Method and apparatus of supporting artificial intelligence (AI) applications in wireless communications
By integrating AI-based JSCC encoders and decoders with digital modulation to process sensory data alongside sensing reference signals, the system effectively identifies and tracks targets with reduced overhead, addressing inefficiencies in existing wireless communication systems.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- LENOVO (BEIJING) LTD
- Filing Date
- 2025-07-15
- Publication Date
- 2026-05-07
AI Technical Summary
Existing wireless communication systems face challenges in identifying and tracking targets with radio signals alone, particularly in integrated sensing and communication systems, as they struggle to determine the category and status of sensed targets effectively, leading to inefficiencies and increased communication overhead.
The integration of AI-based joint source-channel coding (JSCC) encoders and decoders, combined with digital modulation, processes input data from cameras and other sensors to generate semantic data, which is transmitted alongside sensing reference signals, enabling better target identification and tracking with reduced overhead.
This approach allows for improved target identification and tracking with reduced communication overhead by leveraging AI models to process sensory data, enhancing the accuracy and efficiency of integrated sensing and communication systems.
Smart Images

Figure CN2025108611_07052026_PF_FP_ABST
Abstract
Description
METHOD AND APPARATUS OF SUPPORTING ARTIFICIAL INTELLIGENCE (AI) APPLICATIONS IN WIRELESS COMMUNICATIONSTECHNICAL FIELD
[0001] The present disclosure relates to wireless communications, and more specifically to techniques of supporting artificial intelligence (AI) applications in wireless communications.BACKGROUND
[0002] A wireless communications system may include one or multiple network communication devices, such as base stations, which may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE) , or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like) . Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G) ) .SUMMARY
[0003] An article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a, ” “at least one, ” “one or more, ” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of” or “one or more of” or “one or both of” ) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C) . Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on. Further, as used herein, including in the claims, a “set” may include one or more elements.
[0004] Some implementations of the methods and apparatuses described herein may further include a UE for wireless communication, which may include: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the UE to: receive, from a network equipment (NE) , subframe configuration and sensing reference signal configuration both associated with a sensing service request; and send, to the NE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by an AI function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration
[0005] In some implementations of the methods and apparatuses described herein, the data in the radio subframes is sent via physical uplink shared channel (PUSCH) indicated by uplink control information (UCI) or via a predefined or configured physical channel different from the PUSCH.
[0006] In some implementations of the methods and apparatuses described herein, the sensing reference signals and the radio subframes are associated by configured identity (ID) information, and the ID information is same as or different from ID information of the radio subframes.
[0007] In some implementations of the methods and apparatuses described herein, the AI function includes a joint source-channel coding (JSCC) encoder, including a coding module of performing joint source coding and channel coding on input of the JSCC encoder and a digital modulation module of performing modulation on output of the coding module.
[0008] In some implementations of the methods and apparatuses described herein, the JSCC encoder includes one or more AI models.
[0009] In some implementations of the methods and apparatuses described herein, the at least one processor is configured to further cause the UE to: receive, from the NE, a request of intrusion detection as a sensing task; and report a detected intrusion to the NE in the case of detecting an intrusion based on the request of intrusion detection, wherein the sensing service request is initiated by the NE based on the detected intrusion reported to the NE.
[0010] Some implementations of the methods and apparatuses described herein may further include a processor for wireless communication, which may include: at least one controller coupled with at least one memory and configured to cause the processor to: receive, from a NE, subframe configuration and sensing reference signal configuration both associated with a sensing service request; and send, to the NE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by an AI function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration.
[0011] Some implementations of the methods and apparatuses described herein may further include a NE for wireless communication, which may include: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the NE to: transmit, to a UE, subframe configuration and sensing reference signal configuration both associated with a sensing service request; and receive, from the UE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by a first AI function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration.
[0012] In some implementations of the methods and apparatuses described herein, the at least one processor is configured to further cause the NE to: determine measurement results from the sensing reference signals in received radio subframes; and transmit, to a core network (CN) entity, one or multiple of received data associated with the sensing service request or the measurement results.
[0013] In some implementations of the methods and apparatuses described herein, the at least one processor is configured to further cause the NE to: determine measurement results from the sensing reference signals in received radio subframes; determine status information of a sensed target associated with the sensing service request based on the measurement results; and transmit the status information to a CN entity.
[0014] In some implementations of the methods and apparatuses described herein, the at least one processor is configured to further cause the NE to: determine category information of the sensed target based on received data associated with the sensing service request by a classification module corresponding to the first AI function; and transmit the category information to the CN entity.
[0015] In some implementations of the methods and apparatuses described herein, the at least one processor is configured to further cause the NE to: determine input data of the first function based on the received data associated with the sensing service request by a reconstruction module corresponding to the first AI function; and transmit the input data of the first function to the CN entity.
[0016] In some implementations of the methods and apparatuses described herein, the at least one processor is configured to further cause the NE to: determine the subframe configuration and sensing reference signal configuration based on the sensing service request.
[0017] In some implementations of the methods and apparatuses described herein, the at least one processor is configured to further cause the NE to: receive, from a CN entity, the sensing service request after sending to the CN entity a report of a detected intrusion received from the UE.
[0018] In some implementations of the methods and apparatuses described herein, the first AI function includes a JSCC encoder, and the classification module and the classification module include JSCC decoders.
[0019] In some implementations of the methods and apparatuses described herein, the JSCC encoder and the JSCC decoders include associated AI models.
[0020] In some implementations of the methods and apparatuses described herein, the status information of a sensed target includes velocity information of the sensed target, or location information of the sensed target, or a combination thereof.
[0021] Some implementations of the methods and apparatuses described herein may further include a CN entity for wireless communication, which may include: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the CN entity to: receive, from a NE, one or multiple data associated with a sensing service request generated by an AI function or measurement results determined from sensing reference signals associated with the data associated with the sensing service request; in the case of receiving the data associated with the sensing service request, determine category information of a sensed target based on the data associated with the sensing service request by a classification module corresponding to the AI function; and in the case of receiving the measurement results, determine status information of the sensed target associated with the sensing service request based on the measurement results.
[0022] In some implementations of the methods and apparatuses described herein, the at least one processor is configured to further cause the CN entity to: in the case of receiving the data associated with the sensing service request, determine input data of the AI function based on the data associated with the sensing service request by a reconstruction module corresponding to the AI function.BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure.
[0024] Figure 2 illustrates an example of integrated sensing and semantic communication system in accordance with aspects of the present disclosure.
[0025] Figure 3 illustrates an example of radio subframes with data transmitted together with the associated sensing signals in accordance with aspects of the present disclosure.
