WO2025237141A1 - 能力信息交互方法、装置及设备 - Google Patents

能力信息交互方法、装置及设备

Info

Publication number
WO2025237141A1
WO2025237141A1 PCT/CN2025/093290 CN2025093290W WO2025237141A1 WO 2025237141 A1 WO2025237141 A1 WO 2025237141A1 CN 2025093290 W CN2025093290 W CN 2025093290W WO 2025237141 A1 WO2025237141 A1 WO 2025237141A1
Authority
WO
WIPO (PCT)
Prior art keywords
perception
sensing
data
capabilities
capability
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2025/093290
Other languages
English (en)
French (fr)
Inventor
姚健
孙布勒
袁雁南
蒲文娟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Vivo Mobile Communication Co Ltd
Original Assignee
Vivo Mobile Communication Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Vivo Mobile Communication Co Ltd filed Critical Vivo Mobile Communication Co Ltd
Publication of WO2025237141A1 publication Critical patent/WO2025237141A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information

Definitions

  • This application belongs to the field of communication technology, specifically relating to a capability information interaction method, apparatus, and device.
  • Some communication systems support sensing, such as sensing the location, distance, and speed of target objects, or supporting the detection, tracking, identification, and imaging of target objects, events, or environments.
  • the exchange of capability information between devices is limited to their communication capabilities, such as the capabilities of the Packet Data Convergence Protocol (PDCP), Radio Link Control (RLC), and Medium Access Control (MAC) layers.
  • PDCP Packet Data Convergence Protocol
  • RLC Radio Link Control
  • MAC Medium Access Control
  • This application provides a capability information interaction method, apparatus, and device that can solve the problem that the interaction of communication capability information between devices is not very effective for sensing services.
  • a method for exchanging capability information including:
  • the first device reports perception capability information, which is used to indicate the first device's perception capability based on artificial intelligence (AI).
  • AI artificial intelligence
  • a method for exchanging capability information including:
  • the second device receives sensing capability information, which is used to indicate the first device's AI-based sensing capabilities.
  • a capability information interaction device comprising:
  • the sending module is used to report perception capability information, which is used to indicate the perception capability of the first device based on artificial intelligence (AI).
  • AI artificial intelligence
  • a capability information interaction device comprising:
  • the first acquisition module is used to acquire measurement data
  • a receiving module is used to receive sensing capability information, which is used to indicate the AI-based sensing capability of the first device.
  • a device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the first device-side capability information interaction method provided in the embodiments of this application.
  • a device including a processor and a communication interface, wherein the communication interface is used to report perception capability information, and the perception capability information is used to indicate the perception capability of the first device based on artificial intelligence (AI).
  • AI artificial intelligence
  • an apparatus including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the second device-side capability information interaction method as provided in the embodiments of this application.
  • a device including a processor and a communication interface, wherein the communication interface is used to receive sensing capability information, the sensing capability information being used to indicate the artificial intelligence (AI)-based sensing capability of a first device.
  • AI artificial intelligence
  • a readable storage medium on which a program or instructions are stored, wherein when the program or instructions are executed by a processor, the program or instructions implement the steps of the first device-side capability information interaction method provided in the embodiments of this application, or implement the steps of the second device-side capability information interaction method provided in the embodiments of this application.
  • a wireless communication system comprising: a first device and a second device, wherein the first device is configured to perform the steps of the capability information interaction method on the first device side as provided in the embodiments of this application, and the second device is configured to perform the steps of the capability information interaction method on the second device side as provided in the embodiments of this application.
  • a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the first device-side capability information interaction method provided in the embodiments of this application, or to implement the second device-side capability information interaction method provided in the embodiments of this application.
  • a computer program/program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of a first device-side capability information interaction method as provided in the embodiments of this application, or the computer program/program product is executed by at least one processor to implement the steps of a second device-side capability information interaction method as provided in the embodiments of this application.
  • the first device reports perception capability information, which indicates the AI-based perception capabilities of the first device. This enables information exchange based on AI-based perception capabilities, thus improving the effectiveness of perception services. Furthermore, reporting perception capability information also helps improve the perception performance between devices.
  • Figure 1 is a block diagram of a wireless communication system applicable to an embodiment of this application
  • Figure 2 is a schematic diagram of a measurement scenario provided in an embodiment of this application.
  • Figure 3 is a schematic diagram of another measurement scenario provided by an embodiment of this application.
  • Figure 4 is a schematic diagram of a neural network provided in an embodiment of this application.
  • Figure 5 is a schematic diagram of a neuron provided in an embodiment of this application.
  • Figure 6 is a flowchart of a capability information interaction method provided in an embodiment of this application.
  • FIG. 7 is a flowchart of another capability information interaction method provided in an embodiment of this application.
  • Figure 8 is a schematic diagram of a capability information interaction method provided in an embodiment of this application.
  • Figure 9 is a schematic diagram of another capability information interaction method provided in an embodiment of this application.
  • Figure 10 is a schematic diagram of another capability information interaction method provided in an embodiment of this application.
  • Figure 11 is a schematic diagram of a capability information interaction device provided in an embodiment of this application.
  • Figure 12 is a schematic diagram of another capability information interaction device provided in an embodiment of this application.
  • Figure 13 is a structural diagram of a device provided in an embodiment of this application.
  • Figure 14 is a structural diagram of another device provided in an embodiment of this application.
  • Figure 15 is a structural diagram of another device provided in an embodiment of this application.
  • Figure 16 is a structural diagram of another device provided in an embodiment of this application.
  • first and second are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by “first” and “second” are generally of the same class, not limited in number; for example, the first object can be one or more.
  • “or” in this application indicates at least one of the connected objects.
  • the scope of protection for "A or B” covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B.
  • the terms “A and/or B,” “at least one of A and B,” and “at least one of A or B” also cover at least the above three scenarios.
  • the character “/” generally indicates that the preceding and following objects are in an "or” relationship.
  • instruction in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction).
  • a direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent.
  • An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.
  • LTE Long Term Evolution
  • LTE-A Long Term Evolution-Advanced
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency-Division Multiple Access
  • NR New Radio
  • FIG. 1 shows a block diagram of a wireless communication system applicable to an embodiment of this application.
  • the wireless communication system includes a terminal 11 and a network-side device 12.
  • Terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM, or self-service machine, etc.
  • PDA personal digital assistant
  • UMPC ultra-mobile personal computer
  • MID mobile internet device
  • AR augmented reality
  • VR virtual reality
  • robot wearable device
  • flight vehicle vehicle user equipment
  • VUE shipboard equipment
  • pedestrian user equipment PUE
  • smart home home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines
  • Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc.
  • in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment.
  • Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit.
  • Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (APs), or Wireless Fidelity (WiFi) nodes, etc.
  • WLAN Wireless Local Area Network
  • WiFi Wireless Fidelity
  • a base station may be referred to as a Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit/Receive Point (TRP), or any other suitable term in the relevant field, as long as the same technical effect is achieved.
  • the base station is not limited to specific technical terms. It should be noted that in this application embodiment, only a base station in an NR system is used as an example for introduction, and the specific type of base station is not limited.
  • Core network equipment also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), and Unified Data Warehouse (UDM).
  • MME Mobility Management Entity
  • AMF Access and Mobility Management Function
  • SMF Session Management Function
  • UPF User Plane Function
  • PCF Policy Control Function
  • PCF Policy and Charging Rules Function
  • EASDF Edge Application Server Discovery Function
  • UDM Unified Data Management
  • UDM Unified Data Management
  • UDM Unified Data Warehouse
  • the core network equipment includes: Data Repository (UDR), Home Subscriber Server (HSS), Centralized Network Configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), Binding Support Function (BSF), Application Function (AF), Location Management Function (LMF), Gateway Mobile Location Centre (GMLC), and Network Data Analytics Function (NWDAF).
  • UDR Data Repository
  • HSS Home Subscriber Server
  • CNC Centralized Network Configuration
  • NEF Network Exposure Function
  • L-NEF Local NEF
  • BSF Binding Support Function
  • AF Application Function
  • LMF Location Management Function
  • GMLC Gateway Mobile Location Centre
  • NWDAF Network Data Analytics Function
  • the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that the aforementioned functional modules can be network elements in hardware devices, software functional modules running on dedicated hardware, or virtualized functional modules instantiated on a platform (e.g., a cloud platform).
  • a platform e.g., a cloud platform
  • network-side devices and terminals in addition to communication capabilities, may possess sensing capabilities.
  • Sensing capabilities refer to the ability of one or more devices to sense information such as the location, distance, and speed of a target object through the transmission and reception of wireless signals, or to detect, track, identify, and image target objects, events, or environments.
  • Integrated communication and sensing refers to the integrated design of communication and sensing functions in the same system through spectrum sharing and hardware sharing. While transmitting information, the system can sense information such as location, distance, and speed, and detect, track, and identify target devices or events. The communication system and the sensing system complement each other, thereby improving overall performance and bringing a better service experience.
  • the integration of communication and radar is a typical application of communication and sensing integration (communication and sensing fusion).
  • the integration of communication and radar systems can bring many advantages, such as cost savings, size reduction, power consumption reduction, improved spectrum efficiency, and reduced mutual interference, thereby improving the overall system performance.
  • each sensing link in Figure 2 is illustrated with one transmitting node and one receiving node. In actual systems, different sensing links can be selected according to different sensing requirements. Each sensing link may have one or more transmitting and receiving nodes, and the actual sensing system may include multiple different sensing links.
  • the sensing targets in Figure 2 are people and vehicles as examples, and it is assumed that neither people nor vehicles carry or have installed signal transceiver equipment. The sensing targets in actual scenarios will be much more diverse.
  • Sensing Link 1 Base station self-transmitting and self-receiving sensing. In this method, the base station sends sensing signals and obtains the sensing results by receiving the echoes of these signals;
  • Sensing Link 2 Inter-base station air interface sensing. In this mode, base station 2 receives sensing signals sent by base station 1 and obtains the sensing results.
  • Sensing Link 3 Uplink air interface sensing. In this mode, the base station receives sensing signals sent by the terminal and obtains the sensing results.
  • Sensing Link 4 Downlink Air Interface Sensing. In this mode, the terminal receives sensing signals sent by the base station and obtains the sensing results.
  • Sensing Link 5 Terminal Self-Sending and Receiving Sensing.
  • the terminal sends a sensing signal and obtains the sensing result by receiving the echo of the sensing signal.
  • Sensing Link 6 Sidelink sensing between terminals. For example, terminal 2 receives a sensing signal sent by terminal 1 and obtains a sensing result, or terminal 1 receives a sensing signal sent by terminal 2 and obtains a sensing result.
  • signaling transmission between radio access network devices and terminals, and between different terminals may be via Radio Resource Control (RRC) signaling, Medium Access Control Control Element (MAC CE), Layer 1 signaling, or other newly defined sensing signaling; signaling transmission between sensing network functions and terminals may be via Non-Access-Stratum (NAS) signaling (forwarded via AMF), or via RRC signaling, MAC CE, Layer 1 signaling, or other newly defined sensing signaling; interaction between sensing network functions and base stations may be via AMF forwarding to the radio access network through the N2 interface; or the core network sensing network function may send the signal to the UPF, which in turn sends it to the radio access network through the N3 interface; or the signal may be sent to the radio access network (e.g., a base station) through a newly defined interface; signaling transmission between radio access network devices may be via the Xn interface.
  • RRC Radio Resource Control
  • MAC CE Medium Access Control Element
  • Layer 1 signaling or other newly defined sensing signaling
  • the sensing network function can also be called a sensing network element or sensing management function (Sensing MF). It can be located on the radio access network side or the core network side, that is, it can be a radio access network device or a core network device. Specifically, it can refer to a network node in the core network or RAN that is responsible for at least one of the following functions: sensing request processing, sensing resource scheduling, sensing information interaction, and sensing data processing. It can be an upgrade based on the AMF or LMF in the mobile communication network, or it can be other network nodes or newly defined network nodes. Specifically, the functional characteristics of the sensing network function/sensing network element can include at least one of the following:
  • the system interacts with wireless signal transmitting devices or wireless signal measuring devices (including target terminals or base stations serving the target terminals or associated with the target area) to exchange target information.
  • the target information includes sensing processing requests, sensing capabilities, sensing auxiliary data, sensing measurement types, sensing resource configuration information, etc., in order to obtain the value of the target sensing result or sensing measurement (uplink measurement or downlink measurement) sent by the wireless signal measuring device.
  • the wireless signal can also be referred to as the sensing signal.
  • the sensing method used is determined based on factors such as the type of sensing service, the information of sensing service consumers, the required Quality of Service (QoS) requirements, the sensing capabilities of the wireless signal transmitting equipment, and the sensing capabilities of the wireless signal measuring equipment.
  • the sensing method may include: wireless access network device A transmitting and wireless access network device B receiving, or wireless access network device transmitting and terminal receiving, or wireless access network device A transmitting and receiving, or terminal transmitting and receiving, or terminal A transmitting and terminal B receiving, etc.
  • the sensing equipment serving the sensing service is determined based on factors such as the type of sensing service, information about the sensing service consumers, the required sensing QoS requirements, the sensing capabilities of the wireless signal transmitting equipment, and the sensing capabilities of the wireless signal measuring equipment.
  • the sensing equipment includes either wireless signal transmitting equipment or wireless signal measuring equipment.
  • the overall coordination and scheduling of resources required for managing sensing services such as configuring sensing resources for wireless access network devices or terminals accordingly;
  • the system processes or calculates the values of sensed measurements to obtain sensing results. It can also verify sensing results and estimate sensing accuracy.
  • the LMF is a core network element in the 5G core network that provides control plane positioning, completes the calculation and feedback of location information in the 5G network, and provides functions such as positioning process management, terminal capability acquisition, auxiliary data provision, and terminal location estimation. Specifically, it provides at least one of the following functions:
  • NG RAN Next Generation Radio Access Network
  • LMF supports medium-to-high precision positioning methods such as Cell ID, Uplink Time Difference of Arrival (UL-TDOA), and Assisting Global Navigation Satellite System (A-GNSS).
  • UL-TDOA Uplink Time Difference of Arrival
  • A-GNSS Assisting Global Navigation Satellite System
  • radars can be classified into monostatic radars and bistatic/multistatic radars based on whether the transmitter and receiver are separate.
  • Bistatic radars generally require a long distance between the transmitting and receiving antennas, comparable to the radar's effective range.
  • external radiation source radar is a special case of bistatic radar. It utilizes relevant electromagnetic wave detection theories and signal processing techniques to acquire non-cooperative electromagnetic signals emitted by a third party (such as a communication base station) to achieve target detection, location, tracking, and identification. It is also called passive radar, bistatic/multistatic passive radar, passive radar, non-cooperative illumination source radar, or non-cooperative passive detection system.
  • RT is the distance from the signal transmitter (Tx) to the target
  • RR is the distance from the signal receiver (Tx) to the target
  • L is the baseline distance
  • ⁇ T is the angle of the target relative to the signal transmitter
  • ⁇ R ⁇ R1 , ⁇ R2 ) are the angles of the target relative to the signal receiver
  • ⁇ is the bistatic angle.
  • AI has been widely applied in various fields. Integrating artificial intelligence into wireless communication networks to significantly improve technical indicators such as throughput, latency, and user capacity is an important task for future wireless communication networks.
  • AI modules can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers.
  • a neural network is used as an example for illustration, but the specific type of AI module is not limited.
  • a schematic diagram of a neural network is shown in Figure 4.
  • the neural network consists of neurons, and a schematic diagram of a neuron is shown in Figure 5.
  • a1, a2, ..., aK are the inputs
  • w is the weight (multiplicative coefficient)
  • b is the bias (additive coefficient)
  • ⁇ (.) is the activation function.
  • Common activation functions include Sigmoid, tanh, Rectified Linear Unit (ReLU), etc.
  • the parameters of the neural network are optimized using gradient optimization algorithms.
  • Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (sometimes called a loss function), which is often a mathematical combination of model parameters and data.
  • an objective function sometimes called a loss function
  • f(.) the probability density function
  • the optimization algorithm can be based on the error back propagation (BP) algorithm.
  • BP error back propagation
  • the basic idea of the BP algorithm is that the learning process consists of two processes: forward propagation of the signal and backward propagation of the error.
  • forward propagation the input sample is introduced from the input layer, processed layer by layer by the hidden layers, and then propagated to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to the error back propagation stage.
  • Error back propagation involves propagating the output error back to the input layer layer by layer through the hidden layers in a certain form, distributing the error to all units in each layer, thereby obtaining the error signal of each unit. This error signal serves as the basis for adjusting the weights of each unit.
  • This process of adjusting the weights of each layer through forward and backward propagation is repeated continuously. This continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the predetermined number of learning iterations is reached.
  • optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum descent, Nesterov (named after the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square propagation (RMSprop), and adaptive momentum estimation (Adam).
  • these optimization algorithms calculate the gradient based on the error/loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients/derivatives/partial derivatives, etc., and then pass the gradient to the previous layer.
  • the AI unit may also be referred to as an AI model, machine learning (ML) model, ML unit, AI structure, AI function, AI characteristic, machine learning model, neural network, neural network function, neural network functionality, etc.
  • an AI unit may refer to a processing unit capable of implementing specific algorithms, formulas, processing flows, capabilities, etc., related to AI.
  • An AI unit may also be a processing method, algorithm, function, module, or unit for a specific dataset.
  • an AI unit may be a processing method, algorithm, function, module, or unit running on AI/ML related hardware such as a graphics processing unit (GPU), neural processing unit (NPU), tensor processing unit (TPU), or application-specific integrated circuit (ASIC). This application embodiment does not specifically limit this.
  • the aforementioned specific dataset includes the input and/or output of the AI unit.
  • the identifier of the AI unit may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific dataset associated with the AI unit, or an identifier of a specific scenario, environment, channel characteristics, or device related to AI/ML, or an identifier of a function, feature, capability, or module related to AI/ML. This application embodiment does not specifically limit this.
  • Figure 6 is a flowchart of a capability information interaction method provided in an embodiment of this application. As shown in Figure 6, it includes the following steps:
  • Step 601 The first device reports perception capability information, which is used to indicate the AI-based perception capability of the first device.
  • the aforementioned first device can be a terminal or a network-side device.
  • the aforementioned first device may report sensing capability information to one or more devices, such as a second device.
  • the second device may be a terminal or a network-side device, and it may also be a core network device.
  • the first and second devices may be terminals or base stations (or TRPs).
  • the first device may be a terminal and the second device a base station; or, the first device may be a base station and the second device a terminal; or, both the first and second devices may be base stations; or, both the first and second devices may be terminals.
  • the first device may be a terminal or a base station
  • the second device may be a sensing network function.
  • the above-mentioned reporting of perception capability information can also be referred to as sending perception capability information.
  • the aforementioned perception capability information used to indicate the AI-based perception capability of the first device can be understood as the perception capability information used to indicate the AI-based perception capability supported by the first device. Specifically, it can indicate whether the first device supports or does not support AI-based perception capability, and it can indicate the specific AI-based perception capability supported by the first device.
  • the aforementioned perception capability information could indicate that the first device supports AI-based perception capabilities, such as AI-based perception data processing, or the AI unit deployed on the first device used for inference of perception data.
  • the perception capability information could indicate the specific AI perception capabilities supported by the first device, such as the types of perception data and perception services supported for AI processing.
  • the aforementioned perception capability information indicates that the first device does not possess AI-based perception capabilities.
  • the aforementioned AI-based perception capability may represent the ability to infer perception data based on an AI unit, or the ability to infer intermediate results of perception data based on an AI unit, which are used to determine the perception data.
  • perception data can also be referred to as perception results.
  • perception data of the perception target such as including at least one of the following:
  • the time delay Doppler effect, angle, distance, speed, orientation, spatial location, acceleration, presence of the target, number of targets, trajectory, gestures, actions, expressions, vital signs, quantity, imaging results, weather, air quality, shape, material, and composition of the target.
  • the first device reports perception capability information, which indicates the AI-based perception capabilities of the first device.
  • This enables information exchange based on AI-based perception capabilities, improving the effectiveness of perception services.
  • reporting perception capability information also enhances the perception performance between devices.
  • the perception capability information indicates the AI-based perception capabilities of the first device, it supports AI-based perception, enabling the inference of perception data or intermediate results from perception data using AI, thereby improving perception performance.
  • the aforementioned sensing capability information can be used to determine the devices, sensing methods, and sources of sensing data involved in the sensing process. By reporting the sensing capability information, more suitable or matching devices, sensing methods, and sources of sensing data can be identified, thereby improving sensing performance.
  • the sensing capability information includes at least one of the following:
  • the information includes AI-based perception data processing capabilities, supervision capabilities of perception-associated AI units, training capabilities of perception-associated AI units, reporting capabilities of perception-associated AI units, signal configuration information supported by the first device, and priority information for perception services supported by the first device using AI capabilities.
  • the signal configuration information refers to the configuration information of perception signals corresponding to perception-associated AI units.
  • AI-based perceptual data processing may include at least one of the following:
  • the intermediate results of AI unit reasoning perception data are used to determine the perception data.
  • the AI unit performs reasoning on the perceived data, such as processing the perceived data.
  • the aforementioned AI-based perception data processing capability information can indicate the reasoning ability of perception-related AI units.
  • These perception-related AI units can be AI units used to reason about perception results, or AI units used to reason about intermediate results of perception results, or other perception-related AI units.
  • the AI-based perception data processing capability information is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports AI-based perception data types
  • the first device supports AI-based perception data formats
  • the first device supports AI-processed sensing data sources
  • the first device is based on the latency of AI processing of perceived data
  • the first device is based on the accuracy of AI processing of perceived data
  • the first device is based on the performance level of AI processing perceived data
  • the first device is based on the confidence level of the perceived data processed by AI.
  • the number of AI units associated with perception supported by the first device is the number of AI units associated with perception supported by the first device
  • the types of AI units associated with perception supported by the first device are The types of AI units associated with perception supported by the first device;
  • the parameters of the AI units associated with perception supported by the first device are the parameters of the AI units associated with perception supported by the first device.
  • the aforementioned AI-processed perception data refers to the perception data input to the AI unit, that is, the AI unit processes this perception data and performs inference based on it.
  • the aforementioned AI-processed perception data type includes the type of perception data input to the AI unit;
  • the aforementioned AI-processed perception data format includes the format of the perception data input to the AI unit;
  • the aforementioned AI-processed perception data source includes the source of the perception data input to the AI unit.
  • the aforementioned AI-processed perception data can be perception results or perception-related data, such as intermediate data used to determine perception results, measurement data used to determine perception results, or measurement data used to determine intermediate results of perception results.
  • the aforementioned AI processing of perception data can involve processing perception-related data.
  • the AI-based perceptual data type includes at least one of the following:
  • Received signal channel information, spectrum information, and basic measurement quantities.
  • the aforementioned channel information can be raw channel information, such as time-domain channel response and frequency-domain channel response, and specifically can include at least one of the complex result of the channel response, amplitude/phase, and I-channel/Q-channel data.
  • the aforementioned spectral information can be spectral information calculated based on channel information or received signals, and may include at least one of the following: time delay (distance) spectrum, Doppler (velocity) spectrum, angle spectrum, time delay (distance)-Doppler (velocity) spectrum, time delay (distance)-angle spectrum, time delay (distance)-Doppler (velocity)-angle spectrum, time-Doppler spectrum (micro-Doppler spectrum).
  • the spectral information mentioned above can refer to complex results, such as a time-delay-Doppler spectrum, which refers to the time delay, Doppler index, and corresponding complex values (including phase information) in a 2D spectrum; the spectral information can also refer to a power spectrum, such as a time-delay-Doppler spectrum, which refers to the time delay, Doppler index, and corresponding power values (excluding phase information) in a 2D spectrum.
  • the aforementioned basic measurement quantities may include at least one of the following:
  • Time delay Doppler, angle, intensity, power.
  • the aforementioned basic measurement quantity can be a quantification of the actual value or soft information.
  • corresponding data types can be provided to the first device in subsequent AI sensing processes, thereby improving the AI sensing performance of the first device.
  • the AI-based perception data format includes at least one of the following:
  • channel information The dimensions of channel information, the range of spectral information, the number of basic measurements, and the types of basic measurements.
  • the dimensions of the aforementioned channel information can be frequency domain channel response information on a single symbol (one-dimensional channel information), time-frequency domain channel response information on multiple symbols (two-dimensional channel information), time-frequency spatial domain channel response information of multiple symbols and multiple antennas (three-dimensional channel information), as well as different dimensions of scale, i.e. the number of sampling points or sampling interval (e.g., time-frequency domain density).
  • the range of spectral information can be used to limit the range of different spectral information, or it can be called a truncation window for different dimensions of spectral information. That is, spectral information can be the complete spectral information calculated based on channel information, or it can be a subset of the complete spectral information. For example, it can be a subset of spectral information corresponding to a specific time delay or Doppler range in a time-delay-Doppler spectrum, or information about paths or sampling points in a time-delay-Doppler spectrum whose power or amplitude exceeds a preset threshold. It can also indicate the upper limit of the number of paths or sampling points of a specific input spectrum that the AI unit supports. It can also indicate the minimum granularity of a specific input spectrum that the AI unit supports, that is, the interval between two adjacent sampling points (corresponding to the sensing resolution).
  • the number of basic measurements can be the number of measurements input into the AI unit at one time.
  • the types of the basic measurements mentioned above can be the quantification method of the measurement value (e.g., quantification granularity) or soft information types, such as providing the mean + variance, or soft information such as confidence intervals and confidence levels.
  • quantification method of the measurement value e.g., quantification granularity
  • soft information types such as providing the mean + variance, or soft information such as confidence intervals and confidence levels.
  • the corresponding type of data can be provided to the first device in subsequent AI perception, thereby improving the AI perception performance of the first device.
  • the type of perception data output by the AI unit supported by the first device can be one or more types of perception data processed and output by the AI unit supported by the first device.
  • This perception data can be the perception result or an intermediate result of the perception result.
  • the types of perception data output by the AI unit supported by the first device include:
  • the AI units supported by the first device jointly process the output of multiple types of sensory data, or the AI units supported by the first device independently process the output of at least one type of sensory data.
  • the data types of perception output by the AI unit supported by the first device may include at least one of the following: target latency, Doppler, angle, distance, speed, orientation, spatial location, acceleration, target presence, number of targets, trajectory, gesture, action, expression, vital signs, quantity, imaging results, weather, air quality, shape, material, and composition.
  • the first device can be selected to participate in suitable perception services based on the perception data, thereby improving perception performance.
  • the source of the perception data supported by the first device based on AI processing can indicate the source of the perception data processed by the AI unit supported by the first device.
  • the sources of the aforementioned AI-based perception data include at least one of the following:
  • RAT radio access technology
  • the phrase "from a single device” indicates that the first device supports the processing of perception data from a single device by the AI unit, while “from multiple devices” indicates that the first device supports the joint processing of perception data from different devices.
  • the aforementioned sources of AI-based perception data can also indicate the maximum number of devices that can generate the AI-based perception data.
  • the aforementioned target perception mode indicates that the first device supports AI processing of perception data acquired from the target perception mode.
  • This target perception mode can be one mode or multiple modes. When multiple modes are used, it indicates that the first device supports AI processing of perception data acquired from multiple different perception modes.
  • the aforementioned target perception mode includes at least one of the following: base station self-transmission and self-reception, base station A transmitting and base station B receiving, base station transmitting and terminal receiving, terminal transmitting and base station receiving, terminal self-transmission and self-reception, terminal A transmitting and terminal B receiving; or the aforementioned target perception mode can refer to single-base perception or dual-base perception.
  • the aforementioned "from sensors” can indicate that the first device supports AI processing of perceived data from sensors, or supports joint AI processing of perceived data from sensors and wireless sensing.
  • the sensors can include at least one of the following: visible light cameras, infrared cameras, Global Navigation Satellite System (GNSS), lidar, millimeter-wave radar, thermometers, hygrometers, barometers, gyroscopes, accelerometers, magnetometers, gravity sensors, sonar, rain gauges, etc.
  • GNSS Global Navigation Satellite System
  • lidar lidar
  • millimeter-wave radar thermometers
  • hygrometers hygrometers
  • barometers gyroscopes
  • accelerometers magnetometers
  • gravity sensors sonar, rain gauges, etc.
  • the above-mentioned “from at least one RAT” can indicate that the first device supports the processing of sensing data from one or more RATs.
  • the first device supports AI processing of sensing data acquired based on more than one wireless access technology (including but not limited to 4G, 5G, 6G, Wifi, Ultra Wide Band (UWB), Bluetooth, etc.).
  • the corresponding source data can be provided to the first device in subsequent AI sensing, thereby improving the AI sensing performance of the first device.
  • the latency of the first device in processing perceived data based on AI can be the inference speed of the AI unit, specifically the maximum or minimum processing latency of the AI unit, and can be the corresponding processing latency given according to different types of perceived data input or output.
  • the latency of AI-based processing of sensing data by the aforementioned first device can help improve the sensing performance of sensing services that have latency requirements, such as selecting devices whose latency meets the needs of sensing services to participate in sensing.
  • the accuracy of the first device in processing the perception data based on AI can be the accuracy of the perception data output by the AI unit of different perception data types, and this accuracy can be expressed as error.
  • the performance level of the first device in processing sensing data based on AI can be the performance level of sensing data output by AI units of different sensing data types.
  • the confidence level of the first device based on AI processing of the perceived data can be the confidence level of the perceived data output by the AI unit of different types of perceived data.
  • the first device when the first device has higher processing power, it can provide more accurate perception data processing results, that is, it can achieve a higher performance level or confidence level.
  • the accuracy, performance level, and confidence level of the first device in processing perception data based on AI can help improve the perception performance of perception services that have relevant requirements for perception results. For example, selecting devices with accuracy, performance level, and confidence level that meet the requirements of the perception service to participate in perception can improve perception performance.
  • the number of perception-related AI units supported by the first device may be the number of perception-related AI units supported by the first device, or the number of AI units of the AI unit type supported by the first device.
  • the types of AI units supported by the first device can be a list of AI unit IDs supported by the first device, and different types of AI units can be associated with different perception scenarios, perception use cases, perception targets or perception services, or different types of AI units can be associated with different AI unit parameters.
  • the aforementioned sensing scenarios include at least one of the following: indoor, outdoor, office area, living room, factory, suburb, town, street, vehicle scenario, vehicle to everything (V2X) scenario, macro station, micro station, high-speed rail, highway intersection, shopping mall, parking lot, scenic spot.
  • V2X vehicle to everything
  • the aforementioned perceived targets include at least one of the following: unmanned aerial vehicle (UAV), human, automotive vehicle, automated guided vehicle (AGV), and objects on roads/railways.
  • UAV unmanned aerial vehicle
  • AGV automated guided vehicle
  • the aforementioned sensing services include at least one of the following: for example, detecting the presence or absence of a target, detecting the number of targets, localization, trajectory tracking, speed detection, distance detection, angle detection, acceleration detection, material analysis, composition analysis, shape detection, category classification, radar cross section (RCS) detection, polarization scattering characteristic detection, fall detection, intrusion detection, indoor positioning, gesture recognition, lip reading, gait recognition, expression recognition, facial recognition, respiration monitoring, heart rate monitoring, pulse monitoring, humidity/brightness/temperature/atmospheric pressure monitoring, air quality monitoring, weather condition monitoring, environmental reconstruction, terrain and geomorphology detection, etc.
  • RCS radar cross section
  • detection-type sensing services e.g., intrusion detection, fall detection
  • parameter estimation-type sensing services distance, angle, speed calculation
  • recognition-type sensing services action recognition, identity recognition
  • it can also be divided according to the range of sensing near-
  • the aforementioned sensing capability information may also include AI unit capability information associated with a specific sensing service.
  • AI unit capability information associated with a specific sensing service.
  • target number detection and parameter (distance, speed, angle, position, etc.) estimation it may also include the maximum number of targets that can be detected, the maximum range of distance measurement, the maximum range of speed measurement, or the maximum range of angle measurement, etc.
  • action recognition it may also include the maximum number of actions that can be recognized or the set of action types that can be recognized.
  • the types of perception-associated AI units supported by the aforementioned first device may include at least one of the following:
  • Gaussian processes support vector machines, and neural networks
  • the neural network can be a fully connected neural network, a convolutional neural network, a recurrent neural network, or a residual network, or a combination of multiple small networks, such as fully connected + convolution, convolution + residual, etc.
  • the types of AI units that the first device supports for perception association can help other devices better select suitable devices to participate in perception, which is beneficial to improving perception performance.
  • the parameters of the aforementioned perception-related AI unit include at least one of the following:
  • Unit structure information hyperparameter configuration, data processing method, running cycle, update information, complexity information, available AI resources, AI framework, and AI algorithm.
  • the aforementioned unit structure information may include structural information such as the number of layers in the neural network, the number of neurons in each layer, and the activation function.
  • hyperparameter configurations mentioned above can be parameters in the AI unit that need to be manually specified and are not updated during the data training process, such as relevant parameters in the kernel function, relevant parameters in the activation function, and relevant parameters in the normalization layer.
  • the data processing methods described above can be preprocessing methods for data before it is input into the AI unit. These data processing methods may include, but are not limited to, normalization, upsampling, downsampling, etc.
  • the above-mentioned operating cycle can be defined as how often the AI unit executes its operation.
  • the above update information can be the update cycle, such as how often the AI unit updates.
  • the aforementioned update information may include at least one of the following: kernel function update information, hyperparameter update information, prediction model update information, computation model update information, etc.
  • the complexity information mentioned above can be the number of floating-point operations (FLOPs) in the AI unit's inference, such as 100 iterations, or it can be the hardware and computational conditions of the AI unit.
  • FLOPs floating-point operations
  • the available AI resources mentioned above can be computing or storage resources that can be used by AI.
  • the parameters of the AI units associated with the aforementioned perception can enable suitable devices to participate in perception during the perception process, thereby improving perception performance.
  • the supervisory capability information of the aforementioned perception-related AI unit can indicate the first device's ability to supervise the AI unit, whereby supervision refers to the supervision of the perception data output by the AI unit.
  • This AI unit can be an AI unit deployed on the first device or an AI unit deployed on other devices.
  • the supervisory capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports reference data types, wherein the reference data is reference data used for AI unit supervision of perception association;
  • the first device supports reporting supervisory metrics for AI units associated with perception.
  • the first device supports reporting the supervision results of the AI units associated with perception.
  • Whether the aforementioned first device supports supervision of AI units associated with perception can be determined by whether it supports supervision of AI units for specific perception scenarios or perception services.
  • supervision of the AI unit can be carried out based on the supervision cycle, supervision duration, or number of supervisions in the subsequent AI unit supervision process, thereby improving the AI unit supervision performance.
  • the aforementioned reference data can be understood as the actual label or reference label of the aforementioned AI unit, that is, as a reference for the perception data output by the aforementioned first AI unit. Furthermore, the aforementioned reference data can be a reference signal acquired by the first device, or a reference signal acquired by other devices.
  • the reference data type includes at least one of the following:
  • Perceptual data acquired by an AI unit with capabilities superior to the AI unit associated with the perception acquired by an AI unit with capabilities superior to the AI unit associated with the perception.
  • the sensing target with known sensing characteristics can be a sensing reference target or a sensing reference unit.
  • the aforementioned sensor data can be understood as a reference for the sensor data obtained through sensor acquisition, which is used as the sensor data obtained through AI unit reasoning in wireless sensing.
  • the target perception mode mentioned above can be at least one of the modes shown in Figure 2.
  • the perception data obtained by the monostatic perception mode can be used as a reference for the perception data obtained by AI inference in the bistatic perception mode.
  • the aforementioned target sensing device can be a base station or a terminal.
  • the sensing data acquired by the base station can serve as a reference for the sensing data obtained by the terminal through AI reasoning.
