding data (not shown in FIG. 9) . The embedding quality indicator can be in one of the following formats (e.g., as described above with reference to the various forms of EQI) : a numerical value; a scale indicator; a direction indicator indicating whether to increase or decrease an embedding quality; or a description in natural language.
[0228] In some implementations, determining the embedding quality indicator can include determining the embedding quality indicator based on the first embedding data and an embedding quality measurement method. For example, the UE calculates a downlink EQI based on the received embedding information and the agreed EQI calculation method. In some implementations, the UE can also calculate a traditional CQI.
[0229] At 904, the UE transmits the embedding quality indicator to the gNB. Accordingly, the gNB can receive the embedding quality indicator from the UE. In other words, the UE can report the downlink EQI to the gNB via the PUCCH or a dedicated channel. In some implementations, the UE can report the CQI to the gNB. The downlink EQI and CQI can be carried via the same channel or via different channels. Accordingly, the gNB can receive the downlink EQI and CQI information reported by the UE (e.g., at 904) .
[0230] In some implementations (not shown in FIG. 9) , the gNB can determine an embedding adjustment based on the embedding quality indicator. In some implementations, the embedding adjustment can be determined (e.g., by the gNB) based on the embedding quality indicator and the CQI (e.g., as described above with reference to the mixed adjustment) .
[0231] At 906, the gNB transmits second embedding data to the UE. The second embedding data can include the embedding adjustment. In other words, the gNB can adjust the embedding representation and transmission of the second embedding data (e.g., applying the embedding adjustment to the second embedding data) according to the received EQI and / or CQI.
[0232] While the procedures in FIGS. 6-9 are 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, these procedures can be applied to other instances of network nodes and terminal devices or equivalents thereof. For example, the procedures 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) , a CU and a DU, two CUs, or two DUs. It is understood that steps or operations shown in these procedures 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 FIGS. 6-9.
[0233] In addition, optional solutions shown in the following for more efficient EQI transmission may be applied to the procedures in FIGS. 6-9.
[0234] In some implementations, EQI quantization can be used to minimize transmission overhead. In other words, EQI data can be quantized. This technique can reduce the data volume, leading to improved transmission efficiency and lower bandwidth usage. By simplifying the data representation, quantization also helps in managing network resources more effectively.
[0235] In some implementations, an EQI reporting mechanism can be configured to be continuous, periodic, or event-triggered based on specific intervals. This flexibility allows for real-time network adjustments and optimizations, ensuring that the network adapts to changes in channel quality promptly and effectively.
[0236] In some implementations, EQI reports can be enriched with detailed content, including specific spectrum information, various metrics, and other relevant data. Such comprehensive reporting can offer a clearer and more accurate depiction of channel quality, aiding in better decision-making and network management.
[0237] In some implementations, EQI prediction (e.g., AI-based EQI prediction by leveraging AI technologies, such as machine learning) can be performed by both gNB and UE. Based on these predictions, transmission parameters can be adjusted in advance, optimizing network performance and user experience.
[0238] 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.
[0239] 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.
[0240] 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.
[0241] 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.
[0242] 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.
[0243] 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.
[0244] 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.
[0245] 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.
[0246] 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.