[0026] Figure 4 illustrates an example of integrated sensing and semantic communication system based on cases#1 in accordance with aspects of the present disclosure.
[0027] Figure 5 illustrates an example of a 2-step sensing procedure in accordance with aspects of the present disclosure.
[0028] Figure 6 illustrates an example of a UE in accordance with aspects of the present disclosure.
[0029] Figure 7 illustrates an example of a processor in accordance with aspects of the present disclosure.
[0030] Figure 8 illustrates an example of a NE in accordance with aspects of the present disclosure.
[0031] Figure 9 illustrates an example of a CN entity in accordance with aspects of the present disclosure.
[0032] Figure 10 illustrates a flowchart of method performed by a UE in accordance with aspects of the present disclosure.
[0033] Figure 11 illustrates a flowchart of method performed by a NE in accordance with aspects of the present disclosure.
[0034] Figure 12 illustrates a flowchart of method performed by a CN entity in accordance with aspects of the present disclosure.DETAILED DESCRIPTION
[0035] AI, at least including machine learning (ML) is used to learn and perform certain tasks via training neural networks (NNs) with vast amounts of data, which is successfully applied in computer vison (CV) and nature language processing (NLP) areas. Deep learning, which is a subordinate concept of ML, utilizes multi-layered NNs as an “AI / ML model” (or referred to as AI / ML model or the like) or "AI-based model" (or referred to as AI / ML based model or the like) to learn how to solve problems and / or optimize performance from vast amounts of data. If AI / ML models used on AI-based methods are well trained, the AI-based methods can obtain better performance than the traditional methods. Thus, 3rd generation partnership program (3GPP) has been considering to introduce AI / ML into 3GPP since 2016.
[0036] Considering AI application in wireless communications, various aspects of the present disclosure propos technical solutions of supporting integrated sensing and semantic communications, including AI-based digital modulation scheme without losing gradient information for end-to-end training required by semantic communications, procedures to enable semantic information assisted sensing and other enabling features (e.g., features for obtaining category information and / or status information of the target) .
[0037] For example, in accordance with aspects of the present disclosure, based on a sensing service request (or sensing request or service request or the like) , UE performs the requested sensing task (or sensing service or sensing session or the like) and inputs sensed data to an AI function, e.g., a JSCC encoder. The data generated or output by the AI function may be referred to as semantic data in some cases. UE transfers the data generated by the AI function, e.g., semantic data generated by the JSCC encoder in radio subframes, which can be indicated by control information in physical channel. UE will also send sensing reference signals (or sensing signals or radio signals for sensing or the like) for the sensing task associated with the semantic data in the radio subframes. The radio subframes are configured by subframe configuration for the UE provided by network side, and the sensing reference signals are configured by sensing reference signal configuration for the UE provided by network side. The RAN side or CN side or both may jointly process the semantic data and measurement results (or sensing measurement results) determined from the associated sensing reference signals by AI function (s) associated with that at UE side and sensing reference signal process module to derive the sensing results of the requested service task.
[0038] Accordingly, compared with legacy sensing technologies, technical solutions in accordance with various aspects of the present disclosure would be advantageous in that the target can be better identified with less communication overhead and well tracked.
[0039] Aspects of the present disclosure are described in the context of a wireless communications system.
[0040] Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NE 102, one or more UE 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE-Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a NR network, such as a 5G network, a 5G-Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi) , IEEE 802.16 (WiMAX) , IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA) , frequency division multiple access (FDMA) , or code division multiple access (CDMA) , etc.
[0041] The one or more NE 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NE 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN) , a NodeB, an eNodeB (eNB) , a next-generation NodeB (gNB) , or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.
[0042] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc. ) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN) . In some implementations, different geographic coverage areas 112 associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102. In some embodiments, the NEs 102 may include one or more relay nodes, integrated access and backhaul (IAB) nodes or wireless access backhaul (WAB) nodes which can provide wireless access services for UEs 104. A relay node (or an IAB node or a WAB node) can directly connect to a BS or hop through one or more relay nodes (or one or more IAB or WAB nodes) before reaching the BS.
[0043] The one or more UE 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of-Things (IoT) device, an Internet-of-Everything (IoE) device, or machine-type communication (MTC) device, among other examples.
[0044] A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, the communication link 114 may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.
[0045] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g., S1, N2, N3, or network interface) . In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other indirectly (e.g., via the CN 106. In some implementations, one or more NE 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC) . An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs) .
[0046] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC) , or a 5G core (5GC) , which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME) , an access and mobility management functions (AMF) ) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW) , a Packet Data Network (PDN) gateway (P-GW) , or a user plane function (UPF) ) . In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc. ) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.
[0047] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g., via an S1, N2, N3, or another network interface) . The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server using the established session (e.g., the established PDU session) . The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106) .
[0048] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers) ) to perform various operations (e.g., wireless communications) . In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures) . The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.
[0049] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., μ=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., μ=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., μ=1) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., μ=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., μ=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., μ=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.
[0050] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames) . Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.
[0051] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., μ=0, μ=1, μ=2, μ=3, μ=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., OFDM symbols) . In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing) , a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., μ=0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.
[0052] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz –7.125 GHz) , FR2 (24.25 GHz –52.6 GHz) , FR3 (7.125 GHz –24.25 GHz) , FR4 (52.6 GHz –114.25 GHz) , FR4a or FR4-1 (52.6 GHz –71 GHz) , and FR5 (114.25 GHz –300 GHz) . In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data) . In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.
[0053] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies) . For example, FR1 may be associated with a first numerology (e.g., μ=0) , which includes 15 kHz subcarrier spacing; a second numerology (e.g., μ=1) , which includes 30 kHz subcarrier spacing; and a third numerology (e.g., μ=2) , which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies) . For example, FR2 may be associated with a third numerology (e.g., μ=2) , which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., μ=3) , which includes 120 kHz subcarrier spacing.
[0054] To meet the demand of higher data rates in future, e.g., 6G systems, semantic communication has been proposed, focusing on the fidelity of information transmission. The semantic communication solutions can provide a novel paradigm that goes beyond merely transmitting raw data and emphasizes understanding and extracting of task-related information in transmitted messages.
[0055] On the other hand, integrated sensing and communication (ISAC) system has been considered as crucial for next-generation communication systems by merging information collection and exchange within a common framework. Such integration or merging enables real-time decision-making, efficient resource utilization, enhancing adaptability in challenging environments, such as internet of things (IoT) and vehicle to infrastructure (V2I) networks.