  • the sensing data obtained through non-AI methods mentioned above can be sensing data calculated based on channel information using conventional parameter estimation algorithms, such as...
  • Perceptual data calculated by 2D-Fast Fourier Transform (2D-FFT), 3D-Fast Fourier Transform (3D-FFT), Multiple Signal Classification (MUSIC), and ESPRIT algorithm are used as reference data for perceptual data obtained by AI unit inference.
  • the location data of the aforementioned active device can be used as reference data for the location results obtained by wireless sensing and AI reasoning when the device is regarded as a passive target, through the result of device location by transmitting and receiving location signals with the device.
  • the perception data obtained by the AI unit with stronger capabilities than the perception-associated AI unit can be understood as the perception data output by the stronger AI unit as reference data for the perception data inferred by the perception-associated AI unit.
  • the reference data types supported by the first device can be used to provide corresponding reference data to the first device during the AI unit supervision process, or for the first device to obtain this reference data, which is beneficial to improving the supervision performance of the AI unit.
  • the aforementioned first device supports reporting the supervision metrics of the AI unit associated with perception.
  • This can be understood as the first device supporting the reporting of these supervision metrics.
  • These supervision metrics refer to the metrics supervised by the AI unit associated with perception, such as the statistical results of the error between the perceived data output by the AI unit and the reference data, which can be the root mean square error (RMSE).
  • RMSE root mean square error
  • the aforementioned first device's ability to report the supervision results of the AI unit associated with perception can be understood as the first device being able to report the supervision results of the AI unit, such as the first device supervising the AI unit and being able to report the supervision results.
  • the supervision results can be obtained from the first device during the AI unit supervision process, which is conducive to improving the effectiveness of AI unit supervision.
  • the training capability information of the aforementioned perception-related AI unit can indicate the training capability of the AI unit of the first device.
  • the training capability information of the aforementioned perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the training time of the AI units associated with perception supported by the first device is the training time of the AI units associated with perception supported by the first device
  • the amount of training data for the AI units associated with perception supported by the first device is the amount of training data for the AI units associated with perception supported by the first device
  • the first device supports perceptual data types for training AI for perceptual association.
  • the first device supports the following perception data formats for AI used in perception association.
  • the first device supports the source of perception data for AI used in perception association
  • the first device supports fine-tuning of the AI units associated with perception
  • the first device supports retraining of the AI units associated with perception
  • the first device supports hybrid training of AI units that are associated with perception in multiple perception scenarios
  • the first device supports hybrid training of AI units that are associated with multiple sensing services.
  • Whether the aforementioned first device supports the training of AI units associated with perception can refer to whether it supports the training of AI units for specific perception scenarios or perception services.
  • the training time of the AI units associated with perception supported by the first device mentioned above may include the training time of AI units corresponding to different perception scenarios or perception services.
  • the training perception data type, training perception data format, or training perception data source supported by the first device for perception association can be found in the perception data type, perception data format, or perception data source in the above embodiments, and will not be repeated here.
  • the aforementioned AI unit-related reporting capability information is used to instruct the first device to report AI unit-related capabilities.
  • the reporting capability information associated with the perception-related AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports the reporting of sensor data types
  • the first device supports the reported sensing data formats
  • the first device supports the reporting of sensor data sources
  • the first device supports the reporting of reference data types
  • the first device supports the reported reference data format
  • the first device supports reporting reference data sources
  • the first device supports reporting AI capability limitation information for perception.
  • the reference data refers to the reference data used for supervising or training AI units that are used for perception association.
  • the reported perception data can be perception data input to the AI unit, such as measurement data, or intermediate results of perception. It can also be perception data output by the AI unit, i.e., perception data used for AI unit inference, such as perception results or intermediate results of perception.
  • perception data used for AI unit inference such as perception results or intermediate results of perception.
  • the first device supports reporting perception data input to the AI unit, it indicates that the first device does not support AI-based perception data processing capabilities, but can provide perception data input to the AI unit, which can be used for AI unit inference or training.
  • sensing data types, sensing data formats, or sensing data sources can be found in the sensing data types, sensing data formats, or sensing data sources described in the above embodiments, and will not be repeated here.
  • reference data types, reference data formats, or reference data sources mentioned above can be found in the reference data types, reference data formats, or reference data sources in the above embodiments, and will not be repeated here.
  • the fact that the first device supports reporting the aforementioned reference data indicates that the first device does not have the ability to supervise or train the AI unit associated with perception, but can provide reference perception data for the supervision or training of the AI unit.
  • the aforementioned reporting capability information related to the AI unit of perception association may also include the accuracy of the reference data that the first device supports reporting.
  • relevant data can be acquired from the first device in subsequent processes, thereby enhancing the effectiveness of perception, AI unit supervision, or AI unit training.
  • the aforementioned first device's ability to report AI capability limitation information for perception can be understood as the first device being able to report AI capability limitation information for perception.
  • This AI capability limitation information can be used to indicate the resources that the first device limits for AI capabilities, such as the absolute value or proportion of computing power, power consumption, and processing timeline that can be allocated to the perception business. Furthermore, different resources can be allocated for the AI unit inference stage and the AI unit training stage.
  • the terminal's AI capability limitation information can be obtained in subsequent processes, thereby avoiding exceeding the limitations of the first device and ensuring perception performance.
  • the signal configuration information supported by the first device mentioned above can be used to obtain the perception data input during the inference or training of the AI unit.
  • the signal configuration information supported by the first device can be used to configure the corresponding signal configuration information for the first device in the subsequent sensing process or AI unit training, or to measure the signal sent by the first device based on the signal configuration information in the subsequent sensing process or AI unit training, which is beneficial to improving sensing performance.
  • the signal configuration information described above includes at least one of the following:
  • Signal resource identifiers are used to distinguish different signal resource configurations
  • the purpose of the signal indicates whether it is used for communication (e.g., channel measurement, channel estimation, synchronization, carrying data information, etc.), for sensing, or for both communication and sensing. More specifically, it can also specify which sensing service the signal is used for, or which type of sensing service it is used for.
  • Waveforms such as orthogonal frequency division multiplex (OFDM), single-carrier frequency-division multiple access (SC-FDMA), orthogonal time-frequency space (OTFS), frequency-modulated continuous wave (FMCW), pulse signals, etc.
  • OFDM orthogonal frequency division multiplex
  • SC-FDMA single-carrier frequency-division multiple access
  • OTFS orthogonal time-frequency space
  • FMCW frequency-modulated continuous wave
  • pulse signals etc.
  • Subcarrier spacing for example, 30 kHz in an OFDM system
  • the guard interval is the time interval between the end of signal transmission and the latest echo signal of the signal being received. This parameter is proportional to the maximum sensing distance. For example, it can be calculated by c/(2R max ), where R max is the maximum sensing distance (belonging to the sensing requirement information). For example, for self-transmitting and self-receiving sensing signals, R max represents the maximum distance from the sensing signal transmission point to the signal transmission point.
  • the OFDM signal cyclic prefix (CP) can serve as the minimum guard interval.
  • CP the OFDM signal cyclic prefix
  • the starting frequency domain position i.e., the starting frequency point, can also be the starting RE or RB index;
  • the starting time domain position i.e. the starting time point, can also be the starting symbol index, time slot index, or frame index;
  • the terminating frequency domain position i.e., the terminating frequency point, can be represented by the terminating RE and RB indices;
  • the termination time domain position i.e. the termination time point, can be represented using the termination RE and RB indices;
  • Frequency domain resource length i.e. frequency domain bandwidth
  • the frequency domain bandwidth B of each first signal is B ⁇ c/(2 ⁇ R), where c is the speed of light and ⁇ R is the distance resolution.
  • the time-domain resource length also known as the burst duration, is inversely proportional to the Doppler resolution.
  • the frequency domain resource spacing is inversely proportional to the maximum unambiguous distance/delay. For OFDM systems, when subcarriers are continuously mapped, the frequency domain spacing is equal to the subcarrier spacing.
  • the frequency domain resource unit spacing can also be represented by the comb mapping parameter K comb .
  • Time-domain resource interval is the time interval between two adjacent signal resource units.
  • the time-domain resource interval is related to the maximum unambiguous Doppler frequency shift or the maximum unambiguous velocity.
  • Temporal resource characteristics such as periodic transmission, semi-persistent transmission, and non-periodic transmission.
  • the time-domain burst resource interval or time-domain burst transmission period is related to the refresh frequency of the sensing results.
  • Signal power for example, taking a value every 2dBm from -20dBm to 23dBm;
  • Sequence information including sequence type information (ZC sequence, PN sequence, etc.), sequence generation method, sequence length, etc.;
  • Signal direction including the angle or beam information of signal transmission
  • Quasi-co-location (QCL) relationships such as a signal comprising multiple resources, each resource being associated with a Synchronization Signal Block (SSB) QCL, where the QCL can be of type A, type B, type C, or type D.
  • SSB Synchronization Signal Block
  • Cyclic prefix (CP) information can include CP type or CP length, such as normal cyclic prefix (NCP), extended cyclic prefix (ECP), or newly designed sensing measurement-specific CP.
  • NCP normal cyclic prefix
  • ECP extended cyclic prefix
  • the priority information of the AI capabilities used by the sensing services supported by the first device is used to indicate the priority of the AI capabilities used by the sensing services supported by the first device.
  • a priority level can be defined, with three levels from high to low priority.
  • the priority of AI processing for sensing services is 2, the priority of AI processing for RAN is 3, and the priority of external services is 1. In this way, when there is competition or conflict, it is processed according to priority to improve the working performance of the first device.
  • the sensing capability information is carried in at least one of the following:
  • AS Access Stratum
  • NAS Non-Access Stratum
  • the AS capability information mentioned above can be terminal wireless capability information, which enables the reporting of sensing capability information in the AS capability information, thus eliminating the need for additional messages and saving transmission overhead.
  • the sensing capability information may include AI-based sensing capabilities related to a band, band combination, or carrier.
  • the sensing capability information may also include AI-based sensing data processing accuracy information, achievable performance level, confidence level, or inference speed on the corresponding band, band combination, or carrier.
  • the aforementioned NAS capability information can be terminal core network capability information, which enables the reporting of perception capability information on the NAS capability information, thereby eliminating the need for additional messages and saving transmission overhead.
  • the method further includes:
  • the first device obtains a device capability request
  • the device capability request is used to request the capabilities of the first device; or, the device capability request is used to request the sensing capabilities of the first device.
  • the aforementioned device capability request may be a device capability request sent by a second device.
  • the aforementioned device capability request is used to request the capabilities of the first device. This can be understood as the aforementioned device capability request being used to request the general capabilities or all capabilities of the first device, such as the aforementioned device capability request being a general device capability request.
  • the first device may report the aforementioned sensing capability information and other capability information.
  • the first device When the aforementioned device capability request is used to request the sensing capability of the first device, the first device reports the aforementioned sensing capability information.
  • the device capability request when used to request the capability of the first device, the device capability request includes an information unit for requesting the sensing capability of the first device.
  • the device capability request may be used to request at least one sensing capability of the first device.
  • the aforementioned device capability request includes an information unit for requesting the perception capability of the first device.
  • This can be understood as the information unit in the device capability request including request information for requesting the aforementioned perception capability, that is, the AI-based perception capability request information is the information unit of the aforementioned device capability request.
  • the aforementioned device request for requesting at least one sensing capability of the first device can be understood as the aforementioned device request capability being used to request a specific capability, such as: requesting to obtain AI-based sensing capabilities supported by the first device, or requesting to obtain information on the first device's AI-based sensing data processing capabilities, or requesting one or more specific capability information, such as requesting to obtain the sensing data type, format, or source supported by the first device for input to the AI unit, and the first device reporting at least one of the AI-based sensing capability information according to the capability request information.
  • a specific capability such as: requesting to obtain AI-based sensing capabilities supported by the first device, or requesting to obtain information on the first device's AI-based sensing data processing capabilities, or requesting one or more specific capability information, such as requesting to obtain the sensing data type, format, or source supported by the first device for input to the AI unit, and the first device reporting at least one of the AI-based sensing capability information according to the capability request information.
  • the aforementioned sensing capability information may be actively reported by the first device.
  • the sensing capability information includes at least one of the following:
  • sensing capability information can be reported at the granularity of frequency band, frequency band combination, or CC, thereby improving the accuracy of capability reporting.
  • the first device reports perception capability information, which indicates the AI-based perception capabilities of the first device. This enables information exchange based on AI-based perception capabilities, thus improving the effectiveness of perception services. Furthermore, reporting perception capability information also helps improve the perception performance between devices.
  • Figure 7 is a flowchart of a capability information interaction method provided in an embodiment of this application. As shown in Figure 7, it includes the following steps:
  • Step 701 The second device receives perception capability information, which is used to indicate the perception capability of the first device based on artificial intelligence (AI).
  • AI artificial intelligence
  • the perception capability information includes at least one of the following:
  • the information includes AI-based perception data processing capabilities, supervision capabilities of perception-associated AI units, training capabilities of perception-associated AI units, reporting capabilities of perception-associated AI units, signal configuration information supported by the first device, and priority information for perception services supported by the first device using AI capabilities.
  • the signal configuration information refers to the configuration information of perception signals corresponding to perception-associated AI units.
  • the AI-based perception data processing capability information is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports AI-based perception data types
  • the first device supports AI-based perception data formats
  • the first device supports AI-processed sensing data sources
  • the first device is based on the latency of AI processing of perceived data
  • the first device is based on the accuracy of AI processing of perceived data
  • the first device is based on the performance level of AI processing perceived data
  • the first device is based on the confidence level of the perceived data processed by AI.
  • the number of AI units associated with perception supported by the first device is the number of AI units associated with perception supported by the first device
  • the types of AI units associated with perception supported by the first device are The types of AI units associated with perception supported by the first device;
  • the parameters of the AI units associated with perception supported by the first device are the parameters of the AI units associated with perception supported by the first device.
  • the AI-based perceptual data type includes at least one of the following:
  • the AI-based perception data format may include at least one of the following:
  • channel information The dimensions of channel information, the range of spectral information, the number of basic measurements, and the types of basic measurements;
  • the types of perception data output by the AI unit supported by the first device include:
  • the AI units supported by the first device jointly process the output of multiple types of sensory data, or the AI units supported by the first device independently process the output of at least one type of sensory data.
  • the sources of the AI-based perception data include at least one of the following:
  • RAT wireless access technology
  • the parameters of the perception-associated AI unit include at least one of the following:
  • Unit structure information hyperparameter configuration, data processing method, running cycle, update information, complexity information, available AI resources, AI framework, and AI algorithm.
  • the supervisory capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports reference data types, wherein the reference data is reference data used for AI unit supervision of perception association;
  • the first device supports reporting supervisory metrics for AI units associated with perception.
  • the first device supports reporting the supervision results of the AI units associated with perception.
  • the reference data type includes at least one of the following:
  • Perceptual data acquired by an AI unit with capabilities superior to the AI unit associated with the perception acquired by an AI unit with capabilities superior to the AI unit associated with the perception.
  • the training capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the training time of the AI units associated with perception supported by the first device is the training time of the AI units associated with perception supported by the first device
  • the amount of training data for the AI units associated with perception supported by the first device is the amount of training data for the AI units associated with perception supported by the first device
  • the first device supports perceptual data types for training AI for perceptual association.
  • the first device supports the following perception data formats for AI used in perception association.
  • the first device supports the source of perception data for AI used in perception association
  • the first device supports fine-tuning of the AI units associated with perception
  • the first device supports retraining of the AI units associated with perception
  • the first device supports hybrid training of AI units that are associated with perception in multiple perception scenarios
  • the first device supports hybrid training of AI units that are associated with multiple sensing services.
  • the reporting capability information related to the AI unit associated with the perception is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports the reporting of sensor data types
  • the first device supports the reported sensing data formats
  • the first device supports the reporting of sensor data sources
  • the first device supports the reporting of reference data types
  • the first device supports the reported reference data format
  • the first device supports reporting reference data sources
  • the first device supports reporting AI capability limitation information for perception.
  • the reference data refers to the reference data used for supervising or training AI units that are used for perception association.
  • the perception capability information is carried in at least one of the following:
  • Access layer AS capability information is available.
  • non-access layer NAS capability information is available.
  • the method further includes:
  • the second device sends a device capability request
  • the device capability request is used to request the capabilities of the first device; or, the device capability request is used to request the sensing capabilities of the first device.
  • the device capability request when used to request the capability of the first device, includes an information unit for requesting the sensing capability of the first device;
  • the device capability request may be used to request at least one sensing capability of the first device.
  • the perception capability information includes at least one of the following:
  • the method further includes:
  • the second device performs a determination operation based on the sensing capability information, the determination operation being used to determine at least one of the following:
  • the devices involved in sensing the sensing methods, and the sources of sensing data.
  • the aforementioned second device may perform the aforementioned determining operation based on the perception capability information reported by one or more first devices. For example: selecting a first device whose AI-based perception capability matches the perception service or perception scenario from among multiple first devices as the device participating in perception; or selecting a perception method that matches the AI-based perception capability of the first device based on the perception capability information of the first device; or selecting a perception data source that matches the first device based on the perception capability information of the first device.
  • the aforementioned determination process can better match the perception with the AI-based perception capabilities of the first device, thereby improving perception performance.
  • this embodiment is an implementation of the third device corresponding to the embodiment shown in FIG6.
  • This embodiment mainly describes how to determine whether a first device participates in sensing through capability interaction.
  • the first device is a terminal or base station
  • the second device is a sensing network function.
  • the first device is a sensing data processing device, which can be a device participating in sensing measurement (e.g., a device that receives sensing signals and performs measurements to obtain measurement results), or it can be a device not participating in sensing measurement, where the device participating in sensing measurement sends the acquired measurement results to the first device for processing.
  • the sensing network function selects devices to participate in the sensing service.
  • the sensing data corresponding to the sensing service needs to be calculated and output by an AI unit, which is a network architecture obtained through deep learning/machine learning.
  • the sensing data can be the final sensing result (e.g., target location, trajectory, gesture, or action), or intermediate measurement results used to calculate the final sensing result (e.g., latency, Doppler, angle).
  • the sensing network function needs to select devices with AI-based sensing data processing capabilities to participate in the sensing service. The specific process is shown in Figure 8, including the following steps:
  • Step 1 The Sensing Network Function (SensingMF) acquires sensing requirement information.
  • the sources of sensing requirements can be:
  • the sensing requirement information comes from an external application.
  • the application function (AF) sends the sensing requirement information to the NEF, which then sends it to the AMF.
  • the AMF selects SensingMF and sends the sensing requirement to SensingMF.
  • AF can directly send the sensing requirement to SensingMF;
  • Sensing demand information can also come from base stations and/or terminals.
  • the base station and/or terminal sends the information to the AMF, and the AMF selects SensingMF and sends the sensing demand to SensingMF.
  • the base station and/or terminal may directly send the sensing requirements to SensingMF;
  • Sensing demand information can also come from core network elements, which send sensing demands to the AMF.
  • AMF selects SensingMF and sends the sensing requirements to SensingMF
  • core network elements can directly send sensing requirement information to SensingMF.
  • the method of forwarding sensing requirements through AMF may appear, but is not limited to, in scenarios where multiple sensing network elements are deployed in the network, and the AMF needs to select a suitable sensing network element from multiple sensing network elements based on information such as the location of the sensing object, the type of sensing service, or the sensing QoS requirements; the method of forwarding sensing requirements without AMF may appear, but is not limited to, in scenarios where one or fewer SensingMFs are deployed in the network.
  • the perceived demand information includes at least one of the following:
  • sensing service or sensing service type is described in the corresponding description of the above implementation method, and will not be repeated here.
  • the target area for perception can refer to the area where the object being perceived may exist, or the area where imaging or environmental reconstruction is required.
  • the sensing object type can be a classification of sensing objects based on their possible motion characteristics.
  • Each sensing object type contains information such as the motion velocity, motion acceleration, and typical RCS of a typical sensing object.
  • Sensitive QoS can be a performance metric for sensing target areas or objects, including at least one of the following:
  • Perception resolution can be categorized into: ranging resolution, angle measurement resolution, velocity measurement resolution, and imaging resolution, etc.
  • Sensing accuracy can be categorized into: ranging accuracy, angle measurement accuracy, velocity measurement accuracy, positioning accuracy, etc.
  • the sensing range can be divided into: ranging range, velocity measuring range, angle measuring range, imaging range, etc.
  • Perception latency can be the time interval from the transmission of a sensing signal to the acquisition of a sensing result, or the time interval from the initiation of a sensing demand to the acquisition of a sensing result.
  • the perception update rate such as the time interval between two consecutive perception operations and the acquisition of perception results
  • Detection probability such as the probability of correctly detecting an object given its presence
  • Recognition probability (used in multivariate detection scenarios, representing the probability of correctly detecting a target state or category when the target is in a specific state or belongs to a specific category);
  • False alarm probability such as the probability of falsely detecting a target when the target does not exist
  • Step 2 SensingMF sends a capability request message (i.e., a device capability request in the above embodiment) to the first device (referring to multiple candidate devices participating in sensing) to request the capability of the first device.
  • a capability request message i.e., a device capability request in the above embodiment
  • AI-based perception capability request information is carried by an information element (IE) in the capability request information sent by the perception network function to the first device.
  • IE information element
  • This capability request information is used to request the perception capability of the first device.
  • the first device responds to the capability request information and reports its perception capability information, which includes AI-based perception capability information.
  • Step 3 The first device (referring to multiple candidate devices participating in sensing) responds to the capability request information sent by SensingMF and feeds back its sensing capability information, which includes AI-based sensing capability information to indicate the AI-based sensing capability of the first device.
  • AI-based perception capability information includes the supported AI unit types associated with perception, which can be AI unit identifiers (AI model index), AI unit configuration identifiers, perception scenario or use case identifiers, perception target type identifiers, or perception business identifiers; AI-based perception capability information also includes AI-based perception data processing accuracy information, or achievable performance level or confidence level, or AI unit inference speed.
  • Step 4 SensingMF selects a device with AI-based sensing data processing capabilities or supporting AI units corresponding to specific sensing services, based on the first device's support for AI-based sensing capabilities, or selects a device with AI-based sensing data processing capabilities that can meet sensing requirements (e.g., processing latency meets sensing result refresh rate requirements, or output sensing data accuracy meets sensing accuracy requirements) to participate in the sensing service.
  • sensing requirements e.g., processing latency meets sensing result refresh rate requirements, or output sensing data accuracy meets sensing accuracy requirements
  • the aforementioned interactive information can be used to identify devices that meet the sensing requirements and prevent unqualified devices from participating in sensing, which can effectively ensure sensing performance and improve resource utilization efficiency.
  • This embodiment mainly describes how the perception of the first device is determined through capability interaction.
  • the first device is the device that is determined to participate in sensing.
  • the second device determines the first device's AI-based sensing capabilities through capability query, and then determines the first device's sensing method, such as selecting an AI-based method or a non-AI method, and instructs the first device to report one or more types of sensing data after processing by the AI unit, which can effectively ensure sensing performance and improve the efficiency of sensing measurement reporting.
  • the second device may determine the sensing signal resources and related configurations allocated to the first device based on the first device's AI-based sensing capabilities, thereby enabling the first device to have better sensing data processing performance.
  • the first device may not be a device involved in sensing and measurement (a device that sends or receives sensing signals and performs measurements to obtain measurement results), but is only responsible for sensing data processing.
  • the second device determines the type, format, or source of the sensing data to be sent to the first device based on the first device's information about AI-based sensing capabilities, so that the first device can further process the sensing data based on AI.
  • the second device determines the sensing signal resources and related configurations allocated to the first device based on the AI-based sensing capability information of the first device.
  • the first device obtains sensing data that meets the input requirements of the AI unit by measuring the sensing signals, so as to enable it to have better sensing data processing performance.
  • the first information in step 4 includes at least one of the following: sensing signal configuration information, sensing measurement configuration information (including measurement method, reporting configuration, etc.), and sensing data to be processed (sent to the first device and processed based on the AI unit on the first device side);
  • Step 5 After receiving the first information, the first device executes the wireless sensing measurement process (if the first device is a device participating in sensing), and processes the sensing data through the AI unit.
  • the sensing data can be obtained through wireless sensing measurement, or it can be sent to the first device by the second device, or it can be sent to the first device by other devices.
  • Step 6 The first device sends the perception data output after processing by the AI unit to the second device.
  • the first device is equipped with an AI unit, which determines its model training capability through capability interaction, and performs model fine-tuning or retraining when the perceived scene changes.
  • the first device deploys an AI unit.
  • the second device queries whether the first device has the training capability for the AI unit associated with sensing, and the supported sensing data types, formats, or sources for model training. It then instructs the first device on the training configuration for model training, such as hyperparameters (pre-given parameters used to control the learning process, including, for example, the topology and size of the neural network, learning rate, and mini-batch size), the expected sensing accuracy, the number of training iterations, or the training duration.
  • hyperparameters pre-given parameters used to control the learning process, including, for example, the topology and size of the neural network, learning rate, and mini-batch size
  • the data used for model training can be sensing data sent to the first device by the second device or other devices, or sensing signal resources allocated to the first device, which then collects the sensing data for model training through wireless sensing measurements.
  • Fine-tuning refers to using specific, limited perceptual data for small-scale training based on pre-trained AI units associated with perception. This allows for minor adjustments to the parameters of the pre-trained model, ultimately resulting in a model adapted to a specific perception scenario or business.
  • the first device is provided with suitable perceptual data based on its fine-tuning capabilities for the perception-associated AI units. This assists the first device in adjusting its original model to adapt to the changed perception scenario or target, ensuring perception performance. If the first device does not support model fine-tuning, it can also be instructed to re-collect suitable perceptual data based on the changed perception scenario or target to retrain the model, thereby maintaining perception performance.
  • the first device can be instructed to switch to an AI unit that adapts to the changed perception scene, or the first device can be stopped from being used as a device to participate in perception, thereby avoiding the first device from reporting invalid perception data and ensuring perception performance.
  • the first device does not deploy an AI unit, but it can provide perception data.
  • the perception data obtained from the first device is determined through capability interaction.
  • the first device does not deploy an AI unit
  • the second device deploys an AI unit associated with sensing.
  • the second device queries the sensing data input to the AI unit that the first device supports reporting, including the types, formats, or sources of sensing data input to the AI unit that it supports reporting (see the application scheme for details).
  • the second device requests corresponding sensing data from the first device for inference or training of its own AI unit.
  • the second device may request the reference perception data from the first device, which supports reporting the reference perception data for the supervision of the AI unit.
  • This reference perception data includes the types or formats of perception data input to the AI unit that support reporting (see the application scheme for details), and is used for the supervision of its own AI unit.
  • the second device determines whether the model is effective by comparing the perception data output by its own AI unit with the reference perception data reported by the first device.
  • This embodiment mainly describes how to determine whether a first device participates in sensing through AS or NAS capability interaction.
  • the first device is a terminal
  • the second device is a core network sensing network function
  • the third device is a wireless access network node (such as a base station).
  • the first device is a sensing data processing device, which can be a device participating in sensing measurements (e.g., a device that receives sensing signals and performs measurements to obtain measurement results), or a device that does not participate in sensing measurements, whereby the device participating in sensing measurements sends the acquired measurement results to the first device for processing.
  • the sensing network function selects devices to participate in the sensing process.
  • the sensing data corresponding to the sensing service needs to be calculated and output by an AI unit, which is a network architecture obtained through deep learning/machine learning.
  • the sensing data can be the final sensing result (e.g., target location, trajectory, gesture, or action) or intermediate measurement results used to calculate the final sensing result (e.g., latency, Doppler, angle).
  • the sensing network function needs to select devices with AI-based sensing data processing capabilities to participate in the sensing service.
  • the specific process is as follows:
  • Step 1 The first device (referring to a device with sensing capabilities) sends capability information to the network function (such as AMF) responsible for terminal capability management in the core network.
  • the terminal sends capability information to the AMF through a registration request message, wherein the capability information includes at least one of the following:
  • UE radio capabilities can also be referred to as access layer (AS) capabilities.
  • UE radio capabilities specifically AI-based sensing capabilities reporting/updating, include AI-based sensing capabilities related to bands, band combinations, and carriers. Specifically, this can be indicated by an AI unit identifier (AI model index), an AI unit configuration identifier, a sensing scenario or use case identifier, a sensing target type identifier, or a sensing service identifier, indicating the sensing-related AI units supported by a particular band, band combination, or carrier.
  • the AI-based sensing capability information also includes information on the accuracy of AI-based sensing data processing on the corresponding band, band combination, or carrier, or the achievable performance level or confidence level, or inference speed.
  • Terminal core network capabilities that include AI-based sensing capabilities can also be called NAS capabilities.
  • UE Mobility Management Core Network Capability includes information on whether it supports AI-based sensing protocols.
  • the protocol between the terminal and the SF (Service Provider) is called a sensing protocol, and this sensing protocol includes an AI-based sensing process.
  • the capability information indicates whether the sensing protocol is supported. If the sensing method includes sidelink sensing between terminals or terminal-initiated sensing, then the above capability information may also include whether it supports AI-based sidelink sensing protocols or AI-based UE-initiated sensing.
  • Step 2 the process of the Sensing Network Function (SensingMF) acquiring sensing requirement information is the same as step 1 in the embodiment, and will not be repeated here.
  • SensingMF sends capability request information to the network function (such as AMF) in the core network responsible for terminal capability management, requesting to acquire the capabilities of one or more candidate first devices.
  • the capability request indicates a request for non-access stratum capabilities (such as terminal mobility management core network capabilities) and/or access stratum capabilities (such as terminal radio capabilities).
  • the core network function is only responsible for storing terminal access stratum capabilities and sending them to the terminal's serving base station when needed, thereby avoiding repeated transmission of terminal access stratum capabilities over the air interface. That is, in some embodiments, the core network function does not use terminal access stratum capabilities.
  • the Sensing Network Function can request terminal radio access stratum capabilities to determine the sensing UE, etc.
  • Step 3 SensingMF selects, based on the first device's support for AI-based sensing capabilities, devices with AI-based sensing data processing capabilities or AI units supporting specific sensing services, or devices with AI-based sensing data processing capabilities that can meet sensing requirements (e.g., processing latency meets sensing result refresh rate requirements, or output sensing data accuracy meets sensing accuracy requirements) to participate in the sensing service.
  • sensing requirements e.g., processing latency meets sensing result refresh rate requirements, or output sensing data accuracy meets sensing accuracy requirements
  • the devices that meet the sensing requirements can be identified through the aforementioned capability interaction information.
  • the terminal can avoid repeatedly reporting sensing capabilities over the air interface.
  • This embodiment mainly describes the first device selection assisted by the base station based on AS capability.
  • the first device is a terminal
  • the second device is a core network sensing network function
  • the third device is a wireless access network node (such as a base station).
  • the first device is a sensing data processing device, which can be a device participating in sensing measurements (e.g., a device that receives sensing signals and performs measurements to obtain measurement results), or a device that does not participate in sensing measurements, whereby the device participating in sensing measurements sends the acquired measurement results to the first device for processing.
  • the sensing network function selects devices to participate in the sensing.
  • the sensing data corresponding to the sensing service needs to be calculated and output by an AI unit, which is a network architecture obtained through deep learning/machine learning.
  • the sensing data can be the final sensing result (e.g., target location, trajectory, gesture, or action), or intermediate measurement results used to calculate the final sensing result (e.g., latency, Doppler, angle).
  • the sensing network function needs to select devices with AI-based sensing data processing capabilities to participate in the sensing service.
  • the specific process is as follows. An example is shown in Figure 10, including the following steps:
  • Step 1 The first device (referring to a device with sensing capabilities) sends capability information to the network function (such as AMF) responsible for terminal capability management in the core network.
  • the network function such as AMF
  • the first device sends capability information to the AMF through a registration request message, where the capability information includes the core network capabilities of the first device based on AI sensing capabilities.
  • UE core network capabilities that include AI-based sensing capabilities can also be called NAS capabilities.
  • UE MM Core Network Capability includes information on whether it supports AI-based sensing protocols.
  • the protocol between the terminal and the SF (Service Provider) is called a sensing protocol, and this sensing protocol includes an AI-based sensing process.
  • the capability information indicates whether the sensing protocol is supported. If the sensing method includes sidelink sensing between terminals or terminal-initiated sensing, then the capability information may also include whether it supports AI-based sidelink sensing protocols or AI-based terminal-initiated sensing.
  • SensingMF sends capability request information to the network function (such as AMF) in the core network responsible for terminal capability management, requesting to acquire non-access stratum capabilities (such as UE mobility management core network capabilities) of one or more candidate first devices.
  • the network function such as AMF
  • non-access stratum capabilities such as UE mobility management core network capabilities
  • Step 3 The Sensing Network Function (SensingMF) receives the requested capability information and determines whether terminal access layer capabilities (such as terminal radio capabilities) are required, and/or determines whether radio access network nodes (such as base stations) are required to assist in sensing UE selection based on terminal access layer capabilities.
  • terminal access layer capabilities such as terminal radio capabilities
  • radio access network nodes such as base stations
  • Step 4 If terminal access layer capabilities are required, and/or the capability request indicates a request for non-access layer capabilities (such as terminal mobility management core network capabilities), and/or the radio access network node (such as a base station) assists in terminal selection based on terminal access layer capabilities, then the Sensing Network Function (SensingMF) sends capability request information, and/or, assists in terminal selection request information.
  • the capability request information or assists in terminal selection request information includes a list of candidate terminals, and/or, the requirements of the candidate terminals (such as having AI-based sensing capabilities, mobility speed requirements, terminal location requirements, etc.).
  • the capability request information or assists in terminal selection request information can be sent directly by the Sensing Network Function (SensingMF) to the radio access network node, or it can be forwarded through a core network function node (such as the AMF).
  • Step 5 The wireless access network node, based on the capability request information and/or the assisted sensing terminal selecting request information, determines whether it needs to query the terminal access layer capabilities (such as terminal wireless capabilities) from the terminal.
  • the terminal access layer capabilities include at least one of the following: terminal sensing capabilities and AI-based sensing capabilities.
  • the aforementioned AI-based sensing capability reporting/updating of terminal wireless capabilities includes AI-based sensing capabilities related to bands, band combinations, and carriers. Specifically, this can be indicated by AI unit identifiers (AI model indexes), AI unit configuration identifiers, sensing scenario or use case identifiers, sensing target type identifiers, or sensing service identifiers, showing the sensing-related AI units supported by a particular band, band combination, or carrier.
