Model inference method and apparatus

Abstract

The present application relates to the technical field of communications, and discloses a model inference method and apparatus. The model inference method in the embodiments of the present application comprises: a first device acquires an inference sample, wherein the inference sample is determined on the basis of communication measurement-related data and sensing measurement-related data; the first device inputs the inference sample into an AI unit to obtain an inference result.

Description

Model reasoning method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202311782184.7 filed on December 21, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application belongs to the field of communication technology, and specifically relates to a model reasoning method and device. Background Art

[0004] With the development of artificial intelligence (AI) technology, AI technology is expected to be applied to communication technology. For example, in related technologies, it is proposed to use AI neural network models to implement communication functions such as beam prediction, channel state information (CSI) prediction, or positioning services. In related technologies, the data used for model inference (i.e., inference samples) is basically derived from data obtained from communication measurements. However, the data obtained from communication measurements is relatively limited, which limits the inference accuracy of the model. Summary of the Invention

[0005] The embodiments of the present application provide a model reasoning method and device that can solve the problem of limited model reasoning accuracy existing in related technologies.

[0006] In a first aspect, a model inference method is provided, which is performed by a first device, and the method includes:

[0007] The first device obtains an inference sample, where the inference sample is determined based on communication measurement related data and perception measurement related data;

[0008] The first device inputs the inference sample into an artificial intelligence (AI) unit to obtain an inference result.

[0009] In a second aspect, a model inference method is provided, which is performed by a second device, and the method includes:

[0010] 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;

[0011] The second device performs a first operation, where the first operation includes any one of the following:

[0012] The second device sends a target signal based on the first request;

[0013] The second device determines configuration information of the target signal based on the first request;

[0014] The second device sends configuration information of the target signal based on the first request;

[0015] The second device sends the perception measurement related data based on the first request;

[0016] The target signal is a signal used for perception.

[0017] In a third aspect, a model inference method is provided, which is performed by a third device, and the method includes:

[0018] The third device sends first information to the first device, where the first information includes at least one of communication measurement-related data and perception measurement-related data;

[0019] The first information includes at least one of the following:

[0020] a target communication measurement amount and a target communication measurement amount, wherein the target communication measurement amount and the target communication measurement amount are determined to belong to the same inference sample;

[0021] a target communication measurement amount and a third indication, wherein the target communication measurement amount and the perception measurement amount indicated by the third indication are determined to belong to the same inference sample;

[0022] a target communication measurement amount, wherein the target communication measurement amount and a perception measurement amount of a most recent reasoning sample are determined to belong to the same reasoning sample;

[0023] or,

[0024] The first information includes at least one of the following:

[0025] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0026] Configuration identifier of the perception measurement quantity;

[0027] identification of perceptual measurement quantities;

[0028] Identification of the perception measurement link;

[0029] Identification of perceived services;

[0030] Identification of the perceived service type;

[0031] Perceptual measurement quantity;

[0032] timestamps of perceived measurements;

[0033] Information about the sending device that senses the measured quantity;

[0034] Perceive the coordinate information of the measured quantity;

[0035] Information indicating a performance indicator of a perceptual measurement quantity;

[0036] Information indicating the source of the perceived measurement;

[0037] Information indicating the type of the perceptual measurement;

[0038] Information indicating the purpose of the perceived measurement;

[0039] information indicating a perceptual mode of a perceptual measurement quantity;

[0040] Communication measurement quantities;

[0041] Communication measurement resource identifier;

[0042] Timestamps of communication measurements;

[0043] Information indicating the first time window;

[0044] Information indicating a first effective time;

[0045] Configuration identification of the target signal;

[0046] Configuration information of the target signal;

[0047] Information about the device sending the target signal;

[0048] Information on the receiving equipment of the target signal;

[0049] The target signal is a signal used for perception.