[0056] In ISAC system, communication signals can also be employed for sensing, enabling tasks like object or target detection and tracking. However, it is difficult to identify the category of the sensed target, e.g., whether an unmanned aerial vehicle (UAV) or a bird or other category, via only analyzing the radio signals for sensing. Thus, it is expected to explore more kinds of data from other kinds of sensing manners to assist radio signal sensing, where terminals, e.g., UE or network nodes, e.g., RAN nodes or NEs are always equipped with several kinds of sensors, such as cameras etc. Although there are some research works focus on embedding semantic communications into ISAC models, all the works are only theoretical analyses without consideration the practice, e.g., air interface impact in future, e.g., 6G.
[0057] At least considering the above issues, various aspects of the present disclosure propose jointly and effectively combining or integrating the transmission of sensing reference signals for a sensing service with transmission of semantic data for the sensing service, which are generated by functions, e.g., AI functions based on other kinds of sensors except radio signaling, e.g., images and / or video from cameras.
[0058] Figure 2 illustrates an example of integrated sensing and semantic communication system in accordance with aspects of the present disclosure.
[0059] Referring to Figure 2, the illustrated example of integrated sensing and semantic communication system is a digital integrated sensing and semantic communication system to perform target detection, classification and positioning etc., via sensing together with data transmission. For example, the integrated sensing and semantic communication system may detect, identify and track a target in an area, wherein the category of the target, e.g., UAV, and / or the status or state of the target, e.g., velocity information, and location information etc., can be determined.
[0060] Exemplary nodes and features considered in the illustrated example of integrated sensing and semantic communication system may include a UE, e.g., road side unit (RSU) or the like, a RAN node (or NE or BS or the lie) serving the UE, and one or multiple CN entities communicating with the RAN node, e.g., a sensing function (SF) or the like. There are cameras (or other kinds of sensors) besides radio sensing capabilities in the UE, which can perform mono-static sensing with the RAN node, or bi-static sensing with the RAN node, or both. The shown nodes and features may have a sensing data analysis function.
[0061] At the UE side, an AI function or model or module is deployed together with the digital modulation. The input of the AI function includes but not limited to images, videos and / or other information sensed or captured by the cameras or other non-radio-signal sensor (s) , and the output of the AI function is referred to as semantic data (or other term) . The input data or information of the AI function may be referred to as raw data compared with that generated by the AI function. In some implementations of the present disclosure, the AI function in the UE side may be deployed as a JSCC encoder, which may include one or multiple AI models or functionalities.
[0062] The data generated by the UE-side AI function, e.g., semantic data may be further processed via baseband processing with associated sensing reference signals before transmission to the network via RF. At the RAN side, after the corresponding baseband processing, the RAN node may obtain the data generated by the UE-side AI function, e.g., semantic data and the associated sensing reference signals. The RAN node may determine the measurement results from the received sensing reference signals associated with the received semantic data.
[0063] Considering the semantic data, one or multiple AI functions corresponding to or associated with the UE-sided AI function may be deployed at the RAN side or CN side. For example, a classification module may be deployed to infer the target category based on the semantic data, and a reconstruction module may be deployed to recover the input data of the UE-side AI function based on the semantic data, e.g., the image and / or video captured by the camera at the UE side. There may be more function (s) or module (s) to derive more information based on the semantic data. In the case of the UE-side AI function being deployed as a JSCC encoder, the reconstruction module and classification module may be deployed as JSCC decoders, e.g., JSCC decoder A and JSCC decoder B associated with the JSCC encoder at the UE side. Similarly, each JSCC decoder may include one or multiple AI models or functionalities. These AI models or functionalities, e.g., in JSCC encoder and JSCC decoders A and B are jointly trained via multi-task learning, incorporating the channel characteristics to achieve integrated sensing and semantic communication functionalities.
[0064] Considering the measurement results determined from the associated sensing reference signals, a sensing reference signal processing module (or radio signal processing module or the like) may be deployed at the RAN side or CN side to derive the target status information e.g., velocity information, and location information etc. The sensing reference signal processing module may include AI models or functionalities or not.
[0065] In some implementations of the present disclosure (cases#1) , all the AI function (s) for processing semantic data, e.g., the classification module, reconstruction module and / or other AI function (s) (if any) and the sensing reference signal processing module are deployed at the CN side. The RAN node may send the semantic data and measurement results determined from the sensing reference signals to the CN side, e.g., to the SF. The CN side, e.g., SF may extract the target status information from the received measurement results, classify the target category from the semantic data (e.g., JSCC decoder B is deployed) and / or recover raw data from the semantic data (e.g., JSCC decoder A is deployed) .
[0066] In some implementations of the present disclosure (cases#2) , all the AI function (s) for processing semantic data, e.g., the classification module, reconstruction module and / or other AI function (s) (if any) and the sensing reference signal processing module are deployed at the RAN side. The RAN node may extract the target status information from the measurement results determined from the received sensing reference signals, classify the target category from the semantic data (e.g., JSCC decoder B is deployed) and / or recover raw data from the semantic data (e.g., JSCC decoder A is deployed) . Then, the RAN node may send the target status information, and target category information and / or recovered data to the CN side, e.g., to the SF.
[0067] In some implementations of the present disclosure (cases#3) , all the AI function (s) for processing semantic data, e.g., the classification module, reconstruction module and / or other AI function (s) (if any) are deployed at the CN side, while the sensing reference signal processing module is deployed at the RAN side. The RAN node may send the semantic data to the CN side, e.g., to the SF. The CN side, e.g., SF may classify the target category from the semantic data and / or recover raw data from the semantic data. The RAN node may extract the target status information from the measurement results, and send the target status information to the CN side, e.g., to the SF.
[0068] In some implementations of the present disclosure (cases#4) , all the AI function (s) for processing semantic data, e.g., the classification module, reconstruction module and / or other AI function (s) (if any) are deployed at the RAN side, while the sensing reference signal processing module is deployed at the CN side, e.g., SF. The RAN node may send measurement results determined from the sensing reference signals to the CN side, e.g., to the SF, so that the CN side can extract the target status information from the received measurement results. The RAN node may classify the target category from the semantic data and / or recover raw data from the semantic data. Then, the RAN node may send the target category information and / or recovered data to the CN side, e.g., to the SF.
[0069] Persons skilled in the art would understand that the above deployments are only illustrated as examples. There may be multiple UE-side AI function (s) besides JSCC encoder to satisfy different sensing requirements, and there may be more kinds of deployments of function and / or modules for processing semantic data, which are associated with the corresponding UE-side AI function. In some cases, the semantic data received at the RAN side may be further transferred to the external application (APP) , e.g., via the CN to derive the raw or original data, e.g., images or video, via the corresponding AI function, e.g., JSCC decoder A.