  • the AI-based sensing capability information also includes information on the accuracy of AI-based sensing data processing on the corresponding band, band combination, or carrier, or the achievable performance level or confidence level, or model inference speed.
  • Step 6 The first device receives capability request information from the radio access network node and sends capability reporting information to provide UE perception capabilities, and/or, terminal AI-based perception capabilities.
  • Step 7 The radio access network (RAN) node sends a capability reporting message to provide capability information for one or more terminals based on the newly acquired terminal access layer capabilities (e.g., terminal radio capabilities) and the already acquired terminal access layer capabilities (e.g., terminal radio capabilities). Alternatively, the RAN node determines a candidate sensing terminal list based on the newly acquired terminal access layer capabilities (e.g., terminal radio capabilities), the already acquired terminal access layer capabilities (e.g., terminal radio capabilities), and the candidate UE requirements received in Step 4, etc., to indicate terminal information that potentially meets the requirements. The RAN node sends the candidate terminal information to the Sensing Network Function (SensingMF). Similar to Step 4, the capability reporting information, and/or the candidate terminal information, can be sent directly from the RAN node to the SensingMF, or forwarded through a core network function node (e.g., AMF).
  • a core network function node e.g., AMF
  • Step 8 SensingMF selects a device with AI-based sensing data processing capabilities or supporting AI units corresponding to specific sensing services, based on the first device's support for AI-based sensing capabilities, or selects a device with AI-based sensing data processing capabilities that can meet sensing requirements (e.g., processing latency meets sensing result refresh rate requirements, or output sensing data accuracy meets sensing accuracy requirements) to participate in the sensing service.
  • sensing requirements e.g., processing latency meets sensing result refresh rate requirements, or output sensing data accuracy meets sensing accuracy requirements
  • WLAN nodes For some sensing services that require AI to participate in sensing data processing, devices that meet the sensing requirements are identified through the aforementioned capability interaction information.
  • the wireless access network (WLAN) nodes then assist in acquiring terminal access layer capabilities or reuse terminal access layer capabilities already acquired by the WLAN nodes.
  • the WLAN nodes can assist in selecting sensing terminals based on terminal access layer capabilities, avoiding the need for core network functional nodes to acquire and use terminal access layer capabilities.
  • the first device reports AI-based perception capability information, including AI-based perception data processing capability, AI unit supervision capability associated with perception, AI unit training capability associated with perception, support for reporting perception data types, formats, or sources input to the AI unit, support for reporting reference perception data types used for AI unit supervision, and supported perception signal configuration information, etc.;
  • the second device selects a perception device, determines a suitable perception method, or determines the perception data obtained from the first device based on the capability information reported by the first device.
  • the selection of sensing devices, the determination of appropriate sensing methods, or the determination of sensing data obtained from devices can be based on the device's capability information, thereby improving the performance and efficiency of sensing.
  • the capability information interaction method provided in this application can be executed by a capability information interaction device.
  • This application uses the example of a capability information interaction device executing the capability information interaction method to illustrate the capability information interaction device provided in this application.
  • the capability information interaction device may be a communication device or a component within a communication device, such as a chip.
  • the communication device may be a terminal, a network-side device, or a server, etc.
  • the terminal may include, but is not limited to, the type of terminal 11 listed above
  • the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.
  • the capability information interaction device may include a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware.
  • the processing module can be implemented by a processor.
  • the processor may include a general-purpose processor, a special-purpose processor, such as a Central Processing Unit (CPU), a microprocessor, a Digital Signal Processor (DSP), an Artificial Intelligence (AI) processor, a Graphics Processing Unit (GPU), an Application Specific Integrated Circuit (ASIC), a Network Processor (NP), a Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc.
  • the receiving and transmitting modules may be implemented by a communication interface, which may include one or more of the following: a transceiver, pins, circuits, a bus, and a radio frequency unit.
  • the capability information interaction device 1100 when the capability information interaction device is a first device or a component of the first device, the capability information interaction device 1100 includes:
  • the sending module 1101 is used to report perception capability information, which is used to indicate the perception capability of the first device based on artificial intelligence (AI).
  • AI artificial intelligence
  • the perception capability information includes at least one of the following:
  • the information includes AI-based perception data processing capabilities, supervision capabilities of perception-associated AI units, training capabilities of perception-associated AI units, reporting capabilities of perception-associated AI units, signal configuration information supported by the first device, and priority information for perception services supported by the first device using AI capabilities.
  • the signal configuration information refers to the configuration information of perception signals corresponding to perception-associated AI units.
  • the AI-based perception data processing capability information is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports AI-based perception data types
  • the first device supports AI-based perception data formats
  • the first device supports AI-processed sensing data sources
  • the first device is based on the latency of AI processing of perceived data
  • the first device is based on the accuracy of AI processing of perceived data
  • the first device is based on the performance level of AI processing perceived data
  • the first device is based on the confidence level of the perceived data processed by AI.
  • the number of AI units associated with perception supported by the first device is the number of AI units associated with perception supported by the first device
  • the types of AI units associated with perception supported by the first device are The types of AI units associated with perception supported by the first device;
  • the parameters of the AI units associated with perception supported by the first device are the parameters of the AI units associated with perception supported by the first device.
  • the AI-based perceptual data type includes at least one of the following:
  • Received signal channel information, spectrum information, and basic measurement quantities
  • the AI-based perception data format may include at least one of the following:
  • channel information The dimensions of channel information, the range of spectral information, the number of basic measurements, and the types of basic measurements;
  • the types of perception data output by the AI unit supported by the first device include:
  • the AI units supported by the first device jointly process the output of multiple types of sensory data, or the AI units supported by the first device independently process the output of at least one type of sensory data.
  • the sources of the AI-based perception data include at least one of the following:
  • RAT wireless access technology
  • the parameters of the perception-associated AI unit include at least one of the following:
  • Unit structure information hyperparameter configuration, data processing method, running cycle, update information, complexity information, available AI resources, AI framework, and AI algorithm.
  • the supervisory capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports reference data types, wherein the reference data is reference data used for AI unit supervision of perception association;
  • the first device supports reporting supervisory metrics for AI units associated with perception.
  • the first device supports reporting the supervision results of the AI units associated with perception.
  • the reference data type includes at least one of the following:
  • Perceptual data acquired by an AI unit with capabilities superior to the AI unit associated with the perception acquired by an AI unit with capabilities superior to the AI unit associated with the perception.
  • the training capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the training time of the AI units associated with perception supported by the first device is the training time of the AI units associated with perception supported by the first device
  • the amount of training data for the AI units associated with perception supported by the first device is the amount of training data for the AI units associated with perception supported by the first device
  • the first device supports perceptual data types for training AI for perceptual association.
  • the first device supports the following perception data formats for AI used in perception association.
  • the first device supports the source of perception data for AI used in perception association
  • the first device supports fine-tuning of the AI units associated with perception
  • the first device supports retraining of the AI units associated with perception
  • the first device supports hybrid training of AI units that are associated with perception in multiple perception scenarios
  • the first device supports hybrid training of AI units that are associated with multiple sensing services.
  • the reporting capability information related to the AI unit associated with the perception is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports the reporting of sensor data types
  • the first device supports the reported sensing data formats
  • the first device supports the reporting of sensor data sources
  • the first device supports the reporting of reference data types
  • the first device supports the reported reference data format
  • the first device supports reporting reference data sources
  • the first device supports reporting AI capability limitation information for perception.
  • the reference data refers to the reference data used for supervising or training AI units that are used for perception association.
  • the perception capability information is carried in at least one of the following:
  • Access layer AS capability information is available.
  • non-access layer NAS capability information is available.
  • the device further includes:
  • the receiving module is used to obtain device capability requests
  • the device capability request is used to request the capabilities of the first device; or, the device capability request is used to request the sensing capabilities of the first device.
  • the device capability request when used to request the capability of the first device, includes an information unit for requesting the sensing capability of the first device;
  • the device capability request may be used to request at least one sensing capability of the first device.
  • the perception capability information includes at least one of the following:
  • the aforementioned capability information interaction device is beneficial for improving the effectiveness of perception services.
  • the signal monitoring device provided in this application embodiment can implement the various processes implemented in the method embodiment of FIG6 and achieve the same technical effect. To avoid repetition, it will not be described again here.
  • the capability information interaction device 1200 when the capability information interaction device is a second device, or a component of a second device, the capability information interaction device 1200 includes:
  • the receiving module 1201 is used to receive sensing capability information, which is used to indicate the AI-based sensing capability of the first device.
  • the perception capability information includes at least one of the following:
  • the information includes AI-based perception data processing capabilities, supervision capabilities of perception-associated AI units, training capabilities of perception-associated AI units, reporting capabilities of perception-associated AI units, signal configuration information supported by the first device, and priority information for perception services supported by the first device using AI capabilities.
  • the signal configuration information refers to the configuration information of perception signals corresponding to perception-associated AI units.
  • the AI-based perception data processing capability information is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports AI-based perception data types
  • the first device supports AI-based perception data formats
  • the first device supports AI-processed sensing data sources
  • the first device is based on the latency of AI processing of perceived data
  • the first device is based on the accuracy of AI processing of perceived data
  • the first device is based on the performance level of AI processing perceived data
  • the first device is based on the confidence level of the perceived data processed by AI.
  • the number of AI units associated with perception supported by the first device is the number of AI units associated with perception supported by the first device
  • the types of AI units associated with perception supported by the first device are The types of AI units associated with perception supported by the first device;
  • the parameters of the AI units associated with perception supported by the first device are the parameters of the AI units associated with perception supported by the first device.
  • the AI-based perceptual data type includes at least one of the following:
  • Received signal channel information, spectrum information, and basic measurement quantities
  • the AI-based perception data format may include at least one of the following:
  • channel information The dimensions of channel information, the range of spectral information, the number of basic measurements, and the types of basic measurements;
  • the types of perception data output by the AI unit supported by the first device include:
  • the AI units supported by the first device jointly process the output of multiple types of sensory data, or the AI units supported by the first device independently process the output of at least one type of sensory data.
  • the sources of the AI-based perception data include at least one of the following:
  • RAT wireless access technology
  • the parameters of the perception-associated AI unit include at least one of the following:
  • Unit structure information hyperparameter configuration, data processing method, running cycle, update information, complexity information, available AI resources, AI framework, and AI algorithm.
  • the supervisory capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports reference data types, wherein the reference data is reference data used for AI unit supervision of perception association;
  • the first device supports reporting supervisory metrics for AI units associated with perception.
  • the first device supports reporting the supervision results of the AI units associated with perception.
  • the reference data type includes at least one of the following:
  • Perceptual data acquired by an AI unit with capabilities superior to the AI unit associated with the perception acquired by an AI unit with capabilities superior to the AI unit associated with the perception.
  • the training capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the training time of the AI units associated with perception supported by the first device is the training time of the AI units associated with perception supported by the first device
  • the amount of training data for the AI units associated with perception supported by the first device is the amount of training data for the AI units associated with perception supported by the first device
  • the first device supports perceptual data types for training AI for perceptual association.
  • the first device supports the following perception data formats for AI used in perception association.
  • the first device supports the source of perception data for AI used in perception association
  • the first device supports fine-tuning of the AI units associated with perception
  • the first device supports retraining of the AI units associated with perception
  • the first device supports hybrid training of AI units that are associated with perception in multiple perception scenarios
  • the first device supports hybrid training of AI units that are associated with multiple sensing services.
  • the reporting capability information related to the AI unit associated with the perception is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports the reporting of sensor data types
  • the first device supports the reported sensing data formats
  • the first device supports the reporting of sensor data sources
  • the first device supports the reporting of reference data types
  • the first device supports the reported reference data format
  • the first device supports reporting reference data sources
  • the first device supports reporting AI capability limitation information for perception.
  • the reference data refers to the reference data used for supervising or training AI units that are used for perception association.
  • the perception capability information is carried in at least one of the following:
  • Access layer AS capability information is available.
  • non-access layer NAS capability information is available.
  • the device further includes:
  • the sending module is used to send device capability requests
  • the device capability request is used to request the capabilities of the first device; or, the device capability request is used to request the sensing capabilities of the first device.
  • the device capability request when used to request the capability of the first device, includes an information unit for requesting the sensing capability of the first device;
  • the device capability request may be used to request at least one sensing capability of the first device.
  • the perception capability information includes at least one of the following:
  • the device further includes:
  • the processing module is configured to perform a determination operation based on the perception capability information, wherein the determination operation is configured to determine at least one of the following:
  • the devices involved in sensing the sensing methods, and the sources of sensing data.
  • the aforementioned capability information interaction device is beneficial for improving the effectiveness of perception services.
  • the signal monitoring device provided in this application embodiment can implement the various processes implemented in the method embodiment of FIG7 and achieve the same technical effect. To avoid repetition, it will not be described again here.
  • this application embodiment also provides a communication device 1300, including a processor 1301 and a memory 1302.
  • the memory 1302 stores a program or instructions that can run on the processor 1301.
  • the communication device 1300 is a first device
  • the program or instructions are executed by the processor 1301
  • the communication device 1300 is a second device
  • the program or instructions are executed by the processor 1301
  • they implement the various steps of the capability information interaction method embodiment for the second device side described above, and achieve the same technical effect. To avoid repetition, this will not be repeated here.
  • This application also provides a device, which is a first device, including a processor and a communication interface.
  • the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps in the method embodiment shown in FIG6.
  • This device embodiment corresponds to the above-described first device-side method embodiment. All implementation processes and methods of the above method embodiments can be applied to this terminal embodiment and achieve the same technical effect.
  • This device may be the capability information interaction device shown in FIG12.
  • This application embodiment also provides a device, including a processor and a communication interface, wherein the communication interface is used to report perception capability information, and the perception capability information is used to indicate the perception capability of the first device based on artificial intelligence (AI).
  • AI artificial intelligence
  • Figure 14 is a schematic diagram of the hardware structure of a device that implements an embodiment of this application.
  • the device 1400 includes, but is not limited to, at least some of the following components: radio frequency unit 1401, network module 1402, audio output unit 1403, input unit 1404, sensor 1405, display unit 1406, user input unit 1407, interface unit 1408, memory 1409, and processor 1410.
  • device 1400 may also include a power supply (such as a battery) to power the various components.
  • the power supply may be logically connected to processor 1410 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.
  • the device structure shown in Figure 14 does not constitute a limitation on the device.
  • the device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.
  • the input unit 1404 may include a graphics processor 14041 and a microphone 14042.
  • the graphics processor 14041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode.
  • the display unit 1406 may include a display panel 14061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like.
  • the user input unit 1407 includes at least one of a touch panel 14071 and other input devices 14072.
  • the touch panel 14071 is also called a touch screen.
  • the touch panel 14071 may include a touch detection device and a touch controller.
  • Other input devices 14072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.
  • the radio frequency unit 1401 can transmit it to the processor 1410 for processing; in addition, the radio frequency unit 1401 can send uplink data to the network-side device.
  • the radio frequency unit 1401 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.
  • the memory 1409 can be used to store software programs or instructions, as well as various data.
  • the memory 1409 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data.
  • the first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.).
  • the memory 1409 may include volatile memory or non-volatile memory.
  • the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.
  • Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM).
  • RAM random access memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous dynamic random access memory
  • DDRSDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous link dynamic random access memory
  • DRRAM direct memory bus RAM
  • the memory 1409 in this embodiment includes, but is not limited to, these and any other suitable types of memory.
  • Processor 1410 may include one or more processing units; optionally, processor 1410 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 1410.
  • the aforementioned device is used as the first device, and the first device is a terminal for illustrative purposes.
  • the radio frequency unit 1401 is used to report sensing capability information, which is used to indicate the sensing capability of the first device based on artificial intelligence (AI).
  • AI artificial intelligence
  • the perception capability information includes at least one of the following:
  • the information includes AI-based perception data processing capabilities, supervision capabilities of perception-associated AI units, training capabilities of perception-associated AI units, reporting capabilities of perception-associated AI units, signal configuration information supported by the first device, and priority information for perception services supported by the first device using AI capabilities.
  • the signal configuration information refers to the configuration information of perception signals corresponding to perception-associated AI units.
  • the AI-based perception data processing capability information is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports AI-based perception data types
  • the first device supports AI-based perception data formats
  • the first device supports AI-processed sensing data sources
  • the first device is based on the latency of AI processing of perceived data
  • the first device is based on the accuracy of AI processing of perceived data
  • the first device is based on the performance level of AI processing perceived data
  • the first device is based on the confidence level of the perceived data processed by AI.
  • the number of AI units associated with perception supported by the first device is the number of AI units associated with perception supported by the first device
  • the types of AI units associated with perception supported by the first device are The types of AI units associated with perception supported by the first device;
  • the parameters of the AI units associated with perception supported by the first device are the parameters of the AI units associated with perception supported by the first device.
  • the AI-based perceptual data type includes at least one of the following:
  • Received signal channel information, spectrum information, and basic measurement quantities
  • the AI-based perception data format may include at least one of the following:
  • channel information The dimensions of channel information, the range of spectral information, the number of basic measurements, and the types of basic measurements;
  • the types of perception data output by the AI unit supported by the first device include:
  • the AI units supported by the first device jointly process the output of multiple types of sensory data, or the AI units supported by the first device independently process the output of at least one type of sensory data.
  • the sources of the AI-based perception data include at least one of the following:
  • RAT wireless access technology
  • the parameters of the perception-associated AI unit include at least one of the following:
  • Unit structure information hyperparameter configuration, data processing method, running cycle, update information, complexity information, available AI resources, AI framework, and AI algorithm.
  • the supervisory capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports reference data types, wherein the reference data is reference data used for AI unit supervision of perception association;
  • the first device supports reporting supervisory metrics for AI units associated with perception.
  • the first device supports reporting the supervision results of the AI units associated with perception.
  • the reference data type includes at least one of the following:
  • Perceptual data acquired by an AI unit with capabilities superior to the AI unit associated with the perception acquired by an AI unit with capabilities superior to the AI unit associated with the perception.
  • the training capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the training time of the AI units associated with perception supported by the first device is the training time of the AI units associated with perception supported by the first device
  • the amount of training data for the AI units associated with perception supported by the first device is the amount of training data for the AI units associated with perception supported by the first device
  • the first device supports perceptual data types for training AI used for perceptual association.
  • the first device supports the following perception data formats for AI used in perception association.
  • the first device supports the source of perception data for AI used in perception association
  • the first device supports fine-tuning of the AI units associated with perception
  • the first device supports retraining of AI units associated with perception
  • the first device supports hybrid training of AI units that are associated with perception in multiple perception scenarios
  • the first device supports hybrid training of AI units that are associated with multiple sensing services.
  • the reporting capability information related to the AI unit associated with the perception is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports the reporting of sensor data types
  • the first device supports the reported sensing data formats
  • the first device supports the reporting of sensor data sources
  • the first device supports the reporting of reference data types
  • the first device supports the reported reference data format
  • the first device supports reporting reference data sources
  • the first device supports reporting AI capability limitation information for perception.
  • the reference data refers to the reference data used for supervising or training AI units that are used for perception association.
  • the perception capability information is carried in at least one of the following:
  • Access layer AS capability information is available.
  • non-access layer NAS capability information is available.
  • the radio frequency unit 1401 is also used for:
  • the device capability request is used to request the capabilities of the first device; or, the device capability request is used to request the sensing capabilities of the first device.
  • the device capability request when used to request the capability of the first device, includes an information unit for requesting the sensing capability of the first device;
  • the device capability request may be used to request at least one sensing capability of the first device.
  • the perception capability information includes at least one of the following:
  • the aforementioned equipment is beneficial for improving the effectiveness of sensing services.
  • This application embodiment also provides a device, including a processor and a communication interface, wherein the communication interface is used to receive sensing capability information, and the sensing capability information is used to indicate the artificial intelligence (AI) based sensing capability of the first device.
  • a device including a processor and a communication interface, wherein the communication interface is used to receive sensing capability information, and the sensing capability information is used to indicate the artificial intelligence (AI) based sensing capability of the first device.
  • AI artificial intelligence
  • This application also provides a device, which is a second device, including a processor and a communication interface.
  • the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method embodiment shown in FIG10.
  • This device embodiment corresponds to the above-described second device-side method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this device embodiment and can achieve the same technical effect.
  • the device 1500 includes: an antenna 1501, a radio frequency device 1502, a baseband device 1503, a processor 1504, and a memory 1505.
  • the antenna 1501 is connected to the radio frequency device 1502.
  • the radio frequency device 1502 receives information through the antenna 1501 and sends the received information to the baseband device 1503 for processing.
  • the baseband device 1503 processes the information to be transmitted and sends it to the radio frequency device 1502, which processes the received information and then transmits it through the antenna 1501.
  • the methods executed by the device in the above embodiments can be implemented in the baseband device 1503, which includes a baseband processor.
  • the baseband device 1503 may include at least one baseband board, on which multiple chips are disposed, as shown in FIG15.
  • One of the chips is, for example, a baseband processor, which is connected to the memory 1505 via a bus interface to call the program in the memory 1505 and execute the network device operation shown in the above method embodiment.
  • the device may also include a network interface 1506, such as a Common Public Radio Interface (CPRI).
  • a network interface 1506 such as a Common Public Radio Interface (CPRI).
  • CPRI Common Public Radio Interface
  • the device 1500 in this application embodiment further includes: instructions or programs stored in memory 1505 and executable on processor 1504.
  • Processor 1504 calls the instructions or programs in memory 1505 to execute the methods executed by each module shown in FIG12 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.
  • the above-mentioned device is used as the second device, and the second device is a network-side device for illustrative purposes.
  • Radio frequency device 1502 is used to receive sensing capability information, which is used to indicate the AI-based sensing capability of the first device.
  • the perception capability information includes at least one of the following:
  • the information includes AI-based perception data processing capabilities, supervision capabilities of perception-associated AI units, training capabilities of perception-associated AI units, reporting capabilities of perception-associated AI units, signal configuration information supported by the first device, and priority information for perception services supported by the first device using AI capabilities.
  • the signal configuration information refers to the configuration information of perception signals corresponding to perception-associated AI units.
  • the AI-based perception data processing capability information is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports AI-based perception data types
  • the first device supports AI-based perception data formats
  • the first device supports AI-processed sensing data sources
  • the first device is based on the latency of AI processing of perceived data
  • the first device is based on the accuracy of AI processing of perceived data
  • the first device is based on the performance level of AI processing perceived data
  • the first device is based on the confidence level of the perceived data processed by AI.
  • the number of AI units associated with perception supported by the first device is the number of AI units associated with perception supported by the first device
  • the types of AI units associated with perception supported by the first device are The types of AI units associated with perception supported by the first device;
  • the parameters of the AI units associated with perception supported by the first device are the parameters of the AI units associated with perception supported by the first device.
  • the AI-based perceptual data type includes at least one of the following:
  • Received signal channel information, spectrum information, and basic measurement quantities
  • the AI-based perception data format may include at least one of the following:
  • channel information The dimensions of channel information, the range of spectral information, the number of basic measurements, and the types of basic measurements;
  • the types of perception data output by the AI unit supported by the first device include:
  • the AI units supported by the first device jointly process the output of multiple types of sensory data, or the AI units supported by the first device independently process the output of at least one type of sensory data.
  • the sources of the AI-based perception data include at least one of the following:
  • RAT wireless access technology
  • the parameters of the perception-associated AI unit include at least one of the following:
  • Unit structure information hyperparameter configuration, data processing method, running cycle, update information, complexity information, available AI resources, AI framework, and AI algorithm.
  • the supervisory capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports reference data types, wherein the reference data is reference data used for AI unit supervision of perception association;
  • the first device supports reporting supervisory metrics for AI units associated with perception.
  • the first device supports reporting the supervision results of the AI units associated with perception.
  • the reference data type includes at least one of the following:
  • Perceptual data acquired by an AI unit with capabilities superior to the AI unit associated with the perception acquired by an AI unit with capabilities superior to the AI unit associated with the perception.
  • the training capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the training time of the AI units associated with perception supported by the first device is the training time of the AI units associated with perception supported by the first device
  • the amount of training data for the AI units associated with perception supported by the first device is the amount of training data for the AI units associated with perception supported by the first device
  • the first device supports perceptual data types for training AI for perceptual association.
  • the first device supports the following perception data formats for AI used in perception association.
  • the first device supports the source of perception data for AI used in perception association
  • the first device supports fine-tuning of the AI units associated with perception
  • the first device supports retraining of the AI units associated with perception
  • the first device supports hybrid training of AI units that are associated with perception in multiple perception scenarios
  • the first device supports hybrid training of AI units that are associated with multiple sensing services.
  • the reporting capability information related to the AI unit associated with the perception is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports the reporting of sensor data types
  • the first device supports the reported sensing data formats
  • the first device supports the reporting of sensor data sources
  • the first device supports the reporting of reference data types
  • the first device supports the reported reference data format
  • the first device supports reporting reference data sources
  • the first device supports reporting AI capability limitation information for perception.
  • the reference data refers to the reference data used for supervising or training AI units that are used for perception association.
  • the perception capability information is carried in at least one of the following:
  • Access layer AS capability information is available.
  • non-access layer NAS capability information is available.
  • the radio frequency device 1502 is also used for:
  • the device capability request is used to request the capabilities of the first device; or, the device capability request is used to request the sensing capabilities of the first device.
  • the device capability request when used to request the capability of the first device, includes an information unit for requesting the sensing capability of the first device;
  • the device capability request may be used to request at least one sensing capability of the first device.
  • the perception capability information includes at least one of the following:
  • processor 1504 is also used for:
  • a determination operation is performed based on the perception capability information, wherein the determination operation is used to determine at least one of the following:
  • the devices involved in sensing the sensing methods, and the sources of sensing data.
  • the aforementioned equipment is beneficial for improving the effectiveness of sensing services.
  • this application embodiment also provides a network-side device, which is a second device.
  • the network-side device 1600 includes: a processor 1601, a network interface 1602, and a memory 1603.
  • the network interface 1602 is, for example, a common public radio interface (CPRI).
  • CPRI common public radio interface
  • the network-side device 1600 in this application embodiment further includes: instructions or programs stored in memory 1603 and executable on processor 1601.
  • Processor 1601 calls the instructions or programs in memory 1603 to execute the methods executed by each module shown in FIG12 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.
  • the aforementioned third device is used as an example of a core network device.
  • the network interface 1602 is used to receive sensing capability information, which is used to indicate the sensing capability of the first device based on artificial intelligence (AI).
  • AI artificial intelligence
  • the perception capability information includes at least one of the following:
  • the information includes AI-based perception data processing capabilities, supervision capabilities of perception-associated AI units, training capabilities of perception-associated AI units, reporting capabilities of perception-associated AI units, signal configuration information supported by the first device, and priority information for perception services supported by the first device using AI capabilities.
  • the signal configuration information refers to the configuration information of perception signals corresponding to perception-associated AI units.
  • the AI-based perception data processing capability information is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports AI-based perception data types
  • the first device supports AI-based perception data formats
  • the first device supports AI-processed sensing data sources
  • the first device is based on the latency of AI processing of perceived data
  • the first device is based on the accuracy of AI processing of perceived data
  • the first device is based on the performance level of AI processing perceived data
  • the first device is based on the confidence level of the perceived data processed by AI.
  • the number of AI units associated with perception supported by the first device is the number of AI units associated with perception supported by the first device
  • the types of AI units associated with perception supported by the first device are The types of AI units associated with perception supported by the first device;
  • the parameters of the AI units associated with perception supported by the first device are the parameters of the AI units associated with perception supported by the first device.
  • the AI-based perceptual data type includes at least one of the following:
  • Received signal channel information, spectrum information, and basic measurement quantities
  • the AI-based perception data format may include at least one of the following:
  • channel information The dimensions of channel information, the range of spectral information, the number of basic measurements, and the types of basic measurements;
  • the types of perception data output by the AI unit supported by the first device include:
  • the AI units supported by the first device jointly process the output of multiple types of sensory data, or the AI units supported by the first device independently process the output of at least one type of sensory data.
  • the sources of the AI-based perception data include at least one of the following:
  • RAT wireless access technology
  • the parameters of the perception-associated AI unit include at least one of the following:
  • Unit structure information hyperparameter configuration, data processing method, running cycle, update information, complexity information, available AI resources, AI framework, and AI algorithm.
  • the supervisory capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports reference data types, wherein the reference data is reference data used for AI unit supervision of perception association;
  • the first device supports reporting supervisory metrics for AI units associated with perception.
  • the first device supports reporting the supervision results of the AI units associated with perception.
  • the reference data type includes at least one of the following:
  • Perceptual data acquired by an AI unit with capabilities superior to the AI unit associated with the perception acquired by an AI unit with capabilities superior to the AI unit associated with the perception.
  • the training capability information of the perception-associated AI unit is used to indicate at least one of the following AI-based perception capabilities:
  • the training time of the AI units associated with perception supported by the first device is the training time of the AI units associated with perception supported by the first device
  • the amount of training data for the AI units associated with perception supported by the first device is the amount of training data for the AI units associated with perception supported by the first device
  • the first device supports perceptual data types for training AI for perceptual association.
  • the first device supports the following perception data formats for AI used in perception association.
  • the first device supports the source of perception data for AI used in perception association
  • the first device supports fine-tuning of the AI units associated with perception
  • the first device supports retraining of the AI units associated with perception
  • the first device supports hybrid training of AI units that are associated with perception in multiple perception scenarios
  • the first device supports hybrid training of AI units that are associated with multiple sensing services.
  • the reporting capability information related to the AI unit associated with the perception is used to indicate at least one of the following AI-based perception capabilities:
  • the first device supports the reporting of sensor data types
  • the first device supports the reported sensing data formats
  • the first device supports the reporting of sensor data sources
  • the first device supports the reporting of reference data types
  • the first device supports the reported reference data format
  • the first device supports reporting reference data sources
  • the first device supports reporting AI capability limitation information for perception.
  • the reference data refers to the reference data used for supervising or training AI units that are used for perception association.
  • the perception capability information is carried in at least one of the following:
  • Access layer AS capability information is available.
  • non-access layer NAS capability information is available.
  • network interface 1602 is also used for:
  • the device capability request is used to request the capabilities of the first device; or, the device capability request is used to request the sensing capabilities of the first device.
  • the device capability request when used to request the capability of the first device, includes an information unit for requesting the sensing capability of the first device;
  • the device capability request may be used to request at least one sensing capability of the first device.
  • the perception capability information includes at least one of the following:
  • processor 1601 is used for:
  • a determination operation is performed based on the perception capability information, wherein the determination operation is used to determine at least one of the following:
  • the devices involved in sensing the sensing methods, and the sources of sensing data.
  • the aforementioned equipment can enhance the exchange of capability information between devices to perceive the effectiveness of business operations.
  • This application also provides a readable storage medium storing a program or instructions.
  • the program or instructions When the program or instructions are executed by a processor, they implement the various processes of the above-described capability information interaction method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.
  • the processor mentioned above is the processor in the terminal described in the above embodiments.
  • the readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.
  • ROM computer read-only memory
  • RAM random access memory
  • magnetic disk magnetic disk
  • optical disk optical disk
  • the readable storage medium may be a non-transient readable storage medium.
  • This application embodiment also provides a chip, which includes a processor and a communication interface.
  • the communication interface is coupled to the processor.
  • the processor is used to run programs or instructions to implement the various processes of the above-described capability information interaction method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.
  • chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.
  • This application also provides a computer program/program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described capability information interaction method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.
  • This application also provides a wireless communication system, including a first device and a second device, wherein the first device can be used to perform the steps of the capability information interaction method on the first device side as provided in this application, and the second device can be used to perform the steps of the capability information interaction method on the second device side as provided in this application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种能力信息交互方法、装置及设备，属于通信技术领域，本申请实施例的能力信息交互方法包括：第一设备上报感知能力信息，所述感知能力信息用于指示所述第一设备的基于AI的感知能力。