[0050] In a fourth aspect, a model inference method is provided, which is executed by a fourth device, and the method includes:

[0051] The fourth device receives second information from the first device, where the second information includes an inference result and a fourth indication, where the inference result is obtained by the AI ​​unit using the inference sample;

[0052] The fourth indication is used to indicate at least one of the following:

[0053] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0054] Configuration identifier of the perception measurement quantity;

[0055] identification of perceptual measurement quantities;

[0056] Identification of the perception measurement link;

[0057] Identification of perceived services;

[0058] Identification of the perceived service type;

[0059] whether the inference sample uses perceptual measurements;

[0060] the perceptual measurement used by the inference sample;

[0061] the timeliness of the perceptual measurements used in the inference samples;

[0062] a sending device of the perceptual measurement quantity used by the inference sample;

[0063] a receiving device of the perceptual measurement quantity used by the inference sample;

[0064] coordinates of the perceptual measurements used by the inference sample;

[0065] the source of the perceptual measurements used in the inference sample;

[0066] a perceptual pattern of perceptual measurements used by the inference sample;

[0067] the level of processing of the perceptual measurements used by the inference samples;

[0068] the perceptual service of the perceptual measurement quantity used by the inference sample;

[0069] the purpose of the perceptual measurements used in the inference sample;

[0070] performance indicators of perceptual measurements used by the inference samples;

[0071] the number of perceptual measurements used by the inference sample;

[0072] the proportion of perceptual measurements used in the inference sample;

[0073] whether the number of perceptual measurements used by the inference sample meets a minimum number threshold;

[0074] whether the ratio of the perceptual measurements used in the inference sample meets a minimum ratio threshold;

[0075] The proportion of perceptual measurements used in the inference sample that meet timeliness requirements;

[0076] The number of perceptual measurements used in the inference sample that meet timeliness requirements;

[0077] Configuration information of the target signal;

[0078] The target signal is a target signal corresponding to the perceptual measurement quantity used by the inference sample.

[0079] In a fifth aspect, a model inference apparatus is provided, applied to a first device, the apparatus comprising:

[0080] A first processing module is configured to obtain an inference sample, where the inference sample is determined based on communication measurement related data and perception measurement related data;

[0081] The second processing module is used to input the reasoning sample into the artificial intelligence AI unit to obtain the reasoning result.

[0082] In a sixth aspect, a model inference apparatus is provided, applied to a second device, the apparatus comprising:

[0083] A receiving module, configured to receive a first request from a first device, wherein the first request is used to request perception measurement related data required for model inference;

[0084] A processing module is configured to perform a first operation, wherein the first operation includes any one of the following:

[0085] Based on the first request, sending a target signal;

[0086] Determining configuration information of a target signal based on the first request;

[0087] Sending configuration information of the target signal based on the first request;

[0088] Sending perception measurement related data based on the first request;

[0089] The target signal is a signal used for perception.

[0090] In a seventh aspect, a model inference apparatus is provided, applied to a third device, the apparatus comprising:

[0091] 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;

[0092] The first information includes at least one of the following:

[0093] a target communication measurement amount and a target communication measurement amount, wherein the target communication measurement amount and the target communication measurement amount are determined to belong to the same inference sample;

[0094] a target communication measurement amount and a third indication, wherein the target communication measurement amount and the perception measurement amount indicated by the third indication are determined to belong to the same inference sample;

[0095] a target communication measurement amount, wherein the target communication measurement amount and a perception measurement amount of a most recent reasoning sample are determined to belong to the same reasoning sample;

[0096] or,

[0097] The first information includes at least one of the following:

[0098] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0099] Configuration identifier of the perception measurement quantity;

[0100] identification of perceptual measurement quantities;

[0101] Identification of the perception measurement link;

[0102] Identification of perceived services;

[0103] Identification of the perceived service type;

[0104] Perceptual measurement quantity;

[0105] timestamps of perceived measurements;

[0106] Information about the sending device that senses the measured quantity;

[0107] Perceive the coordinate information of the measured quantity;

[0108] Information indicating a performance indicator of a perceptual measurement quantity;

[0109] Information indicating the source of the perceived measurement;

[0110] Information indicating the type of the perceptual measurement;

[0111] Information indicating the purpose of the perceived measurement;

[0112] information indicating a perceptual mode of a perceptual measurement quantity;

[0113] Communication measurement quantities;

[0114] Communication measurement resource identifier;

[0115] Timestamps of communication measurements;

[0116] Information indicating the first time window;

[0117] Information indicating a first effective time;

[0118] Configuration identification of the target signal;

[0119] Configuration information of the target signal;

[0120] Information about the device sending the target signal;

[0121] Information on the receiving equipment of the target signal;

[0122] The target signal is a signal used for perception.

