Model reasoning method and device

Abstract

The invention discloses a model reasoning method and device, and belongs to the technical field of communication, and the model reasoning method comprises the steps that first equipment obtains a reasoning sample, and the reasoning sample is determined based on communication measurement related data and perception measurement related data; and the first device inputs the reasoning sample to an AI unit to obtain a reasoning result.

Description

Technical Field

[0001] This application belongs to the field of communication technologies, and particularly relates to a model inference method and apparatus. Background Art

[0002] With the development of Artificial Intelligence (AI) technology, AI technology is expected to be applied to communication technologies. For example, in related technologies, it has been proposed to use an AI neural network model to implement communication functions such as beam prediction, Channel State Information (CSI) prediction, or positioning services. In related technologies, the data for model inference (i.e., inference samples) basically comes from the data obtained through communication measurements. However, the data obtained through communication measurements is relatively limited, which results in limited inference accuracy of the model. Summary of the Invention

[0003] Embodiments of this application provide a model inference method and apparatus, which can solve the problem of limited inference accuracy of the model in related technologies.

[0004] In a first aspect, a model inference method is provided, which is executed by a first device. The method includes:

[0005] The first device obtains inference samples, where the inference samples are determined based on communication measurement-related data and perception measurement-related data;

[0006] The first device inputs the inference samples into an Artificial Intelligence (AI) unit to obtain an inference result.

[0007] In a second aspect, a model inference method is provided, which is executed by a second device. The method includes:

[0008] The second device receives a first request from the first device, where the first request is used to request perception measurement-related data required for model inference;

[0009] The second device performs a first operation, where the first operation includes any one of the following:

[0010] The second device sends a target signal based on the first request;

[0011] The second device determines configuration information of the target signal based on the first request;

[0012] The second device sends the configuration information of the target signal based on the first request;

[0013] The second device sends perception measurement-related data based on the first request;

[0014] Among them, the target signal is a signal used for sensing.

[0015] In a third aspect, a model inference method is provided, which is executed by a third device. The method includes:

[0016] The third device sends first information to the first device, and the first information includes at least one of communication measurement related data and sensing measurement related data;

[0017] The first information includes at least one of the following:

[0018] Target communication measurement quantities and target communication measurement quantities, and the target communication measurement quantities and the target communication measurement quantities are determined to belong to the same inference sample;

[0019] Target communication measurement quantities and a third indication, and the target communication measurement quantities and the sensing measurement quantities indicated by the third indication are determined to belong to the same inference sample;

[0020] Target communication measurement quantities, and the target communication measurement quantities and the sensing measurement quantities of the most recent inference sample are determined to belong to the same inference sample;

[0021] Or,

[0022] The first information includes at least one of the following:

[0023] Dataset identifier, and the dataset corresponding to the dataset identifier includes sensing measurement related data;

[0024] Configuration identifier of sensing measurement quantities;

[0025] Identifier of sensing measurement quantities;

[0026] Identifier of sensing measurement link;

[0027] Identifier of sensing service;

[0028] Identifier of sensing service type;

[0029] Sensing measurement quantities;

[0030] Timestamp of sensing measurement quantities;

[0031] Information of the sending device of sensing measurement quantities;

[0032] Coordinate information of sensing measurement quantities;

[0033] Information for indicating the performance metrics of sensing measurement quantities;

[0034] Information for indicating the source of sensing measurement quantities;

[0035] Information for indicating the type of sensing measurement quantities;

[0036] Information for indicating the use of the sensed measurement quantity;

[0037] Information for indicating the sensing mode of the sensed measurement quantity;

[0038] Communication measurement quantity;

[0039] Communication measurement resource identifier;

[0040] Timestamp of the communication measurement quantity;

[0041] Information for indicating the first time window;

[0042] Information for indicating the first valid time;

[0043] Configuration identifier of the target signal;

[0044] Configuration information of the target signal;

[0045] Information of the sending device of the target signal;

[0046] Information of the receiving device of the target signal;

[0047] Wherein, the target signal is a signal used for sensing.

[0048] In a fourth aspect, a model inference method is provided, which is executed by a fourth device, and the method includes:

[0049] The fourth device receives second information from the first device, and the second information includes an inference result and a fourth indication, and the inference result is obtained by the AI unit using an inference sample;

[0050] Wherein, the fourth indication is used to indicate at least one of the following:

[0051] Dataset identifier, and the dataset corresponding to the dataset identifier includes sensing measurement-related data;

[0052] Configuration identifier of the sensed measurement quantity;

[0053] Identifier of the sensed measurement quantity;

[0054] Identifier of the sensing measurement link;

[0055] Identifier of the sensing service;

[0056] Identifier of the sensing service type;

[0057] Whether the inference sample uses the sensed measurement quantity;

[0058] The sensed measurement quantity used by the inference sample;

[0059] Timeliness of the sensed measurement quantity used by the inference sample;

[0060] A sending device for the perception measurement quantity used in the inference sample;

[0061] A receiving device for the perception measurement quantity used in the inference sample;

[0062] The coordinates of the perception measurement quantity used in the inference sample;

[0063] The source of the perception measurement quantity used in the inference sample;

[0064] The perception mode of the perception measurement quantity used in the inference sample;

[0065] The processing level of the perception measurement quantity used in the inference sample;

[0066] The perception service of the perception measurement quantity used in the inference sample;

[0067] The use of the perception measurement quantity used in the inference sample;

[0068] The performance index of the perception measurement quantity used in the inference sample;

[0069] The quantity of the perception measurement quantity used in the inference sample;

[0070] The proportion of the perception measurement quantity used in the inference sample;

[0071] Whether the quantity of the perception measurement quantity used in the inference sample meets the minimum quantity threshold;

[0072] Whether the proportion of the perception measurement quantity used in the inference sample meets the minimum proportion threshold;

[0073] The proportion of the perception measurement quantity used in the inference sample that meets timeliness;

[0074] The quantity of the perception measurement quantity used in the inference sample that meets timeliness;

[0075] Configuration information of the target signal;

[0076] Wherein, the target signal is the target signal corresponding to the perception measurement quantity used in the inference sample.

[0077] In a fifth aspect, a model inference device is provided, which is applied to a first device. The device includes:

[0078] A first processing module, configured to obtain an inference sample, where the inference sample is determined based on communication measurement related data and perception measurement related data;

[0079] A second processing module, configured to input the inference sample into an artificial intelligence (AI) unit to obtain an inference result.

[0080] In a sixth aspect, a model inference device is provided, which is applied to a second device. The device includes:

[0081] A receiving module, configured to receive a first request from a first device, where the first request is used to request perception measurement-related data required for model inference;

[0082] A processing module, configured to perform a first operation, where the first operation includes any one of the following:

[0083] Based on the first request, send a target signal;

[0084] Based on the first request, determine configuration information of the target signal;

[0085] Based on the first request, send the configuration information of the target signal;

[0086] Based on the first request, send perception measurement-related data;

[0087] Wherein, the target signal is a signal used for perception.

[0088] In a seventh aspect, a model inference device is provided, which is applied to a third device. The device includes:

[0089] A sending module, configured to send first information to a first device, where the first information includes at least one of communication measurement-related data and perception measurement-related data;

[0090] The first information includes at least one of the following:

[0091] Target communication measurement quantities and target communication measurement quantities, where the target communication measurement quantities and the target communication measurement quantities are determined to belong to the same inference sample;

[0092] A target communication measurement quantity and a third indication, where the target communication measurement quantity and the perception measurement quantity indicated by the third indication are determined to belong to the same inference sample;

[0093] A target communication measurement quantity, where the target communication measurement quantity and the perception measurement quantity of the most recent inference sample are determined to belong to the same inference sample;

[0094] Or,

[0095] The first information includes at least one of the following:

[0096] A dataset identifier, where the dataset corresponding to the dataset identifier includes perception measurement-related data;

[0097] A configuration identifier of the perception measurement quantity;

[0098] Identification of the perceived measurement quantity;

[0099] Identification of the perceived measurement link;

[0100] Identification of the perceived service;

[0101] Identification of the perceived service type;

[0102] Perceived measurement quantity;

[0103] Timestamp of the perceived measurement quantity;

[0104] Information of the sending device of the perceived measurement quantity;

[0105] Coordinate information of the perceived measurement quantity;

[0106] Information for indicating the performance index of the perceived measurement quantity;

[0107] Information for indicating the source of the perceived measurement quantity;

[0108] Information for indicating the type of the perceived measurement quantity;

[0109] Information for indicating the use of the perceived measurement quantity;

[0110] Information for indicating the perception mode of the perceived measurement quantity;

[0111] Communication measurement quantity;

[0112] Communication measurement resource identifier;

[0113] Timestamp of the communication measurement quantity;

[0114] Information for indicating the first time window;

[0115] Information for indicating the first valid time;

[0116] Configuration identifier of the target signal;

[0117] Configuration information of the target signal;

[0118] Information of the sending device of the target signal;

[0119] Information of the receiving device of the target signal;

[0120] Wherein, the target signal is a signal used for perception.

[0121] In an eighth aspect, there is provided a model inference device, which is applied to a fourth device. The device includes:

[0122] A receiving module, configured to receive second information from a first device, where the second information includes an inference result and a fourth indication, and the inference result is obtained by an AI unit using inference samples;

[0123] Among them, the fourth indication is used to indicate at least one of the following:

[0124] A dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data;

[0125] A configuration identifier of a perception measurement quantity;

[0126] An identifier of a perception measurement quantity;

[0127] An identifier of a perception measurement link;

[0128] An identifier of a perception service;

[0129] An identifier of a perception service type;

[0130] Whether the inference sample uses a perception measurement quantity;

[0131] The perception measurement quantity used by the inference sample;

[0132] The timeliness of the perception measurement quantity used by the inference sample;

[0133] The sending device of the perception measurement quantity used by the inference sample;

[0134] The receiving device of the perception measurement quantity used by the inference sample;

[0135] The coordinates of the perception measurement quantity used by the inference sample;

[0136] The source of the perception measurement quantity used by the inference sample;

[0137] The perception mode of the perception measurement quantity used by the inference sample;

[0138] The processing level of the perception measurement quantity used by the inference sample;

[0139] The perception service of the perception measurement quantity used by the inference sample;

[0140] The use of the perception measurement quantity used by the inference sample;

[0141] The performance index of the perception measurement quantity used by the inference sample;

[0142] The quantity of the perception measurement quantity used by the inference sample;

[0143] The proportion of the perception measurement quantity used by the inference sample;

[0144] Whether the quantity of the perception measurement quantity used by the inference sample meets the minimum quantity threshold;

[0145] Whether the proportion of the perception measurement quantities used in the inference sample meets the minimum proportion threshold;

[0146] The proportion of the perception measurement quantities used in the inference sample that meet timeliness requirements;

[0147] The quantity of the perception measurement quantities used in the inference sample that meet timeliness requirements;

[0148] Configuration information of the target signal;

[0149] Wherein, the target signal is the target signal corresponding to the perception measurement quantities used in the inference sample.

[0150] In a ninth aspect, a communication device is provided. The terminal includes a processor and a memory. The memory stores a program or instruction that can run on the processor. When the program or instruction is executed by the processor, it implements the steps of the method described in the first aspect, or implements the steps of the method described in the second aspect, or implements the steps of the method described in the third aspect, or implements the steps of the method described in the fourth aspect.

[0151] In a tenth aspect, a communication device is provided, including a processor and a communication interface. Wherein, the processor is configured to: obtain an inference sample, which is determined based on communication measurement-related data and perception measurement-related data; input the inference sample into an artificial intelligence (AI) unit to obtain an inference result.

[0152] In an eleventh aspect, a communication device is provided, including a processor and a communication interface. Wherein, the communication interface is configured to: receive a first request from a first device, the first request being used to request perception measurement-related data required for model inference; the processor is configured to: perform a first operation, where the first operation includes any one of the following: sending a target signal based on the first request; determining configuration information of a target signal based on the first request; sending configuration information of a target signal based on the first request; sending perception measurement-related data based on the first request; wherein, the target signal is a signal used for perception.

[0153] In a twelfth aspect, a communication device is provided, including a processor and a communication interface. The communication interface is configured to: send first information to a first device, where the first information includes at least one of communication measurement-related data and perception measurement-related data; the first information includes at least one of the following: a target communication measurement quantity and a target communication measurement quantity, where the target communication measurement quantity and the target communication measurement quantity are determined to belong to the same inference sample; a target communication measurement quantity and a third indication, where the target communication measurement quantity and the perception measurement quantity indicated by the third indication are determined to belong to the same inference sample; a target communication measurement quantity, where the target communication measurement quantity and the perception measurement quantity of the most recent inference sample are determined to belong to the same inference sample; or, the first information includes at least one of the following: a dataset identifier, where the dataset corresponding to the dataset identifier includes perception measurement-related data; a configuration identifier of a perception measurement quantity; an identifier of a perception measurement quantity; an identifier of a perception measurement link; an identifier of a perception service; an identifier of a perception service type; a perception measurement quantity; a timestamp of a perception measurement quantity; information about the sending device of a perception measurement quantity; coordinate information of a perception measurement quantity; information for indicating a performance indicator of a perception measurement quantity; information for indicating the source of a perception measurement quantity; information for indicating the type of a perception measurement quantity; information for indicating the use of a perception measurement quantity; information for indicating the perception mode of a perception measurement quantity; a communication measurement quantity; a communication measurement resource identifier; a timestamp of a communication measurement quantity; information for indicating a first time window; information for indicating a first effective time; a configuration identifier of a target signal; configuration information of a target signal; information about the sending device of a target signal; information about the receiving device of a target signal; where the target signal is a signal used for perception.

[0154] In a thirteenth aspect, a communication device is provided, including a processor and a communication interface. The communication interface is configured to: receive second information from a first device, where the second information includes an inference result and a fourth indication. The inference result is obtained by an AI unit using inference samples; where the fourth indication is used to indicate at least one of the following: a dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data; a configuration identifier of a perception measurement quantity; an identifier of a perception measurement quantity; an identifier of a perception measurement link; an identifier of a perception service; an identifier of a perception service type; whether the inference samples use perception measurement quantities; the perception measurement quantities used by the inference samples; the timeliness of the perception measurement quantities used by the inference samples; the sending device of the perception measurement quantities used by the inference samples; the receiving device of the perception measurement quantities used by the inference samples; the coordinates of the perception measurement quantities used by the inference samples; the source of the perception measurement quantities used by the inference samples; the perception mode of the perception measurement quantities used by the inference samples; the processing level of the perception measurement quantities used by the inference samples; the perception service of the perception measurement quantities used by the inference samples; the use of the perception measurement quantities used by the inference samples; the performance indicators of the perception measurement quantities used by the inference samples; the quantity of the perception measurement quantities used by the inference samples; the proportion of the perception measurement quantities used by the inference samples; whether the quantity of the perception measurement quantities used by the inference samples meets a minimum quantity threshold; whether the proportion of the perception measurement quantities used by the inference samples meets a minimum proportion threshold; the proportion of the perception measurement quantities that meet the timeliness among the perception measurement quantities used by the inference samples; the quantity of the perception measurement quantities that meet the timeliness among the perception measurement quantities used by the inference samples; configuration information of a target signal; where the target signal is the target signal corresponding to the perception measurement quantities used by the inference samples.

[0155] In a fourteenth aspect, a readable storage medium is provided. A program or instructions are stored on the readable storage medium, and when the program or instructions are executed by a processor, the steps of the method described in the first aspect, or the steps of the method described in the second aspect, or the steps of the method described in the third aspect, or the steps of the method described in the fourth aspect are implemented.

[0156] In a fifteenth aspect, a wireless communication system is provided, including: a first device and a second device. The first device can be used to execute the steps of the method described in the first aspect, and the second device can be used to execute the steps of the method described in the second aspect.

[0157] In a sixteenth aspect, a chip is provided, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is configured to run programs or instructions to implement the method described in the first aspect, or to implement the method described in the second aspect, or to implement the steps of the method described in the third aspect, or to implement the steps of the method described in the fourth aspect.

[0158] In a seventeenth aspect, a computer program / program product is provided. The computer program / program product is stored in a storage medium and is executed by at least one processor to implement the steps of the method described in the first aspect, or to implement the method described in the second aspect, or to implement the steps of the method described in the third aspect, or to implement the steps of the method described in the fourth aspect.

[0159] In an embodiment of the present application, a first device obtains an inference sample, which is determined based on communication measurement-related data and perception measurement-related data; the first device inputs the inference sample into an AI unit to obtain an inference result. In this way, the inference sample includes multi-dimensional data of communication measurement-related data and perception measurement-related data, expanding the data information for model inference and capable of improving the inference accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0160] Figure 1 is a block diagram of a wireless communication system provided by an embodiment of the present application;

[0161] Figure 2 is a schematic diagram of different perception modes of communication and perception integration;

[0162] Figure 3 is a flowchart of a model inference method provided by an embodiment of the present application;

[0163] Figure 4 is a flowchart of a model inference method provided by an embodiment of the present application;

[0164] Figure 5 is a flowchart of a model inference method provided by an embodiment of the present application;

[0165] Figure 6 is a flowchart of a model inference method provided by an embodiment of the present application;

[0166] Figure 7 is a flowchart of Embodiment 1 provided by an embodiment of the present application;

[0167] Figures 8 to 10 is an example diagram of possible situations of using perception measurement quantities in a sample;

[0168] Figure 11It is the flowchart of Embodiment 2 provided by the embodiments of the present application;

[0169] Figure 12 It is the flowchart of Embodiment 3 provided by the embodiments of the present application;

[0170] Figure 13 It is the flowchart of Embodiment 4 provided by the embodiments of the present application;

[0171] Figure 14 It is the flowchart of Embodiment 5 provided by the embodiments of the present application;

[0172] Figure 15 It is the flowchart of Embodiment 6 provided by the embodiments of the present application;

[0173] Figure 16 It is the flowchart of Embodiment 7 provided by the embodiments of the present application;

[0174] Figures 17 to 18 It is the corresponding example diagram of Embodiment 7;

[0175] Figure 19 It is the flowchart of Embodiment 8 provided by the embodiments of the present application;

[0176] Figure 20 It is the flowchart of Embodiment 9 provided by the embodiments of the present application;

[0177] Figure 21 It is the structural diagram of a model inference device provided by the embodiments of the present application;

[0178] Figure 22 It is the structural diagram of a model inference device provided by the embodiments of the present application;

[0179] Figure 23 It is the structural diagram of a model inference device provided by the embodiments of the present application;

[0180] Figure 24 It is the structural diagram of a model inference device provided by the embodiments of the present application;

[0181] Figure 25 It is the structural diagram of a communication device provided by the embodiments of the present application;

[0182] Figure 26 It is the schematic diagram of the hardware structure of a terminal provided by the embodiments of the present application;

[0183] Figure 27 It is the schematic diagram of the hardware structure of a network-side device provided by the embodiments of the present application;

[0184] Figure 28 It is the schematic diagram of the hardware structure of another network-side device provided by the embodiments of the present application. Detailed implementation manners

[0185] The technical solutions in the embodiments of the present application will be clearly described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application belong to the scope of protection of the present application.

[0186] The terms "first", "second", etc. in the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein. The objects distinguished by "first" and "second" are usually of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "or" in the present application means at least one of the connected objects. For example, "A or B" covers three scenarios, namely, Scenario 1: including A and not including B; Scenario 2: including B and not including A; Scenario 3: including both A and B. The character " / " generally indicates an "or" relationship between the associated objects before and after.

[0187] The term "indication" in the present application can be either a direct indication (or an explicit indication) or an indirect indication (or an implicit indication, a hidden indication). Among them, a direct indication can be understood as that the sender clearly informs the recipient of specific information, operations to be performed, or request results, etc. in the sent indication; an indirect indication can be understood as that the recipient determines the corresponding information according to the indication sent by the sender, or makes a judgment and determines the operations to be performed or request results, etc. according to the judgment result.

[0188] It should be noted that the technology described in the embodiments of this application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, and can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in the embodiments of this application are often used interchangeably, and the described technology can be used in the systems and radio technologies mentioned above, as well as in other systems and radio technologies. The following description describes the New Radio (NR) system for example purposes, and the NR term is used in most of the following descriptions, but these technologies can also be applied to systems other than the NR system, such as the 6th Generation (6 th Generation, 6G) communication system.