Description

能力信息交互方法、装置及设备
相关申请的交叉引用
本申请主张在2024年05月14日提交的中国专利申请No.202410597760.9的优先权，其全部内容通过引用包含于此。
技术领域
本申请属于通信技术领域，具体涉及一种能力信息交互方法、装置及设备。
背景技术
在一些通信系统中支持感知，如支持来感知目标物体的方位、距离、速度等信息，或者支持对目标物体、事件或环境等进行检测、跟踪、识别、成像等。在一些相关技术中，设备之间的能力信息交互，仅限于设备的通信能力，如分组数据汇聚协议(Packet Data Convergence Protocol，PDCP)层、无线链路控制(Radio Link Control，RLC)层、媒体接入控制(Medium Access Control，MAC)层等的能力。而设备之间的通信能力信息交互用于感知业务效果比较差。
发明内容
本申请实施例提供一种能力信息交互方法、装置及设备，能够解决设备之间的通信能力信息交互用于感知业务效果比较差的问题。
第一方面，提供了一种能力信息交互方法，包括：
第一设备上报感知能力信息，所述感知能力信息用于指示所述第一设备的基于人工智能(Artificial Intelligence，AI)的感知能力。
第二方面，提供了一种能力信息交互方法，包括：
第二设备接收感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
第三方面，提供了一种能力信息交互装置，包括：
发送模块，用于上报感知能力信息，所述感知能力信息用于指示所述第一设备的基于人工智能AI的感知能力。
第四方面，提供了一种能力信息交互装置，包括：
第一获取模块，用于获取测量数据；
接收模块，用于接收感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
第五方面，提供了一种设备，该终端包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如本申请实施例提供的第一设备侧的能力信息交互方法的步骤。
第六方面，提供了一种设备，包括处理器及通信接口，其中，所述通信接口用于上报感知能力信息，所述感知能力信息用于指示所述第一设备的基于人工智能AI的感知能力。
第七方面，提供了一种设备，该设备包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如本申请实施例提供的第二设备侧的能力信息交互方法的步骤。
第八方面，提供了一种设备，包括处理器及通信接口，其中，所述通信接口用于接收感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
第九方面，提供了一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如本申请实施例提供的第一设备侧的能力信息交互方法的步骤，或者实现如本申请实施例提供的第二设备侧的能力信息交互方法的步骤。
第十方面，提供了一种无线通信系统，包括：第一设备及第二设备，其中，所述第一设备可用于执行如本申请实施例提供的第一设备侧的能力信息交互方法的步骤，所述第二设备可用于执行如本申请实施例提供的第二设备侧的能力信息交互方法的步骤。
第十一方面，提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如本申请实施例提供的第一设备侧的能力信息交互方法，或实现如本申请实施例提供的第二设备侧的能力信息交互方法。
第十二方面，提供了一种计算机程序/程序产品，所述计算机程序/程序产品被存储在存储介质中，所述计算机程序/程序产品被至少一个处理器执行以实现如本申请实施例提供的第一设备侧的能力信息交互方法的步骤，或者所述计算机程序/程序产品被至少一个处理器执行以实现如本申请实施例提供的第二设备侧的能力信息交互方法的步骤。
在本申请实施例中，第一设备上报感知能力信息，所述感知能力信息用于指示所述第一设备的基于AI的感知能力。这样可以实现基于AI的感知能力的信息的交互，有利于提升感知业务效果。另外，由于上报感知能力信息还有利于提升设备之间的感知性能。
附图说明
图1是本申请实施例可应用的一种无线通信系统的框图；
图2是本申请实施例提供的一种测量的场景示意图；
图3是本申请实施例提供的另一种测量的场景示意图；
图4是本申请实施例提供的一种神经网络的示意图；
图5是本申请实施例提供的一神经元的示意图；
图6是本申请实施例提供的一种能力信息交互方法的流程图；
图7是本申请实施例提供的另一种能力信息交互方法的流程图；
图8是本申请实施例提供的一种能力信息交互方法的示意图；
图9是本申请实施例提供的另一种能力信息交互方法的示意图；
图10是本申请实施例提供的另一种能力信息交互方法的示意图；
图11是本申请实施例提供的一种能力信息交互装置的示意图；
图12是本申请实施例提供的另一种能力信息交互装置的示意图；
图13是本申请实施例提供的一种设备的结构图；
图14是本申请实施例提供的另一种设备的结构图；
图15是本申请实施例提供的另一种设备的结构图；
图16是本申请实施例提供的另一种设备的结构图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员所获得的所有其他实施例，都属于本申请保护的范围。
本申请的术语“第一”、“第二”等是用于区别类似的对象，而不用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换，以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施，且“第一”、“第二”所区别的对象通常为一类，并不限定对象的个数，例如第一对象可以是一个，也可以是多个。此外，本申请中的“或”表示所连接对象的至少其中之一。例如“A或B”的保护范围至少涵盖三种方案，即，方案一：包括A且不包括B；方案二：包括B且不包括A；方案三：既包括A又包括B。此外，术语“A和/或B”、“A和B中的至少一项”、“A或B中的至少一项”也分别至少涵盖上述三种方案。字符“/”一般表示前后关联对象是一种“或”的关系。
本申请的术语“指示”既可以是一个直接的指示(或者说显式的指示)，也可以是一个间接的指示(或者说隐含的指示)。其中，直接的指示可以理解为，发送方在发送的指示中明确告知了接收方具体的信息、需要执行的操作或请求结果等内容；间接的指示可以理解为，接收方根据发送方发送的指示确定对应的信息，或者进行判断并根据判断结果确定需要执行的操作或请求结果等。
值得指出的是，本申请实施例所描述的技术不限于长期演进型(Long Term Evolution，LTE)/LTE的演进(LTE-Advanced，LTE-A)系统，还可用于其他无线通信系统，诸如码分多址(Code Division Multiple Access，CDMA)、时分多址(Time Division Multiple Access，TDMA)、频分多址(Frequency Division Multiple Access，FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access，OFDMA)、单载波频分多址(Single-carrier Frequency-Division Multiple Access，SC-FDMA)或其他系统。本申请实施例中的术语“系统”和“网络”常被可互换地使用，所描述的技术既可用于以上提及的系统和无线电技术，也可用于其他系统和无线电技术。以下描述出于示例目的描述了新空口(New Radio，NR)系统，并且在以下大部分描述中使用NR术语，但是这些技术也可应用于NR系统以外的系统，如第6代(6th Generation，6G)通信系统。
图1示出本申请实施例可应用的一种无线通信系统的框图。无线通信系统包括终端11和网络侧设备12。其中，终端11可以是手机、平板电脑(Tablet Personal Computer)、膝上型电脑(Laptop Computer)、笔记本电脑、个人数字助理(Personal Digital Assistant，PDA)、掌上电脑、上网本、超级移动个人计算机(Ultra-mobile Personal Computer，UMPC)、移动上网装置(Mobile Internet Device，MID)、增强现实(Augmented Reality，AR)、虚拟现实(Virtual Reality，VR)设备、机器人、可穿戴式设备(Wearable Device)、飞行器(flight vehicle)、车载用户设备(Vehicle User Equipment，VUE)、船载设备、行人用户设备(Pedestrian User Equipment，PUE)、智能家居(具有无线通信功能的家居设备，如冰箱、电视、洗衣机或者家具等)、游戏机、个人计算机(Personal Computer，PC)、柜员机或者自助机等终端侧设备。可穿戴式设备包括：智能手表、智能手环、智能耳机、智能眼镜、智能首饰(智能手镯、智能手链、智能戒指、智能项链、智能脚镯、智能脚链等)、智能腕带、智能服装等。其中，车载设备也可以称为车载终端、车载控制器、车载模块、车载部件、车载芯片或车载单元等。需要说明的是，在本申请实施例并不限定终端11的具体类型。网络侧设备12可以包括接入网设备或核心网设备，其中，接入网设备也可以称为无线接入网(Radio Access Network,RAN)设备、无线接入网功能或无线接入网单元。接入网设备可以包括基站、无线局域网(Wireless Local Area Network，WLAN)接入点(Access Point，AP)或无线保真(Wireless Fidelity，WiFi)节点等。其中，基站可被称为节点B(Node B，NB)、演进节点B(Evolved Node B，eNB)、下一代节点B(the next generation Node B，gNB)、新空口节点B(New Radio Node B，NR Node B)、接入点、中继站(Relay Base Station，RBS)、服务基站(Serving Base Station，SBS)、基收发机站(Base Transceiver Station，BTS)、无线电基站、无线电收发机、基本服务集(Basic Service Set，BSS)、扩展服务集(Extended Service Set，ESS)、家用B节点(home Node B，HNB)、家用演进型B节点(home evolved Node B)、发送接收点(Transmit/Receive Point，TRP)或所属领域中其他某个合适的术语，只要达到相同的技术效果，所述基站不限于特定技术词汇，需要说明的是，在本申请实施例中仅以NR系统中的基站为例进行介绍，并不限定基站的具体类型。
核心网设备也可以称为核心网节点、核心网功能或核心网网元等，其包含但不限于如下至少一项：移动管理实体(Mobility Management Entity，MME)、接入移动管理功能(Access and Mobility Management Function，AMF)、会话管理功能(Session Management Function，SMF)、用户平面功能(User Plane Function，UPF)、策略控制功能(Policy Control Function，PCF)、策略与计费规则功能单元(Policy and Charging Rules Function，PCRF)、边缘应用服务发现功能(Edge Application Server Discovery Function，EASDF)、统一数据管理(Unified Data Management，UDM)、统一数据仓储(Unified Data Repository，UDR)、归属用户服务器(Home Subscriber Server，HSS)、集中式网络配置(Centralized network configuration，CNC)、网络存储功能(Network Repository Function，NRF)、网络开放功能(Network Exposure Function，NEF)、本地NEF(Local NEF，或L-NEF)、绑定支持功能(Binding Support Function，BSF)、应用功能(Application Function，AF)、位置管理功能(Location Management Function，LMF)、网关的移动位置中心(Gateway Mobile Location Centre，GMLC)、网络数据分析功能(Network Data Analytics Function，NWDAF)等。需要说明的是，在本申请实施例中仅以NR系统中的核心网设备为例进行介绍，并不限定核心网设备的具体类型，如果在后续协议版本(例如6G)中本申请实施例提到的核心网设备的名称发生变化，也在本申请的保护范围内。
可选的，核心网设备可以由一个设备中的一个或多个功能模块实现，也可以由多个设备共同实现，本申请实施例对此不作具体限定。可以理解的是，上述功能模块既可以是硬件设备中的网络元件，也可以是在专用硬件上运行的软件功能模块，或者是平台(例如，云平台)上实例化的虚拟化功能模块。
在一些实施例中，网络侧设备和终端除了具备通信能力外可以具备感知能力，感知能力，即具备感知能力的一个或多个设备，能够通过无线信号的发送和接收，来感知目标物体的方位、距离、速度等信息，或者对目标物体、事件或环境等进行检测、跟踪、识别、成像等。一些感知功能与应用场景如表1所示：
表1
需要说明的是，上述表1所示的感知类别仅是一个举例说明，本申请实施例中对感知测量的类别并不作限定。
另外，本申请实施例可以应用于通信感知一体化场景，其中，通信感知一体化是指在同一系统中通过频谱共享与硬件共享，实现通信和感知功能一体化设计，系统在进行信息传递的同时，能够感知方位、距离、速度等信息，对目标设备或事件进行检测、跟踪、识别，通信系统与感知系统相辅相成，实现整体性能上的提升并带来更好的服务体验。
例如：通信与雷达的一体化属于典型的通信感知一体化(通信感知融合)应用，且通信与雷达系统融合能够带来许多优势，例如节约成本、减小尺寸、降低功耗、提升频谱效率、减小互干扰等，从而提升系统整体性能。
本申请实施例中，根据感知信号发送节点和接收节点的不同，可以包括但不限于图2所示的6种感知链路。需要说明的是，图2中每种感知链路都是以一个发送节点和一个接收节点进行举例说明，实际系统中，根据不同的感知需求可以选择不同的感知链路，每种感知链路的发送节点和接收节点可以有一个或多个，且实际感知系统可以包括多种不同的感知链路。且图2中的感知目标以人和车作为例子，且假设人和车均没有携带或安装信号收/发设备，实际场景的感知目标将更加丰富。
感知链路1：基站自发自收感知。该方式下基站发送感知信号，并通过接收该感知信号的回波来获得感知结果；
感知链路2：基站间空口感知。该方式下基站2接收基站1发送的感知信号，获得感知结果。
感知链路3：上行空口感知。该方式下基站接收终端发送的感知信号，获得感知结果。
感知链路4：下行空口感知。该方式下终端接收基站发送的感知信号，获得感知结果。
感知链路5：终端自发自收感知。该方式下终端发送感知信号，并通过接收该感知信号的回波来获得感知结果。
感知链路6：终端间旁链路(Sidelink)感知。例如，终端2接收终端1发送的感知信号，获得感知结果，或者终端1接收终端2发送的感知信号，获得感知结果。
在一些实施例中，无线接入网设备和终端、不同终端之间的信令传输以是通过无线资源控制(Radio Resource Control，RRC)信令或媒体接入控制控制单元(Medium Access Control Control Element，MAC CE)或层1信令或其他新定义感知信令；感知网络功能和终端之间的信令传输可以是通过非接入层(Non-Access-Stratum，NAS)信令(经AMF转发)或通过RRC信令或MAC CE或层1信令或其他新定义感知信令；感知网络功能和基站之间的交互可以是利用AMF通过N2接口转发给无线接入网；或者核心网感知网络功能发送给UPF，UPF通过N3接口发送给无线接入网；或者通过新定义的接口发送给无线接入网(如基站)；无线接入网设备间的信令传输可以是通过Xn接口。
在一些实施例中，感知网络功能也可以叫做感知网元或者感知管理功能(Sensing Management Function，Sensing MF)，可以处于无线接入网侧或核心网侧，即可以是无线接入网设备或者核心网设备，具体可以是指核心网或RAN中负责感知请求处理、感知资源调度、感知信息交互、感知数据处理等至少一项功能的网络节点，可以是基于移动通信网络中AMF或LMF升级，也可以是其他网络节点或新定义的网络节点，具体的，感知网络功能/感知网元的功能特性可以包括以下至少一项：
与无线信号发送设备或无线信号测量设备(包括目标终端或者目标终端的服务基站或者目标区域关联的基站)进行目标信息交互，其中，目标信息包括感知处理请求，感知能力，感知辅助数据，感知测量量类型，感知资源配置信息等，以获得无线信号测量设备发送目标感知结果或感知测量量(上行测量量或下行测量量)的值；其中，无线信号也可以称作感知信号。
根据感知业务的类型、感知业务消费者信息、所需的感知服务质量(Quality of Service，QoS)要求信息、无线信号发送设备的感知能力、无线信号测量设备的感知能力等因素来决定使用的感知方法，该感知方法可以包括：无线接入网设备A发无线接入网设备B收，或者无线接入网设备发终端收，或者无线接入网设备A自发自收，或者终端发无线接入网设备收，或者终端自发自收，或者终端A发终端B收等。
根据感知业务的类型、感知业务消费者的信息、所需的感知QoS要求信息、无线信号发送设备的感知能力、无线信号测量设备的感知能力等因素，来决定为感知业务服务的感知设备，其中，感知设备包括无线信号发送设备或无线信号测量设备。
管理感知业务所需资源的整体协调和调度，如对无线接入网设备或终端的感知资源进行相应的配置；
对感知测量量的值进行数据处理，或进行计算获得感知结果。还可以验证感知结果，估计感知精度等。
在一些实施例中，LMF是5G核心网中提供控制面定位的核心网元，完成5G网络中位置信息的计算和反馈，提供定位过程管理、终端能力获取、辅助数据提供、终端位置估计等功能，具体提供如下至少一项功能：
支持终端的位置计算；
获得来自终端的下行链路位置测量或位置估计；
从下一代无线接入网(Next Generation Radio Access Network，NG RAN)获得上行链路位置测量。；
从NG RAN获得非终端相关的辅助数据。
LMF支持小区标识(CELLID)、上行时间差到达(Uplink Time Difference of Arrival，UL-TDOA)、辅助全球导航卫星系统(Assisting Global Navigation Satellite System，A-GNSS等中高精度定位方法。
在一些实施例中，雷达按发射机和接收机是否分置可分为单基地雷达和双/多基地雷达，双基地雷达一般要求发射和接收天线距离很远，与雷达作用距离可比拟。其中，外辐射源雷达是双基地雷达的一种特例，利用相关的电磁波探测理论技术与信号处理技术，获取第三方(例如通信基站)发射的非合作电磁信号，实现对目标的探测、定位、跟踪和识别，又叫做无源雷达、双/多基地无源雷达、被动雷达、非合作照射源雷达或非合作无源探测系统。
其中，双基地雷达感知结果计算一般需要基于参考信道(直达径)信号和监测信道(反射径)信号，典型的双基地雷达架构示意图如图3所示。其中，RT为信号发端(Tx)到目标距离，RR为信号接收端(Tx)到目标距离，L为基线距离，θT为目标相对于信号发送端的角度，θR(θR1、θR2)为目标相对于信号接收端的角度，β为双基地角。
AI目前在各个领域获得了广泛的应用，将人工智能融入无线通信网络，显著提升吞吐量、时延以及用户容量等技术指标是未来的无线通信网络的重要任务。AI模块有多种实现方式，例如神经网络、决策树、支持向量机、贝叶斯分类器等。
在一些实施例中，以神经网络为例进行说明，但是并不限定AI模块的具体类型。一个神经网络的示意图如图4所示。其中，神经网络由神经元组成，神经元的示意图如图5所示。其中a1,a2,…aK为输入，w为权值(乘性系数)，b为偏置(加性系数)，σ(.)为激活函数。常见的激活函数包括Sigmoid、tanh、线性整流函数(Rectified Linear Unit，ReLU)等等。
在一些实施例中，神经网络的参数通过梯度优化算法进行优化。梯度优化算法是一类最小化或者最大化目标函数(有时候也叫损失函数)的算法，而目标函数往往是模型参数和数据的数学组合。例如给定数据X和其对应的标签Y，我们构建一个神经网络模型f(.)，有了模型后，根据输入x就可以得到预测输出f(x)，并且可以计算出预测值和真实值之间的差距(f(x)-Y)，这个就是损失函数。目的是找到合适的W,b使上述的损失函数的值达到最小，损失值越小，则说明模型越接近于真实情况。
优化算法可以是基于误差反向传播(error Back Propagation，BP)算法。BP算法的基本思想是，学习过程由信号的正向传播与误差的反向传播两个过程组成。正向传播时，输入样本从输入层传入，经各隐层逐层处理后，传向输出层。若输出层的实际输出与期望的输出不符，则转入误差的反向传播阶段。误差反传是将输出误差以某种形式通过隐层向输入层逐层反传，并将误差分摊给各层的所有单元，从而获得各层单元的误差信号，此误差信号即作为修正各单元权值的依据。这种信号正向传播与误差反向传播的各层权值调整过程，是周而复始地进行的。权值不断调整的过程，也就是网络的学习训练过程。此过程一直进行到网络输出的误差减少到可接受的程度，或进行到预先设定的学习次数为止。
优化算法还可以有梯度下降(Gradient Descent)、随机梯度下降(Stochastic Gradient Descent，SGD)、小批量梯度下降(mini-batch gradient descent)、动量法(Momentum)、Nesterov(发明者的名字，具体为带动量的随机梯度下降)、自适应梯度下降(ADAptive GRADient descent，Adagrad)、Adadelta、均方根误差降速(root mean square prop，RMSprop)、自适应动量估计(Adaptive Moment Estimation，Adam)等。
这些优化算法在误差反向传播时，都是根据损失函数得到的误差/损失，对当前神经元求导数/偏导，加上学习速率、之前的梯度/导数/偏导等影响，得到梯度，将梯度传给上一层。
本申请实施例中，AI单元也可称为AI模型、机器学习(machine learning，ML)模型、ML单元、AI结构、AI功能、AI特性、机器学习模型、神经网络、神经网络函数、神经网络功能等，或者AI单元也可以是指能够实现与AI相关的特定的算法、公式、处理流程、能力等的处理单元，或者AI单元可以是针对特定数据集的处理方法、算法、功能、模块或单元，或者AI单元可以是运行在图形处理器(graphics processing unit，GPU)、神经处理单元(Neural Processing Unit，NPU)、张量处理单元即(Tensor Processing Unit，TPU)、专用集成电路(application specific integrated circuit，ASIC)等AI/ML相关硬件上的处理方法、算法、功能、模块或单元，本申请实施例对此不做具体限定。可选地，上述特定数据集包括AI单元的输入和/或输出。
在一些实施例中，AI单元的标识可以是AI模型标识、AI结构标识、AI算法标识，或者AI单元关联的特定数据集的标识，或者AI/ML相关的特定场景、环境、信道特征、设备的标识，或者AI/ML相关的功能、特性、能力或模块的标识，本申请实施例对此不做具体限定。
下面结合附图，通过一些实施例及其应用场景对本申请实施例提供的能力信息交互方法、装置及设备进行详细地说明。
请参见图6，图6是本申请实施例提供的一种能力信息交互方法的流程图，如图6所示，包括以下步骤：
步骤601、第一设备上报感知能力信息，所述感知能力信息用于指示所述第一设备的基于AI的感知能力。
上述第一设备可以是终端或者网络侧设备。
上述第一设备可以是向一个或者多个设备上报感知能力信息，如向第二设备上报上述感知能力信息，第二设备可以是终端或者网络侧设备，且第二设备可以是核心网设备。例如：第一设备和第二设备是终端或基站(或TRP)，具体地，第一设备为终端，第二设备为基站；或者，第一设备为基站，第二设备为终端；或者，第一设备和第二设备均为基站；或者，第一设备和第二设备均为终端。或者，第一设备是终端或基站，第二设备为感知网络功能。
本申请实施例中，上述上报感知能力信息也可以称作发送感知能力信息。
在一些实施方式中，上述感知能力信息用于指示第一设备的基于AI的感知能力可以理解为感知能力信息用于指示第一设备支持的基于AI的感知能力，具体可以指示第一设备支持或者不支持基于AI的感知能力，以及可以指示第一设备支持的具体的基于AI的感知能力。
例如：上述感知能力信息可以表示第一设备支持基于AI的感知能力，如第一设备支持基于AI的感知数据处理，如第一设备部署的AI单元，该AI单元用于推理感知数据。或者，感知能力信息可以表示第一设备支持的具体的AI感知能力，如支持AI处理的感知数据类型、感知业务等。
或者，在上述第一设备不具备基于AI的感知能力的情况下，上述感知能力信息表示第一设备不具备基于AI的感知能力。
在一些实施方式中，上述基于AI的感知能力可以表示基于AI单元推理感知数据的能力，或者基于AI单元推理感知数据的中间结果的能力，该中间结果用于确定感知数据。
上述感知数据也可以称作感知结果，具体可以是对感知目标的感知数据，如上述感知数据可以包括如下至少一项：
感知目标的时延、多普勒、角度、距离、速度、朝向、空间位置、加速度、感知目标是否存在、目标个数、轨迹、手势、动作、表情、生命体征、数量、成像结果、天气、空气质量、形状、材质、成分。
在本申请实施例中，第一设备上报感知能力信息，所述感知能力信息用于指示所述第一设备的基于AI的感知能力。这样可以实现基于AI的感知能力的信息的交互，有利于提升感知业务效果。另外，由于上报感知能力信息还有利于提升设备之间的感知性能。且由于感知能力信息用于指示所述第一设备的基于AI的感知能力，这样可以支持基于AI的感知，即支持通过AI推理感知数据或者推理感知数据的中间结果，从而提升感知性能。
在一些实施方式中，上述感知能力信息可以用于确定参与感知的设备、感知方式、感知数据来源等，这样通过上报感知能力信息可以确定更加匹配或合适的参与感知的设备、感知方式、感知数据来源等，进而提升感知性能。
作为一种可选的实施方式，所述感知能力信息包括如下至少一项：
基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力信息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
上述基于AI的感知数据处理能力信息可以指示基于AI的感知数据处理能力。例如：基于AI的感知数据处理可以包括如下至少一项：
基于AI单元推理感知数据；
基于AI单元推理感知数据的中间结果，该中间结果用于确定感知数据；
通过AI单元对感知数据进行推理，如AI单元对感知数据进行处理；
提供用于AI单元携带感知数据的测量数据。
上述基于AI的感知数据处理能力信息可以指示感知关联的AI单元的推理能力。其中，感知关联的AI单元可以是用于推理感知结果的AI单元，或者可以是用于推理感知结果的中间结果的AI单元等与感知关联的AI单元。
在一些实施方式中，所述基于AI的感知数据处理能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持基于AI的感知数据处理；
所述第一设备支持的基于AI处理的感知数据类型；
所述第一设备支持的基于AI处理的感知数据格式；
所述第一设备支持的基于AI处理的感知数据来源；
所述第一设备支持的AI单元输出的感知数据类型；
所述第一设备基于AI处理感知数据的时延；
所述第一设备基于AI处理感知数据的精度；
所述第一设备基于AI处理感知数据的性能等级；
所述第一设备基于AI处理感知数据的置信度水平；
所述第一设备支持的感知关联的AI单元的个数；
所述第一设备支持的感知关联的AI单元的类型；
所述第一设备支持的感知关联的AI单元的参数。
上述基于AI处理的感知数据是指输入到AI单元的感知数据，即AI单元对该感知数据处理，AI单元基于该感知数据进行推理。如上述基于AI处理的感知数据类型包括输入到AI单元的感知数据的类型，上述基于AI处理的感知数据格式包括输入到AI单元的感知数据的格式，上述基于AI处理的感知数据来源包括输入到AI单元的感知数据的来源。
在一些实施方式中，上述基于AI处理的感知数据可以是感知结果，或者与感知关联的数据，如用于确定感知结果的中间数据，用于确定感知结果的测量数据，用于确定感知结果的中间结果的测量数据。上述AI处理感知数据可以是对感知关联的数据进行处理。
在一些实施方式，所述基于AI处理的感知数据类型包括如下至少一项：
接收信号、信道信息、谱信息、基本测量量。
其中，上述信道信息可以是原始信道信息，如包括时域信道响应和频域信道响应)，具体可以包括信道响应的复数结果、幅度/相位、I路/Q路数据中的至少一项。
上述谱信息可以是基于信道信息或接收信号计算得到的谱信息，可以包括以下至少一项：时延(距离)谱，多普勒(速度)谱，角度谱，时延(距离)-多普勒(速度)谱，时延(距离)-角度谱，时延(距离)-多普勒(速度)-角度谱，时间-多普勒谱(微多普勒谱)。
在一些实施方式中，上述谱信息可以是指复数结果，例如时延-多普勒谱指的是2维谱中的时延、多普勒索引以及对应的复数值(含相位信息)；所述谱信息也可以是指功率谱，例如时延-多普勒谱指的是2维谱中的时延、多普勒索引以及对应的功率值(不含相位信息)。