[0070] An exemplary JSCC encoder for transmission data and signal encoding and modulation at the US side are illustrated below in accordance with some aspects of the present disclosure.
[0071] Specifically, the exemplary JSCC encoder employed at RSU / UE is responsible for processing input raw images via performing joint source coding and channel coding to generate wireless signals followed by the digital modulation for transmission over the air. The outputs are the modulated latent-space representations of the input data to serving dual functions: enabling data communication and supporting sensing. Note that this output has a reduced dimension compared to the input data via extracting the semantic information, which means fewer bits needed over the air as the benefit of the semantic communication. By jointly optimizing the functions conventionally handled by source coding, channel coding, and modulation, the JSCC encoder with AI models ensures efficient resource utilization and minimizes transmission and semantic errors.
[0072] The architecture of the JSCC encoder can be split into a deep neural network (DNN) , e.g., JSCC module and a digital modulation module.
[0073] The JSCC module is composed of one compound convolutional layer, four residual blocks and one multilayer perception. The compound convolutional layer is used to reshape the input raw data and includes a convolutional layer with a kernel size of 64 × 3 ×3 × 3, a batch normalization layer, a dropout layer and a rectified linear unit (ReLU) non-linear activation layer. The ReLU function is defined as follows: where x represents the input to the non-linear activation layer. The inputs of the compound convolutional layer are RPG images with size 3 × 32 × 32, and the output is a feature map of size 64 × 32 × 32.
[0074] The residual block is used to address the problem of vanishing gradients and each of block contains two compound convolutional layer.
[0075] Instead of simply passing the output F (x) to the next layer, a shortcut connection is introduced in a residual block. The input x bypasses the layers and is added directly to the output F (x) . Thus, the block produces: Output =F (x) +x, This addition is element-wise and ensures that the network learns the residual function F (x) =H (x) -x, where H (x) is the true mapping desired by the network. In simpler terms, the block learns the difference between the input and the desired output. The dimensions of the input and output channels of each residual block are shown in Table 1. Table 1
[0076] The multilayer perception is designed to reshape the output of residual blocks to a desired size for the modulation module.
[0077] The modulation module is composed of a Gumbel-Softmax non-linear activation layer and a constellation projection module. Gumble-Softmax is a reparameterization technique that allows differentiable sampling from a categorical distribution, enabling backpropagation through discrete variables in neural networks. This method is especially useful in scenarios where models need to learn discrete decisions, such as choosing which constellation point to be modulated. It uses the Gumbel distribution and the Softmax function to create a differentiable approximation of a categorical distribution. The Gumbel distribution is used to model the maximum of a set of samples from a distribution, which in this case helps in simulating the "argmax" operation. A Gumbel-distributed noise is added to the raw predictions before applying Softmax to induce randomness in the selection process. For a given logits πi, Gumbel noise gi can be sampled by: gi=-log (-log (ui) ) , where ui is sampled from a uniform distribution ui~U (0, 1) . Once the Gumbel noise has been added to the logits, the Softmax function is applied to convert the noisy logits into a differentiable approximation of the one-hot vector. The Gumbel-Softmax distribution vi for category i is given by: where τ is a temperature parameter that controls how closely the output resembles the one- hot vector. After sampling the Gumbel-Softmax approximation, the model applies a hard decision during the forward pass, but in the backward pass, the continuous approximation is used for gradient computation. The realization is given as below: vi, hard=vi+sg (q (vi) -vi) , where vi, hard is the final output of the Gumbel-Softmax non-linear activation layer, sg (·) means stop gradient, and q (·) is used to quantize vi to a one-hot vector. During forward pass, to make a hard decision, the value of vi, hard equals to q (vi) ; during backward pass, to ensure gradient propagation, the gradient of vi, hard equals to vi. This allows the model to make discrete decisions while still propagating gradients. The output of the Gumbel-Softmax non-linear activation layer is a one-hot vector indicating which constellation point to be chosen.
[0078] To ensure the gradient propagation, the constellation projection must be in the form of matrix multiplication instead of simply choosing the constellation point with respect to the input one-hot vector. For example, in QPSK system, the projection matrix CQPSK are designed as below: and the final transmit signal without normalization is given by:
[0079] Exemplary JSCC decoders at RAN side for received semantic data or communication signal processing are illustrated below in accordance with some aspects of the present disclosure. Persons skilled in the art would well understand how to apply them at the CN side.
[0080] The received signal at RAN node or BS is given by YBS=shH+N Where Nr is the number of received antennas, T is the length of transmitted signals, is the near-field channel vector from UE, e.g., RSU to RAN node or BS, is the normalized transmitted signal with is the additive Gaussian white noise with distribution For given SNR γ, σ2 is obtained by
[0081] There are two DNNs employed at RAN node, one of which is responsible for reconstructing data samples (inputs to the encoder at RSU) , e.g., JSCC decoder A and another one is designed to extract semantic information from received signal, e.g., JSCC decoder B.
[0082] The reconstruction module (or information reconstruction module) , e.g., JSCC decoder A performs joint operations, including demodulating the received signals, decoding the channel-encoded data, and recovering the original data samples through source decoding. It is composed of several compound convolutional layers and residual blocks. The first compound convolutional layer consists of a convolutional layer with a kernel size of 256 ×16 × 3 × 3 and a ReLU non-linear activation layer. The second compound convolutional layer consists of a convolutional layer with a kernel size of 128× 16 × 3 × 3 and a ReLU non-linear activation layer. The third compound convolutional layer consists of a convolutional layer with a kernel size of 32× 3 × 3 × 3 and a ReLU non-linear activation layer. The numbers of input and output channels of each residual block are shown in Table 2. Table 2
[0083] The information reconstruction module can be trained by minimizing the reconstruction loss such as the mean squared error (MSE) as the loss function: where M is the number of elements in x.
[0084] The classification module (or semantic task classification module) , e.g., JSCC decoder B is used to validating the semantic content of the received data, performing deep learning tasks that go beyond simple data reconstruction.
[0085] The semantic task classification module is composed of one compound convolutional layer, two residual blocks and one multilayer perception. The compound convolutional layer includes a convolutional layer with a kernel size of 8 × 4 × 3 × 3, a dropout layer and a ReLU non-linear activation layer. The numbers of input and output channels of each residual block are shown in Table 3. Table 3
[0086] The multilayer perception is designed to classify the feature extracted by residual blocks to a certain category.
[0087] The semantic task classification module can be trained by minimizing the categorical cross-entropy as the loss function for the underlying task classifier: where C is the number of classes, l is the ground truth label related to the task and is the output of semantic task classification module serving as an estimation of l.