[0189] Figure 1A block diagram of a wireless communication system to which embodiments of the present application can be applied is shown. The wireless communication system includes a terminal 11 and a network-side device 12. Among them, the terminal 11 can be a mobile phone, a tablet personal computer, a laptop computer, a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device, a flight vehicle, a vehicle user equipment (VUE), a shipborne device, a pedestrian user equipment (PUE), a smart home (home devices with wireless communication functions, such as refrigerators, TVs, washing machines, or furniture, etc.), a game console, a personal computer (PC), a teller machine, or a self-service machine, etc., which are terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart earphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart ankle chains, etc.), smart wristbands, smart clothing, etc. Among them, vehicle user equipment can also be referred to as vehicle terminals, vehicle controllers, vehicle modules, vehicle components, vehicle chips, or vehicle units, etc. In addition to the above terminal devices, it can also be a chip inside the terminal, such as a modem chip or a system on chip (SoC). It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. Among them, the access network device can also be referred to as a radio access network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a wireless local area network (WLAN) access point (AP), or a wireless fidelity (WiFi) node, etc.Among them, the base station may be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay BaseStation (RBS), Serving Base Station (SBS), Base TransceiverStation (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), home Node B (HNB), home evolved Node B, Transmission Reception Point (TRP), or some other suitable term in the art. 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 the embodiments of this application, the base station in the NR system is mainly taken as an example for introduction, and the specific type of the base station is not limited.

[0190] The core network device may include but is not limited to at least one of the following: core network node, core network function, 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 unit (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC),

[0191] Location Management Function (LMF), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (L-NEF), Binding Support Function (BSF), Application Function (AF), etc. It should be noted that in the embodiments of this application, the core network devices in the NR system are mainly used as examples for introduction, and the specific types of core network devices are not limited.

[0192] The following first gives a brief introduction to the related technologies.

[0193] Related Technology 1: AI Technology and Communication Technology

[0194] 1) AI-based Beam Prediction

[0195] In millimeter-wave wireless communication, both communication transceiver ends, such as base stations and User Equipment (UE, also known as terminals), are configured with multiple analog beams. For the same UE, when measuring different transmit analog beams and receive analog beams, the measured channel quality varies. How to quickly and accurately find the transceiver beam group with the highest channel quality from all possible transceiver analog beam combinations is the key to affecting the transmission quality. After introducing the AI neural network model, the terminal can effectively predict the transmit analog beam with the highest channel quality based on historical channel quality information and report it to the network side.

[0196] In 5G, beam prediction mainly uses beam quality information obtained based on CSI measurement, measurement resource identification, or beam identification information, etc. as model inputs. In the AI-based beam prediction use cases discussed in 5G, the model inputs include beam quality obtained based on CSI measurement, beam identification / CSI resource identification, or measurement timestamp, and the inference output of the AI unit is the strongest beam identification or the beam quality of each beam.

[0197] 2) AI-based CSI Prediction

[0198] In the AI-based CSI prediction use cases discussed in 5G, the model inputs include the historical channel matrix obtained based on CSI measurement, Precoding matrix indicator (PMI), channel eigenvector / eigenvalue, or measurement timestamp; the inference output of the AI unit is the predicted channel matrix, PMI, or channel eigenvector / eigenvalue.

[0199] 3) AI - based positioning

[0200] The AI - based positioning use cases discussed in 5G, where the model inputs include time - domain channel - based and positioning reference signal measurement results; the inference output of the AI unit is the predicted distance relative to the base station or the time of arrival (TOA).

[0201] Related Technology 2: Communication - sensing integration

[0202] Mobile communication systems such as B5G systems or 6G systems will not only have communication capabilities but also sensing capabilities. The sensing capability means that one or more devices with sensing capabilities can sense information such as the orientation, distance, or speed of a target object through the transmission and reception of wireless signals, or detect, track, identify, or image a target object, event, or environment, etc. With the deployment of small base stations with high - frequency - band large - bandwidth capabilities such as millimeter - wave and terahertz in 6G networks, the sensing resolution will be significantly improved compared to centimeter - wave, enabling the 6G network to provide more refined sensing services. Typical sensing functions and application scenarios are shown in Table 1.

[0203] Table 1

[0204]

[0205] Communication - sensing integration (abbreviated as communication - perception integration) means that in the same system, through spectrum sharing and hardware sharing, the integrated design of communication and sensing functions is realized. While the system is transmitting information, it can sense information such as orientation, distance, and speed, detect, track, and identify target devices or events. The communication system and the sensing system complement each other, achieving an improvement in overall performance and bringing a better service experience.

[0206] The integration of communication and radar belongs to typical communication sensing integration (communication sensing fusion) applications. In the past, radar systems and communication systems were strictly separated due to different research objects and focuses, and the two systems were studied independently in most scenarios. In fact, both radar and communication systems are typical ways of information transmission, acquisition, processing, and exchange, and there are many similarities in terms of working principles, system architectures, and frequency bands. The design of communication and radar integration has great feasibility, which is mainly reflected in the following aspects: First, both communication systems and sensing systems are based on electromagnetic wave theory and use the transmission and reception of electromagnetic waves to complete information acquisition and transmission; Second, both communication systems and sensing systems have structures such as antennas, transmitters, receivers, and signal processors, and there is a large overlap in hardware resources; With the development of technology, there is also an increasing overlap in their working frequency bands; In addition, there are similarities in key technologies such as signal modulation, reception detection, and waveform design. The integration of communication and radar systems can bring many advantages, such as cost savings, size reduction, power consumption reduction, spectrum efficiency improvement, mutual interference reduction, etc., thereby improving the overall performance of the system.

[0207] According to the different sending and receiving nodes of the sensing signal, it can be divided into 6 basic sensing modes. As Figure 2 shown, specifically including:

[0208] (1) Base station echo sensing. In this sensing mode, base station A sends a sensing signal and performs sensing measurement by receiving the echo of the sensing signal.

[0209] (2) Air interface sensing between base stations. In this sensing mode, base station B receives the sensing signal sent by base station A and performs sensing measurement.

[0210] (3) Uplink air interface sensing. In this sensing mode, base station A receives the sensing signal sent by terminal A and performs sensing measurement.

[0211] (4) Downlink air interface sensing. In this sensing mode, terminal B receives the sensing signal sent by base station B and performs sensing measurement.

[0212] (5) Terminal echo sensing. In this sensing mode, terminal A sends a sensing signal and performs sensing measurement by receiving the echo of the sensing signal.

[0213] (6) Sidelink sensing between terminals. In this sensing mode, terminal B receives the sensing signal sent by terminal A and performs sensing measurement.

[0214] It should be noted that Figure 2Each sensing mode is exemplified by a sensing signal transmitting node and a sensing signal receiving node. In an actual system, according to different sensing use cases and sensing requirements, one or more different sensing modes can be selected, and there can be one or more transmitting nodes and receiving nodes for each sensing mode. Figure 2 The sensing targets in it take people and vehicles as examples, and it is assumed that neither people nor vehicles carry or install signal transceiver devices. The sensing targets in the actual scenario will be more diverse.

[0215] The following introduces three ways to obtain sensing results:

[0216] Obtain sensing results by A transmitting and B receiving:

[0217] Node A sends a sensing reference signal (or called a sensing measurement signal), node B receives the sensing reference signal, and node B obtains the sensing measurement quantity / sensing result. Among them, node A can be base station 1, node B can be the target UE, or a UE near the target UE, or base station 2.

[0218] Obtain sensing results by self-transmitting and self-receiving:

[0219] Node A sends a sensing reference signal, node A receives the sensing reference signal, and node A obtains the sensing measurement quantity / sensing result. Among them, node A can be the target UE, or a UE near the target UE, or the serving base station of the target UE, or other base stations.

[0220] Obtain sensing results through sensors:

[0221] The network node obtains the sensing measurement quantity / sensing result through the sensor-type sensing devices deployed by itself or in the environment.

[0222] It should be noted that, without special instructions, the sensing measurement quantity, sensing measurement result, etc. can all be understood as the sensing result.

[0223] Sensor-based sensing is a sensing method that performs sensing services through means other than the communication and sensing integrated system. Typical devices include lidar, millimeter-wave radar, vision sensors (such as monocular vision sensors, binocular vision sensors, infrared sensors, etc.), inertial measurement units (IMUs), and various other sensors (such as rain gauges, thermometers, hygrometers, etc.).

[0224] In 6G, the network can obtain perception results through sensors or perception measurement signals. If the perception results can be used as auxiliary inputs to the model, the inference accuracy of the AI model (see Explanation 1 later) can be further improved. However, in Related Technology 1, in the physical layer AI use cases currently discussed in 5G, the data used for model inference does not involve the acquisition of perception information and how to utilize perception information. Related Technology 2 is a commonly used method for obtaining perception measurement quantities / perception results and does not involve how to use them as inference data for the AI model to improve the inference accuracy of the AI model. Currently, there is no mature solution for using perception results and communication measurement results as input data for model inference. In view of this, the embodiments of this application propose a perception-assisted model inference scheme, enabling network nodes, such as terminals, base stations, core network functions, etc., to obtain perception information as auxiliary information for the AI model for model inference, thereby improving the inference accuracy of the AI model.

[0225] The embodiments of this application involve the interaction of multiple communication devices, and each communication device can be represented by various network nodes. The functions corresponding to each communication device and the network nodes representing each communication device can be seen in Table 2.

[0226] Table 2

[0227]

[0228] In the embodiments of this application, the target signal refers to a dedicated signal used for perception, such as a CSI reference signal (CSI-RS), a CSI-RS for tracking (TRS), a sounding reference signal (SRS), or a synchronization signal. The target signal can be referred to as a perception reference signal or a perception measurement signal.

[0229] Next, in conjunction with the accompanying drawings, the model inference method provided by the embodiments of this application will be described in detail.

[0230] Figure 3 The flowchart of a model inference method provided by the embodiments of this application is shown. As Figure 3 shown, the model inference method includes the following steps:

[0231] Step 301: The first device obtains an inference sample, which is determined based on communication measurement-related data and perception measurement-related data;

[0232] Step 302: The first device inputs the inference sample into the AI unit to obtain an inference result.

[0233] Communication measurement related data: Data related to communication measurement. For example, the communication measurement related data includes one of the following: CSI measurement quantity (or CSI measurement result), CSI measurement resource identifier, reference signal received power (RSRP) of a beam, reference signal received quality (RSRQ) of a beam, signal-to-noise and interference ratio (SINR) of a beam, RSRP of a cell channel, RSRQ of a cell channel, SINR of a cell channel, received signal strength indication (RSSI) of a cell channel, impulse response of a cell channel, precoding matrix indicator (PMI), rank indicator (RI), channel quality indicator (CQI), beam identifier, subband identifier.

[0234] Sensing measurement related data: Data related to sensing measurement. For example, it includes data such as sensing measurement configuration, sensing results (such as sensing measurement quantity), sensing performance, and sensing characteristic description information.

[0235] The first device can obtain communication measurement related data through communication measurements (such as CSI measurement, radio resource management (RRM) measurement).

[0236] There are many ways for the first device to obtain sensing measurement related data. It can be achieved by the first device performing sensing measurements, or obtained from other devices. For specific details, refer to the various embodiments provided later.

[0237] The first device obtains an inference sample. It can be understood that the first device synchronizes samples of communication measurement related data and sensing measurement related data to determine whether to combine the communication measurement related data and sensing measurement related data as an inference sample. For example, the first device synchronizes samples based on the communication measurement related data to determine the sensing measurement related data that can belong to the same inference sample as the communication measurement related data.

[0238] The inference samples obtained by the first device may include communication measurement-related data and perception measurement-related data, or may only include communication measurement-related data. The inference samples are the model input data in the model inference process, that is, the model input data may include communication measurement-related data or perception measurement-related data. The embodiments of the present application do not limit this.

[0239] In the embodiments of the present application, through sample synchronization, it is possible to make each obtained inference sample include communication measurement-related data and perception measurement-related data as much as possible, so that each inference sample has multi-dimensional data such as communication and perception as much as possible, which is beneficial to expanding the model inference data and thus beneficial to improving the model inference accuracy.

[0240] In the embodiments of the present application, the first device obtains inference samples, and the inference samples are determined based on communication measurement-related data and perception measurement-related data; the first device inputs the inference samples into the AI unit to obtain an inference result. In this way, the inference samples include multi-dimensional data of communication measurement-related data and perception measurement-related data, expanding the data information for model inference and being able to improve the model inference accuracy.

[0241] Optionally, the perception measurement-related data includes at least one of the following information:

[0242] Perception measurement quantity;

[0243] Indicator of perception measurement quantity;

[0244] Timestamp of perception measurement quantity;

[0245] Information of the sending device of perception measurement quantity;

[0246] Information of the receiving device of perception measurement quantity;

[0247] Coordinate information of perception measurement quantity;

[0248] Information indicating the performance index of perception measurement quantity;

[0249] Information indicating the source of perception measurement quantity;

[0250] Information indicating the type of perception measurement quantity;

[0251] Information indicating the perception mode of perception measurement quantity;

[0252] Configuration information of the target signal;

[0253] Information of the sending device of the target signal;

[0254] Information of the receiving device of the target signal;

[0255] Among them, the target signal is a signal used for sensing.

[0256] In the embodiments of the present application, the types of sensed measurement quantities can be referred to in Explanation 2 below, and the configuration information of the target signal can be referred to in Explanation 3 below.

[0257] The timestamp of the sensed measurement quantity can refer to the measurement timestamp of the sensed measurement quantity or the reception timestamp of the sensed measurement quantity, and its meaning can be flexibly determined according to specific circumstances.

[0258] In some embodiments, the method further includes:

[0259] The first device sends a first request to the second device, and the first request is used to request the sensed measurement-related data required for model inference.

[0260] For example, when the first device is a terminal, it can send a first request to its serving base station. The first request can reflect the first device's need for the sensed information required for model inference data, which is beneficial for the first device to obtain the model inference data that meets the requirements, and thus is beneficial to improving the model inference effect.

[0261] Optionally, the first request includes at least one of the following information:

[0262] Information indicating that the model is in the inference stage;

[0263] A dataset identifier, and the dataset corresponding to the dataset identifier includes sensed measurement-related data;

[0264] The configuration identifier of the sensed measurement quantity;

[0265] The identifier of the sensed measurement quantity;

[0266] Information indicating the sensing characteristics of the target dataset;

[0267] The identifier of the target dataset;

[0268] The configuration information of the sensed measurement quantity required for model inference;

[0269] Information indicating the number threshold of the sensed measurement quantity required for model inference;

[0270] Information indicating the source of the sensed measurement quantity required for model inference;

[0271] Information indicating the type of the sensed measurement quantity required for model inference;

[0272] Information indicating the sensing mode of the sensed measurement quantity required for model inference;

[0273] Information indicating the sensing requirement;

[0274] Configuration information of the target signal;

[0275] Information of the sending device of the target signal;

[0276] Information of the receiving device of the target signal;

[0277] Wherein, the target data set is the data set used by the AI unit in the training phase;

[0278] The target signal is a signal used for perception.

[0279] Each of the above identifiers can be a predefined identifier.

[0280] Each of the above instructions can be either an implicit instruction or an explicit instruction, and the embodiments of the present application do not limit this.

[0281] It should be noted that the above information for indicating the perception characteristics of the target data set, as well as the identifier of the target data set, can both reflect the perception characteristics used by the target AI model in the training phase, thereby facilitating the first device to obtain model inference data that is relatively consistent with the perception characteristics in the training phase, which is beneficial to improving the model inference accuracy.

[0282] In some embodiments, the first device obtains inference samples, including at least one of the following:

[0283] The first device obtains inference samples based on the timestamp of the communication measurement quantity, the timestamp of the perception measurement quantity, and the effective duration of the perception measurement quantity;

[0284] The first device obtains inference samples based on the timestamp corresponding to the prediction result of the target AI model, the timestamp of the perception measurement quantity, and the effective duration of the perception measurement quantity;

[0285] The first device obtains inference samples based on the first indication and the timestamp of the communication measurement quantity;

[0286] The first device obtains inference samples based on the first indication and the timestamp corresponding to the prediction result of the target AI model;

[0287] The first device obtains inference samples based on whether the second indication is received;

[0288] Wherein, the first indication is used to indicate the expiration time or the expiration time difference of the perception measurement quantity;

[0289] The second indication is used to indicate the expiration of the perception measurement quantity.

[0290] In this embodiment, the first device determines whether to synchronize the sensing result and the communication measurement result into an inference sample based on the invalid time of the sensing result. In this way, it can be ensured that the sensing measurement-related data in the inference sample is up-to-date data, which can improve the reliability of the inference sample and thus improve the model inference effect.

[0291] Optionally, it includes at least one of the following:

[0292] When the time corresponding to the timestamp of the communication measurement quantity is earlier than the first time, the first device obtains an inference sample including communication measurement-related data and sensing measurement-related data;

[0293] When the time corresponding to the timestamp of the prediction result of the target AI model is earlier than the first time, the first device obtains an inference sample including communication measurement-related data and sensing measurement-related data;

[0294] When the time corresponding to the timestamp of the communication measurement quantity is earlier than the second time, the first device obtains an inference sample including communication measurement-related data and sensing measurement-related data;

[0295] When the time corresponding to the timestamp of the prediction result of the target AI model is earlier than the second time, the first device obtains an inference sample including communication measurement-related data and sensing measurement-related data;

[0296] When the first device does not receive the second indication, the first device obtains an inference sample including communication measurement-related data and sensing measurement-related data;

[0297] Wherein, the first time is the time corresponding to the timestamp of the sensing measurement quantity plus the effective duration of the sensing measurement quantity;

[0298] The second time is the invalid time of the sensing measurement quantity determined based on the first indication.

[0299] For details, please refer to the embodiments provided later.

[0300] Optionally, the determination method of the effective duration of the sensing measurement quantity includes at least one of the following:

[0301] When a first effective duration is pre-configured or defined, the effective duration of the sensing measurement quantity is the first effective duration;

[0302] When a second effective duration is pre-configured or defined and the target signal carries a time adjustment value, the effective duration of the sensing measurement quantity is determined according to the second effective duration and the time adjustment value;

[0303] When the target signal carries a third effective duration, the effective duration of the perception measurement quantity is the third effective duration;

[0304] wherein, the target signal is a signal used for perception.

[0305] For specific details, reference can be made to the embodiments provided later.

[0306] In some embodiments, the first device obtains an inference sample, including:

[0307] The first device receives first information from a third device, where the first information includes at least one of communication measurement related data and perception measurement related data;

[0308] The first device obtains an inference sample based on the first information; or, the first device obtains an inference sample based on the first information and stored historical data;

[0309] wherein, the historical data includes at least one of communication measurement related data and perception measurement related data.

[0310] This embodiment lies in that the first device obtains an inference sample based on the first information (or the first information and historical data) sent by the third device.

[0311] When the first information only includes communication measurement related data, the first device can obtain an inference sample according to the first information and historical perception measurement related data. Correspondingly, when the first information only includes perception measurement related data, the first device can obtain an inference sample according to the first information and historical communication measurement related data. When the first information includes both communication measurement related data and perception measurement related data, if the communication measurement related data and perception measurement related data therein are data with sample synchronization performed by the third device, the first device can directly use the communication measurement related data and perception measurement related data therein as an inference sample; if the communication measurement related data and perception measurement related data therein are data without sample synchronization performed by the third device, the first device can perform sample synchronization on the communication measurement related data and perception measurement related data therein to obtain an inference sample.

[0312] Optionally, the first information includes at least one of the following:

[0313] A dataset identifier, where the dataset corresponding to the dataset identifier includes perception measurement related data;

[0314] A configuration identifier of the perception measurement quantity;

[0315] An identifier of the perception measurement quantity;

[0316] An identifier of the perception measurement link;

[0317] Identifier of the sensing service

[0318] Identifier of the sensing service type

[0319] Sensing measurement quantity

[0320] Timestamp of the sensing measurement quantity

[0321] Information of the sending device of the sensing measurement quantity

[0322] Coordinate information of the sensing measurement quantity

[0323] Information for indicating the performance index of the sensing measurement quantity

[0324] Information for indicating the source of the sensing measurement quantity

[0325] Information for indicating the type of the sensing measurement quantity

[0326] Information for indicating the use of the sensing measurement quantity

[0327] Information for indicating the sensing mode of the sensing measurement quantity

[0328] Communication measurement quantity

[0329] Communication measurement resource identifier

[0330] Timestamp of the communication measurement quantity

[0331] Information for indicating the first time window

[0332] Information for indicating the first valid time

[0333] Configuration identifier of the target signal

[0334] Configuration information of the target signal

[0335] Information of the sending device of the target signal

[0336] Information of the receiving device of the target signal

[0337] Wherein, the target signal is a signal used for sensing.