[0123] In an eighth aspect, a model reasoning apparatus is provided, applied to the fourth device, the apparatus comprising:

[0124] a receiving module, configured to receive second information from the first device, the second information including an inference result and a fourth indication, the inference result being obtained by the AI ​​unit using the inference sample;

[0125] The fourth indication is used to indicate at least one of the following:

[0126] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0127] Configuration identifier of the perception measurement quantity;

[0128] identification of perceptual measurement quantities;

[0129] Identification of the perception measurement link;

[0130] Identification of perceived services;

[0131] Identification of the perceived service type;

[0132] whether the inference sample uses perceptual measurements;

[0133] the perceptual measurement used by the inference sample;

[0134] the timeliness of the perceptual measurements used in the inference samples;

[0135] a sending device of the perceptual measurement quantity used by the inference sample;

[0136] a receiving device of the perceptual measurement quantity used by the inference sample;

[0137] coordinates of the perceptual measurements used by the inference sample;

[0138] the source of the perceptual measurements used in the inference sample;

[0139] a perceptual pattern of perceptual measurements used by the inference sample;

[0140] the level of processing of the perceptual measurements used by the inference samples;

[0141] the perceptual service of the perceptual measurement quantity used by the inference sample;

[0142] the purpose of the perceptual measurements used in the inference sample;

[0143] performance indicators of perceptual measurements used by the inference samples;

[0144] the number of perceptual measurements used by the inference sample;

[0145] the proportion of perceptual measurements used in the inference sample;

[0146] whether the number of perceptual measurements used by the inference sample meets a minimum number threshold;

[0147] whether the ratio of the perceptual measurements used in the inference sample meets a minimum ratio threshold;

[0148] The proportion of perceptual measurements used in the inference sample that meet timeliness requirements;

[0149] The number of perceptual measurements used in the inference sample that meet timeliness requirements;

[0150] Configuration information of the target signal;

[0151] The target signal is a target signal corresponding to the perceptual measurement quantity used by the inference sample.

[0152] In the ninth aspect, a communication device is provided, which terminal includes a processor and a memory, the memory storing a program or instruction that can be run on the processor, and the program or instruction, when executed by the processor, 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.

[0153] In the tenth aspect, a communication device is provided, including a processor and a communication interface, wherein the processor is used to: obtain an inference sample, the inference sample being determined based on communication measurement-related data and perception measurement-related data; and inputting the inference sample into an artificial intelligence AI unit to obtain an inference result.

[0154] In the eleventh aspect, a communication device is provided, comprising a processor and a communication interface, wherein the communication interface is used 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 used to: perform a first operation, wherein the first operation includes any one of the following: based on the first request, sending a target signal; based on the first request, determining configuration information of the target signal; based on the first request, sending configuration information of the target signal; based on the first request, sending perception measurement-related data; wherein the target signal is a signal used for perception.

[0155] In a twelfth aspect, a communication device is provided, comprising a processor and a communication interface, wherein the communication interface is used to: send first information to a first device, the first information including at least one of communication measurement-related data and perception measurement-related data; the first information including at least one of the following: a target communication measurement amount and a target communication measurement amount, the target communication measurement amount and the target communication measurement amount are determined to belong to the same inference sample; a target communication measurement amount and a third indication, the target communication measurement amount and the perception measurement amount indicated by the third indication are determined to belong to the same inference sample; a target communication measurement amount, the target communication measurement amount and the perception measurement amount of the most recent inference sample are determined to belong to the same inference sample; or, the first information including at least one of the following: a data set identifier, the data set corresponding to the data set identifier includes perception measurement-related data; a perception measurement amount. 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 the perception measurement quantity; information of a sending device of the perception measurement quantity; coordinate information of the perception measurement quantity; information for indicating a performance indicator of the perception measurement quantity; information for indicating a source of the perception measurement quantity; information for indicating a type of the perception measurement quantity; information for indicating a purpose of the perception measurement quantity; information for indicating a perception mode of the perception measurement quantity; a communication measurement quantity; a communication measurement resource identifier; a timestamp of the communication measurement quantity; information for indicating a first time window; information for indicating a first valid time; a configuration identifier of a target signal; configuration information of the target signal; information of a sending device of the target signal; information of a receiving device of the target signal; wherein the target signal is a signal used for perception.