[0088] Exemplary sensing reference signal processing module at RAN side is illustrated below in accordance with some aspects of the present disclosure. Persons skilled in the art would well understand how to apply them at the CN side.
[0089] Similarly, the received signal at RAN side or BS is given by YBS=shH+N .
[0090] The channel vector h is modelled by Saleh-Valenzuela model, represented as where, ηRSU and ηTarget are the complex gain of each scattering path, satisfying Furthermore, a (θ, r) represents the receive steering vector, θRSU and θTarget denote the azimuth angle of RSU and target relative to the center of the antenna array respectively, and rRSU and rTarget denote the distance from RSU and target to the center of the antenna array respectively. In the near-field, a (θ, r) is expressed as where λ denotes the carrier wavelength, rn represents the distance from the RSU or target to the receive antenna element n. The antenna spacing is and the distance rn can be calculated as
[0091] When a target is present in the environment, the transmitted signal reflects off the target and returns to the transmitter in a mono-static way, or is received by the receiver in a bi-static way. The sensing module is composed of one compound convolutional layer and one multilayer perception.
[0092] The compound convolutional layer includes a convolutional layer with a kernel size of 16 × 4 × 3 × 3 and a ReLU non-linear activation layer. The multilayer perception is designed to identify the existence of the target from the extracted feature. Same as semantic task classification module, the sensing reference signal processing module can also be trained by minimizing the categorical cross-entropy as the loss function.
[0093] On the other hand, considering that the overhead for transferring data from surveillance cameras or the like to servers or functions for analyses over air interface is higher than that for transferring measurement results from radio signals for sensing, radio signals for sensing will be effectively integrated within semantic communication systems in accordance with aspects of the present disclosure.
[0094] For example, in accordance with some embodiments of the present disclosure, dedicated radio subframes are defined and scheduled to transfer data from the UE-side AI function, e.g., JSCC encoder. In some cases, data in the radio subframe may be sent via PUSCH indicated by UCI, e.g., via some special bits and / or other method, e.g., special transmission format. In another example, data in the radio subframe may be sent via a predefined or configured physical channel different from the PUSCH, that is a special physical channel can be provided a pre-defined transmission format or defined (or configured) by information from high layer, e.g., media access control (MAC) control element (CE) or radio resource control (RRC) signaling.
[0095] The sensing reference signals for the associated sensing task are scheduled and configured in such dedicated radio subframes, which means the measurement results from the sensing reference signals are associated with the data transferred in the radio subframes. For example, as shown in Figure 3, the radio subframes with data may be transmitted together with the associated sensing signals or each radio subframe carrying the semantic data also carries associated sensing reference signals. The association between the sensing reference signals and the radio subframes can be identified with a configured ID, which may be same as or different from the ID of the radio subframes.
[0096] In addition, in an integrated sensing and semantic communication system, the CN may require a continuous or constant sensing or monitoring without requirements for specific target. To save energy for sensing, aspects of the present disclosure propose that the CN may firstly initiate or send an intrusion (or event) detection request (hereinafter, a first sensing request) as a sensing task, and then initiate a further sensing request (hereinafter, second sensing request) in the case of an intrusion being detected or monitored, e.g., after receiving a report of the detected intrusion. Such a sensing procedure may be referred to as a 2-step sensing procedure.
[0097] Hereinafter, an exemplary 2-step sensing procedure is illustrated in view of an integrated sensing and semantic communication system based on cases#1, where semantic data and sensing measurement results will be transferred from RAN side to the related function or module (AI based or not) in CN, e.g., SF, to be jointly processed or fused to derive the sensing results. Persons skilled in the art would understand how to apply a 2-step sensing procedure in other kinds of integrated sensing and semantic communication system in view of various aspects of the present disclosure.
[0098] Specifically, Figure 4 illustrates an example of integrated sensing and semantic communication system based on cases#1 in accordance with aspects of the present disclosure, and Figure 5 illustrates an example of a 2-step sensing procedure in accordance with aspects of the present disclosure, which can be applied at least in the integrated sensing and semantic communication system shown in Figure 4.
[0099] Referring to Figure 4, exemplary nodes and features considered in the illustrated integrated sensing and semantic communication system may include a UE, e.g., RSU or the like, a RAN node serving the UE, CN, e.g., a SF or the like in the CN communicating with the RAN node, and external applications. There are cameras besides radio sensing capabilities in the UE, which can perform mono-static sensing with the RAN node, or bi-static sensing with the RAN node, or both. It is assumed that at least the CN, e.g., SF has sensing data analysis function. For example, the SF may at least deploy a classification module and sensing reference signal processing module, and may deploy more function (s) or module (s) , e.g., reconstruction module. Other shown nodes and features, e.g., the UE, RAN node and external applications may potentially have sensing data analysis function.
[0100] Referring to Figure 5, a CN entity, e.g., SF may send a first sensing request to the UE, e.g., via the RAN node (may be transparent to the RAN node or not) at step 501a and 501b. The first sensing request or intrusion detection request is to sense intrusion in an area, which means that the sensing task is to detect whether an event or intrusion happens or not. An exemplary first sensing request at least includes the area to be monitored and the duration of such sensing service.
[0101] After receiving the intrusion detection request, the UE may perform mono-static or bi-static sensing, e.g., sending and receiving sensing signals, to detect whether any intrusion happens or not, which may be assisted by the RAN node, e.g., to allocate and reserve some radio resources for such sensing. In the case of detecting an intrusion, at step 503a, the UE may indicate or report the detected intrusion to the RAN node via air interface. In some cases, the UE may also report the probability of the detected intrusion or event.
[0102] After receiving the report of detected intrusion from the UE, the RAN node may report the intrusion to the CN, e.g., to the SF at step 503b. Similarly, in some cases, the report of intrusion from the UE to the SF is transparent for the RAN node. In some cases, the RAN node may query whether a new or further sensing task is needed or not.
[0103] Based on the reported intrusion, the SF may determine to initiate a second sensing request for a new sensing task (or the second sensing task) . For example, if the intrusion is detected in the sensing area, it may be necessary to further detect the target category and / or status information, e.g., velocity and location etc. The SF may activate the relevant functions or modules for further processing according to the requirements of the second sensing task, e.g., JSCC decoder A (e.g., raw data is required) , JSCC decoder B (e.g., target category information is required) and sensing reference signal processing module (e.g., target status information is required) .