[0338] This embodiment may include the following four optional cases:

[0339] Case 1: The first information includes the sensing measurement quantity, the timestamp of the sensing measurement quantity, the communication measurement quantity, and the timestamp of the communication measurement quantity;

[0340] Based on the first information, the first device obtains an inference sample, including at least one of the following:

[0341] When the time difference between the timestamp of the sensed measurement quantity and the timestamp of the communication measurement quantity is less than or equal to the first time window indicated by the first information, the first device obtains an inference sample including communication measurement-related data and sensed measurement-related data;

[0342] When the time difference between the timestamp of the sensed measurement quantity and the timestamp of the communication measurement quantity is less than or equal to a predefined second time window, the first device obtains an inference sample including communication measurement-related data and sensed measurement-related data.

[0343] In this case, the first information includes communication measurement-related data and sensed measurement-related data, and the third device does not perform sample synchronization. The first device performs sample synchronization based on the first information to obtain an inference sample.

[0344] For details, please refer to the embodiments provided later.

[0345] Case 2: The first information includes the target sensed measurement quantity and the timestamp of the target sensed measurement quantity;

[0346] The first device obtains an inference sample based on the first information and the stored historical data, including:

[0347] The first device obtains an inference sample including the target communication measurement quantity and the target sensed measurement quantity;

[0348] Wherein, the target communication measurement quantity includes at least one of the following:

[0349] The communication measurement quantity whose difference between the timestamp of the historical data and the timestamp of the target sensed measurement quantity is less than or equal to the first time window indicated by the first information;

[0350] The communication measurement quantity whose difference between the timestamp of the historical data and the timestamp of the target sensed measurement quantity is less than or equal to a predefined second time window.

[0351] It should be noted that in this case, the inference sample obtained by the first device including the target communication measurement quantity and the target sensed measurement quantity does not limit that there is only a measurement quantity in the inference sample, and may also include other communication measurement-related data and other sensed measurement-related data.

[0352] It should be noted that in this case, the first information includes the target perception measurement quantity and the time stamp of the target perception measurement quantity, which can be understood as follows: The first information can only include perception measurement-related data (for example, the first information only includes the target perception measurement quantity and the time stamp of the target perception measurement quantity), or the first information includes both perception measurement-related data and communication measurement-related data (for example, in addition to the target perception measurement quantity and the time stamp of the target perception measurement quantity, the first information further includes one or more communication measurement quantities (and the time stamps of the communication measurement quantities)).

[0353] In this case, the third device does not perform sample synchronization, and the first device performs sample synchronization based on the first information and historical data to obtain an inference sample.

[0354] For details, reference can be made to the embodiments provided later.

[0355] Case 3: The first information includes the target communication measurement quantity and the time stamp of the target communication measurement quantity;

[0356] The first device obtains an inference sample based on the first information and the stored historical data, including:

[0357] The first device obtains an inference sample including the target communication measurement quantity and the target perception measurement quantity;

[0358] Wherein, the target perception measurement quantity includes at least one of the following:

[0359] The time difference between the time stamp of the historical data and the time stamp of the target communication measurement quantity is less than or equal to the perception measurement quantity of the first time window indicated by the first information;

[0360] The time stamp of the historical data is less than or equal to the perception measurement quantity of the first effective time indicated by the first information;

[0361] The time stamp of the historical data is less than or equal to the perception measurement quantity of the predefined second effective time.

[0362] It should be noted that in this case, the first information includes the target communication measurement quantity and the time stamp of the target communication measurement quantity, which can be understood as follows: The first information can only include communication measurement-related data (for example, the first information only includes the target communication measurement quantity and the time stamp of the target communication measurement quantity), or the first information includes both perception measurement-related data and communication measurement-related data (for example, in addition to the target communication measurement quantity and the time stamp of the target communication measurement quantity, the first information further includes one or more perception measurement quantities (and the time stamps of the perception measurement quantities)).

[0363] In this case, the third device does not perform sample synchronization, and the first device performs sample synchronization based on the first information and historical data to obtain inference samples.

[0364] For details, refer to the embodiments provided later.

[0365] Case 4: The first device obtains inference samples based on the first information, including at least one of the following:

[0366] The first device obtains inference samples including target communication measurement quantities and target perception measurement quantities;

[0367] Wherein, the first information includes the target communication measurement quantity and the target communication measurement quantity; or,

[0368] The first information includes the target communication measurement quantity and a third indication, and the target perception measurement quantity is the perception measurement quantity corresponding to the third indication; or,

[0369] The first information includes the target communication measurement quantity, and the target perception measurement quantity is the perception measurement quantity of the most recent inference sample.

[0370] Optionally, the third indication includes at least one of the following:

[0371] The identifier of the inference sample;

[0372] The identifier of the resource used for the communication measurement result;

[0373] The reporting identifier of the communication measurement result;

[0374] The identifier of the resource used for the perception measurement quantity;

[0375] The reporting identifier of the perception measurement quantity;

[0376] The identifier of the perception measurement quantity.

[0377] It should be noted that in this case, the inference samples obtained by the first device, which include target communication measurement quantities and target perception measurement quantities, do not limit that there are only measurement quantities in the inference samples, and may also include other communication measurement-related data and other perception measurement-related data.

[0378] In this case, the first information includes at least communication measurement-related data, and the third device has performed sample synchronization. The first device obtains synchronized data based on the first information (or the first information and historical data) to obtain inference samples.

[0379] For details, refer to the embodiments provided later.

[0380] It should be noted that the perception measurement quantity (or communication measurement quantity) in each of the above cases is an arbitrary perception measurement quantity (or communication measurement quantity), not a specific perception measurement quantity (or communication measurement quantity).

[0381] In some embodiments, the method further includes:

[0382] The first device sends second information to the fourth device, where the second information includes the inference result of the AI unit and a fourth indication;

[0383] Wherein, the fourth indication is used to indicate at least one of the following:

[0384] A dataset identifier, where the dataset corresponding to the dataset identifier includes perception measurement-related data;

[0385] A configuration identifier of the perception measurement quantity;

[0386] An identifier of the perception measurement quantity;

[0387] An identifier of the perception measurement link;

[0388] An identifier of the perception service;

[0389] An identifier of the perception service type;

[0390] Whether the inference sample uses the perception measurement quantity;

[0391] The perception measurement quantity used by the inference sample;

[0392] The timeliness of the perception measurement quantity used by the inference sample;

[0393] The sending device of the perception measurement quantity used by the inference sample;

[0394] The receiving device of the perception measurement quantity used by the inference sample;

[0395] The coordinates of the perception measurement quantity used by the inference sample;

[0396] The source of the perception measurement quantity used by the inference sample;

[0397] The perception mode of the perception measurement quantity used by the inference sample;

[0398] The processing level of the perception measurement quantity used by the inference sample;

[0399] The perception service of the perception measurement quantity used by the inference sample;

[0400] The use of the perception measurement quantity used by the inference sample;

[0401] Performance indicators of the perception measurement quantities used in the inference samples;

[0402] The number of perception measurement quantities used in the inference samples;

[0403] The proportion of the perception measurement quantities used in the inference samples;

[0404] Whether the number of the perception measurement quantities used in the inference samples meets the minimum quantity threshold;

[0405] Whether the proportion of the perception measurement quantities used in the inference samples meets the minimum proportion threshold;

[0406] The proportion of the perception measurement quantities used in the inference samples that meet timeliness requirements;

[0407] The number of the perception measurement quantities used in the inference samples that meet timeliness requirements;

[0408] Configuration information of the target signal;

[0409] Wherein, the target signal is the target signal corresponding to the perception measurement quantities used in the inference samples.

[0410] In this embodiment, the first device may also send the inference result of the AI unit to the fourth device. When sending the inference result to the fourth device, the first device may also carry a fourth indication for indicating the perception characteristics of the inference sample, so that the fourth device can obtain the perception characteristics of the inference sample through the fourth indication.

[0411] The above items included in the fourth indication reflect the perception characteristics of the inference sample from two perspectives: the usage of perception measurement quantities and the perception configuration situation.

[0412] It should be noted that the perception characteristics of the inference sample can be used to assist in analyzing the model inference result, which is beneficial to the monitoring or subsequent optimization of model inference.

[0413] The above is the embodiment of the first device side of the present application. The embodiments of the second device side, the third device side, and the fourth device side of the present application will be described below respectively.

[0414] Figure 4 Shows a flowchart of a model inference method provided by an embodiment of the present application. As Figure 4 shown, the model inference method includes the following steps:

[0415] Step 401: The second device receives a first request from the first device, and the first request is used to request perception measurement-related data required for model inference;

[0416] Step 402: The second device performs a first operation, where the first operation includes any one of the following:

[0417] The second device sends a target signal based on the first request;

[0418] The second device determines configuration information of the target signal based on the first request;

[0419] The second device sends the configuration information of the target signal based on the first request;

[0420] The second device sends perception measurement-related data based on the first request;

[0421] Wherein, the target signal is a signal used for perception.

[0422] In the embodiments of the present application, in addition to representing a data request receiving device, the second device can also represent a target signal sending device, that is, the second device and the fifth device can be co-located in the same network node.

[0423] Specifically, when the first operation includes sending a target signal, the second device and the fifth device are co-located; when the first operation includes sending configuration information of the target signal, the device receiving the configuration information of the target signal can be used as the fifth device.

[0424] When the first operation includes sending a target signal, the receiver of the target signal is not unique. For example, the second device can send and receive the target signal by itself, the second device can send the target signal to the first device, the second device can also send the target signal to the neighboring cell base station, the second device can also send the target signal to the UE near the first device, and the second device can also send the target signal to the sixth device.

[0425] Correspondingly, when the first operation includes sending configuration information of the target signal, the receiver of the configuration information of the target signal is not unique either.

[0426] In some embodiments, when the first operation includes sending perception measurement-related data, the second device represents both the second device and the third device (i.e., the perception result sending device), that is, the second device and the third device are co-located in the same network node. The second device sends perception measurement-related data based on the first request, which can be that the second device directly sends perception measurement-related data to the first device based on the first request.

[0427] Optionally, the first request includes at least one of the following information:

[0428] Information for indicating that the AI unit is in the inference stage;

[0429] A dataset identifier, where the dataset corresponding to the dataset identifier includes perception measurement-related data;

[0430] A configuration identifier of a perception measurement quantity;

[0431] An identifier of a perception measurement quantity;

[0432] Information for indicating the perception characteristics of a target dataset;

[0433] An identifier of a target dataset;

[0434] Configuration information of perception measurement quantities required for model inference;

[0435] Information for indicating a count threshold of perception measurement quantities required for model inference;

[0436] Information for indicating the source of perception measurement quantities required for model inference;

[0437] Information for indicating the types of perception measurement quantities required for model inference;

[0438] Information for indicating the perception mode of perception measurement quantities required for model inference;

[0439] Information for indicating a perception requirement;

[0440] Configuration information of a target signal;

[0441] Information about the sending device of the target signal;

[0442] Information about the receiving device of the target signal;

[0443] Wherein, the target dataset is the dataset used by the AI unit in the training phase;

[0444] The target signal is a signal used for perception.

[0445] For the relevant descriptions of the embodiments of this application, reference can be made to Figure 3 the relevant descriptions of the method embodiments, and the same technical effects can be achieved. To avoid repetition, they will not be elaborated here.

[0446] Figure 5 The flowchart of a model inference method provided by the embodiments of this application is shown. As Figure 5 shown, the model inference method includes the following steps:

[0447] Step 501: A third device sends first information to a first device, where the first information includes at least one of communication measurement-related data and perception measurement-related data.

[0448] In the embodiments of this application, the third device may or may not perform sample synchronization.

[0449] For the case where the third device does not perform sample synchronization, the first information may include at least one of the following:

[0450] A dataset identifier, where the dataset corresponding to the dataset identifier includes perception measurement-related data;

[0451] A configuration identifier of the perception measurement quantity;

[0452] An identifier of the perception measurement quantity;

[0453] An identifier of the perception measurement link;

[0454] An identifier of the perception service;

[0455] An identifier of the perception service type;

[0456] The perception measurement quantity;

[0457] The timestamp of the perception measurement quantity;

[0458] Information about the sending device of the perception measurement quantity;

[0459] The coordinate information of the perception measurement quantity;

[0460] Information for indicating the performance index of the perception measurement quantity;

[0461] Information for indicating the source of the perception measurement quantity;

[0462] Information for indicating the type of the perception measurement quantity;

[0463] Information for indicating the use of the perception measurement quantity;

[0464] Information for indicating the perception mode of the perception measurement quantity;

[0465] The communication measurement quantity;

[0466] The communication measurement resource identifier;

[0467] The timestamp of the communication measurement quantity;

[0468] Information for indicating the first time window;

[0469] Information for indicating the first valid time;

[0470] The configuration identifier of the target signal;

[0471] The configuration information of the target signal;

[0472] Information about the sending device of the target signal;

[0473] Information about the receiving device of the target signal;

[0474] Among them, the target signal is a signal used for sensing.

[0475] For the case where the third device performs sample synchronization, the first information may include at least one of the following:

[0476] Target communication measurement quantities and target communication measurement quantities, where the target communication measurement quantities and the target communication measurement quantities are determined to belong to the same inference sample;

[0477] Target communication measurement quantity and a third indication, where the target communication measurement quantity and the sensing measurement quantity indicated by the third indication are determined to belong to the same inference sample;

[0478] Target communication measurement quantity, where the target communication measurement quantity and the sensing measurement quantity of the most recent inference sample are determined to belong to the same inference sample;

[0479] Optionally, the third indication includes at least one of the following:

[0480] Identifier of the inference sample;

[0481] Identifier of the resource used for the communication measurement result;

[0482] Reporting identifier of the communication measurement result;

[0483] Identifier of the resource used for the sensing measurement quantity;

[0484] Reporting identifier of the sensing measurement quantity;

[0485] Identifier of the sensing measurement quantity.

[0486] It should be noted that regardless of whether the third device performs sample synchronization, the third device can be referred to as a sensing result sending device. For the case where the third device performs sample synchronization, the third device may not send the communication measurement result and the sensing result simultaneously in the first information. However, since it can implicitly indicate the sensing result it has sent through the third indication, the third device has actually sent the sensing result before, that is, the third device is a sensing result sending device.

[0487] For the relevant descriptions of the embodiments of the present application, reference can be made to Figure 3 the relevant descriptions of the method embodiments, and the same technical effects can be achieved. To avoid repetition, they will not be elaborated here.

[0488] Figure 6 The flowchart of a model inference method provided by the embodiments of the present application is shown. As Figure 6 shown, the model inference method includes the following steps:

[0489] Step 601: The fourth device receives second information from the first device. The second information includes an inference result and a fourth indication, where the inference result is obtained by the AI unit using inference samples.

[0490] Among them, the fourth indication is used to indicate at least one of the following:

[0491] A dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data;

[0492] A configuration identifier of a perception measurement quantity;

[0493] An identifier of a perception measurement quantity;

[0494] An identifier of a perception measurement link;

[0495] An identifier of a perception service;

[0496] An identifier of a perception service type;

[0497] Whether the inference sample uses a perception measurement quantity;

[0498] The perception measurement quantity used by the inference sample;

[0499] The timeliness of the perception measurement quantity used by the inference sample;

[0500] The sending device of the perception measurement quantity used by the inference sample;

[0501] The receiving device of the perception measurement quantity used by the inference sample;

[0502] The coordinates of the perception measurement quantity used by the inference sample;

[0503] The source of the perception measurement quantity used by the inference sample;

[0504] The perception mode of the perception measurement quantity used by the inference sample;

[0505] The processing level of the perception measurement quantity used by the inference sample;

[0506] The perception service of the perception measurement quantity used by the inference sample;

[0507] The use of the perception measurement quantity used by the inference sample;

[0508] The performance index of the perception measurement quantity used by the inference sample;

[0509] The quantity of the perception measurement quantity used by the inference sample;

[0510] The proportion of the perception measurement quantity used by the inference sample;

[0511] Whether the number of perception measurement quantities used in the inference sample meets the minimum number threshold;

[0512] Whether the proportion of the perception measurement quantities used in the inference sample meets the minimum proportion threshold;

[0513] The proportion of the perception measurement quantities used in the inference sample that meets timeliness;

[0514] The number of the perception measurement quantities used in the inference sample that meets timeliness;

[0515] Configuration information of the target signal;

[0516] Wherein, the target signal is the target signal corresponding to the perception measurement quantity used in the inference sample.

[0517] For the relevant descriptions of the embodiments of the present application, reference can be made to Figure 3 the relevant descriptions of the method embodiments, and the same technical effects can be achieved. To avoid repetition, no further elaboration will be provided here.

[0518] Specific embodiments are provided below to exemplarily illustrate the interaction process involved in the embodiments of the present application.

[0519] Embodiment 1: The serving base station (abbreviated as the base station) sends a perception reference signal, the UE receives the perception reference signal, and the UE performs model inference

[0520] In this embodiment, the UE represents the first device and the sixth device (i.e., the first device and the sixth device are integrated in the UE), and the base station represents the second device, the fourth device, and the fifth device (i.e., the second device, the fourth device, and the fifth device are integrated in the base station).

[0521] As Figure 7 shown, the following steps are included:

[0522] 1. The base station sends a perception reference signal to the UE;

[0523] 2. The UE receives the perception reference signal sent by the base station, obtains perception measurement quantities, synchronizes the perception measurement quantities and the CSI measurement results, obtains an inference sample for model inference, and performs model inference; (Note: One inference sample is the model input data for one model inference.)

[0524] 3. The UE reports the inference result to the base station.

[0525] Before step 1, the UE sends a first request to the base station for requesting the perception measurement quantities required for model inference.

[0526] The first request can reflect the needs of the UE. It can implicitly or explicitly reflect the needs of the UE. The first request may include at least one of the following:

[0527] AI lifecycle management process indication, for example: indicating that the model is in the inference stage;

[0528] Dataset identifier, which can implicitly indicate, for example: the configuration of a certain sensing reference signal or sensing measurement used in the previous training process, the reporting configuration of the sensing measurement used in the previous training process; (implicit indication)

[0529] Identifier of a predefined sensing measurement, which can implicitly indicate what kind of sensing measurement or combination of sensing measurements is required; (implicit indication)

[0530] Configuration identifier of a predefined sensing measurement, which can implicitly indicate the processing level, configuration density, etc. of the required sensing measurement; (implicit indication)

[0531] Information for indicating the source of the required sensing measurement, for example, measurement from a sensing reference signal (i.e., integrated communication and sensing), or from sensor sensing, or which sensing method (i.e., the 6 basic sensing methods in related technology 2) of the measurement from a sensing reference signal (i.e., integrated communication and sensing), or which type of sensor of sensor sensing;

[0532] Information for indicating the sending device of the sensing reference signal (which can also be understood as the source of the sensing measurement), for example, serving base station, neighboring cell base station, nearby UE;

[0533] Information for indicating the receiving device of the sensing reference signal (which can also be understood as the source of the sensing measurement), for example, serving base station, neighboring cell base station, nearby UE, target UE;

[0534] Information for indicating the type of the required sensing measurement (see Explanation 2 later);

[0535] Configuration information of the sensing reference signal (see Explanation 3 later);

[0536] Information for indicating the total number of the required sensing measurements;

[0537] Information for indicating the minimum number of the required sensing measurements;

[0538] Information for indicating the sensing requirements (see Explanation 4 later).

[0539] In this embodiment, the combination of sensing measurements corresponding to the identifier of the sensing measurement can be seen in Table 3.

[0540] Table 3

[0541] Identification of perceived measurement quantity Perceived measurement quantity corresponding to the use 1 Doppler, time delay, power / amplitude / energy, angle, etc. of the path 2 Doppler, time delay, power / amplitude / energy of the path 3 Doppler, time delay of the path 4 Doppler, angle, Doppler resolution, angle resolution of the path

[0542] In this embodiment, when the serving base station of the UE only represents the second device and does not represent the fifth device, that is, the transmitting device of the sensing reference signal is not the serving base station of the UE, how does the serving base station of the UE coordinate the configuration of the sensing reference signal with the fifth device? The following provides three coordination methods:

[0543] Method 1: The fifth device itself determines the configuration of the sensing reference signal and notifies the serving base station of the UE after the determination. In this method, the serving base station of the UE receives the configuration of the sensing reference signal sent by the fifth device.