上述基本测量量可以包括以下至少一项：
时延、多普勒、角度、强度、功率。
一些实施方式中，上述基本测量量可以是实际数值的量化结果，也可以是软信息。
通过上述第一设备支持的基于AI处理的感知数据类型，这样可以实现在后续AI感知中向第一设备提供对应类型的数据，以提高第一设备AI感知性能。
在一些实施方式，所述基于AI处理的感知数据格式包括如下至少一项：
信道信息的维度、谱信息的范围、基本测量量的个数、基本测量量的类型。
上述信道信息的维度可以是某个符号上的频域信道响应息(一维信道信息)，或者多个符号上的时频域信道响应信息(二维信道信息)，或者多个符号、多个天线的时频空域信道响应信息(三维信道信息)，以及不同维度的规模，即采样点个数或采样间隔(例如时频域密度)；
谱信息的范围可以用于限制不同谱信息的范围，或者称之为针对谱信息不同维度的截断窗口，即谱信息可以是根据信道信息计算得到的完整谱信息，也可以是完整谱信息的子集。例如时延-多普勒谱中特定时延或多普勒范围对应的谱信息子集，又例如时延-多普勒谱中功率或幅度超过预设门限的径或采样点的信息；也可以指示AI单元支持输入的特定谱的径的个数的上限值或采样点个数的上限值；也可以是指示AI单元支持输入的特定谱的最小粒度，即相邻两个采样点间的间隔(对应感知分辨率)。
基本测量量的个数可以是AI单元一次性输入的测量量个数。
上述基本测量量的类型可以是测量量的值的量化方式(例如量化粒度)或者软信息类型，如提供均值+方差，或置信区间和置信度的软信息。
通过上述第一设备支持的基于AI处理的感知数据格式，这样可以实现在后续AI感知中向第一设备提供对应的类型的数据，以提高第一设备AI感知性能。
上述第一设备支持的AI单元输出的感知数据类型可以是第一设备支持的AI单元处理并输出的感知数据类型，一种或者多种感知数据类型。该感知数据可以是感知结果或者感知结果的中间结果。
在一些实施方式，所述第一设备支持的AI单元输出的感知数据类型包括：
所述第一设备支持的AI单元联合处理输出的多种感知数据，或者，所述第一设备支持的AI单元独立处理输出的至少一种感知数据。
具体的，第一设备支持的AI单元输出的感知数据类型可以包括以下至少一项：目标的时延、多普勒、角度、距离、速度、朝向、空间位置、加速度、目标是否存在、目标个数、轨迹、手势、动作、表情、生命体征、数量、成像结果、天气、空气质量、形状、材质、成分。
通过第一设备支持的AI单元输出的感知数据类型，这样可以基于该感知数据类型选择第一设备参与适合的感知业务，以提高感知性能。
上述第一设备支持的基于AI处理的感知数据来源可以指示第一设备支持的通过AI单元处理的感知数据的来源。
在一些实施方式中，上述基于AI处理的感知数据来源包括如下至少一项：
来自于单个设备，或者来自于多个设备；
来自于目标感知模式；
来自于传感器；
来自于至少一种无线接入技术(Radio Access Technology，RAT)。
上述来自于单个设备表示第一设备支持AI单元对自单个设备的感知数据的处理，上述来自于多个设备表示第一设备持来自不同设备的感知数据的联合处理。上述基于AI处理的感知数据来源还可以指示基于AI处理的感知数据来源的最大设备个数。
上述来自于目标感知模式可以表示第一设备支持来自目标感知模式获取的感知数据的AI处理，上述目标感知模式可以是一种模式，或者多种模式，其中，为多种模式时可以表示第一设备支持多种不同感知模式获取的感知数据的AI处理。具体的，上述目标感知模式包括以下至少一项：基站自发自收，基站A发基站B收，基站发终端收，终端发基站收，终端自发自收，终端A发终端B收；或者上述目标感知模式可以是指单基地感知或双基地感知。
上述来自于传感器可以表示第一设备支持来自传感器的感知数据的AI处理，或者支持来自传感器和无线感知的感知数据的联合AI处理。其中，传感器可以包括以下至少一项：可见光摄像头、红外摄像头、全球导航卫星系统(Global Navigation Satellite System，GNSS)、激光雷达、毫米波雷达、温度计、湿度计、气压计、陀螺仪、加速度计、磁力计、重力传感器、声呐、雨量计等。
上述来自于至少一种RAT可以表示第一设备支持来自一种或者多种下RAT的感知数据的处理，如第一设备支持AI处理基于大于一种无线接入技术(包括但不限于4G、5G、6G、Wifi、超宽带(Ultra Wide Band，UWB)、蓝牙等)进行感知获取的感知数据。
通过第一设备支持的AI单元输出的感知数据来源，这样可以实现在后续AI感知中向第一设备提供对应来源的数据，以提高第一设备AI感知性能。
上述第一设备基于AI处理感知数据的时延可以是AI单元的推理速度，具体可以是AI单元的最大处理时延或最小处理时延，且可以是根据不同感知数据类型输入或输出给出相对应的处理时延。
通过上述第一设备基于AI处理感知数据的时延有利于提升对时延有要求的感知业务感知性能，如选择时延满足感知业务的设备参与感知。
上述第一设备基于AI处理感知数据的精度可以是不同感知数据类型AI单元输出的感知数据的精度，且该精度可以表示为误差。
上述第一设备基于AI处理感知数据的性能等级可以是不同感知数据类型AI单元输出的感知数据的性能等级。
上述第一设备基于AI处理感知数据的置信度水平可以是不同感知数据类型AI单元输出的感知数据的置信度水平。
一般情况下，第一设备具有较高处理器运算能力时能够提供更高精度的感知数据处理结果，即能够达到更高的性能等级或置信度水平。
通过上述第一设备基于AI处理感知数据的精度、性能等级、置信度水平有利于提升对感知结果有相关要求的感知业务感知性能，如选择精度、性能等级、置信度水平满足感知业务的设备参与感知，从而提升感知性能。
上述第一设备支持的感知关联的AI单元的个数可以是第一设备支持的与感知相关的AI单元的个数，或者可以是第一设备支持的AI单元类型的AI单元的个数。
上述第一设备支持的感知关联的AI单元的类型可以是第一设备支持的AI单元的ID列表，且不同类型的AI单元可以关联不同的感知场景、感知用例、感知目标或感知业务，或者不同类型的AI单元关联不同的AI单元参数。
其中，上述感知场景包括以下至少一项：室内，室外，办公区，起居室，工厂，郊区，城镇，街道，车载场景，车联万物(vehicle to everything，V2X)场景，宏站，微站，高铁，高速路口，商场，停车场，景区。
上述感知目标包括以下至少一项：无人机(Unmanned Aerial Vehicle，UAV)，人(Human)，汽车(Automotive vehicle)，自动导向车(Automated Guided Vehicle，AGV)，公路/铁路上的物体(Objects on roads/railways)。
上述感知业务包括以下至少一项：可以是例如检测目标是否存在，检测目标个数，定位，轨迹跟踪，速度探测，距离探测、角度探测、加速度探测，材料分析，成分分析，形状检测，类别划分，雷达散射截面积(Radar Cross Section，RCS)检测，极化散射特性检测，跌倒检测，入侵检测，室内定位，手势识别，唇语识别，步态识别，表情识别，面部识别，呼吸监测，心率监测，脉搏监测，湿度/亮度/温度/大气压强监测，空气质量监测，天气情况监测，环境重构，地形地貌、建筑/植被分布检测，人流量或车流量检测，人群密度、车辆密度检测等；也可以是指某一类别的感知业务，即按照一定特征把多个不同的感知业务进行分类，例如按照功能划分为检测类感知业务(例如包括入侵检测、跌倒检测)、参数估计类感知业务(距离、角度、速度计算)、识别类感知业务(动作识别、身份识别)等，还可以是按照感知的范围(近距离感知、中距离感知、远距离感知)划分，按照感知的精细程度划分(粗粒度感知、精细力度感知等)，按照功耗/能耗划分，按照资源占用划分等。
对于不同的感知业务，上述感知能力信息还可以包括与特定感知业务关联的AI单元能力信息，例如：对于目标个数检测和参数(距离、速度、角度、位置等)估计，还包括支持检测的最大目标个数，支持的最大测距范围或最大测速范围或最大测角范围等；对于动作识别，还包括支持识别的最大动作个数或支持识别的动作类型集合。
上述第一设备支持的感知关联的AI单元的类型可以包括如下至少一项：
高斯过程、支持向量机、神经网络；
其中，神经网络可以是全连接神经网络、卷积神经网络、循环神经网络或残差网络，或者多个小网络的组合方式，例如全连接+卷积，卷积+残差等。
上述第一设备支持的感知关联的AI单元的类型可以方便其他设备更好地选择合适的设备参与感知，有利于提升感知性能。
上述感知关联的AI单元的参数包括如下至少一项：
单元结构信息、超参数配置、数据处理方式、运行周期、更新信息、复杂度信息、可用的AI资源、AI框架、AI算法。
上述单元结构信息可以包括神经网络的层数、各层神经元个数、激活函数等结构信息。
上述超参数配置可以是AI单元中需要人为指定且不随数据训练过程更新的参数，如核函数中的相关参数、激活函数中的相关参数、归一化层中的相关参数等。
上述数据处理方式可以是数据在输入到AI单元之前对数据的预处理方式。其中，数据处理方式可以包括但不限于归一化、上采样、降采样等等。
上述运行周期可以是AI单元每隔多长时间执行一次。
上述更新信息可以是更新周期，如AI单元每隔多长时间更新一次。
或者，上述更新信息可以包括以下至少一项：核函数的更新信息、超参数的更新信息、预测模式的更新信息、计算模式的更新信息等。
上述复杂度信息可以是AI单元推理的浮点数运算次数(Floating Point Operations，FLOPs)数，如100次迭代，或者可以是AI单元的硬件条件，计算条件。
上述可用的AI资源可以是可供AI使用的计算或存储资源。
通过上述感知关联的AI单元的参数可以使得在感知业务过程上支持适合的设备参与感知，以提高感知性能。
上述感知关联的AI单元的监督能力信息可以指示第一设备对于AI单元进行监督的能力，该监督是指对AI单元输出的感知数据的监督。其中，该AI单元可以是部署在第一设备上的AI单元，也可以是部署在其他设备的AI单元。
可选地，所述感知关联的AI单元的监督能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的监督；
所述第一设备支持的感知关联的AI单元的监督周期；
所述第一设备支持的感知关联的AI单元的监督时长；
所述第一设备支持的感知关联的AI单元的监督次数；
所述第一设备支持的参考数据类型，所述参考数据为用于感知关联的AI单元监督的参考数据；
所述第一设备支持上报感知关联的AI单元的监督度量指标；
所述第一设备支持上报感知关联的AI单元的监督结果。
上述第一设备是否支持感知关联的AI单元的监督可以是是否支持针对特定感知场景或感知业务的AI单元的监督。
通过上述第一设备支持的感知关联的AI单元的监督周期、监督时长或监督次数可以实现在后续AI单元监督过程上基于监督周期、监督时长或监督次数进行AI单元的监督，以提高AI单元监督性能。
上述参考数据可以理解为上述AI单元的真实标签或者参考标签，即作为上述第一AI单元输出的感知数据的参考。且上述参考数据可以是第一设备获取的参考信号，或者其他设备获取的参考信号。
在一些实施方式中，所述参考数据类型包括如下至少一项：
感知特征已知的感知目标的感知数据；
通过传感器获取的感知数据；
通过目标感知模式获取的感知数据；
通过目标感知设备获取的感知数据；
通过非AI的方式获取的感知数据；
有源设备的定位数据；
通过能力强于所述感知关联的AI单元的AI单元获取的感知数据。
上述感知特征已知的感知目标可以是感知参考目标或者感知参考单元。
上述通过传感器获取的感知数据可以理解为通过传感器获取的感知数据作为无线感知中基于AI单元推理得到的感知数据的参考。
上述目标感知模式可以如图2所示的至少一种模式，如单基地感知模式获取的感知数据作为双基地感知模式下，通过AI推理得到的感知数据的参考。
上述目标感知设备可以是基站或者终端，如基站获取的感知数据作为终端通过AI推理得到的感知数据的参考；
上述通过非AI的方式获取的感知数据可以是根据信道信息通过常规参数估计算法计算的感知数据，如通过
二维快速傅里叶变换(2D-Fast Fourier Transform，2D-FFT)、三维快速傅里叶变换(3D-Fast Fourier Transform，3D-FFT)、多重信号分类(Multiple Signal Classification，MUSIC)、ESPRIT算法计算的感知数据作为AI单元推理得到的感知数据的参考数据。
上述有源设备的定位数据可以是通过与该设备收发定位信号进行设备定位的结果作为将该设备视为无源目标时，通过无线感知并基于AI推理得到的定位结果的参考数据。
上述通过能力强于所述感知关联的AI单元的AI单元获取的感知数据可以理解为通过能力更强的AI单元输出的感知数据作为上述感知关联的AI单元推理得到的感知数据的参考数据。
通过上述第一设备支持的参考数据类型可以实现在AI单元监督过程中向第一设备提供相应的参考数据，或者多第一设备获取这些参考数据，有利于提升AI单元的监督性能。
上述第一设备支持上报感知关联的AI单元的监督度量指标可以理解为第一设备支持上报这些监督度量指标，这些监督度量指标是指感知关联的AI单元监督的度量指标，如包括AI单元推理输出的感知数据与参考数据之间的误差的统计结果，可以是均方根差(root mean square error，RMSE)。
通过上述第一设备支持上报感知关联的AI单元的监督度量指标可以使得在AI单元监督过程中确定第一设备能够上报的监督度量指标，有利于提升AI单元监督的效果。
上述第一设备支持上报感知关联的AI单元的监督结果可以理解为第一设备能够上报AI单元监督的结果，如第一设备对AI单元进行监督，并可以上报监督的结果。
通过第一设备支持上报感知关联的AI单元的监督结果可以使得在AI单元监督过程中能够从第一设备获取监督结果，有利于提升AI单元监督的效果。
上述感知关联的AI单元的训练能力信息可以指示第一设备的AI单元的训练能力。
在一些实施方式中，上述感知关联的AI单元的训练能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的训练；
所述第一设备支持的感知关联的AI单元的训练时间；
所述第一设备支持的感知关联的AI单元的训练数据量；
所述第一设备支持的用于感知关联的AI的训练的感知数据类型；
所述第一设备支持的用于感知关联的AI的感知数据格式；
所述第一设备支持的用于感知关联的AI的感知数据来源；
所述第一设备支持感知关联的AI单元的微调；
所述第一设备支持感知关联的AI单元的重训练；
所述第一设备支持多种感知场景的感知关联的AI单元的混合训练；
所述第一设备支持多种感知业务的感知关联的AI单元的混合训练。
上述第一设备是否支持感知关联的AI单元的训练可以是指是否支持特定感知场景或感知业务的AI单元的训练。
上述第一设备支持的感知关联的AI单元的训练时间可以包括不同感知场景或感知业务对应的AI单元的训练时间。
上述第一设备支持的用于感知关联的AI的训练感知数据类型、训练感知数据格式或训练感知数据来源可以参见上述实施方式中的感知数据类型、感知数据格式或感知数据来源，此处不作赘述。
通过上述感知关联的AI单元的训练能力信息，可以实现在后续AI单元训练过程中选择适合的设备参数AI单元训练，有利于提升AI单元训练效果。
上述感知关联的AI单元相关的上报能力信息用于指示第一设备上报AI单元相关的能力。
在一些实施方式中，所述感知关联的AI单元相关的上报能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备支持上报的感知数据类型；
所述第一设备支持上报的感知数据格式；
所述第一设备支持上报的感知数据来源；
所述第一设备支持上报的参考数据类型；
所述第一设备支持上报的参考数据格式；
所述第一设备支持上报的参考数据来源；
所述第一设备支持上报用于感知的AI能力限制信息；
其中，所述参考数据为用于感知关联的AI单元监督或者训练的参考数据。
其中，上述上报的感知数据可以是用于输入到AI单元的感知数据，如测量数据，或者感知结果的中间结果，上述上报的感知数据可以是AI单元输出的感知数据，即AI单元推理的感知数据，如感知结果或者感知结果的中间结果。其中，在第一设备支持上报输入到AI单元的感知数据的情况下，可以表示第一设备不支持AI单元基于AI的感知数据处理能力，但可以提供输入到AI单元的感知数据，该感知数据可以用于AI单元的推理或训练。
上述感知数据类型、感知数据格式或感知数据来源可以参见上述实施方式中的感知数据类型、感知数据格式或感知数据来源，此处不作赘述。
上述参考数据类型、参考数据格式或参考数据来源可以参见上述实施方式中的参考数据类型、参考数据格式或参考数据来源，此处不作赘述。
在第一设备支持上报上述参考数据可以表示第一设备不具备与感知关联的AI单元的监督或训练能力，但可以提供用于AI单元的监督或训练的参考感知数据。
上述感知关联的AI单元相关的上报能力信息还可以包括第一设备支持上报的参考数据的精度。
通过上述感知关联的AI单元相关的上报能力信息，可以实现在后续过程从第一设备获取相应的数据，以利于提升感知、AI单元监督或AI单元训练的效果。
上述第一设备支持上报用于感知的AI能力限制信息可以理解为第一设备能够上报用于感知的AI能力限制信息，该AI能力限制信息可以用于表示第一设备对于AI能力限定的资源，如上报算力、功耗、处理时间线等绝对值或占比最多能分配多少给感知个业务的限制信息，且对于AI单元推理阶段和AI单元训练阶段可以分配不一样资源。
通过上述第一设备支持上报用于感知的AI能力限制信息可以在后续过程上获取终端的AI能力限制信息，从而避免在后续过程中超出第一设备的限制，有利于保证感知性能。
上述第一设备支持的信号配置信息对应用感知信号可以用于获取AI单元的推理或训练时输入的感知数据。
通过上述第一设备支持的信号配置信息可以实现在后续感知过程或者AI单元训练中为第一设备配置相应的信号配置信息，或者在后续感知过程或者AI单元训练基于该信号配置信息对第一设备发送的信号进行测量，这样有利于提升感知性能。
在一些实施方式中，上述信号配置信息包括如下至少一项：
信号资源标识，用于区分不同的信号资源配置；
信号用途，表示该信号是用于通信(例如信道测量、信道估计、同步、承载数据信息等)的信号，用于感知的信号，或者是同时用于通信和感知的信号。具体的，还可以是，用于哪种感知业务的信号，或者是用于哪一类感知业务的信号。
波形，所述波形例如为正交频分复用(Orthogonal frequency division multiplex，OFDM)，单载波频分多址(Single-carrier Frequency-Division Multiple Access,SC-FDMA)，正交时频空间(Orthogonal Time Frequency Space，OTFS)，调频连续波(Frequency Modulated Continuous Wave，FMCW)，脉冲信号等；
子载波间隔，例如，OFDM系统的子载波间隔30KHz；
保护间隔，保护间隔为从信号结束发送的时刻到该信号的最迟回波信号被接收的时刻之间的时间间隔；该参数正比于最大感知距离；例如，可以通过c/(2Rmax)计算得到，Rmax为最大感知距离(属于感知需求信息)，例如对于自发自收的感知信号，Rmax代表感知信号收发点到信号发射点的最大距离；在某些情况下，OFDM信号循环前缀(CP)可以起到最小保护间隔的作用；c是光速。
起始频域位置，即起始频点，也可以是起始RE、RB索引；
起始时域位置，即起始时间点，也可以是起始符号索引、时隙索引、帧索引；
终止频域位置，即终止频点，可以用终止RE、RB索引表示；
终止时域位置，即终止时间点，可以表示用终止RE、RB索引表示；
频域资源长度，即频域带宽，所述频域带宽反比于距离分辨率，每个所述第一信号的频域带宽B≥c/(2ΔR)，其中，c为光速，ΔR为距离分辨率；
时域资源长度，也称为突发(burst)持续时间，时域资源长度反比于多普勒分辨率；
频域资源间隔，表示相邻的信号频域资源单元间隔，可以用RE数或RB数表示，也可以用密度值Density表示，例如Density＝1表示每个RB中有一个RE用于承载信号。所述频域资源间隔反比于最大无模糊距离/时延，其中，对于OFDM系统当子载波采用连续映射时频域间隔等于子载波间隔；所述频域资源单元间隔也可以用梳状映射参数Kcomb表示，例如表示comb1(Kcomb＝1)频域上连续映射，comb2(Kcomb＝2)表示频域上每隔1个子载波进行序列映射(例如信号占子载波0，2，4，…)，comb4(Kcomb＝4)为表示频域上每隔3个子载波进行序列映射(例如信号占子载波0，4，8，…)；
时域资源间隔，时域资源间隔是相邻的两个信号资源单元之间的时间间隔，时域资源间隔与最大无模糊多普勒频移或最大无模糊速度关联；
时域资源特性，如周期性发送，半持续性发送，非周期性发送。
时域burst资源间隔或时域burst发送周期，时域burst资源间隔或时域burst发送周期与感知结果刷新频率关联；
信号功率，如从-20dBm到23dBm每隔2dBm取一个值；
序列信息，包括序列类型信息(ZC序列、PN序列等)，序列生成方式，序列长度等；
信号方向，信号发送的角度信息或波束信息；
准共址(Quasi co-location，QCL)关系，例如信号包括多个资源，每个资源与一个同步信号块(Synchronization Signal Block，SSB)QCL，QCL包括类型A，类型B，类型C或者类型D。
循环前缀(Cyclic Prefix，CP)信息可以包括CP类型或CP长度等，例如常规循环前缀(Normal Cyclic Prefix，NCP)、扩展循环前缀(Extended Cyclic Prefix，ECP)或者新设计的感知测量专用CP等。
上述第一设备支持的感知业务使用AI能力的优先级信息用于表示第一设备支持的感知业务使用AI能力的优先级，如比如定义一个优先等级，分3个等级从高到底依次优先级变低，感知业务的AI处理的优先级是2，RAN的AI处理的优先级是3，网外业务是1，这样在有竞争或冲突的时候按照优先级去处理，以提升第一设备的工作性能。
作为一种可选的实施方式，所述感知能力信息携带在如下至少一项：
接入层(Access Stratum，AS)能力信息、非接入层(Non-Access Stratum，NAS)能力信息。
其中，上述AS能力信息可以是终端无线能力信息，这样可以实现在AS能力信息上报感知能力信息，从而不需要增加额外的消息，以节约传输开销。
在一些实施方式中，在上述感知能力信息携带有AS能力信息的情况下，上述感知能力信息可以包括频带(band)、频带组合(band combination)或者载波(carrier)相关的基于AI的感知能力。上述感知能力信息还可以包括对应band、band combination、carrier上基于AI的感知数据处理精度信息或可以达到的性能等级或置信度水平或推理速度等。
其中，上述NAS能力信息可以是终端核心网能力信息，这样可以实现在NAS能力信息上报感知能力信息，从而不需要增加额外的消息，以节约传输开销。
作为一种可选的实施方式，所述方法还包括：
所述第一设备获取设备能力请求；
其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
上述设备能力请求可以是接收第二设备发送的设备能力请求。
上述设备能力请求用于请求所述第一设备的能力可以理解为上述设备能力请求用于请求第一设备的通用能力或者所有能力，如上述设备能力请求为通用的设备能力请求。
在上述设备能力请求用于请求所述第一设备的能力的情况下，第一设备可以上报上述感知能力信息和其他能力信息。
在上述设备能力请求用于请求所述第一设备的感知能力的情况下，第一设备上报上述感知能力信息。
在一些实施方式中，在所述设备能力请求用于请求所述第一设备的能力的情况下，所述设备能力请求中包括用于请求所述第一设备的感知能力的信息单元；
或者，所述设备能力请求用于请求所述第一设备的至少一项感知能力。
上述设备能力请求中包括用于请求所述第一设备的感知能力的信息单元可以理解为该设备能力请求中的信息单元中包括用于请求上述感知能力的请求信息，即基于AI的感知能力请求信息为上述设备能力请求的信息单元。
上述设备请求用于请求所述第一设备的至少一项感知能力可以理解为上述设备请求能力用于请求特定的能力，例如：用于请求获取第一设备支持的基于AI的感知能力，或请求获取第一设备基于AI的感知数据处理能力信息，也可以是请求某一项或多项具体的能力信息，如请求获取第一设备支持的输入到AI单元的感知数据类型或格式或来源，第一设备根据该能力请求信息上报基于AI的感知能力信息中的至少一项。
上述实施方式中，可以实现基于设备能力请求上报感知能力信息，从而实现按需上报，以避免不必要的上报，以节约上报开销。
在一些实施方式中，上述感知能力信息可以是第一设备主动上报的。
作为一种可选的实施方式，所述感知能力信息包括如下至少一项：
至少一个频带的感知能力信息；
至少一个频带组合的感知能力信息；
至少一个载波单元(Component Carrier，CC)的感知能力信息。
上述实施方式中，可以实现以频带、频带组合或CC为粒度上报感知能力信息，以提高能力上报的精度。
在本申请实施例中，第一设备上报感知能力信息，所述感知能力信息用于指示所述第一设备的基于AI的感知能力。这样可以实现基于AI的感知能力的信息的交互，有利于提升感知业务效果。另外，由于上报感知能力信息还有利于提升设备之间的感知性能。
请参见图7，图7是本申请实施例提供的一种能力信息交互方法的流程图，如图7所示，包括如下步骤：
步骤701、第二设备接收感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
可选地，所述感知能力信息包括如下至少一项：
基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力信息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
可选地，所述基于AI的感知数据处理能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持基于AI的感知数据处理；
所述第一设备支持的基于AI处理的感知数据类型；
所述第一设备支持的基于AI处理的感知数据格式；
所述第一设备支持的基于AI处理的感知数据来源；
所述第一设备支持的AI单元输出的感知数据类型；
所述第一设备基于AI处理感知数据的时延；
所述第一设备基于AI处理感知数据的精度；
所述第一设备基于AI处理感知数据的性能等级；
所述第一设备基于AI处理感知数据的置信度水平；
所述第一设备支持的感知关联的AI单元的个数；
所述第一设备支持的感知关联的AI单元的类型；
所述第一设备支持的感知关联的AI单元的参数。
可选地，所述基于AI处理的感知数据类型包括如下至少一项：
接收信号、信道信息、谱信息、基本测量量；
或，所述基于AI处理的感知数据格式包括如下至少一项：
信道信息的维度、谱信息的范围、基本测量量的个数、基本测量量的类型；
或，
所述第一设备支持的AI单元输出的感知数据类型包括：
所述第一设备支持的AI单元联合处理输出的多种感知数据，或者，所述第一设备支持的AI单元独立处理输出的至少一种感知数据。
可选地，所述基于AI处理的感知数据来源包括如下至少一项：
来自于单个设备，或者来自于多个设备；
来自于目标感知模式；
来自于传感器；
来自于无线感知；
来自于至少一种无线接入技术RAT。
可选地，所述感知关联的AI单元的参数包括如下至少一项：
单元结构信息、超参数配置、数据处理方式、运行周期、更新信息、复杂度信息、可用的AI资源、AI框架、AI算法。
可选地，所述感知关联的AI单元的监督能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的监督；
所述第一设备支持的感知关联的AI单元的监督周期；
所述第一设备支持的感知关联的AI单元的监督时长；
所述第一设备支持的感知关联的AI单元的监督次数；
所述第一设备支持的参考数据类型，所述参考数据为用于感知关联的AI单元监督的参考数据；
所述第一设备支持上报感知关联的AI单元的监督度量指标；
所述第一设备支持上报感知关联的AI单元的监督结果。
可选地，所述参考数据类型包括如下至少一项：
感知特征已知的感知目标的感知数据；
通过传感器获取的感知数据；
通过目标感知模式获取的感知数据；
通过目标感知设备获取的感知数据；
通过非AI的方式获取的感知数据；
有源设备的定位数据；
通过能力强于所述感知关联的AI单元的AI单元获取的感知数据。
可选地，所述感知关联的AI单元的训练能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的训练；
所述第一设备支持的感知关联的AI单元的训练时间；
所述第一设备支持的感知关联的AI单元的训练数据量；
所述第一设备支持的用于感知关联的AI的训练的感知数据类型；
所述第一设备支持的用于感知关联的AI的感知数据格式；
所述第一设备支持的用于感知关联的AI的感知数据来源；
所述第一设备支持感知关联的AI单元的微调；
所述第一设备支持感知关联的AI单元的重训练；
所述第一设备支持多种感知场景的感知关联的AI单元的混合训练；
所述第一设备支持多种感知业务的感知关联的AI单元的混合训练。
可选地，所述感知关联的AI单元相关的上报能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备支持上报的感知数据类型；
所述第一设备支持上报的感知数据格式；
所述第一设备支持上报的感知数据来源；
所述第一设备支持上报的参考数据类型；
所述第一设备支持上报的参考数据格式；
所述第一设备支持上报的参考数据来源；
所述第一设备支持上报用于感知的AI能力限制信息；
其中，所述参考数据为用于感知关联的AI单元监督或者训练的参考数据。
可选地，所述感知能力信息携带在如下至少一项：