[0104] At step 505, the SF may initiate the second sensing request with related requirements and configurations, e.g., the application conditions of the JSCC decoder (s) , and the expected estimation accuracy, e.g., the estimated accuracy of the velocity and / or location information. In some cases, the second sensing request may also provide other information, e.g., conditions to terminate the second sensing task etc.
[0105] After receiving the second sensing request, at step 507, the RAN node may transfer the second sensing request to the UE with the transmission configurations of the sensing reference signals and semantic data (or communication signals) , including but not limited to subframe configuration and sensing reference signal configuration. For example, in some cases, considering the semantic data transmission, the RAN node may also send other related information to the UE, such as the application conditions of JSCC decoder (s) , to assist the JSCC encoder selection for pairing.
[0106] During performing the sensing task requested by the second sensing request, when the UE is aware of the existence of a target in an area, e.g., a UAV, the UE may take the photo of the target by the camera, compress and input the images to the AI function, e.g., JSCC encoder to generate semantic data. The semantic data will be carried in configured radio subframes together with the associated configured sensing reference signals, where the configured sensing reference signals are inserted in the radio subframes as shown in Figure 3.At step 509, the radio subframes with semantic data and sensing reference signals are transferred to the RAN node over the air interface, e.g., as shown in Figure 4, with some interaction to support effective transmission, e.g., acknowledgement and link adaptation etc.
[0107] After receiving the radio subframes, the RAN node will process the subframes and determine the semantic data, which will be as the inputs to the corresponding JSCC decoders. In addition, the RAN node will also determine measurement results from the sensing reference signals. At step 511, the RAN node will report the measurement results and semantic data to the SF, e.g., as shown in Figure 4.
[0108] After receiving the semantic data and measurement results, the SF may derive the sensing results by the activated AI functions and sensing reference signal processing module. For example, the SF may use the JSCC decoder A to recover the input data of the JSCC encoder, use the JSCC decoder B to derive the target category information, e.g., UAV, and use the sensing reference signal processing module to derive the target status information, e.g., velocity and location of the UAV etc.
[0109] Persons skilled in the art would understand that the UE may track the target in the area and keep performing the second sensing task until the second service task is terminated. For example, the UE may keep sensing the target with the camera and report the semantic data with associated sensing reference signals to the RAN node, and then to the SF to derive the target category information, target status information and / or raw data etc., that is steps 509 and 511 may be iterated according to the second sensing task.
[0110] In the case that the second sensing task is not needed or the performance is not satisfying, or due to other reasons, the SF may send a request or indication to the RAN node to terminate or stop the sensing task with or without the termination reason at step 513a, which will be further indicated to the UE by the RAN node at step 513b. The UE will terminate the second sensing task after receiving the termination request or indication.
[0111] In some cases, the UE may send acknowledgement information on the termination request to the RAN node at step 515a. The RAN node may terminate the second sensing task after receiving the acknowledgement information, and send the acknowledgement information on the termination request to the SF at step 515b.
[0112] Figure 6 illustrates an example of a UE 600 in accordance with aspects of the present disclosure. The UE 600 may include a processor 602, a memory 604, a controller 606, and a transceiver 608. The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.
[0113] The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations or components thereof may be implemented in hardware (e.g., circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.
[0114] The processor 602 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof) . In some implementations, the processor 602 may be configured to operate the memory 604. In some other implementations, the memory 604 may be integrated into the processor 602. The processor 602 may be configured to execute computer-readable instructions stored in the memory 604 to cause the UE 600 to perform various functions of the present disclosure.
[0115] The memory 604 may include volatile or non-volatile memory. The memory 604 may store computer-readable, computer-executable code including instructions when executed by the processor 602 cause the UE 600 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 604 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.
[0116] In some implementations, the processor 602 and the memory 604 coupled with the processor 602 may be configured to cause the UE 600 to perform one or more of the functions described herein (e.g., executing, by the processor 602, instructions stored in the memory 604) . For example, the processor 602 may support wireless communication at the UE 600 in accordance with examples as disclosed herein. The UE 600 may be configured to support a means for receiving, from a NE, subframe configuration and sensing reference signal configuration both associated with a sensing service request; and means for sending, to the NE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by an AI function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration.
[0117] The controller 606 may manage input and output signals for the UE 600. The controller 606 may also manage peripherals not integrated into the UE 600. In some implementations, the controller 606 may utilize an operating system such as or other operating systems. In some implementations, the controller 606 may be implemented as part of the processor 602.
[0118] In some implementations, the UE 600 may include at least one transceiver 608. In some other implementations, the UE 600 may have more than one transceiver 608. The transceiver 608 may represent a wireless transceiver. The transceiver 608 may include one or more receiver chains 610, one or more transmitter chains 612, or a combination thereof.
[0119] A receiver chain 610 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 610 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 610 may include at least one amplifier (e.g., a low-noise amplifier (LNA) ) configured to amplify the received signal. The receiver chain 610 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 610 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.
[0120] A transmitter chain 612 may be configured to generate and transmit signals (e.g., control information, data, packets) . The transmitter chain 612 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmitter chain 612 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 612 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.
[0121] Figure 7 illustrates an example of a processor 700 in accordance with aspects of the present disclosure. The processor 700 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 700 may include a controller 702 configured to perform various operations in accordance with examples as described herein. The processor 700 may optionally include at least one memory 704, which may be, for example, an L1 / L2 / L3 cache. Additionally, or alternatively, the processor 700 may optionally include one or more arithmetic-logic units (ALUs) 706. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses) .
[0122] The processor 700 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 700) or other memory (e.g., random access memory (RAM) , read-only memory (ROM) , dynamic RAM (DRAM) , synchronous dynamic RAM (SDRAM) , static RAM (SRAM) , ferroelectric RAM (FeRAM) , magnetic RAM (MRAM) , resistive RAM (RRAM) , flash memory, phase change memory (PCM) , and others) .
[0123] The controller 702 may be configured to manage and coordinate various operations (e.g., signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 700 to cause the processor 700 to support various operations in accordance with examples as described herein. For example, the controller 702 may operate as a control unit of the processor 700, generating control signals that manage the operation of various components of the processor 700. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.
[0124] The controller 702 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 704 and determine subsequent instruction (s) to be executed to cause the processor 700 to support various operations in accordance with examples as described herein. The controller 702 may be configured to track memory address of instructions associated with the memory 704. The controller 702 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 702 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 700 to cause the processor 700 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 702 may be configured to manage flow of data within the processor 700. The controller 702 may be configured to control transfer of data between registers, arithmetic logic units (ALUs) , and other functional units of the processor 700.