[0544] Method 2: The serving base station of the UE determines the corresponding configuration of the sensing reference signal according to the first request and then notifies (or forwards) it to the fifth device. In this method, the serving base station of the UE receives the feedback from the fifth device on the configuration of the sensing reference signal. For example: the fifth device agrees to the configuration of the sensing reference signal; or, the fifth device does not agree to the configuration of the sensing reference signal and negotiates the configuration of the sensing reference signal with the serving base station of the UE.

[0545] Method 3: The fifth device first determines the configuration of the sensing reference signal and then sends it to the serving base station of the UE for negotiation. In this method, the serving base station of the UE receives the configuration of the sensing reference signal sent by the fifth device and, based on the first request, feeds back the configuration difference or the expected configuration to the fifth device.

[0546] In step 2, the UE performs sample synchronization on the sensing measurement quantity and the CSI measurement result, including the following two methods:

[0547] Method 1:

[0548] The UE determines whether to combine the sensing measurement quantity and the CSI measurement quantity as an inference sample based on the timestamp of the sensing reference signal measurement, the effective duration of the sensing measurement quantity, the CSI measurement quantity (such as L1-RSRP), and the timestamp of the CSI measurement.

[0549] Specifically, if the timestamp of the CSI measurement is earlier than the timestamp of the sensing measurement + the effective duration, the UE combines the sensing measurement quantity and the CSI measurement result as an inference sample. Or,

[0550] If the timestamp corresponding to the prediction result of the AI unit is earlier than the timestamp of the sensing measurement + the effective time, the UE combines the sensing measurement quantity and the CSI measurement result as an inference sample.

[0551] Method 2:

[0552] The UE determines whether to combine the sensing measurement quantity with the CSI measurement quantity as an inference sample based on the sensing reference signal measurement quantity, the sensing control message, the CSI measurement quantity, and the time stamp of the CSI measurement.

[0553] Specifically, if the UE obtains the sensing measurement quantity and does not receive a message indicating the invalidation of the sensing result from the base station, the UE combines the sensing measurement quantity with the CSI measurement quantity as an inference sample.

[0554] If the latest time stamp corresponding to the CSI measurement quantity is earlier than the invalidation time indicated by the first indication, the UE combines the sensing measurement quantity with the CSI measurement quantity as an inference sample. Here, the first indication is used to indicate the invalidation of the sensing result or includes the time difference of the invalidation of the sensing result. The time difference can also be predefined. Or,

[0555] If the time stamp corresponding to the prediction result of the AI unit is earlier than the invalidation time indicated by the first indication, the UE combines the sensing measurement quantity and the CSI measurement result as an inference sample.

[0556] In the above method 1, the UE needs to obtain the timeliness (i.e., the effective duration) of the sensing measurement quantity to synchronize the samples of the sensing measurement quantity and the CSI measurement result. The methods for the UE to obtain the timeliness include the following three:

[0557] Method 1: Initially configure or predefine an effective duration of the sensing measurement quantity (e.g., 1 s, which can be implicitly indicated or explicitly indicated), and no additional effective duration is carried when sending the sensing reference signal each time;

[0558] Method 2: Initially configure or predefine an effective duration of the sensing measurement quantity, and carry an adjustment value (e.g., -100 ms, which can be implicitly indicated or explicitly indicated) when sending the sensing reference signal each time;

[0559] Method 3: Carry the absolute effective duration (e.g., 900 ms, which can be implicitly indicated or explicitly indicated) when sending the sensing reference signal each time.

[0560] In step 3, in addition to reporting the inference result to the base station, the UE can also report a fourth indication, indicating at least one of the following:

[0561] Whether the sensing measurement quantity is used;

[0562] The sensing measurement quantity indication (such as explicitly indicating the use of a certain one of Doppler, time delay, power, angle, etc. of the path, or implicitly indicating the corresponding combination, or indicating the processing level of the sensing measurement quantity); (see Table 4)

[0563] Timeliness indication of the perceived measurement quantity (for example, using 1 bit to indicate whether the inference sample uses a valid perceived measurement quantity or an invalid perceived measurement quantity).

[0564] Table 4

[0565] Perceived measurement quantity indication Perceived measurement quantity / processing level actually used Whether it is valid 1 Doppler Yes 2 Doppler, time delay Yes 3 Doppler, time delay, power None

[0566] The above items reflect the perception characteristics of the inference sample from the perspective of the usage of the perceived measurement quantity.

[0567] The following provides examples to illustrate the possible situations of using the perceived measurement quantity in a sample.

[0568] Example 1: As Figure 8 shown, if the latest timestamp predicted by step 7 is earlier than the expiration timestamp of the perceived result corresponding to step 8, and the timestamp of obtaining the perceived measurement quantity in step 2 is earlier than the timestamp of model inference in step 5, then in the reporting of the inference result in step 6, use 1 bit to indicate that the used perceived result is within the validity period, or do not indicate.

[0569] Example 2: As Figure 9 shown, if after the model is activated in step 3, the timestamp of obtaining the perceived measurement quantity in step 2 is later than the timestamp of model inference in step 5, then do not use the perceived result for model inference; then in the reporting of the inference result in step 6, use 1 bit to indicate that the perceived result is not used.

[0570] Example 3: As Figure 10 shown, if the expiration timestamp of the perceived result corresponding to step 8 is earlier than the timestamp corresponding to the prediction in step 7, then when performing model inference in step 5, the perceived measurement result can be used or not used as the model input.

[0571] If the perceived measurement quantity is not used, then indicate in the reporting of the inference result in step 6 that the perceived measurement result is not used;

[0572] If the perceived measurement quantity is used, then in the reporting of the inference result in step 6, indicate that the perceived measurement quantity is used, or indicate that an expired perceived measurement quantity is used, or indicate the expiration time.

[0573] Embodiment 2: The serving base station (referred to as the base station for short) sends a perceived reference signal, the UE receives the perceived reference signal and feeds it back to the base station, and the base station performs model inference

[0574] In this embodiment, the base station represents the first device and the fifth device (that is, the first device and the fifth device are co-located in the base station), and the UE represents the third device and the sixth device (that is, the third device and the sixth device are co-located in the UE).

[0575] In this embodiment, the second device and the fourth device can be core network functions (such as AMF, LMF).

[0576] As shown in Figure 11 the following steps are included:

[0577] 1. The base station sends a sensing reference signal to the UE; the base station may also send CSI-RS to the UE;

[0578] 2. The UE receives the sensing reference signal sent by the base station, performs sensing measurements, obtains sensing measurement quantities or sensing results, and the UE may also perform CSI measurements to obtain CSI measurement results;

[0579] 3. The UE reports at least one of the following information to the base station:

[0580] Sensing measurement quantities;

[0581] CSI measurement quantities;

[0582] Sensing measurement resource indication (such as an identifier);

[0583] CSI measurement resource indication (such as an identifier);

[0584] Timestamp of the sensing measurement quantity;

[0585] Timestamp of the CSI measurement quantity;

[0586] Associated sensing measurement quantity indication;

[0587] Timestamp of the associated sensing measurement quantity.

[0588] Figure 11 In step 3, it includes 3a and 3b, where 3a is the reporting of sensing measurement quantities and 3b is the reporting of CSI measurement quantities.

[0589] 4. The base station obtains inference samples for model inference based on the information reported by the UE (or the information reported by the UE and the stored historical data), and performs model inference.

[0590] In this embodiment, the information reported by the UE to the base station may be the information after sample synchronization (or sample alignment), that is, the sample synchronization is performed by the UE; the information reported by the UE to the base station may also be the information without sample synchronization, that is, the sample synchronization is performed by the base station.

[0591] In the case where the sample synchronization is performed by the UE, the information reported by the UE may include at least one of the following:

[0592] The sensing measurement quantities and CSI measurement quantities that have been time-aligned and can be used for one inference sample;

[0593] After time alignment, the CSI measurement of an inference sample + a third indication, where the third indication is used to indicate the sensed measurement that has been sent to the base station; wherein, the third indication may include a sample indication (such as an identifier) that has been sent to the base station, or, a CSI measurement indication (such as a resource identifier / CSI reporting identifier) that has been sent to the base station, or, a sensed measurement indication (such as an identifier) that has been sent to the base station;

[0594] The CSI measurement of an inference sample, without a third indication. In this case, the sensed measurement of the most recent inference sample is used by default.

[0595] When the sample synchronization is performed by the base station, the information reported by the UE may include at least one of the following:

[0596] Sensed measurement and CSI measurement. When the time difference between the received times of a certain sensed measurement and a certain CSI measurement reported by the UE is less than a certain time window, the base station may consider that the sensed measurement and the CSI measurement belong to the same inference sample; or, when the difference between the timestamps of a certain sensed measurement reported by the UE and a certain CSI measurement that the base station has received (or has stored) is within a certain time window, the base station may consider that the sensed measurement and the CSI measurement belong to the same inference sample; or, when the difference between the timestamps of a certain CSI measurement reported by the UE and a certain sensed measurement that the base station has received (or has stored) is within a certain time window, the base station may consider that the sensed measurement and the CSI measurement belong to the same inference sample;

[0597] CSI measurement and the timestamp of the CSI measurement. When the difference between the timestamp of a certain CSI measurement and the timestamp of the sensed measurement that has been received (or has been stored) is within a certain time window, or, when the sensed measurement that has been received (or has been stored) is within the valid time, the base station may consider that the CSI measurement and the sensed measurement that has been received belong to the same inference sample;

[0598] Sensed measurement and the timestamp of the sensed measurement. When the difference between the timestamp of a certain sensed measurement and the timestamp of the CSI measurement that has been received (or has been stored) is within a certain time window, the base station may consider that the sensed measurement and the CSI measurement that has been received (or has been stored) belong to the same inference sample.

[0599] The above time window may be a predefined time window or a time window reported by the UE.

[0600] Embodiment 3: The serving base station (referred to as the base station for short) sends the sensed measurement of the sensor to the UE, and the UE performs model inference

[0601] In this embodiment, the UE represents the first device, and the base station represents the second device, the third device, and the fourth device (i.e., the second device, the third device, and the fourth device are co-located in the base station).

[0602] As Figure 12 shown, it includes the following steps:

[0603] 1. The base station sends sensor-based perception measurement quantities to the UE;

[0604] 2. The UE receives the perception measurement quantities of the sensor sent by the base station, synchronizes the perception measurement quantities and the CSI measurement results, and obtains inference samples for model inference.

[0605] 3. The UE reports the inference result to the base station, and may also report a fourth indication.

[0606] The perception measurement quantities of the sensor may also include some auxiliary information (contained in the first information), for example:

[0607] Dataset identifier, which can implicitly indicate, for example: the configuration of a certain perception reference signal or perception measurement quantity used in the previous training process, the reporting configuration of the perception measurement quantity used in the previous training process; (implicit indication)

[0608] Pre-defined identifier of the perception measurement quantity, which can implicitly indicate what kind of perception measurement quantity or what combination of perception measurement quantities; (implicit indication)

[0609] Pre-defined configuration identifier of the perception measurement quantity, which can implicitly indicate the processing level, configuration density, etc. of the perception measurement quantity; (implicit indication)

[0610] Information indicating the source of the perception measurement quantity, for example, measurement from the perception reference signal (i.e., integrated communication and sensing), or, from sensor perception, or, which perception method from the measurement of the perception reference signal (i.e., integrated communication and sensing), or, which type of sensor from sensor perception;

[0611] Information indicating the type of the perception measurement quantity;

[0612] Information indicating the total number of the perception measurement quantities;

[0613] Information indicating the minimum number of the perception measurement quantities.

[0614] Before step 1, the UE sends a first request to the base station for requesting the perception measurement quantities required for model inference. (Same as

[0615] Embodiment 1)

[0616] In step 2, the method for the UE to synchronize the perception measurement quantity and the CSI measurement result is similar to that in Embodiment 1, including the following two methods:

[0617] Method 1:

[0618] Based on the measurement timestamp or reception timestamp of the perception measurement quantity of the sensor, the effective duration of the perception measurement quantity, the CSI measurement quantity (such as L1-RSRP), and the timestamp of the CSI measurement, the UE determines whether to combine the perception measurement quantity and the CSI measurement quantity as an inference sample.

[0619] Specifically, if the timestamp of the CSI measurement is earlier than the measurement timestamp of the perception measurement quantity + the effective duration, the UE combines the perception measurement quantity and the CSI measurement result as an inference sample. Or,

[0620] if the timestamp of the CSI measurement is earlier than the reception timestamp of the perception measurement quantity + the effective duration, the UE combines the perception measurement quantity and the CSI measurement result as an inference sample. Or,

[0621] if the timestamp corresponding to the prediction result of the AI model is earlier than the measurement timestamp of the perception measurement quantity + the effective time, the UE combines the perception measurement quantity and the CSI measurement result as an inference sample. Or,

[0622] if the timestamp corresponding to the prediction result of the AI model is earlier than the reception timestamp of the perception measurement quantity + the effective time, the UE combines the perception measurement quantity and the CSI measurement result as an inference sample.

[0623] Method 2:

[0624] Based on the perception measurement quantity of the sensor, the perception control message, the CSI measurement quantity, and the timestamp of the CSI measurement, the UE determines whether to combine the perception measurement quantity and the CSI measurement quantity as an inference sample.

[0625] Specifically, if the UE obtains the perception measurement quantity and does not receive a message indicating the invalidation of the perception result from the base station, the UE combines the perception measurement quantity and the CSI measurement quantity as an inference sample. Or,

[0626] if the latest timestamp corresponding to the CSI measurement quantity is earlier than the invalidation time indicated by the first indication, the UE combines the perception measurement quantity and the CSI measurement quantity as an inference sample. Or,

[0627] if the timestamp corresponding to the prediction result of the AI model is earlier than the invalidation time indicated by the first indication, the UE combines the perception measurement quantity and the CSI measurement quantity as an inference sample.

[0628] Among them, the first indication is used to indicate the invalidation of the sensing result or include the time difference of the invalidation of the sensing result. The time difference can also be predefined.

[0629] In the above method 1, the UE needs to obtain the timeliness (i.e., the effective duration) of the sensing measurement quantity to synchronize the samples of the sensing measurement quantity and the CSI measurement result. (Same as Embodiment 1)

[0630] Exemplarily, Table 5 lists the timeliness of the sensing measurement quantities corresponding to various sensor types.

[0631] Table 5

[0632] Sensor type Whether it is used Whether it is valid Radar Yes Yes Lidar Yes No Camera No No

[0633] The rest is the same as that in Embodiment 1. To avoid repetition, it will not be elaborated here.

[0634] Embodiment 4: The UE sends the sensing measurement quantity of the sensor to the serving base station (referred to as the base station), and the base station performs model inference. In this embodiment, the base station represents the first device, and the UE represents the third device.

[0635] As Figure 13 shown, the following steps are included:

[0636] 1. The base station sends the reporting configuration of the sensor sensing measurement quantity to the UE;

[0637] 2. The UE reports at least one of the following information to the base station:

[0638] The sensing measurement quantity;

[0639] The CSI measurement quantity;

[0640] The timestamp of the sensing measurement quantity;

[0641] The timestamp of the CSI measurement quantity;

[0642] The associated sensing measurement quantity indication;

[0643] The timestamp of the associated sensing measurement quantity.

[0644] Figure 13 Among them, step 2 includes 2a and 2b, where 2a is the reporting of the sensing measurement quantity of the sensor, and 2b is the reporting of the CSI measurement quantity.

[0645] 3. The base station obtains the inference samples for model inference based on the information reported by the UE (or the information reported by the UE and the stored historical data), and performs model inference.

[0646] In this embodiment, the information reported by the UE to the base station can be the information after sample synchronization (or sample alignment), that is, the sample synchronization is performed by the UE; the information reported by the UE to the base station can also be the information without sample synchronization, that is, the sample synchronization is performed by the base station. (Same as Embodiment 2)

[0647] Embodiment 5: The first base station (serving base station) sends a sensing reference signal, the second base station (neighboring base station) receives the sensing reference signal, the first base station sends the sensing measurement quantity to the UE, and the UE performs model inference

[0648] In this embodiment, the UE represents the first device, the second base station represents the third device and the sixth device (that is, the third device and the sixth device are co-located in the second base station), and the first base station represents the second device, the third device, the fourth device and the fifth device.

[0649] As Figure 14 shown, it includes the following steps:

[0650] 1. The first base station sends a sensing reference signal to the second base station;

[0651] 2. The second base station obtains a sensing measurement quantity or a sensing result based on the sensing reference signal;

[0652] 3. The second base station sends at least one of the following information to the first base station:

[0653] Sensing measurement quantity;

[0654] Sensing measurement resource indication (such as an identifier);

[0655] Timestamp of the sensing measurement quantity;

[0656] Valid duration of the sensing measurement quantity;

[0657] Other relevant information of the sensing measurement quantity.

[0658] 4. The first base station sends at least one of the following information to the UE:

[0659] Sensing measurement quantity;

[0660] Sensing measurement resource indication (such as an identifier);

[0661] Timestamp of the sensing measurement quantity;

[0662] Valid duration of the sensing measurement quantity;

[0663] Indication of the sensing reference signal receiving device (in this embodiment, it is an indication of the second base station, and this indication can be an implicit indication or an explicit indication);

[0664] Other relevant information of the sensing measurement quantity.

[0665] 5. The UE obtains an inference sample for model inference based on the information sent by the first base station and performs model inference.

[0666] 6. The UE reports the inference result to the first base station and may also report a fourth indication.

[0667] In this embodiment, other relevant information of the sensing measurement quantity (included in the first information) or relevant information of the inference result (included in the fourth indication) includes, for example, at least one of the following:

[0668] Dataset identifier, which can implicitly indicate, for example: the configuration of a certain sensing reference signal or sensing measurement quantity used in the previous training process, the reporting configuration of the sensing measurement quantity used in the previous training process; (implicit indication)

[0669] Identifier of a predefined sensing measurement quantity, which can implicitly indicate what kind of sensing measurement quantity or what combination of sensing measurement quantities; (implicit indication)

[0670] Configuration identifier of a predefined sensing measurement quantity, which can implicitly indicate the processing level, configuration density, etc. of the sensing measurement quantity; (implicit indication)

[0671] Sensing measurement link identification information (used to distinguish which sensing link the sensing measurement result comes from, which device sends and which device receives);

[0672] Sensing mode information (monostatic sensing mode or bistatic sensing mode, or at least one of the 6 sensing modes);

[0673] Sensing signal configuration identification information (used to distinguish the measurement of which sensing signal the sensing measurement result comes from);

[0674] Sensing service information (such as sensing service ID);

[0675] Sensing service type information (such as sensing service type ID);

[0676] Data subscription ID;

[0677] Measurement result usage information (such as communication, sensing, communication and sensing, for AI inference, etc.);

[0678] Device information of sensing measurement (such as UE ID, device location, device orientation, device movement information);

[0679] Coordinate information of the measurement result (the value of the measurement quantity), for example, whether it is a result based on the local coordinate system or the global coordinate system, and the description information of the local coordinate system, such as the rotation angles relative to the global coordinate system: α (bearing angle), β (down tilt angle), and γ (tilt angle);

[0680] The measurement results correspond to performance metric information, such as resolution (which can be time-delay resolution, ranging resolution, angle-of-arrival resolution, Doppler resolution, velocity resolution, imaging resolution, etc., i.e., the granularity of the values of the reported measurement quantities), SINR, perceived SINR (the ratio of the power of the path associated with the perceived target to the power of noise and interference), etc.

[0681] The performance metric corresponding to the perception result (such as perceived SINR) can be used as an input to the model together with the perception measurement results. For example, in addition to the Doppler value of the path on the Doppler spectrum being used as an input for training / inference, the ratio of the power of this path to the power of noise and interference is also used as an input to represent the accuracy or reliability of this Doppler value.

[0682] Before step 1, the UE sends a first request to the first base station to request the perception measurement quantities required for model inference. The first request may contain information indicating from which neighboring base stations the perception measurement quantities are obtained. The rest can be the same as in Embodiment 1.

[0683] In step 5, the UE can perform sample synchronization based on the information sent by the first base station. The sample synchronization method is similar to that in Embodiment 1 and includes the following two methods:

[0684] Method 1:

[0685] The UE determines whether to combine the perception measurement quantity and the CSI measurement quantity as an inference sample based on the measurement timestamp or reception timestamp of the perception measurement quantity, the effective duration of the perception measurement quantity, the CSI measurement quantity (such as L1-RSRP), and the timestamp of the CSI measurement.