接入层AS能力信息、非接入层NAS能力信息。
可选地，所述方法还包括：
所述第二设备发送设备能力请求；
其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
可选地，在所述设备能力请求用于请求所述第一设备的能力的情况下，所述设备能力请求中包括用于请求所述第一设备的感知能力的信息单元；
或者，所述设备能力请求用于请求所述第一设备的至少一项感知能力。
可选地，所述感知能力信息包括如下至少一项：
至少一个频带的感知能力信息；
至少一个频带组合的感知能力信息；
至少一个载波单元CC的感知能力信息。
可选地，所述方法还包括：
所述第二设备根据感知能力信息执行确定操作，所述确定操作用于确定如下至少一项：
参与感知的设备、感知方式、感知数据来源。
上述第二设备可以是根据一个或者多个第一设备上报的感知能力信息执行上述确定操作。例如：在多个第一设备中选择基于AI的感知能力与感知业务或者感知场景等匹配的第第一设备作为参与感知的设备；又例如：根据第一设备的感知能力信息选择与该第一设备的基于AI的感知能力匹配的感知方式；又例如：根据第一设备的感知能力信息选择与第一设备匹配的感知数据来源等。
通过上述确定操作可以使用感知与第一设备的基于AI的感知能力更加匹配，以提高感知性能。
需要说明的是，本实施例作为与图6所示的实施例中对应的第三设备的实施方式，其具体的实施方式可以参见图6所示的实施例的相关说明，以为避免重复说明，本实施例不再赘述。
下面通过多个实施例，对本申请实施例提供的方法进行举例说明：
实施例一：
本实施例中主要描述通过能力交互确定第一设备其是否参与感知。
本实施例中，第一设备为终端或基站，第二设备为感知网络功能。其中，第一设备为感知数据处理设备，其可以是参与感知测量的设备(例如接收感知信号并进行测量得到测量结果的设备)，也可以是不参与感知测量的设备，由参与感知测量的设备将获取的测量结果发送给第一设备进行处理。
感知网络功能获取感知需求信息后，选择参与感知业务的设备，假设所述感知业务对应的感知数据需要通过AI单元进行计算输出，该AI单元为通过深度学习/机器学习等获得的一种网络架构。所述感知数据可以是最终的感知结果(例如目标位置、轨迹、手势或动作等)，也可以是用于计算最终感知结果的中间测量结果(例如时延、多普勒、角度等)。此时，感知网络功能需要选择具有基于AI的感知数据处理能力的设备参与该感知业务，具体流程如图8所示，包括如下步骤：
步骤1、感知网络功能(SensingMF)获取感知需求信息，感知需求来源可以是：
感知需求信息来自外部应用，此时应用功能(Application Function，AF)发送感知需求信息给NEF，再发送给AMF，AMF选择SensingMF，并将感知需求发送给SensingMF；
或者，AF直接发送感知需求给SensingMF；
感知需求信息也可以来自基站和/或终端，此时基站和/或终端发送给AMF，AMF选择SensingMF，并将感知需求发送给SensingMF；
或者，基站和/或终端直接将感知需求发送给SensingMF；
感知需求信息也可以来自核心网网元，核心网网元发送感知需求给AMF；
AMF选择SensingMF，并将感知需求发送给SensingMF；
或者核心网网元直接将感知需求信息发送给SensingMF。
其中，经过AMF转发感知需求的方式可能但不限于出现在，网络中部署了多个感知网元，需要由AMF根据感知对象的位置、感知业务类型或感知QoS要求信息等信息从多个感知网元中选择一个合适的感知网元的场景；不经过AMF转发感知需求的方式可能但不限于出现在，网络中部署了一个或较少的SensingMF的场景。
其中，感知需求信息包括以下至少一项：
感知业务或感知业务类型，其中，感知业务或感知业务类型参见上述实施方式的相应说明，此处不作赘述；
感知目标区域，感知目标区域可以是指感知对象可能存在位置区域，或者，需要进行成像或环境重构的位置区域；
感知对象类型，感知对象类型可以是针对感知对象可能的运动特性对感知对象进行分类，每个感知对象类型中包含了典型感知对象的运动速度、运动加速度、典型RCS等信息；
感知QoS，感知QoS可以是对感知目标区域或感知对象进行感知的性能指标，包括以下至少一项：
感知分辨率，可分为：测距分辨率、测角分辨率、测速分辨率、成像分辨率等；
感知精度，可分为：测距精度、测角精度、测速精度、定位精度等；
感知范围，可分为：测距范围、测速范围、测角范围、成像范围等；
感知时延，感知时延可以是从感知信号发送到获得感知结果的时间间隔，或，从感知需求发起到获取感知结果的时间间隔；
感知更新速率，如相邻两次执行感知并获得感知结果的时间间隔；
检测概率，如在感知对象存在的情况下被正确检测出来的概率；
识别概率(用于多元检测场景，表示感知目标处于特定状态或属于特定类别，正确检测到目标状态或类别的概率)；
虚警概率，如在感知对象不存在的情况下错误检测出感知目标的概率；
可感知的最大目标个数。
步骤2、SensingMF向第一设备(指多个候选参与感知的设备)发送能力请求信息(即上述实施例中的设备能力请求)，请求获取第一设备的能力。
一种实现方式是，基于AI的感知能力请求信息是由感知网络功能发给第一设备的能力请求信息中包含的信息元素(Information Element，IE)承载的，该能力请求信息用于请求获取第一设备的感知能力，第一设备响应该能力请求信息，上报其感知能力信息，所述感知能力信息包括基于AI的感知能力信息。
步骤3、第一设备(指多个候选参与感知的设备)响应SensingMF发送的能力请求信息，并反馈其感知能力信息，所述感知能力信息包含基于AI的感知能力信息，用于指示所述第一设备的基于AI的感知能力。
基于AI的感知能力信息包括支持的与感知关联的AI单元类型，具体可以是AI单元的标识(AI model index)，或AI单元配置标识，也可以是感知场景或用例标识，或感知目标类型标识，或感知业务标识；基于AI的感知能力信息还包括基于AI的感知数据处理精度信息或可以达到的性能等级或置信度水平，或AI单元推理速度。
步骤4、SensingMF根据第一设备对基于AI的感知能力的支持情况，选择具有基于AI的感知数据处理能力或支持特定感知业务对应的AI单元的设备，或选择具有基于AI的感知数据处理能力且能够满足感知需求(例如处理时延满足感知结果刷新率要求，或输出的感知数据精度满足感知精度要求)的设备参与该感知业务。
对于一些需要AI参与感知数据处理的感知业务，通过上述能力交互信息确定满足感知需求的设备，避免不满足要求的设备参与感知，能够有效保证感知性能并提升资源利用效率。
实施例二：
本实施例主要描述通过能力交互确定第一设备的感知。
本实施例中，第一设备(终端或基站)为确定参与感知的设备，第二设备(感知网络功能，或其他基站/终端)通过能力查询确定第一设备关于基于AI的感知能力，进而确定第一设备的感知方法，例如选择基于AI的方法或非AI的方法，指示第一设备需要上报经过AI单元处理后某一类或某几类感知数据，能够有效保证感知性能，以及提升感知测量上报的效率；
或者第二设备根据第一设备基于AI的感知能力信息，确定分配给第一设备的感知信号资源和相关配置，以使得其具备更好的感知数据处理性能。
或者第一设备不是参与感知测量的设备(发送感知信号或接收感知信号并进行测量得到测量结果的设备)，仅负责感知数据处理，第二设备根据第一设备关于基于AI的感知能力信息，确定发送给第一设备的感知数据类型或格式或来源，以便于第一设备基于AI对所述感知数据进行进一步处理。
或者第二设备根据第一设备基于AI的感知能力信息，确定分配给第一设备的感知信号资源和相关配置，第一设备通过对所述感知信号的测量获得符合AI单元输入要求的感知数据，以使得其具备更好的感知数据处理性能。
本实施例涉及的主要交互流程如图9所示，其中步骤1～3同实施例一。
步骤4中第一信息包括以下至少一项：感知信号配置信息、感知测量配置信息(包括测量方法，上报配置等)、待处理的感知数据(发送给第一设备，并基于第一设备侧的AI单元进行处理)；
步骤5，第一设备接收第一信息后，执行无线感知测量流程(若第一设备为参与感知的设备)，通过AI单元对感知数据进行处理，所述感知数据可以是通过无线感知测量获取的，也可以是第二设备发送给第一设备的，或者是其他设备发送给第一设备的。
步骤6，第一设备将经过AI单元处理后输出的感知数据发送给第二设备。
实施例三：
本实施例中第一设备部署了AI单元，通过能力交互确定其具备模型训练能力，在感知场景发生变动时进行模型微调或重新训练
本实施例中，第一设备(终端或基站或感知网络功能)部署了AI单元，第二设备通过查询第一设备是否具备与感知关联的AI单元的训练能力，以及支持的用于模型训练的感知数据类型或格式或来源，指示第一设备进行模型训练时的训练配置，例如超参数(事先给定的，用来控制学习过程的参数，包括例如神经网络的拓扑结构及大小、学习率和小批量大小(Mini-Batch size)等)、预期训练达到的感知精度、训练次数或时长等，使得第一设备进行模型训练得到满足感知需求的AI单元。其中，可以是第二设备或其他设备发送给第一设备用于模型训练的感知数据，也可以是为第一设备分配感知信号资源，第一设备通过无线感知测量采集用于模型训练的感知数据。
微调指的是在预训练的与感知关联的AI单元的基础上，使用特定的、有限的感知数据进行小规模训练，实现对预训练模型参数的微小调整，最终得到适配到特定感知场景或感知业务的模型。当感知的场景发生变动，或感知目标特征发生变动时，根据第一设备支持的与感知关联的AI单元的微调的能力，为第一设备提供符合需求的感知数据，辅助第一设备实现对原来的模型进行调整，从而适应变化后的感知场景或目标，保证感知性能。若第一设备不支持模型微调，也可以是根据变化后的感知场景或目标，指示第一设备重新采集符合要求的感知数据，进行模型的重新训练，从而保证感知性能。
若第一设备不支持模型微调或模型训练的能力，则当感知场景发生变动时，可以指示第一设备切换到适配变化后的感知场景的AI单元，或者停止将第一设备作为参与感知的设备，从而避免第一设备上报无效的感知数据,保证感知性能。
实施例四：
本实施例中第一设备未部署AI单元，但可以提供感知数据，通过能力交互确定从第一设备获取的感知数据
本实施例中，第一设备(终端或基站)未部署AI单元，第二设备(其他基站或终端或感知网络功能)部署了与感知关联的AI单元，第二设备查询第一设备支持上报的输入到AI单元的感知数据，包括支持上报的输入到AI单元的感知数据类型或格式或来源(具体见申请方案)。第二设备基于获取的第一设备支持的输入到AI单元的感知数据类型或格式或来源，以及自身AI单元对输入的感知数据的类型或格式或来源的要求，向第一设备请求相应的感知数据，用于自身AI单元的推理或训练。
或者，第二设备通过查询第一设备支持上报的用于AI单元的监督的参考感知数据，向第一设备请求所述参考感知数据，包括支持上报的输入到AI单元的感知数据类型或格式(具体见申请方案)，用于自身AI单元的监督，即通过比较自身AI单元输出的感知数据与第一设备上报的参考感知数据判断模型是否有效。
实施例五：
本实施例主要描述通过AS或NAS能力交互确定第一设备其是否参与感知。
本实施例中，第一设备为终端，第二设备为核心网感知网络功能，第三设备是无线接入网节点(如基站)。其中，第一设备为感知数据处理设备，其可以是参与感知测量的设备(例如接收感知信号并进行测量得到测量结果的设备)，也可以是不参与感知测量的设备，由参与感知测量的设备将获取的测量结果发送给第一设备进行处理。
感知网络功能获取感知需求信息后，选择参与感知的设备，假设感知业务对应的感知数据需要通过AI单元进行计算输出，AI单元为通过深度学习/机器学习等获得的一种网络架构。所述感知数据可以是最终的感知结果(例如目标位置、轨迹、手势或动作等)，也可以是用于计算最终感知结果的中间测量结果(例如时延、多普勒、角度等)。此时，感知网络功能需要选择具有基于AI的感知数据处理能力的设备参与该感知业务，具体流程如下：
步骤1、第一设备(指具备感知能力的设备)向核心网负责终端能力管理的网络功能(如AMF)发送能力信息。例如终端通过注册请求消息发送能力信息给AMF，其中能力信息包括如下至少一项：
包含基于AI的感知能力的UE无线能力上报/更新，也可以称为接入层(AS)能力。例如，UE无线能力(UE Radio Capability)，所述基于AI的感知能力的UE无线能力上报/更新包括与band、band combination、carrier相关的基于AI的感知能力。具体可以是以AI单元的标识(AI model index)，或AI单元配置标识，也可以是感知场景或用例标识，或感知目标类型标识，或感知业务标识指示在某个band、band combination、carrier支持的与感知关联的AI单元。可选地，基于AI的感知能力信息还包括在对应band、band combination、carrier上基于AI的感知数据处理精度信息或可以达到的性能等级或置信度水平，或推理速度；
包含基于AI的感知能力的终端核心网能力，也可以称为NAS能力。例如终端移动性管理核心网能力(UE MM Core Network Capability)，所述能力信息包含是否支持基于AI的感知协议信息。例如将终端和SF之间的协议称为感知协议，并且该感知协议包含基于AI的感知流程。所述能力信息指示是否支持感知协议。如果感知方式包括终端和终端之间的sidelink感知或终端自发自收感知，那么，上述能力信息还可以包含是否支持基于AI的sidelink感知协议或基于AI的UE自发自收感知。
步骤2、感知网络功能(SensingMF)获取感知需求信息的过程与实施例的步骤1相同，此处不再赘述。SensingMF向核心网负责终端能力管理的网络功能(如AMF)发送能力请求信息，请求获取一个或多个候选第一设备的能力。所述能力请求指示请求非接入层能力(如终端移动性管理核心网能力)，和/或，接入层能力(如终端无线能力)。在一些实施方式中，核心网网络功能仅负责存储终端接入层能力，在需要的时候发送给终端的服务基站，从而避免空口重复传输终端接入层能力。即在一些实施方式中核心网网络功能并不使用终端接入层能力，在本实施例中感知网络功能可以请求终端无线接入层能力，用来确定感知UE等。
步骤3、SensingMF根据第一设备对基于AI的感知能力的支持情况，选择具有基于AI的感知数据处理能力或支持特定感知业务对应的AI单元的设备，或选择具有基于AI的感知数据处理能力且能够满足感知需求(例如处理时延满足感知结果刷新率要求，或输出的感知数据精度满足感知精度要求)的设备参与该感知业务。
对于一些需要AI参与感知数据处理的感知业务，通过上述能力交互信息确定满足感知需求的设备，通过复用终端上报的能力信息，可避免终端在空口重复上报感知能力。
实施例六：
本实施例主要描述基于AS能力的基站辅助的第一设备选择。
本实施例中，第一设备为终端，第二设备为核心网感知网络功能，第三设备是无线接入网节点(如基站)。其中，第一设备为感知数据处理设备，其可以是参与感知测量的设备(例如接收感知信号并进行测量得到测量结果的设备)，也可以是不参与感知测量的设备，由参与感知测量的设备将获取的测量结果发送给第一设备进行处理。
感知网络功能获取感知需求信息后，选择参与感知的设备，假设所述感知业务对应的感知数据需要通过AI单元进行计算输出，所述AI单元为通过深度学习/机器学习等获得的一种网络架构。所述感知数据可以是最终的感知结果(例如目标位置、轨迹、手势或动作等)，也可以是用于计算最终感知结果的中间测量结果(例如时延、多普勒、角度等)。此时，感知网络功能需要选择具有基于AI的感知数据处理能力的设备参与该感知业务，具体流程如下。一种示例如图10所示，包括如下步骤：
步骤1、第一设备(指具备感知能力的设备)向核心网负责终端能力管理的网络功能(如AMF)发送能力信息。例如第一设备通过注册请求消息发送能力信息给AMF，其中能力信息包括第一设备基于AI的感知能力的核心网能力。
例如：包含基于AI的感知能力的UE核心网能力，也可以称为NAS能力。例如终端移动性管理核心网能力(UE MM Core Network Capability)，所述能力信息包含是否支持基于AI的感知协议信息。例如将终端和SF之间的协议称为感知协议，并且该感知协议包含基于AI的感知流程。所述能力信息指示是否支持感知协议。如果感知方式包括终端和终端之间的sidelink感知或终端自发自收感知，那么所述能力信息还可以包含是否支持基于AI的sidelink感知协议或基于AI的终端自发自收感知。
步骤2、感知网络功能(SensingMF)获取感知需求信息的过程与实施例一的步骤1相同，此处不再赘述。SensingMF向核心网负责终端能力管理的网络功能(如AMF)发送能力请求信息，请求获取一个或多个候选第一设备的非接入层能力(如UE移动性管理核心网能力)。
步骤3、感知网络功能(SensingMF)接收所请求的能力信息，并确定是否需要终端接入层能力(如终端无线能力)，和/或，确定是否需要无线接入网节点(如基站)基于终端接入层能力来辅助感知UE选择。
步骤4、如果需要终端接入层能力，和/或，能力请求指示请求非接入层能力(如终端移动性管理核心网能力)，和/或，无线接入网节点(如基站)基于终端接入层能力来辅助感知终端选择，那么感知网络功能(SensingMF)发送能力请求信息，和/或，辅助感知终端选择请求信息。能力请求信息或辅助感知终端选择请求信息包括候选终端列表，和/或，候选终端需求(如具有基于AI的感知能力、移动速度要求、终端位置要求等)。能力请求信息或辅助感知终端选择请求信息可以是感知网络功能(SensingMF)直接发送给无线接入网节点，也可以经过核心网网络功能节点(如AMF)转发。
步骤5、无线接入网节点根据能力请求信息，和/或，辅助感知终端选择请求信息，确定是否需要向终端查询终端接入层能力(如终端无线能力)。所述终端接入层能力(如终端无线能力)包括终端感知能力，终端基于AI的感知能力中的至少一项。
上述基于AI的感知能力的终端无线能力上报/更新包括与band、band combination、carrier相关的基于AI的感知能力，具体可以是以AI单元的标识(AI model index)，或AI单元配置标识，也可以是感知场景或用例标识，或感知目标类型标识，或感知业务标识指示在某个band、band combination、carrier支持的与感知关联的AI单元。可选的，基于AI的感知能力信息还包括在对应band、band combination、carrier上基于AI的感知数据处理精度信息或可以达到的性能等级或置信度水平，或模型推理速度。
步骤6、第一设备接收无线接入网节点的能力请求信息，并发送能力上报信息提供UE感知能力，和/或，终端基于AI的感知能力。
步骤7、无线接入网节点根据新获取的终端接入层能力(如终端无线能力)，以及已经获取的终端接入层能力(如终端无线能力)，发送能力上报消息提供一个或多个终端的能力信息。或者，无线接入网节点根据新获取的终端接入层能力(如终端无线能力)，以及已经获取的终端接入层能力(如终端无线能力)，以及在步骤4中接收的候选UE需求等信息确定候选感知终端列表，用于指示潜在满足需求的终端信息。无线接入网节点发送候选终端信息给感知网络功能(SensingMF)。与步骤4类似，能力上报信息，和/或，候选终端信息可以是无线接入网节点直接发送给感知网络功能(SensingMF)，也可以经过核心网网络功能节点(如AMF)转发。
步骤8、SensingMF根据第一设备对基于AI的感知能力的支持情况，选择具有基于AI的感知数据处理能力或支持特定感知业务对应的AI单元的设备，或选择具有基于AI的感知数据处理能力且能够满足感知需求(例如处理时延满足感知结果刷新率要求，或输出的感知数据精度满足感知精度要求)的设备参与该感知业务。
对于一些需要AI参与感知数据处理的感知业务，通过上述能力交互信息确定满足感知需求的设备，通过无线接入网节点辅助获取终端接入层能力或复用无线接入网节点已经获取的终端接入层能力。或者，通过无线接入网节点基于终端接入层能力辅助感知终端选择，避免核心网功能节点获取和使用终端接入层能力。
本申请实施例中，第一设备上报基于AI的感知能力信息，包括基于AI的感知数据处理能力、与感知关联的AI单元监督能力、与感知关联的AI单元的训练能力、支持上报输入到AI单元的感知数据类型或格式或来源、支持上报用于AI单元的监督的参考感知数据类型、支持的感知信号配置信息等；第二设备根据第一设备上报能力信息，进行感知设备的选择，或确定合适的感知方法，或者确定从第一设备处获取的感知数据。
设备之间通过AI感知能力的交互，可以根据设备的能力信息进行感知设备的选择，或确定合适的感知方式，或者确定从设备处获取的感知数据，提升感知的性能和效率。
本申请实施例提供的能力信息交互方法，执行主体可以为能力信息交互装置。本申请实施例中以能力信息交互装置执行能力信息交互方法为例，说明本申请实施例提供的能力信息交互装置。
本申请实施例提供一种能力信息交互装置，作为一种示例，能力信息交互装置可以是通信设备或通信设备中的部件，例如芯片。该通信设备可以是终端、网络侧设备或服务器等。示例性的，终端可以包括但不限于上述所列举的终端11的类型，网络侧设备可以包括但不限于上述所列举的网络侧设备12的类型，本申请实施例不作具体限定。
能力信息交互装置可以包括接收模块、发送模块和处理模块。其中，接收模块、发送模块和处理模块可以是通过软件实现，也可以通过硬件实现。当通过硬件实现时，处理模块可以由处理器实现，示例性的，处理器可以包括通用处理器、专用处理器等，例如包括中央处理单元(Central Processing Unit，CPU)、微处理器、数字信号处理器(Digital Signal Processor，DSP)、人工智能(Artificial Intelligent，AI)处理器、图形处理器(Graphics Processing Unit，GPU)、专用集成电路(Application Specific Integrated Circuit，ASIC)、网络处理器(Network Processor，NP)、现场可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、门电路、晶体管、分立硬件组件等。接收模块和发送模块可以由通信接口实现，通信接口可以包括收发器、管脚、电路、总线、射频单元等其中一种或多种。
具体的，参见图11，当能力信息交互装置为第一设备，或者第一设备中的部件时，能力信息交互装置1100包括：
发送模块1101，用于上报感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
可选地，所述感知能力信息包括如下至少一项：
基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力信息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
可选地，所述基于AI的感知数据处理能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持基于AI的感知数据处理；
所述第一设备支持的基于AI处理的感知数据类型；
所述第一设备支持的基于AI处理的感知数据格式；
所述第一设备支持的基于AI处理的感知数据来源；
所述第一设备支持的AI单元输出的感知数据类型；
所述第一设备基于AI处理感知数据的时延；
所述第一设备基于AI处理感知数据的精度；
所述第一设备基于AI处理感知数据的性能等级；
所述第一设备基于AI处理感知数据的置信度水平；
所述第一设备支持的感知关联的AI单元的个数；
所述第一设备支持的感知关联的AI单元的类型；
所述第一设备支持的感知关联的AI单元的参数。
可选地，所述基于AI处理的感知数据类型包括如下至少一项：
接收信号、信道信息、谱信息、基本测量量；
或，所述基于AI处理的感知数据格式包括如下至少一项：
信道信息的维度、谱信息的范围、基本测量量的个数、基本测量量的类型；
或，
所述第一设备支持的AI单元输出的感知数据类型包括：
所述第一设备支持的AI单元联合处理输出的多种感知数据，或者，所述第一设备支持的AI单元独立处理输出的至少一种感知数据。
可选地，所述基于AI处理的感知数据来源包括如下至少一项：
来自于单个设备，或者来自于多个设备；
来自于目标感知模式；
来自于传感器；
来自于无线感知；
来自于至少一种无线接入技术RAT。
可选地，所述感知关联的AI单元的参数包括如下至少一项：
单元结构信息、超参数配置、数据处理方式、运行周期、更新信息、复杂度信息、可用的AI资源、AI框架、AI算法。
可选地，所述感知关联的AI单元的监督能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的监督；
所述第一设备支持的感知关联的AI单元的监督周期；
所述第一设备支持的感知关联的AI单元的监督时长；
所述第一设备支持的感知关联的AI单元的监督次数；
所述第一设备支持的参考数据类型，所述参考数据为用于感知关联的AI单元监督的参考数据；
所述第一设备支持上报感知关联的AI单元的监督度量指标；
所述第一设备支持上报感知关联的AI单元的监督结果。
可选地，所述参考数据类型包括如下至少一项：
感知特征已知的感知目标的感知数据；
通过传感器获取的感知数据；
通过目标感知模式获取的感知数据；
通过目标感知设备获取的感知数据；
通过非AI的方式获取的感知数据；
有源设备的定位数据；
通过能力强于所述感知关联的AI单元的AI单元获取的感知数据。
可选地，所述感知关联的AI单元的训练能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的训练；
所述第一设备支持的感知关联的AI单元的训练时间；
所述第一设备支持的感知关联的AI单元的训练数据量；
所述第一设备支持的用于感知关联的AI的训练的感知数据类型；
所述第一设备支持的用于感知关联的AI的感知数据格式；
所述第一设备支持的用于感知关联的AI的感知数据来源；
所述第一设备支持感知关联的AI单元的微调；
所述第一设备支持感知关联的AI单元的重训练；
所述第一设备支持多种感知场景的感知关联的AI单元的混合训练；
所述第一设备支持多种感知业务的感知关联的AI单元的混合训练。
可选地，所述感知关联的AI单元相关的上报能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备支持上报的感知数据类型；
所述第一设备支持上报的感知数据格式；
所述第一设备支持上报的感知数据来源；
所述第一设备支持上报的参考数据类型；
所述第一设备支持上报的参考数据格式；
所述第一设备支持上报的参考数据来源；
所述第一设备支持上报用于感知的AI能力限制信息；
其中，所述参考数据为用于感知关联的AI单元监督或者训练的参考数据。
可选地，所述感知能力信息携带在如下至少一项：
接入层AS能力信息、非接入层NAS能力信息。
可选地，所述装置还包括：
接收模块，用于获取设备能力请求；
其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
可选地，在所述设备能力请求用于请求所述第一设备的能力的情况下，所述设备能力请求中包括用于请求所述第一设备的感知能力的信息单元；
或者，所述设备能力请求用于请求所述第一设备的至少一项感知能力。
可选地，所述感知能力信息包括如下至少一项：
至少一个频带的感知能力信息；
至少一个频带组合的感知能力信息；
至少一个载波单元CC的感知能力信息。
上述能力信息交互装置有利于提升感知业务效果。
本申请实施例提供的信号监听装置能够实现图6的方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
具体的，参见图12，当能力信息交互装置为第二设备，或者第二设备中的部件时，能力信息交互装置1200包括：
接收模块1201，用于接收感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
可选地，所述感知能力信息包括如下至少一项：
基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力信息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
可选地，所述基于AI的感知数据处理能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持基于AI的感知数据处理；
所述第一设备支持的基于AI处理的感知数据类型；
所述第一设备支持的基于AI处理的感知数据格式；
所述第一设备支持的基于AI处理的感知数据来源；
所述第一设备支持的AI单元输出的感知数据类型；
所述第一设备基于AI处理感知数据的时延；
所述第一设备基于AI处理感知数据的精度；
所述第一设备基于AI处理感知数据的性能等级；
所述第一设备基于AI处理感知数据的置信度水平；
所述第一设备支持的感知关联的AI单元的个数；
所述第一设备支持的感知关联的AI单元的类型；
所述第一设备支持的感知关联的AI单元的参数。
可选地，所述基于AI处理的感知数据类型包括如下至少一项：
接收信号、信道信息、谱信息、基本测量量；
或，所述基于AI处理的感知数据格式包括如下至少一项：
信道信息的维度、谱信息的范围、基本测量量的个数、基本测量量的类型；
或，
所述第一设备支持的AI单元输出的感知数据类型包括：
所述第一设备支持的AI单元联合处理输出的多种感知数据，或者，所述第一设备支持的AI单元独立处理输出的至少一种感知数据。
可选地，所述基于AI处理的感知数据来源包括如下至少一项：
来自于单个设备，或者来自于多个设备；
来自于目标感知模式；
来自于传感器；
来自于无线感知；
来自于至少一种无线接入技术RAT。
可选地，所述感知关联的AI单元的参数包括如下至少一项：
单元结构信息、超参数配置、数据处理方式、运行周期、更新信息、复杂度信息、可用的AI资源、AI框架、AI算法。