[0125] The memory 704 may include one or more caches (e.g., memory local to or included in the processor 700 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 704 may reside within or on a processor chipset (e.g., local to the processor 700) . In some other implementations, the memory 704 may reside external to the processor chipset (e.g., remote to the processor 700) .
[0126] The memory 704 may store computer-readable, computer-executable code including instructions that, when executed by the processor 700, cause the processor 700 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 702 and / or the processor 700 may be configured to execute computer-readable instructions stored in the memory 704 to cause the processor 700 to perform various functions. For example, the processor 700 and / or the controller 702 may be coupled with or to the memory 704, the processor 700, the controller 702, and the memory 704 may be configured to perform various functions described herein. In some examples, the processor 700 may include multiple processors and the memory 704 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.
[0127] The one or more ALUs 706 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 706 may reside within or on a processor chipset (e.g., the processor 700) . In some other implementations, the one or more ALUs 706 may reside external to the processor chipset (e.g., the processor 700) . One or more ALUs 706 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 706 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 706 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 706 may support logical operations such as AND, OR, exclusive-OR (XOR) , not-OR (NOR) , and not-AND (NAND) , enabling the one or more ALUs 706 to handle conditional operations, comparisons, and bitwise operations.
[0128] The processor 700 may support wireless communication in accordance with examples as disclosed herein. The processor 700 may be configured to or operable to support a means for receiving, from a NE, subframe configuration and sensing reference signal configuration both associated with a sensing service request; and means for sending, to the NE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by an AI function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration.
[0129] Figure 8 illustrates an example of a NE 800 in accordance with aspects of the present disclosure. The NE 800 may include a processor 802, a memory 804, a controller 806, and a transceiver 808. The processor 802, the memory 804, the controller 806, or the transceiver 808, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.
[0130] The processor 802, the memory 804, the controller 806, or the transceiver 808, or various combinations or components thereof may be implemented in hardware (e.g., circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.
[0131] The processor 802 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof) . In some implementations, the processor 802 may be configured to operate the memory 804. In some other implementations, the memory 804 may be integrated into the processor 802. The processor 802 may be configured to execute computer-readable instructions stored in the memory 804 to cause the NE 800 to perform various functions of the present disclosure.
[0132] The memory 804 may include volatile or non-volatile memory. The memory 804 may store computer-readable, computer-executable code including instructions when executed by the processor 802 cause the NE 800 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 804 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.
[0133] In some implementations, the processor 802 and the memory 804 coupled with the processor 802 may be configured to cause the NE 800 to perform one or more of the functions described herein (e.g., executing, by the processor 802, instructions stored in the memory 804) . For example, the processor 802 may support wireless communication at the NE 800 in accordance with examples as disclosed herein. The NE 800 may be configured to support a means for transmitting, to a UE, subframe configuration and sensing reference signal configuration both associated with a sensing service request; and means for receiving, from the UE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by a first AI function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration.
[0134] The controller 806 may manage input and output signals for the NE 800. The controller 806 may also manage peripherals not integrated into the NE 800. In some implementations, the controller 806 may utilize an operating system such as or other operating systems. In some implementations, the controller 806 may be implemented as part of the processor 802.
[0135] In some implementations, the NE 800 may include at least one transceiver 808. In some other implementations, the NE 800 may have more than one transceiver 808. The transceiver 808 may represent a wireless transceiver. The transceiver 808 may include one or more receiver chains 810, one or more transmitter chains 812, or a combination thereof.
[0136] A receiver chain 810 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 810 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 810 may include at least one amplifier (e.g., a low-noise amplifier (LNA) ) configured to amplify the received signal. The receiver chain 810 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 810 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.
[0137] A transmitter chain 812 may be configured to generate and transmit signals (e.g., control information, data, packets) . The transmitter chain 812 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmitter chain 812 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 812 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.
[0138] Figure 9 illustrates an example of a CN entity 900 in accordance with aspects of the present disclosure. The CN entity 900 may include a processor 902, a memory 904, a controller 906, and a transceiver 908. The processor 902, the memory 904, the controller 906, or the transceiver 908, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.
[0139] The processor 902, the memory 904, the controller 906, or the transceiver 908, or various combinations or components thereof may be implemented in hardware (e.g., circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.
[0140] The processor 902 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof) . In some implementations, the processor 902 may be configured to operate the memory 904. In some other implementations, the memory 904 may be integrated into the processor 902. The processor 902 may be configured to execute computer-readable instructions stored in the memory 904 to cause the CN entity 900 to perform various functions of the present disclosure.
[0141] The memory 904 may include volatile or non-volatile memory. The memory 904 may store computer-readable, computer-executable code including instructions when executed by the processor 902 cause the CN entity 900 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 904 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.
[0142] In some implementations, the processor 902 and the memory 904 coupled with the processor 902 may be configured to cause the CN entity 900 to perform one or more of the functions described herein (e.g., executing, by the processor 902, instructions stored in the memory 904) . For example, the processor 902 may support wireless communication at the CN entity 900 in accordance with examples as disclosed herein. The CN entity 900 may be configured to support a means for receiving, from a NE, one or multiple data associated with a sensing service request generated by an AI function or measurement results determined from sensing reference signals associated with the data associated with the sensing service request; means for in the case of receiving the data associated with the sensing service request, determining category information of a sensed target based on the data associated with the sensing service request by a classification module corresponding to the AI function; and means for in the case of receiving the measurement results, determining status information of the sensed target associated with the sensing service request based on the measurement results.
[0143] The controller 906 may manage input and output signals for the CN entity 900. The controller 906 may also manage peripherals not integrated into the CN entity 900. In some implementations, the controller 906 may utilize an operating system such as or other operating systems. In some implementations, the controller 906 may be implemented as part of the processor 902.
[0144] In some implementations, the CN entity 900 may include at least one transceiver 908. In some other implementations, the CN entity 900 may have more than one transceiver 908. The transceiver 908 may represent a wireless transceiver. The transceiver 908 may include one or more receiver chains 910, one or more transmitter chains 912, or a combination thereof.
[0145] A receiver chain 910 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 910 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 910 may include at least one amplifier (e.g., a low-noise amplifier (LNA) ) configured to amplify the received signal. The receiver chain 910 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 910 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.
[0146] A transmitter chain 912 may be configured to generate and transmit signals (e.g., control information, data, packets) . The transmitter chain 912 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmitter chain 912 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 912 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.
[0147] Figure 10 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by a UE as described herein. In some implementations, the UE may execute a set of instructions to control the function elements of the UE to perform the described functions.
[0148] At step 1001, the method may include receiving, from a NE, subframe configuration and sensing reference signal configuration both associated with a sensing service request. The operations of step 1001 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1001 may be performed by a UE as described with reference to Figure 6.