[0686] Specifically, if the timestamp of the CSI measurement is earlier than the measurement timestamp of the perception measurement quantity + the effective duration, the UE combines the perception measurement quantity and the CSI measurement results (including the model input and the ground truth) as an inference sample. Or,

[0687] If the timestamp of the CSI measurement is earlier than the reception timestamp of the perception measurement quantity + the effective duration, the UE combines the perception measurement quantity and the CSI measurement results (including the model input and the ground truth) as an inference sample. Or,

[0688] If the timestamp corresponding to the prediction result of the AI model is earlier than the measurement timestamp of the perception measurement + the effective time, the UE combines the perception measurement quantity and the CSI measurement results (including the model input and the ground truth) as an inference sample. Or,

[0689] If the timestamp corresponding to the prediction result of the AI model is earlier than the reception timestamp of the perception measurement quantity + the effective time, the UE combines the perception measurement quantity and the CSI measurement results (including the model input and the ground truth) as an inference sample.

[0690] Method 2:

[0691] The UE determines whether to combine the sensing measurement quantity with the CSI measurement quantity as an inference sample based on the sensing measurement quantity, the sensing control message, the CSI measurement quantity, and the time stamp of the CSI measurement.

[0692] Specifically, if the UE obtains the sensing measurement quantity and does not receive a message indicating the invalidation of the sensing result from the base station, the UE combines the sensing measurement quantity with the CSI measurement quantity as an inference sample. Or,

[0693] If the latest time stamp corresponding to the CSI measurement quantity is earlier than the invalidation time indicated by the first indication, the UE combines the sensing measurement quantity with the CSI measurement quantity as an inference sample. Or,

[0694] If the time stamp corresponding to the prediction result of the AI model is earlier than the invalidation time indicated by the first indication, the UE combines the sensing measurement quantity with the CSI measurement quantity as an inference sample.

[0695] Wherein, the first indication is used to indicate the invalidation of the sensing result or includes the time difference of the invalidation of the sensing result. The time difference can also be predefined.

[0696] In the above Method 1, the UE needs to obtain the timeliness (i.e., the valid duration) of the sensing measurement quantity to synchronize the samples of the sensing measurement quantity and the CSI measurement result. (Same as Embodiment 1)

[0697] The rest is the same as Embodiment 1. To avoid repetition, it will not be elaborated here.

[0698] Embodiment 6: The first base station (serving base station) sends a sensing reference signal, the second base station (neighboring base station) receives the sensing reference signal, the second base station sends the sensing measurement quantity to the UE, and the UE performs model inference

[0699] In this embodiment, the UE represents the first device, the second base station represents the third device and the sixth device (i.e., the third device and the sixth device are co-located in the second base station), and the first base station represents the second device, the fourth device, and the fifth device (i.e., the second device, the fourth device, and the fifth device are co-located in the first base station).

[0700] In this embodiment, the UE has also established a connection with the second base station. Therefore, the second base station can directly send the sensing measurement quantity to the UE.

[0701] It should be noted that how does the second base station know to send the sensing measurement quantity to the UE? Specifically, when the first base station sends the sensing reference signal to the second base station, or when configuring the sensing reference signal, it is necessary to indicate the receiving device of the sensing measurement quantity, that is, the UE.

[0702] Such asFigure 15 As shown in the figure, it includes the following steps:

[0703] 1. The first base station sends a sensing reference signal to the second base station;

[0704] 2. The second base station obtains a sensing measurement or a sensing result based on the sensing reference signal;

[0705] 3. The second base station sends at least one of the following information to the UE:

[0706] The sensing measurement;

[0707] The timestamp of the sensing measurement;

[0708] The valid duration of the sensing measurement;

[0709] Other relevant information of the sensing measurement;

[0710] The indication of the sensing reference signal receiving device (in this embodiment, it is to indicate the second base station, and this indication can be an implicit indication or an explicit indication).

[0711] 4. The UE synchronizes the sensing measurement and the CSI measurement result based on the information sent by the second base station, obtains an inference sample for model inference, and performs model inference.

[0712] 5. The UE reports the inference result to the first base station and may also report a fourth indication.

[0713] Before step 1, the UE sends a first request to the first base station for requesting the sensing measurement required for model inference. The first request may include information for indicating from which neighboring base stations or how many neighboring base stations the sensing measurement comes from, and the rest may be the same as in Embodiment 1.

[0714] The rest is the same as in Embodiment 5. To avoid repetition, it will not be elaborated here.

[0715] Embodiment 7: The serving base station (referred to as the base station for short) sends a sensing reference signal, the second UE receives the sensing reference signal, the base station sends the sensing measurement to the target UE (or the first UE), and the target UE performs model inference

[0716] In this embodiment, the target UE represents the first device, the base station represents the second device, the third device, the fourth device, and the fifth device (i.e., the second device, the third device, the fourth device, and the fifth device are co-located in the base station), and the second UE represents the third device and the sixth device.

[0717] In this embodiment, the second UE is a UE near the target UE.

[0718] As Figure 16 shown in the figure, it includes the following steps:

[0719] 1. The base station sends a sensing reference signal to the second UE;

[0720] 2. The second UE obtains a sensing measurement quantity or a sensing result based on the sensing reference signal;

[0721] 3. The second UE sends at least one of the following information to the base station:

[0722] The sensing measurement quantity;

[0723] The timestamp of the sensing measurement quantity;

[0724] The effective duration of the sensing measurement quantity;

[0725] The sensing measurement resource indication (such as an identifier);

[0726] Other relevant information of the sensing measurement quantity.

[0727] 4. The base station sends at least one of the following information to the target UE:

[0728] The sensing measurement quantity;

[0729] The timestamp of the sensing measurement quantity;

[0730] The effective duration of the sensing measurement quantity;

[0731] Other relevant information of the sensing measurement quantity;

[0732] The indication of the sensing reference signal receiving device (in this embodiment, it is to indicate the second UE, and this indication can be an implicit indication or an explicit indication).

[0733] 5. The target UE synchronizes the sensing measurement quantity and the CSI measurement result based on the information sent by the base station, obtains an inference sample for model inference, and performs model inference.

[0734] 6. The UE reports the inference result to the base station and may also report a fourth indication.

[0735] It should be noted that the serving base station may directly receive information from the second UE or be forwarded through other devices. For example, if the second UE is a UE of a neighboring cell, the second UE first sends the information to the neighboring cell base station, and then the neighboring cell base station forwards it to the serving base station.

[0736] Before step 1, the target UE sends a first request to the base station for requesting the sensing measurement quantity required for model inference. The first request may include information for indicating from which neighboring cell UE(s) the sensing measurement quantity comes, and the rest may be the same as in Embodiment 1.

[0737] In this embodiment, when the serving base station of the target UE only represents the second device and does not represent the fifth device, that is, the transmitting device of the sensing reference signal is not the serving base station of the target UE, how does the serving base station of the target UE coordinate the configuration of the sensing reference signal with the fifth device? (Same as Embodiment 1)

[0738] Specifically, reference can be made to Figure 17 and Figure 18 . Figure 17 In, the second UE belongs to the first base station (i.e., the serving base station), the target UE represents the first device, the first base station represents the second device and the third device, the second UE represents the third device and the sixth device, and the second base station represents the fifth device. Figure 18 In, the second UE belongs to the second base station, the target UE represents the first device, the first base station represents the second device and the third device, the second UE represents the third device and the sixth device, and the second base station represents the third device and the fifth device.

[0739] The rest is the same as in Embodiment 5. To avoid repetition, it will not be elaborated here.

[0740] Embodiment 8: The serving base station (also known as the first base station) sends a sensing reference signal, the second UE receives the sensing reference signal, the second UE sends the sensing measurement to the target UE (or the first UE), and the target UE performs model inference

[0741] In this embodiment, the target UE represents the first device, the serving base station represents the second device, the fourth device and the fifth device, and the second UE represents the third device and the sixth device.

[0742] In this embodiment, the second device and the fourth device can be the serving base station or core network functions.

[0743] In this embodiment, the second UE is a UE near the target UE, the target UE has established a sidelink with the second UE, and the second UE can directly send the sensing measurement to the target UE.

[0744] The main process of this embodiment is similar to that of Embodiment 6, except that the receiving device of the sensing reference signal is different.

[0745] In this embodiment, the serving base station sends a sensing reference signal to the second UE. In Embodiment 6, the serving base station sends a sensing reference signal to the second base station.

[0746] As Figure 19 shown, it includes the following steps:

[0747] 1. The base station sends a sensing reference signal to the second UE;

[0748] 2. The second UE obtains a sensing measurement or a sensing result based on the sensing reference signal;

[0749] 3. The second UE sends at least one of the following information to the target UE:

[0750] Perceived measurement quantity;

[0751] Timestamp of the perceived measurement quantity;

[0752] Valid duration of the perceived measurement quantity;

[0753] Other relevant information of the perceived measurement quantity;

[0754] Indicator of the perceived reference signal receiving device (in this embodiment, it is to indicate the second UE, and this indicator can be an implicit indicator or an explicit indicator).

[0755] 4. Based on the information sent by the second UE, the target UE synchronizes the perceived measurement quantity and the CSI measurement result to obtain an inference sample for model inference, and performs model inference.

[0756] 5. The target UE reports the inference result to the base station.

[0757] Before step 1, the target UE sends a first request to the base station to request the perceived measurement quantity required for model inference. The first request may include information for indicating from which several or which neighboring cell UEs the perceived measurement quantity comes, and the rest may be the same as in Embodiment 1.

[0758] In step 5, in addition to reporting the inference result to the base station, the target UE may also report a fourth indicator to indicate at least one of the following:

[0759] Whether the perceived measurement quantity is used;

[0760] Perceived measurement quantity indicator (such as explicitly indicating the use of a certain one of Doppler, time delay, power, angle, etc. of a path, or implicitly indicating the corresponding combination, or indicating the processing level of the perceived measurement quantity); (see Table 4)

[0761] Timeliness indicator of the perceived measurement quantity (for example, using 1 bit to indicate whether the inference sample uses a valid perceived measurement quantity or an invalid perceived measurement quantity);

[0762] Which nearby UE the perceived measurement quantity comes from (which can be explicitly indicated or implicitly indicated (such as the measurement identifier of the perceived measurement quantity)).

[0763] The rest is the same as in Embodiment 5. To avoid repetition, it will not be elaborated here.

[0764] Embodiment 9: The base station sends a perceived reference signal, the base station receives the perceived reference signal, the base station sends the perceived measurement quantity to the UE, and the UE performs model inference

[0765] In this embodiment, the UE represents the first device, and the base station represents the second device, the third device, the fourth device, the fifth device, and the sixth device.

[0766] In this embodiment, the second device and the fourth device may also be core network functions (such as AMF, LMF).

[0767] In this embodiment, the base station performing the self-transmission and self-reception operation may be the serving base station or the neighboring cell base station. In addition, other nearby UEs may also perform the self-transmission and self-reception operation, which is not specifically described in this embodiment.

[0768] As Figure 20 shown, it includes the following steps:

[0769] 1. The base station sends a sensing reference signal, receives the sensing reference signal, and obtains a sensing measurement or a sensing result;

[0770] 2. The base station sends at least one of the following information to the UE:

[0771] The sensing measurement;

[0772] The timestamp of the sensing measurement;

[0773] The effective duration of the sensing measurement;

[0774] Other relevant information of the sensing measurement;

[0775] The indication of the sensing reference signal receiving device (in this embodiment, it is to indicate the base station, and this indication can be an implicit indication or an explicit indication).

[0776] 3. Based on the information sent by the base station, the UE synchronizes the sensing measurement and the CSI measurement result to obtain an inference sample for model inference, and performs model inference.

[0777] 4. The UE reports the inference result to the base station.

[0778] Before step 1, the UE sends a first request to the base station, which is used to request the sensing measurement required for model inference. The first request may include:

[0779] Information used to indicate from how many fifth devices the sensing measurement comes;

[0780] Information used to indicate the category (serving cell, neighboring cell, nearby UE) or category combination (such as serving cell, 3 neighboring cells, 4 nearby UEs) of the fifth device.

[0781] The rest of the first request may be the same as that in Embodiment 1.

[0782] In step 4, in addition to reporting the inference result to the base station, the target UE may also report a fourth indication, indicating at least one of the following:

[0783] Whether a sensing measurement quantity is used;

[0784] Sensing measurement quantity indication (such as explicitly indicating one of Doppler, time delay, power, angle, etc. of a path, or implicitly indicating a corresponding combination (see Table 3), or indicating the processing level of the sensing measurement quantity);

[0785] Timeliness indication of the sensing measurement quantity (for example, using 1 bit to indicate whether the inference sample uses a valid sensing measurement quantity or an invalid sensing measurement quantity);

[0786] Receiving device (serving cell, neighboring cell, nearby UE) or receiving device combination of the sensing measurement quantity (such as serving cell, 3 neighboring cells, 4 nearby UEs) (can be explicitly indicated or implicitly indicated (such as the measurement identifier of the sensing measurement quantity, the identifier of the sixth device / receiving device combination)).

[0787] Exemplarily, for the explicit indication of the timeliness of the sensing measurement quantity, see Table 6.

[0788] Table 6

[0789]

[0790] Exemplarily, for the implicit indication of the timeliness of the sensing measurement quantity, see Table 7.

[0791] Table 7

[0792]

[0793]

[0794] The rest is the same as in Embodiment 5. To avoid repetition, it will not be elaborated here.

[0795] The above are the specific embodiments provided by the embodiments of this application.

[0796] Regarding the related terms of this application, the explanations are as follows:

[0797] Explanation 1: AI model

[0798] The AI model can also be referred to as an AI unit, a machine learning (ML) model, an ML unit, an AI architecture, an AI function, an AI feature, a neural network, a neural network function, a neural network capability, etc. Alternatively, the AI unit / AI model can also refer to a processing unit that can implement specific algorithms, formulas, processing flows, capabilities, etc. related to AI. Alternatively, the AI unit / AI model can be a processing method, algorithm, function, module, or unit for a specific data set. Alternatively, the AI unit / AI model can be a processing method, algorithm, function, module, or unit running on AI / ML-related hardware such as GPUs, NPUs, TPUs, ASICs, etc. This application does not make specific limitations in this regard.

[0799] Optionally, the specific data set includes the input or output of the AI unit / AI model.

[0800] Optionally, the identifier of the AI unit / AI model can be an AI model identifier, an AI architecture identifier, an AI algorithm identifier, etc. Alternatively, it can be the identifier of the specific data set associated with the AI unit / AI model. Alternatively, it can be the identifier of a specific scenario, environment, channel feature, device, etc. related to AI / ML. Alternatively, it can be the identifier of a function, feature, capability, or module, etc. related to AI / ML. This application does not make specific limitations in this regard.

[0801] Explanation 2: Types of sensed measurement quantities

[0802] For the sensed measurement quantities related to the integration of communication and sensing, the following types are included:

[0803] (1) First-level measurement quantities (received signal / raw channel information), including: complex results of received signals / channel responses, amplitude / phase, in-phase (I) / quadrature (Q) channels and their operation results (operations include addition, subtraction, multiplication, division, matrix addition, subtraction, multiplication, matrix transpose, trigonometric relation operations, square root operations, power operations, etc., and threshold detection results, maximum / minimum value extraction results, etc. of the above operation results; operations also include Fast Fourier Transform (FFT) / Inverse Fast Fourier Transform (IFFT), Discrete Fourier Transform (DFT) / Inverse Discrete Fourier Transform (IDFT), 2D-FFT, 3D-FFT, matched filtering, autocorrelation operations, wavelet transforms, and digital filtering, etc., and threshold detection results, maximum / minimum value extraction results, etc. of the above operation results);

[0804] Here, H is not limited to the channels between the serving base station and the UE, but also includes the sensing channels obtained by other base stations through self - transmission and self - reception, covering multiple scenarios. The H sensed by the base station through self - transmission and self - reception is different from the H measured by the UE itself. For example, whether the moving target in the environment is caused by the movement of obstacles or the movement of the UE itself. This can achieve interference cancellation and is beneficial to 3D environment reconstruction.

[0805] It should be noted that the above H represents the received signal / original channel information.

[0806] The effective time of the sensed measurement can be long or short. If it is relatively static sensing information (for example, unchanged for several years), it can be directly transmitted; if it is obtained through real - time measurement, it is necessary to configure which devices send the sensing signals and which devices receive the sensing signals. This can improve the prediction accuracy.

[0807] (2) The second - level measurement (basic measurement) includes: delay, Doppler, angle, intensity, and their multi - dimensional combined representations; for example, it can be a delay value, a Doppler value, or a delay power spectrum, a Doppler power spectrum, a velocity power spectrum, an angle power spectrum, a delay - Doppler spectrum, a delay - angle spectrum, a Doppler - angle spectrum, a delay - Doppler - angle spectrum, etc.

[0808] (3) The third - level measurement: sensing result / intermediate sensing result

[0809] Basic attributes / states include: distance, speed, orientation, spatial position, acceleration;

[0810] Advanced attributes / states include: whether the target exists, trajectory, action, expression, vital signs, quantity, imaging result, weather, air quality, shape, material, composition;

[0811] Environmental reconstruction result, trajectory.

[0812] For the measurement of sensor - based sensing, it includes the following types:

[0813] (1) The measurements related to lidar include at least one of the following:

[0814] Lidar point cloud data, and each point in the lidar point cloud data includes: X / Y / Z position information, and additional information;

[0815] The angle and distance of the target obtained from the lidar point cloud data;

[0816] The visual features of the target identified from the lidar point cloud data, such as: people, vehicles, etc.;

[0817] The number of targets identified from the lidar point cloud data.

[0818] Among them, the additional information in the lidar point cloud data includes at least one of the following:

[0819] Intensity: The echo intensity of the laser pulse that generates the lidar point;

[0820] Number of echoes: The number of echoes is the total number of echoes of a given pulse;

[0821] Point classification: Each post-processed lidar point can have a classification that defines the type of object reflecting the lidar pulse. The lidar points can be divided into many categories, such as: ground, bare surface, top of the tree canopy, and water area, etc.;

[0822] RGB: The RGB band can be used as an attribute of the lidar data. This attribute usually comes from the images collected during the lidar measurement;

[0823] GPS time: The GPS timestamp when the laser point is emitted from the aircraft;

[0824] Scanning angle;

[0825] Scanning direction: The traveling direction of the laser scanning mirror. The value 1 represents the positive scanning direction, and the value 0 represents the negative scanning direction.

[0826] (2) Measurement quantities related to vision, including at least one of the following:

[0827] Visual image;

[0828] Luminance of the image pixel;

[0829] RGB value of the image pixel;

[0830] Visual features of the target recognized from the image, such as: people, vehicles, etc.;

[0831] Angle and distance of the target recognized from the image (especially for binocular vision);

[0832] Number of targets recognized from the image.

[0833] (3) Measurement quantities related to radar, including at least one of the following:

[0834] Radar point cloud. Each point in the point cloud includes at least one of: distance / speed / azimuth angle / pitch angle, or at least one of X / Y / Z / speed;

[0835] Distance, speed, and angle of the recognized target;

[0836] Radar imaging;

[0837] Number of targets.

[0838] (4) Measurement quantities related to the inertial measurement unit, including at least one of the following:

[0839] Acceleration: at least one of the three directions of X / Y / Z;

[0840] Velocity: at least one of the three directions of X / Y / Z;

[0841] Angular velocity: around at least one of the three axes of X / Y / Z.

[0842] (5) Measurement quantities of a position sensor such as GNSS, including the position information of the device and the relative distance / angle information between the device and a specific object.

[0843] (6) Other measurement quantities, including at least one of the following: whether the target exists, trajectory, action, expression, vital signs, quantity, imaging result, weather, air quality, shape, material, composition, etc.

[0844] Explanation 3: Signal configuration information (which can be called the configuration information of the target signal, the configuration information of the sensing reference signal, etc.)

[0845] Signal configuration information, including at least one of the following:

[0846] Signal resource identifier (ID), used to distinguish different signal resource configurations;

[0847] Signal usage, indicating that the signal is a signal for communication (such as channel measurement, channel estimation, synchronization, carrying data information, etc.), a signal for sensing, or a signal for both communication and sensing. Specifically, it can also be a signal for which sensing service, or a signal for which type of sensing service. The definitions of the sensing service and the sensing service type can refer to Explanation 3.