[0247] 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
1.A method comprising:receiving first embedding data; anddetermining an embedding quality indicator based on the first embedding data.2.The method of claim 1, further comprising:determining an embedding adjustment based on the embedding quality indicator; andtransmitting the embedding adjustment.3.The method of claim 1 or claim 2, further comprising:transmitting the embedding quality indicator.4.The method of claim 3, further comprising:receiving second embedding data, wherein the second embedding data comprises an embedding adjustment.5.The method of any one of claims 1-4, further comprising:receiving information indicating an embedding quality measurement method.6.The method of claim 5, further comprising:transmitting a response to the information indicating the embedding quality measurement method, wherein determining the embedding quality indicator comprises determining the embedding quality indicator based on the first embedding data and the embedding quality measurement method.7.The method of claim 5, wherein the embedding quality measurement method indicates a weighted combination of at least one of:a first metric measuring a relevance level of embedding data with respect to a target task;a second metric measuring a level of information completeness of embedding data with respect to the target task;a third metric measuring content consistency between semantic content of current embedding data and semantic content of historic embedding data; ora fourth metric measuring a similarity between embedding data and an embedding reference.8.The method of any one of claims 1-7, wherein the embedding quality indicator is in one of the following formats:a numerical value;a scale indicator;a direction indicator indicating whether to increase or decrease an embedding quality; ora description in natural language.9.The method of any one of claims 3 to 8, wherein the embedding quality indicator is carried in a physical layer signaling.10.The method of claim 2 or claim 4, wherein the embedding adjustment comprises a change to at least one of the following embedding parameters:an embedding length;an embedding precision level;a channel coding scheme for embedding; ora compression scheme for embedding.11.The method of claim 2, wherein determining the embedding adjustment comprises:determining the embedding adjustment based on the embedding quality indicator and a channel quality indicator (CQI) .12.A method comprising:transmitting first embedding data; andobtaining information indicating an embedding quality indicator.13.The method of claim 12, wherein obtaining the information indicating the embedding quality indicator comprises:receiving the embedding quality indicator.14.The method of claim 13, further comprising:determining an embedding adjustment based on the embedding quality indicator; andtransmitting second embedding data based on the embedding adjustment.15.The method of any one of claims 12-14, further comprising:transmitting information indicating an embedding quality measurement method; andreceiving a response to the information indicating the embedding quality measurement method.16.The method of claim 15, wherein the embedding quality measurement method indicates a weighted combination of at least one of:a first metric measuring a relevance level of embedding data with respect to a target task;a second metric measuring a level of information completeness of embedding data with respect to the target task;a third metric measuring content consistency between semantic content of current embedding data and semantic content of historic embedding data; ora fourth metric measuring a similarity between embedding data and an embedding reference.17.The method of any one of claims 12 to 16, wherein the embedding quality indicator is in one of the following formats:a numerical value;a scale indicator;a direction indicator indicating whether to increase or decrease an embedding quality; ora description in natural language.18.The method of any one of claims 12 to 17, wherein the embedding quality indicator is carried in a physical layer signaling.19.The method of claim 14, wherein the embedding adjustment comprises a change to at least one of the following embedding parameters:an embedding length;an embedding precision level;a channel coding scheme for embedding; ora compression scheme for embedding.20.The method of claim 14, wherein determining the embedding adjustment comprises:determining the embedding adjustment based on the embedding quality indicator and a channel quality indicator (CQI) .21.An apparatus, configured to perform the method of any one of claims 1-11 or any one of claims 12-20.22.An apparatus comprising:a receiving unit configured to receive first embedding data; anda processing unit configured to determine an embedding quality indicator based on the first embedding data.23.An apparatus comprising:a transmitting unit configured to transmit first embedding data; anda processing unit configured to obtain information indicating an embedding quality indicator.24.An apparatus comprising:an interface circuit configured to receive first embedding data; andone or more processors configured to determine an embedding quality indicator based on the first embedding data.25.An apparatus comprising:an interface circuit configured to transmit first embedding data; andone or more processors configured to obtain information indicating an embedding quality indicator.26.The apparatus of claim 24 or claim 25, wherein the interface circuit comprises one or more transceivers.27.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 1-11 or any one of claims 12-20.28.A communication system, wherein the communication system comprises a first apparatus configured to perform the method of any one of claims 1-11 and a second apparatus configured to perform the method of any one of claims 12-20.29.A non-transitory computer-readable storage medium having instructions stored thereon which, when executed by an apparatus, cause the apparatus to perform the method of any one of claims 1-11 or any one of claims 12-20.30.A computer program product comprising instructions which, when executed, cause an apparatus to perform the method of any one of claims 1-11 or any one of claims 12-20.
Citation Information
Patent Citations
Semantic communication method and device, electronic equipment and storage medium
CN114885370A
Full-reference video quality evaluation method based on semantic communication and network channel parameters
CN118158388A
Communication method, terminal, network device, electronic device and medium
CN118233047A
Resource selection for transmission of pending data unit
US20220294576A1
Semantic compression for compute offloading
US20240121453A1