[0149] At step 1003, the method may include sending, to the NE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by an AI function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration. The operations of step 1003 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of step 1003 may be performed by a UE as described with reference to Figure 6.
[0150] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.
[0151] Figure 11 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by a NE as described herein. In some implementations, the NE may execute a set of instructions to control the function elements of the NE to perform the described functions.
[0152] At step 1101, the method may include transmitting, to a UE, subframe configuration and sensing reference signal configuration both associated with a sensing service request. The operations of step 1101 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of step 1101 may be performed by a NE as described with reference to Figure 8.
[0153] At step 1103, the method may include receiving, from the UE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by a first AI function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration. The operations of step 1103 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of step 1103 may be performed by a NE as described with reference to Figure 8.
[0154] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.
[0155] Figure 12 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by a CN entity as described herein. In some implementations, the CN entity may execute a set of instructions to control the function elements of the CN entity to perform the described functions.
[0156] At step 1201, the method may include receiving, from a NE, one or multiple data associated with a sensing service request generated by an AI function or measurement results determined from sensing reference signals associated with the data associated with the sensing service request. The operations of step 1201 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of step 1201 may be performed by a CN entity as described with reference to Figure 9.
[0157] At step 1203, the method may include in the case of receiving the data associated with the sensing service request, determining category information of a sensed target based on the data associated with the sensing service request by a classification module corresponding to the AI function. The operations of step 1203 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of step 1203 may be performed by a CN entity as described with reference to Figure 9.
[0158] At step 1205, the method may include in the case of receiving the measurement results, determining status information of the sensed target associated with the sensing service request based on the measurement results. The operations of step 1205 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of step 1205 may be performed by a CN entity as described with reference to Figure 9.
[0159] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.
[0160] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.
Claims
1.A user equipment (UE) for wireless communication, comprising:at least one memory; andat least one processor coupled with the at least one memory and configured to cause the UE to:receive, from a network equipment (NE) , subframe configuration and sensing reference signal configuration both associated with a sensing service request; andsend, to the NE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by an artificial intelligence (AI) function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration.2.The UE of claim 1, wherein the data in the radio subframes is sent via physical uplink shared channel (PUSCH) indicated by uplink control information (UCI) or via a predefined or configured physical channel different from the PUSCH.3.The UE of claim 1, wherein the sensing reference signals and the radio subframes are associated by configured identity (ID) information, and the ID information is same as or different from ID information of the radio subframes.4.The UE of claim 1, wherein the AI function comprises a joint source-channel coding (JSCC) encoder, including a coding module of performing joint source coding and channel coding on input of the JSCC encoder and a digital modulation module of performing modulation on output of the coding module.5.The UE of claim 4, wherein the JSCC encoder comprises one or more AI models.6.The UE of claim 1, wherein the at least one processor is configured to further cause the UE to:receive, from the NE, a request of intrusion detection as a sensing task; andreport a detected intrusion to the NE in the case of detecting an intrusion based on the request of intrusion detection, wherein the sensing service request is initiated by the NE based on the detected intrusion reported to the NE.7.A processor for wireless communication, comprising:at least one controller coupled with at least one memory and configured to cause the processor to:receive, from a network equipment (NE) , subframe configuration and sensing reference signal configuration both associated with a sensing service request; andsend, to the NE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by an artificial intelligence (AI) function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration.8.A network equipment (NE) for wireless communication, comprising:at least one memory; andat least one processor coupled with the at least one memory and configured to cause the NE to:transmit, to a user equipment (UE) , subframe configuration and sensing reference signal configuration both associated with a sensing service request; andreceive, from the UE, data associated with the sensing service request in radio subframes based on the subframe configuration, wherein the data is generated by a first artificial intelligence (AI) function and each radio subframe carrying the data also carries associated sensing reference signals configured based on the sensing reference signal configuration.9.The NE of claim 8, wherein the at least one processor is configured to further cause the NE to:determine measurement results from the sensing reference signals in received radio subframes; andtransmit, to a core network (CN) entity, one or multiple of received data associated with the sensing service request or the measurement results.10.The NE of claim 8, wherein the at least one processor is configured to further cause the NE to:determine measurement results from the sensing reference signals in received radio subframes;determine status information of a sensed target associated with the sensing service request based on the measurement results; andtransmit the status information to a core network (CN) entity.11.The NE of claim 10, wherein the at least one processor is configured to further cause the NE to:determine category information of the sensed target based on received data associated with the sensing service request by a classification module corresponding to the first AI function; andtransmit the category information to the CN entity.12.The NE of claim 11, wherein the at least one processor is configured to further cause the NE to:determine input data of the first function based on the received data associated with the sensing service request by a reconstruction module corresponding to the first AI function; andtransmit the input data of the first function to the CN entity.13.The NE of claim 8, wherein the at least one processor is configured to further cause the NE to:determine the subframe configuration and sensing reference signal configuration based on the sensing service request.14.The NE of claim 13, wherein the at least one processor is configured to further cause the NE to:receive, from a core network (CN) entity, the sensing service request after sending to the CN entity a report of a detected intrusion received from the UE.15.The NE of claim 11, wherein the first AI function comprises a joint source-channel coding (JSCC) encoder, and the classification module and the classification module comprise JSCC decoders.16.The NE of claim 15, wherein the JSCC encoder and the JSCC decoders comprise associated AI models.17.The NE of claim 10, wherein the status information of a sensed target comprises velocity information of the sensed target, or location information of the sensed target, or a combination thereof.18.A core network (CN) entity for wireless communication, comprising:at least one memory; andat least one processor coupled with the at least one memory and configured to cause the CN entity to:receive, from a network equipment (NE) , one or multiple data associated with a sensing service request generated by an artificial intelligence (AI) function or measurement results determined from sensing reference signals associated with the data associated with the sensing service request;in the case of receiving the data associated with the sensing service request, determine category information of a sensed target based on the data associated with the sensing service request by a classification module corresponding to the AI function; andin the case of receiving the measurement results, determine status information of the sensed target associated with the sensing service request based on the measurement results.19.The CN entity of claim 18, wherein the at least one processor is configured to further cause the CN entity to:in the case of receiving the data associated with the sensing service request, determine input data of the AI function based on the data associated with the sensing service request by a reconstruction module corresponding to the AI function.
Citation Information
Patent Citations
Target sensing method and related device
CN120186553A
Integrated sensing and communication network
US20230309144A1
Semantic Communication: Protocol Stack and Model Selection
US20230412709A1
Method, apparatus and system for semantic communications
WO2024259861A1