[0848] Waveform, such as Orthogonal Frequency Division Multiplexing (OFDM), Single-Carrier Frequency-Division Multiple Access (SC-FDMA), Orthogonal Time Frequency Space (OTFS), Chirp waveform, Frequency Modulated Continuous Wave (FMCW), pulse signal, etc.;

[0849] Subcarrier spacing, for example, the subcarrier spacing of 30 KHz in an OFDM system.

[0850] Guard interval, which is the time interval from the moment when the signal ends transmission to the moment when the latest echo signal of the signal is 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 a self-transmitting and self-receiving sensing signal, R max represents the maximum distance from the sensing signal transceiver point to the signal transmission point; in some cases, the OFDM signal cyclic prefix (CP) can serve as the minimum guard interval; c is the speed of light.

[0851] Starting frequency domain position, that is, the starting frequency point, which can also be the starting RE or RB index;

[0852] Starting time domain position, that is, the starting time point, which can also be the starting symbol index, time slot index, or frame index;

[0853] Ending frequency domain position, that is, the ending frequency point, which can be represented by the ending RE or RB index;

[0854] Ending time domain position, that is, the ending time point, which can be represented by the ending RE or RB index;

[0855] Frequency domain resource length, that is, the frequency domain bandwidth. The frequency domain bandwidth is inversely proportional to the range resolution. The frequency domain bandwidth B of each of the first signals satisfies B≥c / (2ΔR), where c is the speed of light and ΔR is the range resolution;

[0856] Time domain resource length, also known as the burst duration. The time domain resource length is inversely proportional to the Doppler resolution;

[0857] Frequency domain resource interval, which represents the interval between adjacent signal frequency domain resource units. It can be represented by the number of REs or RBs, or by the density value (Density). For example, Density = 1 means that there is one RE in each RB for carrying the signal. The frequency domain resource interval is inversely proportional to the maximum unambiguous range / delay. For an OFDM system, when subcarriers are continuously mapped, the frequency domain interval is equal to the subcarrier interval;

[0858] Time domain resource interval, which is the time interval between two adjacent signal resource units. The time domain resource interval is associated with the maximum unambiguous Doppler shift or the maximum unambiguous speed;

[0859] Time domain resource characteristics, periodic transmission, semi-persistent transmission, non-periodic transmission;

[0860] Signal power, for example, taking a value every 2 dBm from -20 dBm to 23 dBm;

[0861] Sequence information, including sequence type information (such as ZC sequence, PN sequence, etc.), sequence generation method, sequence length, etc.;

[0862] Signal direction, angle information or beam information of signal transmission;

[0863] QCL relationship. For example, the sensing signal includes multiple resources, each resource is associated with an SSB QCL, and the QCL includes Type A, B, C, or D;

[0864] Antenna port information, such as the maximum number of antenna ports, antenna port index;

[0865] Cyclic prefix (CP) information, including CP type (such as Normal Cyclic Prefix (NCP), Extended Cyclic Prefix (ECP), or a newly designed CP dedicated for sensing measurement, etc.), CP length, etc.

[0866] Explanation 4: Sensing requirements

[0867] The sensing requirement information includes at least one of the following:

[0868] Sensing service or sensing service type. The sensing service can be, for example, detecting the presence of a target, positioning, speed detection, distance detection, angle detection, acceleration detection, material analysis, component analysis, shape detection, category classification, Radar Cross Section (RCS) detection, polarization scattering characteristic detection, fall detection, intrusion detection, quantity statistics, indoor positioning, gesture recognition, lip reading, gait recognition, expression recognition, face recognition, breathing monitoring, heart rate monitoring, pulse monitoring, humidity / brightness / temperature / atmospheric pressure monitoring, air quality monitoring, weather condition monitoring, environment reconstruction, terrain and landform, building / vegetation distribution detection, pedestrian or vehicle flow detection, crowd density / vehicle density detection, etc.; The sensing service type can classify multiple different sensing services according to certain characteristics. For example, it can be classified into detection-type sensing services (such as intrusion detection, fall detection) according to function, parameter estimation-type sensing services (distance, angle, speed calculation), recognition-type sensing services (action recognition, identity recognition), etc., or it can be, for example, target detection and tracking-type sensing services (including the presence of a target, target ranging / ranging / angle measurement / localization / trajectory tracking), environment monitoring-type sensing services (including rainfall detection, flood monitoring), action detection-type sensing services (including gesture / action recognition, breathing / heartbeat detection, fall detection), etc. It can also be classified according to the sensing range (close-range sensing, medium-range sensing, long-range sensing), according to the sensing fineness (coarse-grained sensing, fine-grained sensing, etc.), according to power consumption / energy consumption, according to resource occupancy, etc.

[0869] Perceived target area: It refers to the area where the perceived object may be located, or the area where imaging or environmental reconstruction needs to be performed.

[0870] Perceived object type: Classify the perceived object according to its possible motion characteristics. Each perceived object type contains information such as the motion speed, motion acceleration, and typical RCS of typical perceived objects.

[0871] Perceived QoS: Performance metrics for perceiving the perceived target area or perceived object.

[0872] The perceived QoS includes at least one of the following:

[0873] Perceived resolution (which can be divided into: ranging resolution, angle measurement resolution, speed measurement resolution, imaging resolution, etc.);

[0874] Perceived accuracy (which can be divided into: ranging accuracy, angle measurement accuracy, speed measurement accuracy, positioning accuracy, etc.);

[0875] Perceived range (which can be divided into: ranging range, speed measurement range, angle measurement range, imaging range, etc.);

[0876] Perceived latency (the time interval from sending the perception signal to obtaining the perception result, or the time interval from the perception requirement being initiated to obtaining the perception result);

[0877] Perceived update rate (the time interval between two adjacent executions of perception and obtaining the perception result);

[0878] Detection probability (the probability of being correctly detected when the perceived object exists);

[0879] False alarm probability (the probability of erroneously detecting a perceived target when the perceived object does not exist);

[0880] The maximum number of perceivable targets.

[0881] In summary, in the embodiments of the present application, by proposing a perception-assisted model inference method, the network node can obtain perception information to expand the data information for model inference, thereby improving the inference accuracy of the AI model.

[0882] For the model inference method provided in the embodiments of the present application, the execution subject can be a model inference device. For the model inference method provided in the embodiments of the present application, the execution subject can be a model inference device. In the embodiments of the present application, taking the model inference device executing the model inference method as an example, the model inference device provided in the embodiments of the present application is described.

[0883] Figure 21The structural diagram of the model inference device provided by the embodiment of the present application is shown. The model inference device can be applied to the first device. As Figure 21 shown, the model inference device 910 includes:

[0884] A first processing module 911, configured to obtain an inference sample, where the inference sample is determined based on communication measurement-related data and perception measurement-related data;

[0885] A second processing module 912, configured to input the inference sample into an artificial intelligence (AI) unit to obtain an inference result.

[0886] Optionally, the perception measurement-related data includes at least one of the following information:

[0887] Perception measurement quantity;

[0888] Indicator of the perception measurement quantity;

[0889] Timestamp of the perception measurement quantity;

[0890] Information of the sending device of the perception measurement quantity;

[0891] Information of the receiving device of the perception measurement quantity;

[0892] Coordinate information of the perception measurement quantity;

[0893] Information for indicating the performance index of the perception measurement quantity;

[0894] Information for indicating the source of the perception measurement quantity;

[0895] Information for indicating the type of the perception measurement quantity;

[0896] Information for indicating the perception mode of the perception measurement quantity;

[0897] Configuration information of the target signal;

[0898] Information of the sending device of the target signal;

[0899] Information of the receiving device of the target signal;

[0900] Wherein, the target signal is a signal used for perception.

[0901] Optionally, the device further includes:

[0902] A first sending module, configured to send a first request to a second device, where the first request is used to request perception measurement-related data required for model inference.

[0903] Optionally, the first request includes at least one of the following information:

[0904] Information for indicating that the AI unit is in the inference stage;

[0905] Dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement related data;

[0906] Configuration identifier of the perception measurement quantity;

[0907] Identifier of the perception measurement quantity;

[0908] Information for indicating the perception characteristics of the target dataset;

[0909] Identifier of the target dataset;

[0910] Configuration information of the perception measurement quantity required for model inference;

[0911] Information for indicating the number threshold of the perception measurement quantity required for model inference;

[0912] Information for indicating the source of the perception measurement quantity required for model inference;

[0913] Information for indicating the type of the perception measurement quantity required for model inference;

[0914] Information for indicating the perception mode of the perception measurement quantity required for model inference;

[0915] Information for indicating the perception requirement;

[0916] Configuration information of the target signal;

[0917] Information of the sending device of the target signal;

[0918] Information of the receiving device of the target signal;

[0919] Wherein, the target dataset is the dataset used by the AI unit in the training stage;

[0920] The target signal is a signal used for perception.

[0921] Optionally, the first processing module is specifically used for at least one of the following:

[0922] Obtain inference samples based on the timestamp of the communication measurement quantity, the timestamp of the perception measurement quantity, and the effective duration of the perception measurement quantity;

[0923] Obtain inference samples based on the timestamp corresponding to the prediction result of the AI unit, the timestamp of the perception measurement quantity, and the effective duration of the perception measurement quantity;

[0924] Obtain inference samples based on the first indication and the timestamp of the communication measurement quantity;

[0925] Obtain an inference sample based on the first indication and the timestamp corresponding to the prediction result of the AI unit;

[0926] Obtain an inference sample based on whether the second indication is received;

[0927] Wherein, the first indication is used to indicate the failure time or the failure time difference of the sensed measurement quantity;

[0928] The second indication is used to indicate the failure of the sensed measurement quantity.

[0929] Optionally, the method for determining the effective duration of the sensed measurement quantity includes at least one of the following:

[0930] When a first effective duration is pre-configured or defined, the effective duration of the sensed measurement quantity is the first effective duration;

[0931] When a second effective duration is pre-configured or defined and the target signal carries a time adjustment value, the effective duration of the sensed measurement quantity is determined according to the second effective duration and the time adjustment value;

[0932] When the target signal carries a third effective duration, the effective duration of the sensed measurement quantity is the third effective duration;

[0933] Wherein, the target signal is a signal used for sensing.

[0934] Optionally, the first processing module is specifically configured to perform at least one of the following:

[0935] When the timestamp corresponding to the communication measurement quantity is earlier than the first time, obtain an inference sample including communication measurement-related data and sensed measurement-related data;

[0936] When the timestamp corresponding to the prediction result of the AI unit is earlier than the first time, obtain an inference sample including communication measurement-related data and sensed measurement-related data;

[0937] When the timestamp corresponding to the communication measurement quantity is earlier than the second time, obtain an inference sample including communication measurement-related data and sensed measurement-related data;

[0938] When the timestamp corresponding to the prediction result of the AI unit is earlier than the second time, obtain an inference sample including communication measurement-related data and sensed measurement-related data;

[0939] When the first device does not receive the second indication, obtain an inference sample including communication measurement-related data and sensed measurement-related data;

[0940] Wherein, the first time is the time corresponding to the sum of the timestamp of the sensed measurement quantity and the valid duration of the sensed measurement quantity;

[0941] The second time is the expiration time of the sensed measurement quantity determined based on the first indication.

[0942] Optionally, the first processing module includes:

[0943] A receiving unit, configured to receive first information from a third device, where the first information includes at least one of communication measurement-related data and sensed measurement-related data;

[0944] A processing unit, configured to obtain an inference sample based on the first information; or obtain an inference sample based on the first information and stored historical data;

[0945] Wherein, the historical data includes at least one of communication measurement-related data and sensed measurement-related data.

[0946] Optionally, the first information includes at least one of the following:

[0947] A dataset identifier, where the dataset corresponding to the dataset identifier includes sensed measurement-related data;

[0948] A configuration identifier of the sensed measurement quantity;

[0949] An identifier of the sensed measurement quantity;

[0950] An identifier of the sensed measurement link;

[0951] An identifier of the sensing service;

[0952] An identifier of the sensing service type;

[0953] The sensed measurement quantity;

[0954] The timestamp of the sensed measurement quantity;

[0955] Information about the sending device of the sensed measurement quantity;

[0956] Coordinate information of the sensed measurement quantity;

[0957] Information for indicating the performance metrics of the sensed measurement quantity;

[0958] Information for indicating the source of the sensed measurement quantity;

[0959] Information for indicating the type of the sensed measurement quantity;

[0960] Information for indicating the use of the sensed measurement quantity;

[0961] Information for indicating the sensing mode of the sensed measurement quantity;

[0962] Communication measurement quantity;

[0963] Communication measurement resource identifier;

[0964] Timestamp of the communication measurement quantity;

[0965] Information for indicating a first time window;

[0966] Information for indicating a first valid time;

[0967] Configuration identifier of the target signal;

[0968] Configuration information of the target signal;

[0969] Information of the sending device of the target signal;

[0970] Information of the receiving device of the target signal;

[0971] Wherein, the target signal is a signal used for sensing.

[0972] Optionally, the first processing module is specifically configured to perform at least one of the following:

[0973] When the time difference between the timestamp of the sensing measurement quantity and the timestamp of the communication measurement quantity is less than or equal to the first time window indicated by the first information, obtain an inference sample including communication measurement-related data and sensing measurement-related data;

[0974] When the time difference between the timestamp of the sensing measurement quantity and the timestamp of the communication measurement quantity is less than or equal to a predefined second time window, obtain an inference sample including communication measurement-related data and sensing measurement-related data.

[0975] Optionally, the first information includes a target sensing measurement quantity and the timestamp of the target sensing measurement quantity;

[0976] The first processing module is specifically configured to:

[0977] Obtain an inference sample including a target communication measurement quantity and the target sensing measurement quantity;

[0978] Wherein, the target communication measurement quantity includes at least one of the following:

[0979] The communication measurement quantity whose time difference between the timestamp of the historical data and the timestamp of the target sensing measurement quantity is less than or equal to the first time window indicated by the first information;

[0980] The communication measurement quantity whose time difference between the timestamp of the historical data and the timestamp of the target sensing measurement quantity is less than or equal to a predefined second time window.

[0981] Optionally, the first information includes a target communication measurement and a timestamp of the target communication measurement;

[0982] The first processing module is specifically configured to:

[0983] Obtain an inference sample including the target communication measurement and a target perception measurement;

[0984] Wherein, the target perception measurement includes at least one of the following:

[0985] The time difference between the timestamp of the historical data and the timestamp of the target communication measurement is less than or equal to the perception measurement of the first time window indicated by the first information;

[0986] The timestamp of the historical data is less than or equal to the perception measurement of the first valid time indicated by the first information;

[0987] The timestamp of the historical data is less than or equal to the perception measurement of a predefined second valid time.

[0988] Optionally, the first processing module is specifically configured to:

[0989] Obtain an inference sample including a target communication measurement and a target perception measurement;

[0990] Wherein, the first information includes the target communication measurement and the target communication measurement; or,

[0991] The first information includes the target communication measurement and a third indication, and the target perception measurement is the perception measurement corresponding to the third indication; or,

[0992] The first information includes the target communication measurement, and the target perception measurement is the perception measurement of the most recent inference sample.

[0993] Optionally, the third indication includes at least one of the following:

[0994] An identifier of an inference sample;

[0995] An identifier of a resource used for a communication measurement result;

[0996] A reporting identifier of a communication measurement result;

[0997] An identifier of a resource used for a perception measurement;

[0998] A reporting identifier of a perception measurement;

[0999] An identifier of a perception measurement.

[1000] Optionally, the device further includes:

[1001] A second sending module, configured to send second information to a fourth device, where the second information includes an inference result of the AI unit and a fourth indication;

[1002] Wherein, the fourth indication is used to indicate at least one of the following:

[1003] A dataset identifier, where the dataset corresponding to the dataset identifier includes perception measurement-related data;

[1004] A configuration identifier of a perception measurement quantity;

[1005] An identifier of a perception measurement quantity;

[1006] An identifier of a perception measurement link;

[1007] An identifier of a perception service;

[1008] An identifier of a perception service type;

[1009] Whether the inference sample uses a perception measurement quantity;

[1010] The perception measurement quantity used by the inference sample;

[1011] The timeliness of the perception measurement quantity used by the inference sample;

[1012] The sending device of the perception measurement quantity used by the inference sample;

[1013] The receiving device of the perception measurement quantity used by the inference sample;

[1014] The coordinates of the perception measurement quantity used by the inference sample;

[1015] The source of the perception measurement quantity used by the inference sample;

[1016] The perception mode of the perception measurement quantity used by the inference sample;

[1017] The processing level of the perception measurement quantity used by the inference sample;

[1018] The perception service of the perception measurement quantity used by the inference sample;

[1019] The use of the perception measurement quantity used by the inference sample;

[1020] The performance index of the perception measurement quantity used by the inference sample;

[1021] The quantity of the perception measurement quantity used by the inference sample;

[1022] The proportion of the perception measurement quantity used by the inference sample;

[1023] Whether the number of perception measurement quantities used in the inference sample meets the minimum quantity threshold;

[1024] Whether the proportion of perception measurement quantities used in the inference sample meets the minimum proportion threshold;

[1025] The proportion of perception measurement quantities that meet timeliness requirements among the perception measurement quantities used in the inference sample;

[1026] The number of perception measurement quantities that meet timeliness requirements among the perception measurement quantities used in the inference sample;

[1027] Configuration information of the target signal;

[1028] Wherein, the target signal is the target signal corresponding to the perception measurement quantity used in the inference sample.

[1029] Figure 22 The structure diagram of the model inference device provided by the embodiment of the present application is shown. This model inference device can be applied to the second device. As Figure 22 shown, the model inference device 920 includes:

[1030] A receiving module 921, configured to receive a first request from a first device, where the first request is used to request perception measurement-related data required for model inference;

[1031] A processing module 922, configured to perform a first operation, where the first operation includes any one of the following:

[1032] Based on the first request, send a target signal;

[1033] Based on the first request, determine the configuration information of the target signal;

[1034] Based on the first request, send the configuration information of the target signal;

[1035] Based on the first request, send perception measurement-related data;

[1036] Wherein, the target signal is a signal used for perception.

[1037] Optionally, the first request includes at least one of the following information:

[1038] Information for indicating that the AI unit is in the inference stage;

[1039] A dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data;

[1040] A configuration identifier of the perception measurement quantity;

[1041] An identifier of the perception measurement quantity;

[1042] Information for indicating the perceptual characteristics of the target data set;

[1043] Identification of the target data set;

[1044] Configuration information of the perceptual measurement quantities required for model inference;

[1045] Information for indicating the number threshold of the perceptual measurement quantities required for model inference;

[1046] Information for indicating the source of the perceptual measurement quantities required for model inference;

[1047] Information for indicating the types of the perceptual measurement quantities required for model inference;

[1048] Information for indicating the perceptual mode of the perceptual measurement quantities required for model inference;

[1049] Information for indicating the perceptual requirements;

[1050] Configuration information of the target signal;

[1051] Information of the sending device of the target signal;

[1052] Information of the receiving device of the target signal;

[1053] Wherein, the target data set is the data set used by the AI unit in the training phase;

[1054] The target signal is a signal used for perception.

[1055] Figure 23 The structural diagram of the model inference device provided by the embodiment of the present application is shown. The model inference device can be applied to a third device. As Figure 23 shown, the model inference device 930 includes:

[1056] A sending module 931, configured to send first information to a first device, where the first information includes at least one of communication measurement related data and perceptual measurement related data;

[1057] The first information includes at least one of the following:

[1058] Target communication measurement quantities and target communication measurement quantities, and the target communication measurement quantities and the target communication measurement quantities are determined to belong to the same inference sample;

[1059] Target communication measurement quantities and a third indication, and the target communication measurement quantities and the perceptual measurement quantities indicated by the third indication are determined to belong to the same inference sample;

[1060] Target communication measurement quantities, and the target communication measurement quantities and the perceptual measurement quantities of the most recent inference sample are determined to belong to the same inference sample;

[1061] Or,

[1062] The first information includes at least one of the following:

[1063] A dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data;

[1064] A configuration identifier of a perception measurement quantity;

[1065] An identifier of a perception measurement quantity;

[1066] An identifier of a perception measurement link;

[1067] An identifier of a perception service;

[1068] An identifier of a perception service type;

[1069] A perception measurement quantity;

[1070] A timestamp of a perception measurement quantity;

[1071] Information about the sending device of a perception measurement quantity;

[1072] Coordinate information of a perception measurement quantity;

[1073] Information for indicating a performance metric of a perception measurement quantity;

[1074] Information for indicating the source of a perception measurement quantity;

[1075] Information for indicating the type of a perception measurement quantity;

[1076] Information for indicating the use of a perception measurement quantity;

[1077] Information for indicating the perception mode of a perception measurement quantity;

[1078] A communication measurement quantity;

[1079] A communication measurement resource identifier;

[1080] A timestamp of a communication measurement quantity;

[1081] Information for indicating a first time window;

[1082] Information for indicating a first valid time;

[1083] A configuration identifier of a target signal;

[1084] Configuration information of a target signal;

[1085] Information about the sending device of a target signal;

[1086] Information about the receiving device of a target signal;

[1087] Among them, the target signal is a signal used for sensing.