可选地，所述感知关联的AI单元的监督能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的监督；
所述第一设备支持的感知关联的AI单元的监督周期；
所述第一设备支持的感知关联的AI单元的监督时长；
所述第一设备支持的感知关联的AI单元的监督次数；
所述第一设备支持的参考数据类型，所述参考数据为用于感知关联的AI单元监督的参考数据；
所述第一设备支持上报感知关联的AI单元的监督度量指标；
所述第一设备支持上报感知关联的AI单元的监督结果。
可选地，所述参考数据类型包括如下至少一项：
感知特征已知的感知目标的感知数据；
通过传感器获取的感知数据；
通过目标感知模式获取的感知数据；
通过目标感知设备获取的感知数据；
通过非AI的方式获取的感知数据；
有源设备的定位数据；
通过能力强于所述感知关联的AI单元的AI单元获取的感知数据。
可选地，所述感知关联的AI单元的训练能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的训练；
所述第一设备支持的感知关联的AI单元的训练时间；
所述第一设备支持的感知关联的AI单元的训练数据量；
所述第一设备支持的用于感知关联的AI的训练的感知数据类型；
所述第一设备支持的用于感知关联的AI的感知数据格式；
所述第一设备支持的用于感知关联的AI的感知数据来源；
所述第一设备支持感知关联的AI单元的微调；
所述第一设备支持感知关联的AI单元的重训练；
所述第一设备支持多种感知场景的感知关联的AI单元的混合训练；
所述第一设备支持多种感知业务的感知关联的AI单元的混合训练。
可选地，所述感知关联的AI单元相关的上报能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备支持上报的感知数据类型；
所述第一设备支持上报的感知数据格式；
所述第一设备支持上报的感知数据来源；
所述第一设备支持上报的参考数据类型；
所述第一设备支持上报的参考数据格式；
所述第一设备支持上报的参考数据来源；
所述第一设备支持上报用于感知的AI能力限制信息；
其中，所述参考数据为用于感知关联的AI单元监督或者训练的参考数据。
可选地，所述感知能力信息携带在如下至少一项：
接入层AS能力信息、非接入层NAS能力信息。
可选地，所述装置还包括：
发送模块，用于发送设备能力请求；
其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
可选地，在所述设备能力请求用于请求所述第一设备的能力的情况下，所述设备能力请求中包括用于请求所述第一设备的感知能力的信息单元；
或者，所述设备能力请求用于请求所述第一设备的至少一项感知能力。
可选地，所述感知能力信息包括如下至少一项：
至少一个频带的感知能力信息；
至少一个频带组合的感知能力信息；
至少一个载波单元CC的感知能力信息。
可选地，所述装置还包括：
处理模块，用于根据感知能力信息执行确定操作，所述确定操作用于确定如下至少一项：
参与感知的设备、感知方式、感知数据来源。
上述能力信息交互装置有利于提升感知业务效果。
本申请实施例提供的信号监听装置能够实现图7的方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
如图13所示，本申请实施例还提供一种通信设备1300，包括处理器1301和存储器1302，存储器1302上存储有可在所述处理器1301上运行的程序或指令，例如，该通信设备1300为第一设备时，该程序或指令被处理器1301执行时实现上述第一设备侧的能力信息交互方法实施例的各个步骤，且能达到相同的技术效果。该通信设备1300为第二设备时，该程序或指令被处理器1301执行时实现上述第二设备侧的能力信息交互方法实施例的各个步骤，且能达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例还提供一种设备，该设备为第一设备，包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如图6所示方法实施例中的步骤。该设备实施例与上述第一设备侧方法实施例对应，上述方法实施例的各个实施过程和实现方式均可适用于该终端实施例中，且能达到相同的技术效果。该设备可以是图12所示的能力信息交互装置。
本申请实施例还提供一种设备，包括处理器及通信接口，其中，所述通信接口用于上报感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
具体地，图14为实现本申请实施例的一种设备的硬件结构示意图。
该设备1400包括但不限于：射频单元1401、网络模块1402、音频输出单元1403、输入单元1404、传感器1405、显示单元1406、用户输入单元1407、接口单元1408、存储器1409以及处理器1410等中的至少部分部件。
本领域技术人员可以理解，设备1400还可以包括给各个部件供电的电源(比如电池)，电源可以通过电源管理系统与处理器1410逻辑相连，从而通过电源管理系统实现管理充电、放电以及功耗管理等功能。图14中示出的设备结构并不构成对设备的限定，设备可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置，在此不再赘述。
应理解的是，本申请实施例中，输入单元1404可以包括图形处理器14041和麦克风14042，图形处理器14041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元1406可包括显示面板14061，可以采用液晶显示器、有机发光二极管等形式来配置显示面板14061。用户输入单元1407包括触控面板14071以及其他输入设备14072中的至少一种。触控面板14071，也称为触摸屏。触控面板14071可包括触摸检测装置和触摸控制器两个部分。其他输入设备14072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆，在此不再赘述。
本申请实施例中，射频单元1401接收来自网络侧设备的下行数据后，可以传输给处理器1410进行处理；另外，射频单元1401可以向网络侧设备发送上行数据。通常，射频单元1401包括但不限于天线、放大器、收发器、耦合器、低噪声放大器、双工器等。
存储器1409可用于存储软件程序或指令以及各种数据。存储器1409可主要包括存储程序或指令的第一存储区和存储数据的第二存储区，其中，第一存储区可存储操作系统、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外，存储器1409可以包括易失性存储器或非易失性存储器。其中，非易失性存储器可以是只读存储器(Read-Only Memory，ROM)、可编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory，RAM)，静态随机存取存储器(Static RAM，SRAM)、动态随机存取存储器(Dynamic RAM，DRAM)、同步动态随机存取存储器(Synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM，DDRSDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(Synch link DRAM，SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM，DRRAM)。本申请实施例中的存储器1409包括但不限于这些和任意其它适合类型的存储器。
处理器1410可包括一个或多个处理单元；可选的，处理器1410集成应用处理器和调制解调处理器，其中，应用处理器主要处理涉及操作系统、用户界面和应用程序等的操作，调制解调处理器主要处理无线通信信号，如基带处理器。可以理解的是，上述调制解调处理器也可以不集成到处理器1410中。
该实施例中，以上述设备为第一设备，第一设备为终端进行举例说明。
其中，射频单元1401，用于上报感知能力信息，所述感知能力信息用于指示所述第一设备的基于人工智能AI的感知能力。
可选地，所述感知能力信息包括如下至少一项：
基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力信息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
可选地，所述基于AI的感知数据处理能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持基于AI的感知数据处理；
所述第一设备支持的基于AI处理的感知数据类型；
所述第一设备支持的基于AI处理的感知数据格式；
所述第一设备支持的基于AI处理的感知数据来源；
所述第一设备支持的AI单元输出的感知数据类型；
所述第一设备基于AI处理感知数据的时延；
所述第一设备基于AI处理感知数据的精度；
所述第一设备基于AI处理感知数据的性能等级；
所述第一设备基于AI处理感知数据的置信度水平；
所述第一设备支持的感知关联的AI单元的个数；
所述第一设备支持的感知关联的AI单元的类型；
所述第一设备支持的感知关联的AI单元的参数。
可选地，所述基于AI处理的感知数据类型包括如下至少一项：
接收信号、信道信息、谱信息、基本测量量；
或，所述基于AI处理的感知数据格式包括如下至少一项：
信道信息的维度、谱信息的范围、基本测量量的个数、基本测量量的类型；
或，
所述第一设备支持的AI单元输出的感知数据类型包括：
所述第一设备支持的AI单元联合处理输出的多种感知数据，或者，所述第一设备支持的AI单元独立处理输出的至少一种感知数据。
可选地，所述基于AI处理的感知数据来源包括如下至少一项：
来自于单个设备，或者来自于多个设备；
来自于目标感知模式；
来自于传感器；
来自于无线感知；
来自于至少一种无线接入技术RAT。
可选地，所述感知关联的AI单元的参数包括如下至少一项：
单元结构信息、超参数配置、数据处理方式、运行周期、更新信息、复杂度信息、可用的AI资源、AI框架、AI算法。
可选地，所述感知关联的AI单元的监督能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的监督；
所述第一设备支持的感知关联的AI单元的监督周期；
所述第一设备支持的感知关联的AI单元的监督时长；
所述第一设备支持的感知关联的AI单元的监督次数；
所述第一设备支持的参考数据类型，所述参考数据为用于感知关联的AI单元监督的参考数据；
所述第一设备支持上报感知关联的AI单元的监督度量指标；
所述第一设备支持上报感知关联的AI单元的监督结果。
可选地，所述参考数据类型包括如下至少一项：
感知特征已知的感知目标的感知数据；
通过传感器获取的感知数据；
通过目标感知模式获取的感知数据；
通过目标感知设备获取的感知数据；
通过非AI的方式获取的感知数据；
有源设备的定位数据；
通过能力强于所述感知关联的AI单元的AI单元获取的感知数据。
可选地，所述感知关联的AI单元的训练能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的训练；
所述第一设备支持的感知关联的AI单元的训练时间；
所述第一设备支持的感知关联的AI单元的训练数据量；
所述第一设备支持的用于感知关联的AI的训练的感知数据类型；
所述第一设备支持的用于感知关联的AI的感知数据格式；
所述第一设备支持的用于感知关联的AI的感知数据来源；
所述第一设备支持感知关联的AI单元的微调；
所述第一设备支持感知关联的AI单元的重训练；
所述第一设备支持多种感知场景的感知关联的AI单元的混合训练；
所述第一设备支持多种感知业务的感知关联的AI单元的混合训练。
可选地，所述感知关联的AI单元相关的上报能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备支持上报的感知数据类型；
所述第一设备支持上报的感知数据格式；
所述第一设备支持上报的感知数据来源；
所述第一设备支持上报的参考数据类型；
所述第一设备支持上报的参考数据格式；
所述第一设备支持上报的参考数据来源；
所述第一设备支持上报用于感知的AI能力限制信息；
其中，所述参考数据为用于感知关联的AI单元监督或者训练的参考数据。
可选地，所述感知能力信息携带在如下至少一项：
接入层AS能力信息、非接入层NAS能力信息。
可选地，射频单元1401还用于：
获取设备能力请求；
其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
可选地，在所述设备能力请求用于请求所述第一设备的能力的情况下，所述设备能力请求中包括用于请求所述第一设备的感知能力的信息单元；
或者，所述设备能力请求用于请求所述第一设备的至少一项感知能力。
可选地，所述感知能力信息包括如下至少一项：
至少一个频带的感知能力信息；
至少一个频带组合的感知能力信息；
至少一个载波单元CC的感知能力信息。
上述设备有利于提升感知业务效果。
可以理解，本实施例中提及的各实现方式的实现过程可以参照能力信息交互方法实施例的相关描述，并达到相同或相应的技术效果，为避免重复，在此不再赘述。
需要说明的是，上述设备也可以实现图7所示的方法中的步骤，或者可以实现图12所示的各模块执行的方法。
本申请实施例还提供了一种设备，包括处理器及通信接口，其中，所述通信接口用于接收感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
本申请实施例还提供一种设备，该设备为第二设备，包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如图10所示的方法实施例的步骤。该设备实施例与上述第二设备侧方法实施例对应，上述方法实施例的各个实施过程和实现方式均可适用于该设备实施例中，且能达到相同的技术效果。
具体地，本申请实施例还提供了一种设备，该设备为第二设备，该设备可以是图12所示的信号发送装置。如图15所示，该设备1500包括：天线1501、射频装置1502、基带装置1503、处理器1504和存储器1505。天线1501与射频装置1502连接。在上行方向上，射频装置1502通过天线1501接收信息，将接收的信息发送给基带装置1503进行处理。在下行方向上，基带装置1503对要发送的信息进行处理，并发送给射频装置1502，射频装置1502对收到的信息进行处理后经过天线1501发送出去。
以上实施例中设备执行的方法可以在基带装置1503中实现，该基带装置1503包括基带处理器。
基带装置1503例如可以包括至少一个基带板，该基带板上设置有多个芯片，如图15所示，其中一个芯片例如为基带处理器，通过总线接口与存储器1505连接，以调用存储器1505中的程序，执行以上方法实施例中所示的网络设备操作。
该设备还可以包括网络接口1506，该接口例如为通用公共无线接口(Common Public Radio Interface，CPRI)。
具体地，本申请实施例的设备1500还包括：存储在存储器1505上并可在处理器1504上运行的指令或程序，处理器1504调用存储器1505中的指令或程序执行图12所示各模块执行的方法，并达到相同的技术效果，为避免重复，故不在此赘述。
本实施例中，以上述设备为第二设备，所述第二设备为网络侧设备进行举例说明。
射频装置1502，用于接收感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
可选地，所述感知能力信息包括如下至少一项：
基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力信息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
可选地，所述基于AI的感知数据处理能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持基于AI的感知数据处理；
所述第一设备支持的基于AI处理的感知数据类型；
所述第一设备支持的基于AI处理的感知数据格式；
所述第一设备支持的基于AI处理的感知数据来源；
所述第一设备支持的AI单元输出的感知数据类型；
所述第一设备基于AI处理感知数据的时延；
所述第一设备基于AI处理感知数据的精度；
所述第一设备基于AI处理感知数据的性能等级；
所述第一设备基于AI处理感知数据的置信度水平；
所述第一设备支持的感知关联的AI单元的个数；
所述第一设备支持的感知关联的AI单元的类型；
所述第一设备支持的感知关联的AI单元的参数。
可选地，所述基于AI处理的感知数据类型包括如下至少一项：
接收信号、信道信息、谱信息、基本测量量；
或，所述基于AI处理的感知数据格式包括如下至少一项：
信道信息的维度、谱信息的范围、基本测量量的个数、基本测量量的类型；
或，
所述第一设备支持的AI单元输出的感知数据类型包括：
所述第一设备支持的AI单元联合处理输出的多种感知数据，或者，所述第一设备支持的AI单元独立处理输出的至少一种感知数据。
可选地，所述基于AI处理的感知数据来源包括如下至少一项：
来自于单个设备，或者来自于多个设备；
来自于目标感知模式；
来自于传感器；
来自于无线感知；
来自于至少一种无线接入技术RAT。
可选地，所述感知关联的AI单元的参数包括如下至少一项：
单元结构信息、超参数配置、数据处理方式、运行周期、更新信息、复杂度信息、可用的AI资源、AI框架、AI算法。
可选地，所述感知关联的AI单元的监督能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的监督；
所述第一设备支持的感知关联的AI单元的监督周期；
所述第一设备支持的感知关联的AI单元的监督时长；
所述第一设备支持的感知关联的AI单元的监督次数；
所述第一设备支持的参考数据类型，所述参考数据为用于感知关联的AI单元监督的参考数据；
所述第一设备支持上报感知关联的AI单元的监督度量指标；
所述第一设备支持上报感知关联的AI单元的监督结果。
可选地，所述参考数据类型包括如下至少一项：
感知特征已知的感知目标的感知数据；
通过传感器获取的感知数据；
通过目标感知模式获取的感知数据；
通过目标感知设备获取的感知数据；
通过非AI的方式获取的感知数据；
有源设备的定位数据；
通过能力强于所述感知关联的AI单元的AI单元获取的感知数据。
可选地，所述感知关联的AI单元的训练能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的训练；
所述第一设备支持的感知关联的AI单元的训练时间；
所述第一设备支持的感知关联的AI单元的训练数据量；
所述第一设备支持的用于感知关联的AI的训练的感知数据类型；
所述第一设备支持的用于感知关联的AI的感知数据格式；
所述第一设备支持的用于感知关联的AI的感知数据来源；
所述第一设备支持感知关联的AI单元的微调；
所述第一设备支持感知关联的AI单元的重训练；
所述第一设备支持多种感知场景的感知关联的AI单元的混合训练；
所述第一设备支持多种感知业务的感知关联的AI单元的混合训练。
可选地，所述感知关联的AI单元相关的上报能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备支持上报的感知数据类型；
所述第一设备支持上报的感知数据格式；
所述第一设备支持上报的感知数据来源；
所述第一设备支持上报的参考数据类型；
所述第一设备支持上报的参考数据格式；
所述第一设备支持上报的参考数据来源；
所述第一设备支持上报用于感知的AI能力限制信息；
其中，所述参考数据为用于感知关联的AI单元监督或者训练的参考数据。
可选地，所述感知能力信息携带在如下至少一项：
接入层AS能力信息、非接入层NAS能力信息。
可选地，射频装置1502还用于：
发送设备能力请求；
其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
可选地，在所述设备能力请求用于请求所述第一设备的能力的情况下，所述设备能力请求中包括用于请求所述第一设备的感知能力的信息单元；
或者，所述设备能力请求用于请求所述第一设备的至少一项感知能力。
可选地，所述感知能力信息包括如下至少一项：
至少一个频带的感知能力信息；
至少一个频带组合的感知能力信息；
至少一个载波单元CC的感知能力信息。
可选地，处理器1504还用于：
根据感知能力信息执行确定操作，所述确定操作用于确定如下至少一项：
参与感知的设备、感知方式、感知数据来源。
上述设备有利于提升感知业务效果。
可以理解，本实施例中提及的各实现方式的实现过程可以参照能力信息交互方法实施例的相关描述，并达到相同或相应的技术效果，为避免重复，在此不再赘述。
需要说明的是，上述设备也可以实现图6所示的方法中的步骤，或者可以实现图11所示的各模块执行的方法。
具体地，本申请实施例还提供了一种网络侧设备，该设备为第二设备。如图16所示，该网络侧设备1600包括：处理器1601、网络接口1602和存储器1603。其中，网络接口1602例如为通用公共无线接口(common public radio interface，CPRI)。
具体地，本申请实施例的网络侧设备1600还包括：存储在存储器1603上并可在处理器1601上运行的指令或程序，处理器1601调用存储器1603中的指令或程序执行图12所示各模块执行的方法，并达到相同的技术效果，为避免重复，故不在此赘述。
本实施例中，以上述第三设备为核心网设备进行举例说明。
其中，网络接口1602，用于接收感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
可选地，所述感知能力信息包括如下至少一项：
基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力信息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
可选地，所述基于AI的感知数据处理能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持基于AI的感知数据处理；
所述第一设备支持的基于AI处理的感知数据类型；
所述第一设备支持的基于AI处理的感知数据格式；
所述第一设备支持的基于AI处理的感知数据来源；
所述第一设备支持的AI单元输出的感知数据类型；
所述第一设备基于AI处理感知数据的时延；
所述第一设备基于AI处理感知数据的精度；
所述第一设备基于AI处理感知数据的性能等级；
所述第一设备基于AI处理感知数据的置信度水平；
所述第一设备支持的感知关联的AI单元的个数；
所述第一设备支持的感知关联的AI单元的类型；
所述第一设备支持的感知关联的AI单元的参数。
可选地，所述基于AI处理的感知数据类型包括如下至少一项：
接收信号、信道信息、谱信息、基本测量量；
或，所述基于AI处理的感知数据格式包括如下至少一项：
信道信息的维度、谱信息的范围、基本测量量的个数、基本测量量的类型；
或，
所述第一设备支持的AI单元输出的感知数据类型包括：
所述第一设备支持的AI单元联合处理输出的多种感知数据，或者，所述第一设备支持的AI单元独立处理输出的至少一种感知数据。
可选地，所述基于AI处理的感知数据来源包括如下至少一项：
来自于单个设备，或者来自于多个设备；
来自于目标感知模式；
来自于传感器；
来自于无线感知；
来自于至少一种无线接入技术RAT。
可选地，所述感知关联的AI单元的参数包括如下至少一项：
单元结构信息、超参数配置、数据处理方式、运行周期、更新信息、复杂度信息、可用的AI资源、AI框架、AI算法。
可选地，所述感知关联的AI单元的监督能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的监督；
所述第一设备支持的感知关联的AI单元的监督周期；
所述第一设备支持的感知关联的AI单元的监督时长；
所述第一设备支持的感知关联的AI单元的监督次数；
所述第一设备支持的参考数据类型，所述参考数据为用于感知关联的AI单元监督的参考数据；
所述第一设备支持上报感知关联的AI单元的监督度量指标；
所述第一设备支持上报感知关联的AI单元的监督结果。
可选地，所述参考数据类型包括如下至少一项：
感知特征已知的感知目标的感知数据；
通过传感器获取的感知数据；
通过目标感知模式获取的感知数据；
通过目标感知设备获取的感知数据；
通过非AI的方式获取的感知数据；
有源设备的定位数据；
通过能力强于所述感知关联的AI单元的AI单元获取的感知数据。
可选地，所述感知关联的AI单元的训练能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备是否支持感知关联的AI单元的训练；
所述第一设备支持的感知关联的AI单元的训练时间；
所述第一设备支持的感知关联的AI单元的训练数据量；
所述第一设备支持的用于感知关联的AI的训练的感知数据类型；
所述第一设备支持的用于感知关联的AI的感知数据格式；
所述第一设备支持的用于感知关联的AI的感知数据来源；
所述第一设备支持感知关联的AI单元的微调；
所述第一设备支持感知关联的AI单元的重训练；
所述第一设备支持多种感知场景的感知关联的AI单元的混合训练；
所述第一设备支持多种感知业务的感知关联的AI单元的混合训练。
可选地，所述感知关联的AI单元相关的上报能力信息用于指示如下至少一项基于AI的感知能力：
所述第一设备支持上报的感知数据类型；
所述第一设备支持上报的感知数据格式；
所述第一设备支持上报的感知数据来源；
所述第一设备支持上报的参考数据类型；
所述第一设备支持上报的参考数据格式；
所述第一设备支持上报的参考数据来源；
所述第一设备支持上报用于感知的AI能力限制信息；
其中，所述参考数据为用于感知关联的AI单元监督或者训练的参考数据。
可选地，所述感知能力信息携带在如下至少一项：
接入层AS能力信息、非接入层NAS能力信息。
可选地，网络接口1602还用于：
发送设备能力请求；
其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
可选地，在所述设备能力请求用于请求所述第一设备的能力的情况下，所述设备能力请求中包括用于请求所述第一设备的感知能力的信息单元；
或者，所述设备能力请求用于请求所述第一设备的至少一项感知能力。
可选地，所述感知能力信息包括如下至少一项：
至少一个频带的感知能力信息；
至少一个频带组合的感知能力信息；
至少一个载波单元CC的感知能力信息。
可选地，处理器1601用于：
根据感知能力信息执行确定操作，所述确定操作用于确定如下至少一项：
参与感知的设备、感知方式、感知数据来源。
上述设备可以提高设备之间的能力信息交互用于感知业务的效果。
可以理解，本实施例中提及的各实现方式的实现过程可以参照能力信息交互方法实施例的相关描述，并达到相同或相应的技术效果，为避免重复，在此不再赘述。
需要说明的是，上述设备也可以实现图6所示的方法中的步骤，或者可以实现图11所示的各模块执行的方法。
本申请实施例还提供一种可读存储介质，所述可读存储介质上存储有程序或指令，该程序或指令被处理器执行时实现上述能力信息交互方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
其中，所述处理器为上述实施例中所述的终端中的处理器。所述可读存储介质，包括计算机可读存储介质，如计算机只读存储器ROM、随机存取存储器RAM、磁碟或者光盘等。在一些示例中，可读存储介质可以是非瞬态的可读存储介质。
本申请实施例另提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现上述能力信息交互方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
应理解，本申请实施例提到的芯片还可以称为系统级芯片，系统芯片，芯片系统或片上系统芯片等。
本申请实施例另提供了一种计算机程序/程序产品，所述计算机程序/程序产品被存储在存储介质中，所述计算机程序/程序产品被至少一个处理器执行以实现上述能力信息交互方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例还提供了一种无线通信系统，包括：第一设备及第二设备，其中，所述第一设备可用于执行如本申请实施例提供的第一设备侧的能力信息交互方法的步骤，所述第二设备可用于执行如本申请实施例提供的第二设备侧的能力信息交互方法的步骤。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外，需要指出的是，本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能，还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能，例如，可以按不同于所描述的次序来执行所描述的方法，并且还可以添加、省去或组合各种步骤。另外，参照某些示例所描述的特征可在其他示例中被组合。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助计算机软件产品加必需的通用硬件平台的方式来实现，当然也可以通过硬件。该计算机软件产品存储在存储介质(如ROM、RAM、磁碟、光盘等)中，包括若干指令，用以使得终端或者网络侧设备执行本申请各个实施例所述的方法。
上面结合附图对本申请的实施例进行了描述，但是本申请并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本申请的启示下，在不脱离本申请宗旨和权利要求所保护的范围情况下，还可做出很多形式的实施方式，这些实施方式均属于本申请的保护之内。