[1088] Optionally, the third indication includes at least one of the following:

[1089] The identifier of the inference sample;

[1090] The identifier of the resource used for the communication measurement result;

[1091] The reporting identifier of the communication measurement result;

[1092] The identifier of the resource used for the sensing measurement quantity;

[1093] The reporting identifier of the sensing measurement quantity;

[1094] The identifier of the sensing measurement quantity.

[1095] Figure 24 The structural diagram of the model inference device provided by the embodiment of the present application is shown. The model inference device can be applied to the fourth device. As Figure 24 shown, the model inference device 940 includes:

[1096] A receiving module 941, configured to receive second information from a first device, where the second information includes an inference result and a fourth indication, and the inference result is obtained by an AI unit using an inference sample;

[1097] Among them, the fourth indication is used to indicate at least one of the following:

[1098] The dataset identifier, and the dataset corresponding to the dataset identifier includes sensing measurement-related data;

[1099] The configuration identifier of the sensing measurement quantity;

[1100] The identifier of the sensing measurement quantity;

[1101] The identifier of the sensing measurement link;

[1102] The identifier of the sensing service;

[1103] The identifier of the sensing service type;

[1104] Whether the inference sample uses a sensing measurement quantity;

[1105] The sensing measurement quantity used by the inference sample;

[1106] The timeliness of the sensing measurement quantity used by the inference sample;

[1107] The sending device of the sensing measurement quantity used by the inference sample;

[1108] A receiving device for the perception measurement quantity used in the inference sample;

[1109] The coordinates of the perception measurement quantity used in the inference sample;

[1110] The source of the perception measurement quantity used in the inference sample;

[1111] The perception mode of the perception measurement quantity used in the inference sample;

[1112] The processing level of the perception measurement quantity used in the inference sample;

[1113] The perception service of the perception measurement quantity used in the inference sample;

[1114] The use of the perception measurement quantity used in the inference sample;

[1115] The performance index of the perception measurement quantity used in the inference sample;

[1116] The quantity of the perception measurement quantity used in the inference sample;

[1117] The ratio of the perception measurement quantity used in the inference sample;

[1118] Whether the quantity of the perception measurement quantity used in the inference sample meets the minimum quantity threshold;

[1119] Whether the ratio of the perception measurement quantity used in the inference sample meets the minimum ratio threshold;

[1120] The ratio of the perception measurement quantity used in the inference sample that meets timeliness;

[1121] The quantity of the perception measurement quantity used in the inference sample that meets timeliness;

[1122] The configuration information of the target signal;

[1123] Wherein, the target signal is the target signal corresponding to the perception measurement quantity used in the inference sample.

[1124] The above device in the embodiments of the present application may be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal or other devices other than the terminal. Exemplarily, the terminal may include, but is not limited to, the types of terminals listed above, and other devices may be a server, a Network Attached Storage (NAS), etc., which are not specifically limited in the embodiments of the present application.

[1125] The above device provided by the embodiments of the present application can achieve Figures 3 to 20The various processes implemented by the method embodiments achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[1126] As Figure 25 shown, an embodiment of the present application further provides a communication device 1100, including a processor 1101 and a memory 1102. A program or instruction that can run on the processor 1101 is stored on the memory 1102. When the program or instruction is executed by the processor 1101, it implements the various steps of the above-mentioned method embodiments of model inference on the first device side, or implements the various steps of the above-mentioned method embodiments of model inference on the second device side, or implements the various steps of the above-mentioned method embodiments of model inference on the third device side, or implements the various steps of the above-mentioned method embodiments of model inference on the fourth device side, and can achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[1127] An embodiment of the present application further provides a communication device, including a processor and a communication interface. The processor is used to: obtain an inference sample, where the inference sample is determined based on communication measurement-related data and perception measurement-related data; input the inference sample into an artificial intelligence AI unit to obtain an inference result.

[1128] An embodiment of the present application further provides a communication device, including a processor and a communication interface. The communication interface is used to: receive a first request from a first device, where the first request is used to request perception measurement-related data required for model inference; the processor is used to: perform a first operation, where the first operation includes any one of the following: based on the first request, send a target signal; based on the first request, determine configuration information of the target signal; based on the first request, send the configuration information of the target signal; based on the first request, send perception measurement-related data; where the target signal is a signal used for perception.

[1129] The embodiment of the present application further provides a communication device, including a processor and a communication interface. The communication interface is configured to: send first information to a first device, where the first information includes at least one of communication measurement-related data and perception measurement-related data; the first information includes at least one of the following: a target communication measurement quantity and a target communication measurement quantity, and the target communication measurement quantity and the target communication measurement quantity are determined to belong to the same inference sample; a target communication measurement quantity and a third indication, and the target communication measurement quantity and the perception measurement quantity indicated by the third indication are determined to belong to the same inference sample; a target communication measurement quantity, and the target communication measurement quantity and the perception measurement quantity of the most recent inference sample are determined to belong to the same inference sample; or, the first information includes at least one of the following: a dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data; a configuration identifier of a perception measurement quantity; an identifier of a perception measurement quantity; an identifier of a perception measurement link; an identifier of a perception service; an identifier of a perception service type; a perception measurement quantity; a timestamp of a perception measurement quantity; information about the sending device of a perception measurement quantity; coordinate information of a perception measurement quantity; information for indicating a performance indicator of a perception measurement quantity; information for indicating the source of a perception measurement quantity; information for indicating the type of a perception measurement quantity; information for indicating the use of a perception measurement quantity; information for indicating the perception mode of a perception measurement quantity; a communication measurement quantity; a communication measurement resource identifier; a timestamp of a communication measurement quantity; information for indicating a first time window; information for indicating a first effective time; a configuration identifier of a target signal; configuration information of a target signal; information about the sending device of a target signal; information about the receiving device of a target signal; where the target signal is a signal used for perception.

[1130] An embodiment of this application further provides a communication device, including a processor and a communication interface. Wherein, the communication interface is configured to: receive second information from a first device, where the second information includes an inference result and a fourth indication, and the inference result is obtained by an AI unit using inference samples; wherein, the fourth indication is used to indicate at least one of the following: a dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data; a configuration identifier of a perception measurement quantity; an identifier of a perception measurement quantity; an identifier of a perception measurement link; an identifier of a perception service; an identifier of a perception service type; whether the inference sample uses a perception measurement quantity; the perception measurement quantity used by the inference sample; the timeliness of the perception measurement quantity used by the inference sample; the sending device of the perception measurement quantity used by the inference sample; the receiving device of the perception measurement quantity used by the inference sample; the coordinates of the perception measurement quantity used by the inference sample; the source of the perception measurement quantity used by the inference sample; the perception mode of the perception measurement quantity used by the inference sample; the processing level of the perception measurement quantity used by the inference sample; the perception service of the perception measurement quantity used by the inference sample; the use of the perception measurement quantity used by the inference sample; the performance index of the perception measurement quantity used by the inference sample; the quantity of the perception measurement quantity used by the inference sample; the proportion of the perception measurement quantity used by the inference sample; whether the quantity of the perception measurement quantity used by the inference sample meets a minimum quantity threshold; whether the proportion of the perception measurement quantity used by the inference sample meets a minimum proportion threshold; the proportion of the perception measurement quantity that meets the timeliness among the perception measurement quantities used by the inference sample; the quantity of the perception measurement quantity that meets the timeliness among the perception measurement quantities used by the inference sample; configuration information of a target signal; wherein, the target signal is the target signal corresponding to the perception measurement quantity used by the inference sample.

[1131] The processor of the above communication device is configured to run a program or an instruction to implement the steps in the method embodiment as shown in Figures 3 to 20 and can achieve the same technical effect.

[1132] The above communication device may be a terminal or a network-side device.

[1133] Specifically, Figure 26 FIG. is a schematic hardware structure diagram of a terminal for implementing an embodiment of this application.

[1134] The terminal 1200 includes but is not limited to at least some components such as a radio frequency unit 1201, a network module 1202, an audio output unit 1203, an input unit 1204, a sensor 1205, a display unit 1206, a user input unit 1207, an interface unit 1208, a memory 1209, and a processor 1210.

[1135] Those skilled in the art can understand that the terminal 1200 may further include a power source (such as a battery) for supplying power to each component. The power source can be logically connected to the processor 1210 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. Figure 26 The terminal structure shown in Figure 26 does not limit the terminal. The terminal may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements, which will not be elaborated here.

[1136] It should be understood that in the embodiments of the present application, the input unit 1204 may include a graphics processing unit (GPU) 12041 and a microphone 12042. The graphics processor 12041 processes the image data of static pictures or videos obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1206 may include a display panel 12061, and the display panel 12061 may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1207 includes at least one of a touch panel 12071 and other input devices 12072. The touch panel 12071 is also called a touch screen. The touch panel 12071 may include two parts: a touch detection device and a touch controller. The other input devices 12072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, which will not be elaborated here.

[1137] In the embodiments of the present application, after receiving downlink data from a network-side device, the radio frequency unit 1201 can transmit it to the processor 1210 for processing; in addition, the radio frequency unit 1201 can send uplink data to the network-side device. Generally, the radio frequency unit 1201 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc.

[1138] The memory 1209 can be used to store software programs or instructions and various data. The memory 1209 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area may store an operating system, application programs or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1209 may include volatile memory or non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM). The memory 1209 in the embodiments of the present application includes, but is not limited to, these and any other suitable types of memory.

[1139] The processor 1210 may include one or more processing units; optionally, the processor 1210 integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above modem processor may not be integrated into the processor 1210 either.

[1140] Among them, the processor 1210 is used for:

[1141] Obtain an inference sample, where the inference sample is determined based on communication measurement-related data and perception measurement-related data;

[1142] Input the inference sample into the artificial intelligence AI unit to obtain an inference result.

[1143] Optionally, the perception measurement-related data includes at least one of the following information:

[1144] Perceived measurement quantity;

[1145] Indicator of the perceived measurement quantity;

[1146] Timestamp of the perceived measurement quantity;

[1147] Information on the sending device of the perceived measurement quantity;

[1148] Information on the receiving device of the perceived measurement quantity;

[1149] Coordinate information of the perceived measurement quantity;

[1150] Information for indicating the performance metrics of the perceived measurement quantity;

[1151] Information for indicating the source of the perceived measurement quantity;

[1152] Information for indicating the type of the perceived measurement quantity;

[1153] Information for indicating the perception mode of the perceived measurement quantity;

[1154] Configuration information of the target signal;

[1155] Information on the sending device of the target signal;

[1156] Information on the receiving device of the target signal;

[1157] Wherein, the target signal is a signal used for perception.

[1158] Optionally, the radio frequency unit 1201 is configured to:

[1159] Send a first request to a second device, where the first request is used to request perception measurement-related data required for model inference. Optionally, the first request includes at least one of the following information:

[1160] Information for indicating that the AI unit is in the inference stage;

[1161] Dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data;

[1162] Configuration identifier of the perceived measurement quantity;

[1163] Identifier of the perceived measurement quantity;

[1164] Information for indicating the perception characteristics of the target dataset;

[1165] Identifier of the target dataset;

[1166] Configuration information of the perceived measurement quantity required for model inference;

[1167] Information indicating the number threshold of perceptual measurement quantities required for model inference;

[1168] Information indicating the source of perceptual measurement quantities required for model inference;

[1169] Information indicating the types of perceptual measurement quantities required for model inference;

[1170] Information indicating the perception mode of perceptual measurement quantities required for model inference;

[1171] Information indicating the perception requirements;

[1172] Configuration information of the target signal;

[1173] Information of the sending device of the target signal;

[1174] Information of the receiving device of the target signal;

[1175] Wherein, the target data set is the data set used by the AI unit in the training phase;

[1176] The target signal is a signal used for perception.

[1177] Optionally, the processor 1210 is further configured to perform at least one of the following:

[1178] Obtain an inference sample based on the timestamp of the communication measurement quantity, the timestamp of the perceptual measurement quantity, and the effective duration of the perceptual measurement quantity;

[1179] Obtain an inference sample based on the timestamp corresponding to the prediction result of the AI unit, the timestamp of the perceptual measurement quantity, and the effective duration of the perceptual measurement quantity;

[1180] Obtain an inference sample based on the first indication and the timestamp of the communication measurement quantity;

[1181] Obtain an inference sample based on the first indication and the timestamp corresponding to the prediction result of the AI unit;

[1182] Obtain an inference sample based on whether the second indication is received;

[1183] Wherein, the first indication is used to indicate the expiration time or the expiration time difference of the perceptual measurement quantity;

[1184] The second indication is used to indicate the expiration of the perceptual measurement quantity.

[1185] Optionally, the determination method of the effective duration of the perceptual measurement quantity includes at least one of the following:

[1186] When a first effective duration is pre-configured or defined, the effective duration of the perceptual measurement quantity is the first effective duration;

[1187] When a second effective duration is pre-configured or defined and the target signal carries a time adjustment value, the effective duration of the sensed measurement quantity is determined according to the second effective duration and the time adjustment value;

[1188] When the target signal carries a third effective duration, the effective duration of the sensed measurement quantity is the third effective duration;

[1189] Wherein, the target signal is a signal used for sensing.

[1190] Optionally, the processor 1210 is further configured to perform at least one of the following:

[1191] When the time corresponding to the timestamp of the communication measurement quantity is earlier than the first time, obtain an inference sample including communication measurement-related data and sensed measurement-related data;

[1192] When the time corresponding to the timestamp of the prediction result of the AI unit is earlier than the first time, obtain an inference sample including communication measurement-related data and sensed measurement-related data;

[1193] When the time corresponding to the timestamp of the communication measurement quantity is earlier than the second time, obtain an inference sample including communication measurement-related data and sensed measurement-related data;

[1194] When the time corresponding to the timestamp of the prediction result of the AI unit is earlier than the second time, obtain an inference sample including communication measurement-related data and sensed measurement-related data;

[1195] When the first device does not receive the second indication, obtain an inference sample including communication measurement-related data and sensed measurement-related data;

[1196] Wherein, the first time is the time corresponding to the timestamp of the sensed measurement quantity superimposed with the effective duration of the sensed measurement quantity;

[1197] The second time is the expiration time of the sensed measurement quantity determined based on the first indication.

[1198] Optionally, the radio frequency unit 1201 is configured to:

[1199] Receive first information from a third device, where the first information includes at least one of communication measurement-related data and sensed measurement-related data;

[1200] The processor 1210 is further configured to:

[1201] Obtain an inference sample based on the first information; or, obtain an inference sample based on the first information and the stored historical data;

[1202] Among them, the historical data includes at least one of communication measurement-related data and perception measurement-related data.

[1203] Optionally, the first information includes at least one of the following:

[1204] A dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data;

[1205] A configuration identifier of a perception measurement quantity;

[1206] An identifier of a perception measurement quantity;

[1207] An identifier of a perception measurement link;

[1208] An identifier of a perception service;

[1209] An identifier of a perception service type;

[1210] A perception measurement quantity;

[1211] A timestamp of a perception measurement quantity;

[1212] Information about the sending device of a perception measurement quantity;

[1213] Coordinate information of a perception measurement quantity;

[1214] Information for indicating a performance metric of a perception measurement quantity;

[1215] Information for indicating the source of a perception measurement quantity;

[1216] Information for indicating the type of a perception measurement quantity;

[1217] Information for indicating the use of a perception measurement quantity;

[1218] Information for indicating the perception mode of a perception measurement quantity;

[1219] A communication measurement quantity;

[1220] A communication measurement resource identifier;

[1221] A timestamp of a communication measurement quantity;

[1222] Information for indicating a first time window;

[1223] Information for indicating a first valid time;

[1224] A configuration identifier of a target signal;

[1225] Configuration information of a target signal;

[1226] Information about the sending device of a target signal;

[1227] Information of the receiving device of the target signal;

[1228] Wherein, the target signal is a signal used for sensing.

[1229] Optionally, the processor 1210 is further configured to perform at least one of the following:

[1230] When the time difference between the timestamp of the sensing measurement quantity and the timestamp of the communication measurement quantity is less than or equal to the first time window indicated by the first information, obtain an inference sample including communication measurement-related data and sensing measurement-related data;

[1231] When the time difference between the timestamp of the sensing measurement quantity and the timestamp of the communication measurement quantity is less than or equal to a predefined second time window, obtain an inference sample including communication measurement-related data and sensing measurement-related data.

[1232] Optionally, the first information includes the target sensing measurement quantity and the timestamp of the target sensing measurement quantity;

[1233] The processor 1210 is further configured to:

[1234] Obtain an inference sample including the target communication measurement quantity and the target sensing measurement quantity;

[1235] Wherein, the target communication measurement quantity includes at least one of the following:

[1236] The communication measurement quantity whose difference between the timestamp of the historical data and the timestamp of the target sensing measurement quantity is less than or equal to the first time window indicated by the first information;

[1237] The communication measurement quantity whose difference between the timestamp of the historical data and the timestamp of the target sensing measurement quantity is less than or equal to a predefined second time window.

[1238] Optionally, the first information includes the target communication measurement quantity and the timestamp of the target communication measurement quantity;

[1239] The processor 1210 is further configured to:

[1240] Obtain an inference sample including the target communication measurement quantity and the target sensing measurement quantity;

[1241] Wherein, the target sensing measurement quantity includes at least one of the following:

[1242] The sensing measurement quantity whose time difference between the timestamp of the historical data and the timestamp of the target communication measurement quantity is less than or equal to the first time window indicated by the first information;

[1243] The timestamp of the historical data is less than or equal to the perceived measurement amount of the first effective time indicated by the first information;

[1244] The timestamp of the historical data is less than or equal to the perceived measurement amount of the predefined second effective time.

[1245] Optionally, the processor 1210 is further configured to:

[1246] Obtain an inference sample including a target communication measurement amount and a target perceived measurement amount;

[1247] Wherein, the first information includes the target communication measurement amount and the target communication measurement amount; or,

[1248] The first information includes the target communication measurement amount and a third indication, and the target perceived measurement amount is the perceived measurement amount corresponding to the third indication; or,

[1249] The first information includes the target communication measurement amount, and the target perceived measurement amount is the perceived measurement amount of the most recent inference sample.

[1250] Optionally, the third indication includes at least one of the following:

[1251] The identifier of the inference sample;

[1252] The identifier of the resource used for the communication measurement result;

[1253] The reporting identifier of the communication measurement result;

[1254] The identifier of the resource used for the perceived measurement amount;

[1255] The reporting identifier of the perceived measurement amount;

[1256] The identifier of the perceived measurement amount.

[1257] Optionally, the radio frequency unit 1201 is further configured to:

[1258] Send second information to a fourth device, where the second information includes the inference result of the AI unit and a fourth indication;

[1259] Wherein, the fourth indication is used to indicate at least one of the following:

[1260] The dataset identifier, and the dataset corresponding to the dataset identifier includes perceived measurement-related data;

[1261] The configuration identifier of the perceived measurement amount;

[1262] The identifier of the perceived measurement amount;

[1263] The identifier of the perceived measurement link;

[1264] Identifier of the perception service;

[1265] Identifier of the perception service type;

[1266] Whether the inference sample uses perception measurement quantities;

[1267] Perception measurement quantities used by the inference sample;

[1268] Timeliness of the perception measurement quantities used by the inference sample;

[1269] Transmitting device of the perception measurement quantities used by the inference sample;

[1270] Receiving device of the perception measurement quantities used by the inference sample;

[1271] Coordinates of the perception measurement quantities used by the inference sample;

[1272] Source of the perception measurement quantities used by the inference sample;

[1273] Perception mode of the perception measurement quantities used by the inference sample;

[1274] Processing level of the perception measurement quantities used by the inference sample;

[1275] Perception service of the perception measurement quantities used by the inference sample;

[1276] Purpose of the perception measurement quantities used by the inference sample;

[1277] Performance indicators of the perception measurement quantities used by the inference sample;

[1278] Quantity of the perception measurement quantities used by the inference sample;

[1279] Ratio of the perception measurement quantities used by the inference sample;

[1280] Whether the quantity of the perception measurement quantities used by the inference sample meets the minimum quantity threshold;

[1281] Whether the ratio of the perception measurement quantities used by the inference sample meets the minimum ratio threshold;

[1282] Ratio of the perception measurement quantities that meet the timeliness among the perception measurement quantities used by the inference sample;

[1283] Quantity of the perception measurement quantities that meet the timeliness among the perception measurement quantities used by the inference sample;

[1284] Configuration information of the target signal;

[1285] Wherein, the target signal is the target signal corresponding to the perception measurement quantities used by the inference sample.

[1286] In summary, in the embodiments of the present application, by proposing a method for collecting model inference data assisted by sensing, a network node can obtain sensing information to expand the data information for model inference, thereby improving the inference accuracy of the AI model.

[1287] It can be understood that the implementation processes of the various implementation manners mentioned in this embodiment can Figures 3 to 20 be described in the relevant descriptions of the method embodiments and achieve the same or corresponding technical effects. To avoid repetition, they are not elaborated herein.

[1288] Specifically, the embodiments of the present application further provide a network-side device. As Figure 27 shown, the network-side device 1300 includes: an antenna 131, a radio frequency device 132, a baseband device 133, a processor 134, and a memory 135. The antenna 131 is connected to the radio frequency device 132. In the uplink direction, the radio frequency device 132 receives information through the antenna 131 and sends the received information to the baseband device 133 for processing. In the downlink direction, the baseband device 133 processes the information to be sent and sends it to the radio frequency device 132. After processing the received information, the radio frequency device 132 sends it out through the antenna 131.

[1289] In the above embodiments, the methods executed by the first device, the second device, the third device, and the fourth device can all be implemented in the baseband device 133, and the baseband device 133 includes a baseband processor.

[1290] The baseband device 133 may include, for example, at least one baseband board, and a plurality of chips are arranged on the baseband board. As Figure 27 shown, one of the chips is, for example, a baseband processor, which is connected to the memory 135 through a bus interface to call the program in the memory 135 and execute the operations of the network device shown in the above method embodiments.

[1291] The network-side device may further include a network interface 136, and this interface is, for example, a Common Public Radio Interface (CPRI).

[1292] Specifically, the network-side device 1300 in the embodiments of the present application further includes: instructions or programs stored on the memory 135 and executable on the processor 134. The processor 134 calls the instructions or programs in the memory 135 to execute Figures 21 to 24 the methods executed by the respective modules shown, and achieves the same technical effects. To avoid repetition, they are not elaborated herein.

[1293] Specifically, the embodiments of the present application further provide a network-side device. As Figure 28As shown in the figure, the network-side device 1400 includes: a processor 1401, a network interface 1402, and a memory 1403. Among them, the network interface 1402 is, for example, a Common Public Radio Interface (CPRI).

[1294] Specifically, the network-side device 1400 in the embodiments of the present application further includes: instructions or programs stored on the memory 1403 and executable on the processor 1401. The processor 1401 calls the instructions or programs in the memory 1403 to execute Figures 21 to 24 the methods executed by the modules shown in the figure and achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[1295] The embodiments of the present application further provide a readable storage medium. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, they implement Figures 3 to 20 each process of the method embodiments and can achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[1296] Among them, the processor 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 disks, or optical discs, etc. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[1297] The embodiments of the present application further provide a chip. The chip 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 Figures 3 to 20 each process of the method embodiments and can achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[1298] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[1299] The embodiments of the present application further provide a computer program / program product. The computer program / program product is stored in a storage medium. The computer program / program product is executed by at least one processor to implement Figures 3 to 20 each process of the method embodiments and can achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[1300] The embodiments of the present application further provide a communication system, including: a first device and a second device. The first device can be used to execute the steps of the model inference method on the first device side as described above, and the second device can be used to execute the steps of the model inference method on the second device side as described above.

[1301] Optionally, the communication system further includes a third device, which can be used to execute the steps of the model inference method on the third device side as described above.

[1302] Optionally, the communication system further includes a fourth device, which can be used to execute the steps of the model inference method on the fourth device side as described above.

[1303] It should be noted that in this document, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[1304] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of a computer software product plus a necessary general hardware platform, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disc, etc.) and includes several instructions for causing a terminal or a network-side device to execute the methods described in various embodiments of the present application.

[1305] The embodiments of the present application have been described above in conjunction with the accompanying drawings, but the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms of embodiments without departing from the purpose of the present application and the scope protected by the claims, and these embodiments are all within the protection scope of the present application.

Claims

1. A model inference method, characterized in that, Including: The first device obtains an inference sample, which is determined based on communication measurement-related data and perception measurement-related data; The first device inputs the inference sample into an artificial intelligence (AI) unit to obtain an inference result.

2. The method according to claim 1, characterized in that The perception measurement-related data includes at least one of the following information: Perception measurement quantity; Indicator of the perception measurement quantity; Timestamp of the perception measurement quantity; Information of the sending device of the perception measurement quantity; Information of the receiving device of the perception measurement quantity; Coordinate information of the perception measurement quantity; Information for indicating the performance index of the perception measurement quantity; Information for indicating the source of the perception measurement quantity; Information for indicating the type of the perception measurement quantity; Information for indicating the perception mode of the perception measurement quantity; Configuration information of the target signal; Information of the sending device of the target signal; Information of the receiving device of the target signal; Wherein, the target signal is a signal used for perception.

3. The method according to claim 1 or 2, characterized in that, The method further includes: The first device sends a first request to the second device, and the first request is used to request the perception measurement-related data required for model inference.

4. The method according to claim 3, wherein The first request includes at least one of the following information: Information for indicating that the AI unit is in the inference stage; Dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data; Configuration identifier of the perception measurement quantity; Identifier of the perception measurement quantity; Information for indicating the perception characteristics of the target dataset; Identifier of the target dataset; Configuration information of the perception measurement quantity required for model inference; Information for indicating the number threshold of the perception measurement quantity required for model inference; Information for indicating the source of the perception measurement quantity required for model inference; Information for indicating the type of the perception measurement quantity required for model inference; Information for indicating the perception mode of the perception measurement quantity required for model inference; Information for indicating the perception requirement; Configuration information of the target signal; Information of the sending device of the target signal; Information of the receiving device of the target signal; Wherein, the target dataset is the dataset used by the AI unit in the training stage; The target signal is a signal used for perception.

5. The method according to any one of claims 1 to 4, characterized in that The first device obtains the inference sample, including at least one of the following: The first device obtains the inference sample based on the timestamp of the communication measurement quantity, the timestamp of the perception measurement quantity, and the effective duration of the perception measurement quantity; The first device obtains the inference sample based on the timestamp corresponding to the prediction result of the AI unit, the timestamp of the perception measurement quantity, and the effective duration of the perception measurement quantity; The first device obtains the inference sample based on the first indication and the timestamp of the communication measurement quantity; The first device obtains the inference sample based on the first indication and the timestamp corresponding to the prediction result of the AI unit; The first device obtains the inference sample based on whether the second indication is received; Wherein, the first indication is used to indicate the expiration time or the expiration time difference of the perception measurement quantity; The second indication is used to indicate the expiration of the perception measurement quantity.

6. The method according to claim 5, characterized in that The determination method of the effective duration of the perception measurement quantity includes at least one of the following: When a first effective duration is pre-configured or defined, the effective duration of the perception measurement quantity is the first effective duration; When a second effective duration is pre-configured or defined and the target signal carries a time adjustment value, the effective duration of the sensed measurement quantity is determined according to the second effective duration and the time adjustment value; When the target signal carries a third effective duration, the effective duration of the sensed measurement quantity is the third effective duration; Wherein, the target signal is a signal used for sensing.

7. The method according to claim 5 or 6, characterized in that, The first device obtains an inference sample based on the timestamp of the communication measurement quantity, the timestamp of the sensed measurement quantity, and the effective duration of the sensed measurement quantity, including: When the time corresponding to the timestamp of the communication measurement quantity is earlier than the first time, the first device obtains an inference sample including communication measurement-related data and sensed measurement-related data; The first device obtains an inference sample based on the timestamp corresponding to the prediction result of the AI unit, the timestamp of the sensed measurement quantity, and the effective duration of the sensed measurement quantity, including: When the timestamp corresponding to the prediction result of the AI unit is earlier than the first time, the first device obtains an inference sample including communication measurement-related data and sensed measurement-related data; The first device obtains an inference sample based on the first indication and the timestamp of the communication measurement quantity, including: When the time corresponding to the timestamp of the communication measurement quantity is earlier than the second time, the first device obtains an inference sample including communication measurement-related data and sensed measurement-related data; The first device obtains an inference sample based on the first indication and the timestamp corresponding to the prediction result of the AI unit, including: When the timestamp corresponding to the prediction result of the AI unit is earlier than the second time, the first device obtains an inference sample including communication measurement-related data and sensed measurement-related data; The first device obtains an inference sample based on whether the second indication is received, including: When the first device does not receive the second indication, the first device obtains an inference sample including communication measurement-related data and sensed measurement-related data; Wherein, the first time is the time corresponding to the timestamp of the sensed measurement quantity plus the effective duration of the sensed measurement quantity; The second time is the expiration time of the sensed measurement quantity determined based on the first indication.

8. The method according to any one of claims 1 to 4, characterized in that The first device obtains an inference sample, including: The first device receives first information from a third device, and the first information includes at least one of communication measurement-related data and sensed measurement-related data; The first device obtains an inference sample based on the first information; or, the first device obtains an inference sample based on the first information and stored historical data; Wherein, the historical data includes at least one of communication measurement-related data and sensed measurement-related data.

9. The method according to claim 8, wherein The first information includes at least one of the following: A dataset identifier, and the dataset corresponding to the dataset identifier includes sensed measurement-related data; A configuration identifier of the sensed measurement quantity; An identifier of the sensed measurement quantity; An identifier of the sensed measurement link; An identifier of the sensing service; An identifier of the sensing service type; The sensed measurement quantity; The timestamp of the sensed measurement quantity; Information about the sending device of the sensed measurement quantity; Coordinate information of the sensed measurement quantity; Information for indicating a performance metric of a sensed measurement quantity; Information for indicating the source of a sensed measurement quantity; Information for indicating the type of a sensed measurement quantity; Information for indicating the use of a sensed measurement quantity; Information for indicating the sensing mode of a sensed measurement quantity; Communication measurement quantity; Communication measurement resource identifier; Timestamp of a communication measurement quantity; Information for indicating a first time window; Information for indicating a first valid time; Configuration identifier of a target signal; Configuration information of a target signal; Information about the transmitting device of a target signal; Information about the receiving device of a target signal; Wherein, the target signal is a signal used for sensing.

10. The method according to claim 8 or 9, characterized in that The first device obtains an inference sample, including at least one of the following: When the time difference between the timestamp of the sensed measurement quantity and the timestamp of the communication measurement quantity is less than or equal to the first time window indicated by the first information, the first device obtains an inference sample including communication measurement-related data and sensed measurement-related data; When the time difference between the timestamp of the sensed measurement quantity and the timestamp of the communication measurement quantity is less than or equal to a predefined second time window, the first device obtains an inference sample including communication measurement-related data and sensed measurement-related data.

11. The method according to claim 8 or 9, characterized in that, The first information includes a target sensed measurement quantity and the timestamp of the target sensed measurement quantity; The first device obtains an inference sample based on the first information and stored historical data, including: The first device obtains an inference sample including a target communication measurement quantity and the target sensed measurement quantity; Wherein, the target communication measurement quantity includes at least one of the following: A communication measurement quantity whose time difference between the timestamp of the historical data and the timestamp of the target sensed measurement quantity is less than or equal to the first time window indicated by the first information; A communication measurement quantity whose time difference between the timestamp of the historical data and the timestamp of the target sensed measurement quantity is less than or equal to a predefined second time window.

12. The method according to claim 8 or 9, characterized in that, The first information includes a target communication measurement quantity and the timestamp of the target communication measurement quantity; The first device obtains an inference sample based on the first information and stored historical data, including: The first device obtains an inference sample including the target communication measurement quantity and a target sensed measurement quantity; Wherein, the target sensed measurement quantity includes at least one of the following: A sensed measurement quantity whose time difference between the timestamp of the historical data and the timestamp of the target communication measurement quantity is less than or equal to the first time window indicated by the first information; A sensed measurement quantity whose timestamp of the historical data is less than or equal to the first valid time indicated by the first information; A sensed measurement quantity whose timestamp of the historical data is less than or equal to a predefined second valid time.

13. The method according to claim 8 or 9, characterized in that, The first device obtains an inference sample based on the first information, including: The first device obtains an inference sample including a target communication measurement quantity and a target sensed measurement quantity; Wherein, the first information includes the target communication measurement quantity and the target communication measurement quantity; or, The first information includes the target communication measurement quantity and a third indication, and the target sensed measurement quantity is the sensed measurement quantity corresponding to the third indication; or, The first information includes the target communication measurement quantity, and the target perception measurement quantity is the perception measurement quantity of the most recent inference sample.

14. The method according to claim 13, wherein The third indication includes at least one of the following: The identifier of the inference sample; The identifier of the resource used for the communication measurement result; The reporting identifier of the communication measurement result; The identifier of the resource used for the perception measurement quantity; The reporting identifier of the perception measurement quantity; The identifier of the perception measurement quantity.

15. The method according to any one of claims 1 to 14, characterized in that, The method further includes: The first device sends second information to a fourth device, where the second information includes the inference result of the AI unit and a fourth indication; Wherein, the fourth indication is used to indicate at least one of the following: The dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data; The configuration identifier of the perception measurement quantity; The identifier of the perception measurement quantity; The identifier of the perception measurement link; The identifier of the perception service; The identifier of the perception service type; Whether the inference sample uses a perception measurement quantity; The perception measurement quantity used by the inference sample; The timeliness of the perception measurement quantity used by the inference sample; The sending device of the perception measurement quantity used by the inference sample; The receiving device of the perception measurement quantity used by the inference sample; The coordinates of the perception measurement quantity used by the inference sample; The source of the perception measurement quantity used by the inference sample; The perception mode of the perception measurement quantity used by the inference sample; The processing level of the perception measurement quantity used by the inference sample; The perception service of the perception measurement quantity used by the inference sample; The use of the perception measurement quantity used by the inference sample; The performance index of the perception measurement quantity used by the inference sample; The quantity of the perception measurement quantity used by the inference sample; The proportion of the perception measurement quantity used by the inference sample; Whether the quantity of the perception measurement quantity used by the inference sample meets the minimum quantity threshold; Whether the proportion of the perception measurement quantity used by the inference sample meets the minimum proportion threshold; The proportion of the perception measurement quantity that meets the timeliness among the perception measurement quantities used by the inference sample; The quantity of the perception measurement quantity that meets the timeliness among the perception measurement quantities used by the inference sample; The configuration information of the target signal; Wherein, the target signal is the target signal corresponding to the perception measurement quantity used by the inference sample.

16. A model inference method, characterized in that, Including: The second device receives a first request from the first device, and the first request is used to request perception measurement-related data required for model inference; The second device performs a first operation, where the first operation includes any one of the following: The second device sends a target signal based on the first request; The second device determines the configuration information of the target signal based on the first request; The second device sends the configuration information of the target signal based on the first request; The second device sends perception measurement-related data based on the first request; Wherein, the target signal is a signal used for perception.

17. The method according to claim 16, wherein The first request includes at least one of the following information: Information used to indicate that the AI unit is in the inference stage; The dataset identifier, and the dataset corresponding to the dataset identifier includes perception measurement-related data; The configuration identifier of the perception measurement quantity; The identifier of the perception measurement quantity. Information for indicating the perceptual characteristics of the target data set; Identification of the target data set; Configuration information of the perceptual measurement quantities required for model inference; Information for indicating the number threshold of the perceptual measurement quantities required for model inference; Information for indicating the source of the perceptual measurement quantities required for model inference; Information for indicating the types of the perceptual measurement quantities required for model inference; Information for indicating the perceptual mode of the perceptual measurement quantities required for model inference; Information for indicating the perceptual requirements; Configuration information of the target signal; Information about the sending device of the target signal; Information about the receiving device of the target signal; Wherein, the target data set is the data set used by the AI unit in the training phase; The target signal is a signal used for perception.

18. A model inference device, characterized in that, Applied to the first device, the apparatus includes: A first processing module, configured to obtain an inference sample, where the inference sample is determined based on communication measurement-related data and perceptual measurement-related data; A second processing module, configured to input the inference sample into an artificial intelligence (AI) unit to obtain an inference result.

19. The device according to claim 18, wherein Further includes: A first sending module, configured to send a first request to a second device, where the first request is used to request perceptual measurement-related data required for model inference.

20. The device according to claim 18 or 19, characterized in that, The first processing module is specifically configured to perform at least one of the following: Obtain an inference sample based on the timestamp of the communication measurement quantity, the timestamp of the perceptual measurement quantity, and the effective duration of the perceptual measurement quantity; Obtain an inference sample based on the timestamp corresponding to the prediction result of the AI unit, the timestamp of the perceptual measurement quantity, and the effective duration of the perceptual measurement quantity; Obtain an inference sample based on a first indication and the timestamp of the communication measurement quantity; Obtain an inference sample based on a first indication and the timestamp corresponding to the prediction result of the AI unit; Obtain an inference sample based on whether a second indication is received; Wherein, the first indication is used to indicate the expiration time or the expiration time difference of the perceptual measurement quantity; The second indication is used to indicate the expiration of the perceptual measurement quantity.

21. The device according to claim 18 or 19, characterized in that, The first processing module includes: A receiving unit, configured to receive first information from a third device, where the first information includes at least one of communication measurement-related data and perceptual measurement-related data; A processing unit, configured to obtain an inference sample based on the first information; or obtain an inference sample based on the first information and stored historical data; Wherein, the historical data includes at least one of communication measurement-related data and perceptual measurement-related data.

22. The device according to any one of claims 18 to 21, characterized in that, Further includes: A second sending module, configured to send second information to a fourth device, where the second information includes the inference result of the AI unit and a fourth indication; Wherein, the fourth indication is used to indicate at least one of the following: A data set identifier, where the data set corresponding to the data set identifier includes perceptual measurement-related data; A configuration identifier of the perceptual measurement quantity; An identifier of the perceptual measurement quantity; An identifier of the perceptual measurement link; An identifier of the perceptual service; An identifier of the perceptual service type; Whether the inference sample uses the perceptual measurement quantity; The perceptual measurement quantity used by the inference sample; The timeliness of the perceptual measurement quantity used by the inference sample; The sending device of the perceptual measurement quantity used by the inference sample; A receiving device for the perception measurement quantities used in the inference sample; The coordinates of the perception measurement quantities used in the inference sample; The source of the perception measurement quantities used in the inference sample; The perception mode of the perception measurement quantities used in the inference sample; The processing level of the perception measurement quantities used in the inference sample; The perception service of the perception measurement quantities used in the inference sample; The use of the perception measurement quantities used in the inference sample; The performance indicators of the perception measurement quantities used in the inference sample; The quantity of the perception measurement quantities used in the inference sample; The proportion of the perception measurement quantities used in the inference sample; Whether the quantity of the perception measurement quantities used in the inference sample meets the minimum quantity threshold; Whether the proportion of the perception measurement quantities used in the inference sample meets the minimum proportion threshold; The proportion of the perception measurement quantities used in the inference sample that meets timeliness; The quantity of the perception measurement quantities used in the inference sample that meets timeliness; The configuration information of the target signal; Wherein, the target signal is the target signal corresponding to the perception measurement quantities used in the inference sample.

23. A model inference device, characterized in that, Applied to a second device, the apparatus includes: A receiving module, configured to receive a first request from a first device, where the first request is used to request perception measurement-related data required for model inference; A processing module, configured to perform a first operation, where the first operation includes any one of the following: The second device sends a target signal based on the first request; The second device determines the configuration information of the target signal based on the first request; The second device sends the configuration information of the target signal based on the first request; The second device sends perception measurement-related data based on the first request; Wherein, the target signal is a signal used for perception.

24. A communication device, characterized in that, Comprising a processor and a memory, the memory stores a program or instructions that can run on the processor, and when the program or instructions are executed by the processor, the steps of the method according to any one of claims 1 to 17 are implemented.

25. A readable storage medium, characterized in that, A program or instructions are stored on the readable storage medium, and when the program or instructions are executed by a processor, the steps of the method according to any one of claims 1 to 17 are implemented.

Images