Claims (33)

  1. 一种能力信息交互方法，包括：
    第一设备上报感知能力信息，所述感知能力信息用于指示所述第一设备的基于人工智能AI的感知能力。
  2. 如权利要求1所述的方法，其中，所述感知能力信息包括如下至少一项：
    基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力信息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
  3. 如权利要求2所述的方法，其中，所述基于AI的感知数据处理能力信息用于指示如下至少一项基于AI的感知能力：
    所述第一设备是否支持基于AI的感知数据处理；
    所述第一设备支持的基于AI处理的感知数据类型；
    所述第一设备支持的基于AI处理的感知数据格式；
    所述第一设备支持的基于AI处理的感知数据来源；
    所述第一设备支持的AI单元输出的感知数据类型；
    所述第一设备基于AI处理感知数据的时延；
    所述第一设备基于AI处理感知数据的精度；
    所述第一设备基于AI处理感知数据的性能等级；
    所述第一设备基于AI处理感知数据的置信度水平；
    所述第一设备支持的感知关联的AI单元的个数；
    所述第一设备支持的感知关联的AI单元的类型；
    所述第一设备支持的感知关联的AI单元的参数。
  4. 如权利要求3所述的方法，其中，所述基于AI处理的感知数据类型包括如下至少一项：
    接收信号、信道信息、谱信息、基本测量量；
    或，所述基于AI处理的感知数据格式包括如下至少一项：
    信道信息的维度、谱信息的范围、基本测量量的个数、基本测量量的类型；
    或，
    所述第一设备支持的AI单元输出的感知数据类型包括：
    所述第一设备支持的AI单元联合处理输出的多种感知数据，或者，所述第一设备支持的AI单元独立处理输出的至少一种感知数据。
  5. 如权利要求3或4所述的方法，其中，所述基于AI处理的感知数据来源包括如下至少一项：
    来自于单个设备，或者来自于多个设备；
    来自于目标感知模式；
    来自于传感器；
    来自于无线感知；
    来自于至少一种无线接入技术RAT。
  6. 如权利要求3至5中任一项所述的方法，其中，所述感知关联的AI单元的参数包括如下至少一项：
    单元结构信息、超参数配置、数据处理方式、运行周期、更新信息、复杂度信息、可用的AI资源、AI框架、AI算法。
  7. 如权利要求2至6中任一项所述的方法，其中，所述感知关联的AI单元的监督能力信息用于指示如下至少一项基于AI的感知能力：
    所述第一设备是否支持感知关联的AI单元的监督；
    所述第一设备支持的感知关联的AI单元的监督周期；
    所述第一设备支持的感知关联的AI单元的监督时长；
    所述第一设备支持的感知关联的AI单元的监督次数；
    所述第一设备支持的参考数据类型，所述参考数据为用于感知关联的AI单元监督的参考数据；
    所述第一设备支持上报感知关联的AI单元的监督度量指标；
    所述第一设备支持上报感知关联的AI单元的监督结果。
  8. 如权利要求7所述的方法，其中，所述参考数据类型包括如下至少一项：
    感知特征已知的感知目标的感知数据；
    通过传感器获取的感知数据；
    通过目标感知模式获取的感知数据；
    通过目标感知设备获取的感知数据；
    通过非AI的方式获取的感知数据；
    有源设备的定位数据；
    通过能力强于所述感知关联的AI单元的AI单元获取的感知数据。
  9. 如权利要求2至8中任一项所述的方法，其中，所述感知关联的AI单元的训练能力信息用于指示如下至少一项基于AI的感知能力：
    所述第一设备是否支持感知关联的AI单元的训练；
    所述第一设备支持的感知关联的AI单元的训练时间；
    所述第一设备支持的感知关联的AI单元的训练数据量；
    所述第一设备支持的用于感知关联的AI的训练的感知数据类型；
    所述第一设备支持的用于感知关联的AI的感知数据格式；
    所述第一设备支持的用于感知关联的AI的感知数据来源；
    所述第一设备支持感知关联的AI单元的微调；
    所述第一设备支持感知关联的AI单元的重训练；
    所述第一设备支持多种感知场景的感知关联的AI单元的混合训练；
    所述第一设备支持多种感知业务的感知关联的AI单元的混合训练。
  10. 如权利要求2至9中任一项所述的方法，其中，所述感知关联的AI单元相关的上报能力信息用于指示如下至少一项基于AI的感知能力：
    所述第一设备支持上报的感知数据类型；
    所述第一设备支持上报的感知数据格式；
    所述第一设备支持上报的感知数据来源；
    所述第一设备支持上报的参考数据类型；
    所述第一设备支持上报的参考数据格式；
    所述第一设备支持上报的参考数据来源；
    所述第一设备支持上报用于感知的AI能力限制信息；
    其中，所述参考数据为用于感知关联的AI单元监督或者训练的参考数据。
  11. 如权利要求1至10中任一项所述的方法，其中，所述感知能力信息携带在如下至少一项：
    接入层AS能力信息、非接入层NAS能力信息。
  12. 如权利要求1至11中任一项所述的方法，其中，所述方法还包括：
    所述第一设备获取设备能力请求；
    其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
  13. 如权利要求12所述的方法，其中，在所述设备能力请求用于请求所述第一设备的能力的情况下，所述设备能力请求中包括用于请求所述第一设备的感知能力的信息单元；
    或者，所述设备能力请求用于请求所述第一设备的至少一项感知能力。
  14. 如权利要求1至13中任一项所述的方法，其中，所述感知能力信息包括如下至少一项：
    至少一个频带的感知能力信息；
    至少一个频带组合的感知能力信息；
    至少一个载波单元CC的感知能力信息。
  15. 一种能力信息接收方法，包括：
    第二设备接收感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
  16. 如权利要求15所述的方法，其中，所述感知能力信息包括如下至少一项：
    基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力信息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
  17. 如权利要求16所述的方法，其中，所述基于AI的感知数据处理能力信息用于指示如下至少一项基于AI的感知能力：
    所述第一设备是否支持基于AI的感知数据处理；
    所述第一设备支持的基于AI处理的感知数据类型；
    所述第一设备支持的基于AI处理的感知数据格式；
    所述第一设备支持的基于AI处理的感知数据来源；
    所述第一设备支持的AI单元输出的感知数据类型；
    所述第一设备基于AI处理感知数据的时延；
    所述第一设备基于AI处理感知数据的精度；
    所述第一设备基于AI处理感知数据的性能等级；
    所述第一设备基于AI处理感知数据的置信度水平；
    所述第一设备支持的感知关联的AI单元的个数；
    所述第一设备支持的感知关联的AI单元的类型；
    所述第一设备支持的感知关联的AI单元的参数。
  18. 如权利要求16或17所述的方法，其中，所述感知关联的AI单元的监督能力信息用于指示如下至少一项基于AI的感知能力：
    所述第一设备是否支持感知关联的AI单元的监督；
    所述第一设备支持的感知关联的AI单元的监督周期；
    所述第一设备支持的感知关联的AI单元的监督时长；
    所述第一设备支持的感知关联的AI单元的监督次数；
    所述第一设备支持的参考数据类型，所述参考数据为用于感知关联的AI单元监督的参考数据；
    所述第一设备支持上报感知关联的AI单元的监督度量指标；
    所述第一设备支持上报感知关联的AI单元的监督结果。
  19. 如权利要求16至18中任一项所述的方法，其中，所述感知关联的AI单元的训练能力信息用于指示如下至少一项基于AI的感知能力：
    所述第一设备是否支持感知关联的AI单元的训练；
    所述第一设备支持的感知关联的AI单元的训练时间；
    所述第一设备支持的感知关联的AI单元的训练数据量；
    所述第一设备支持的用于感知关联的AI的训练的感知数据类型；
    所述第一设备支持的用于感知关联的AI的感知数据格式；
    所述第一设备支持的用于感知关联的AI的感知数据来源；
    所述第一设备支持感知关联的AI单元的微调；
    所述第一设备支持感知关联的AI单元的重训练；
    所述第一设备支持多种感知场景的感知关联的AI单元的混合训练；
    所述第一设备支持多种感知业务的感知关联的AI单元的混合训练。
  20. 如权利要求16至19中任一项所述的方法，其中，所述感知关联的AI单元相关的上报能力信息用于指示如下至少一项基于AI的感知能力：
    所述第一设备支持上报的感知数据类型；
    所述第一设备支持上报的感知数据格式；
    所述第一设备支持上报的感知数据来源；
    所述第一设备支持上报的参考数据类型；
    所述第一设备支持上报的参考数据格式；
    所述第一设备支持上报的参考数据来源；
    所述第一设备支持上报用于感知的AI能力限制信息；
    其中，所述参考数据为用于感知关联的AI单元监督或者训练的参考数据。
  21. 如权利要求15至20中任一项所述的方法，其中，所述方法还包括：
    所述第二设备发送设备能力请求；
    其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
  22. 如权利要求15至21中任一项所述的方法，其中，所述感知能力信息包括如下至少一项：
    至少一个频带的感知能力信息；
    至少一个频带组合的感知能力信息；
    至少一个载波单元CC的感知能力信息。
  23. 如权利要求15至22中任一项所述的方法，其中，所述方法还包括：
    所述第二设备根据所述感知能力信息执行确定操作，所述确定操作用于确定如下至少一项：
    参与感知的设备、感知方式、感知数据来源。
  24. 一种能力信息交互装置，包括：
    发送模块，用于上报感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
  25. 如权利要求24所述的装置，其中，所述感知能力信息包括如下至少一项：
    基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
  26. 如权利要求24或25所述的装置，其中，所述装置还包括：
    接收模块，用于获取设备能力请求；
    其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
  27. 一种能力信息接收装置，包括：
    接收模块，用于接收感知能力信息，所述感知能力信息用于指示第一设备的基于人工智能AI的感知能力。
  28. 如权利要求27所述的装置，其中，所述感知能力信息包括如下至少一项：
    基于AI的感知数据处理能力信息、感知关联的AI单元的监督能力信息、感知关联的AI单元的训练能力信息、感知关联的AI单元相关的上报能力信息、所述第一设备支持的信号配置信息、所述第一设备支持的感知业务使用AI能力的优先级信息，其中，所述信号配置信息为感知关联的AI单元对应的感知信号的配置信息。
  29. 如权利要求27或28所述的装置，其中，所述装置还包括：
    发送模块，用于发送设备能力请求；
    其中，所述设备能力请求用于请求所述第一设备的能力；或者，所述设备能力请求用于请求所述第一设备的感知能力。
  30. 如权利要求27至29中任一项所述的装置，其中，所述装置还包括：
    处理模块，用于根据感知能力信息执行确定操作，所述确定操作用于确定如下至少一项：
    参与感知的设备、感知方式、感知数据来源。
  31. 一种设备，包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如权利要求1至14任一项所述的能力信息交互方法的步骤，或者所述程序或指令被所述处理器执行时实现如权利要求15至23任一项所述的能力信息接收方法的步骤。
  32. 一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如权利要求1至14任一项所述的能力信息交互方法的步骤，或者实现如权利要求15至23任一项所述的能力信息接收方法的步骤。
  33. 一种计算机程序产品，所述计算机程序产品被存储在存储介质中，所述计算机程序产品被至少一个处理器执行以实现如权利要求1至14任一项所述的能力信息交互方法的步骤，或者实现如权利要求15至23任一项所述的能力信息接收方法的步骤。
PCT/CN2025/093290 2024-05-14 2025-05-08 能力信息交互方法、装置及设备 Pending WO2025237141A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410597760.9 2024-05-14
CN202410597760.9A CN120957108A (zh) 2024-05-14 2024-05-14 能力信息交互方法、装置及设备

Publications (1)

Publication Number Publication Date
WO2025237141A1 true WO2025237141A1 (zh) 2025-11-20

Family

ID=97617356

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/093290 Pending WO2025237141A1 (zh) 2024-05-14 2025-05-08 能力信息交互方法、装置及设备

Country Status (2)

Country Link
CN (1) CN120957108A (zh)
WO (1) WO2025237141A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114391301A (zh) * 2020-08-19 2022-04-22 北京小米移动软件有限公司 感知能力请求、感知能力发送、感知能力接收方法和装置
CN115843435A (zh) * 2022-08-08 2023-03-24 北京小米移动软件有限公司 一种网络设备管理方法及装置
US20230146887A1 (en) * 2021-11-11 2023-05-11 Qualcomm Incorporated Perception-assisted wireless communication
CN116530112A (zh) * 2023-03-03 2023-08-01 北京小米移动软件有限公司 感知节点发现方法及其装置
WO2024022309A1 (zh) * 2022-07-25 2024-02-01 展讯半导体(南京)有限公司 通信方法及装置、计算机可读存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114391301A (zh) * 2020-08-19 2022-04-22 北京小米移动软件有限公司 感知能力请求、感知能力发送、感知能力接收方法和装置
US20230146887A1 (en) * 2021-11-11 2023-05-11 Qualcomm Incorporated Perception-assisted wireless communication
WO2024022309A1 (zh) * 2022-07-25 2024-02-01 展讯半导体(南京)有限公司 通信方法及装置、计算机可读存储介质
CN115843435A (zh) * 2022-08-08 2023-03-24 北京小米移动软件有限公司 一种网络设备管理方法及装置
CN116530112A (zh) * 2023-03-03 2023-08-01 北京小米移动软件有限公司 感知节点发现方法及其装置

Also Published As

Publication number Publication date
CN120957108A (zh) 2025-11-14

Similar Documents

Publication Publication Date Title
US20240340949A1 (en) Sensing method and apparatus and communication device
CN117202218A (zh) 感知方式切换方法、装置及通信设备
CN118102367A (zh) 测量方法、装置及设备
WO2025237141A1 (zh) 能力信息交互方法、装置及设备
WO2024131761A1 (zh) 感知协作方法、装置及通信设备
WO2025237143A1 (zh) 联合推理方法、装置及设备
WO2025237147A1 (zh) Ai单元监控方法、装置及设备
WO2025237117A1 (zh) 感知处理的方法、装置、设备及介质
WO2025237146A1 (zh) 信息处理方法、装置及设备
CN120957109A (zh) Ai单元监控方法、装置、第一设备及第二设备
WO2025237195A9 (zh) 感知处理的方法、装置、设备及介质
WO2026086684A1 (zh) 协作感知处理方法、装置、终端及网络侧设备
WO2026046135A1 (zh) 感知方法、配置方法、装置及相关设备
WO2025130792A1 (zh) 模型推理方法及装置
WO2026021466A1 (zh) 位置信息获取方法、装置及设备
WO2026092520A1 (zh) 无线通信方法、装置以及设备
WO2026067379A1 (zh) 数据传输方法、装置、第一设备及第二设备
WO2026067305A1 (zh) 位置测量方法、装置及设备
WO2026067394A1 (zh) 数据传输方法、装置及相关设备
WO2025185586A9 (zh) 测量方法、测量配置方法、装置及设备
CN120224266A (zh) 感知测量结果反馈方法、接收方法、装置及设备
WO2025124291A1 (zh) 感知方式切换方法、装置及通信设备
WO2025185587A1 (zh) 测量方法、测量指示方法、装置及设备
WO2026067290A1 (zh) 数据传输方法、装置及相关设备
WO2025124300A1 (zh) 感知方式切换方法、装置及通信设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25802792

Country of ref document: EP

Kind code of ref document: A1