[0156] In a thirteenth aspect, a communication device is provided, comprising a processor and a communication interface, wherein the communication interface is used to: receive second information from a first device, the second information comprising an inference result and a fourth indication, the inference result being obtained by an AI unit using an inference sample; wherein the fourth indication is used to indicate at least one of the following: a data set identifier, the data set corresponding to the data set identifier comprising perception measurement-related data; a configuration identifier of the perception measurement quantity; an identifier of the perception measurement quantity; an identifier of the perception measurement link; an identifier of the perception service; an identifier of the perception service type; whether the perception measurement quantity is used in the inference sample; the perception measurement quantity used by the inference sample; the timeliness of the perception measurement quantity used by the inference sample; a sending device of the perception measurement quantity used by the inference sample; a 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 inference The source of the perceptual measurement quantity used by the reasoning sample; the perceptual mode of the perceptual measurement quantity used by the reasoning sample; the processing level of the perceptual measurement quantity used by the reasoning sample; the perceptual service of the perceptual measurement quantity used by the reasoning sample; the purpose of the perceptual measurement quantity used by the reasoning sample; the performance indicator of the perceptual measurement quantity used by the reasoning sample; the number of perceptual measurement quantities used by the reasoning sample; the proportion of the perceptual measurement quantities used by the reasoning sample; whether the number of perceptual measurement quantities used by the reasoning sample meets the minimum number threshold; whether the proportion of the perceptual measurement quantities used by the reasoning sample meets the minimum proportion threshold; the proportion of the perceptual measurement quantities used by the reasoning sample that meet timeliness; the number of the perceptual measurement quantities used by the reasoning sample that meet timeliness; configuration information of the target signal; wherein, the target signal is the target signal corresponding to the perceptual measurement quantity used by the reasoning sample.

[0157] In the fourteenth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented, or the steps of the method described in the third aspect are implemented, or the steps of the method described in the fourth aspect are implemented.

[0158] In the fifteenth aspect, a wireless communication system is provided, including: a first device and a second device, wherein 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.

[0159] In the sixteenth aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method described in the first aspect, or 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.

[0160] In the seventeenth aspect, a computer program / program product is provided, which is stored in a storage medium, and the program / program product is executed by at least one processor to implement the steps of the method described in the first aspect, or 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.

[0161] In this embodiment of the present application, a first device obtains an inference sample, which is determined based on communication measurement data and perception measurement data. The first device then inputs the inference sample into an AI unit to obtain an inference result. This inference sample includes multi-dimensional data from both communication measurement data and perception measurement data, expanding the data information used for model inference and improving the model's inference accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0162] FIG1 is a block diagram of a wireless communication system provided in an embodiment of the present application;

[0163] FIG2 is a schematic diagram of different perception modes of communication perception integration;

[0164] FIG3 is a flow chart of a model reasoning method provided in an embodiment of the present application;

[0165] FIG4 is a flow chart of a model reasoning method provided in an embodiment of the present application;

[0166] FIG5 is a flow chart of a model reasoning method provided in an embodiment of the present application;

[0167] FIG6 is a flow chart of a model reasoning method provided in an embodiment of the present application;

[0168] FIG7 is a flow chart of Example 1 provided in the embodiments of the present application;

[0169] Figures 8 to 10 are diagrams illustrating possible scenarios for using perceptual measurements in a sample;

[0170] FIG11 is a flow chart of Example 2 provided in the embodiments of the present application;

[0171] FIG12 is a flow chart of Example 3 provided in the embodiments of the present application;

[0172] FIG13 is a flow chart of Example 4 provided in the embodiments of the present application;

[0173] FIG14 is a flow chart of Example 5 provided in the embodiments of the present application;

[0174] FIG15 is a flow chart of Example 6 provided in the embodiments of the present application;

[0175] FIG16 is a flow chart of Example 7 provided in the embodiments of the present application;

[0176] Figures 17 and 18 are example diagrams corresponding to Example 7;

[0177] FIG19 is a flow chart of Example 8 provided in the embodiments of the present application;

[0178] FIG20 is a flow chart of Example 9 provided in the embodiments of the present application;

[0179] FIG21 is a structural diagram of a model reasoning device provided in an embodiment of the present application;

[0180] FIG22 is a structural diagram of a model reasoning device provided in an embodiment of the present application;

[0181] FIG23 is a structural diagram of a model reasoning device provided in an embodiment of the present application;

[0182] FIG24 is a structural diagram of a model reasoning device provided in an embodiment of the present application;

[0183] FIG25 is a structural diagram of a communication device provided in an embodiment of the present application;

[0184] FIG26 is a schematic diagram of the hardware structure of a terminal provided in an embodiment of the present application;

[0185] FIG27 is a schematic diagram of the hardware structure of a network-side device provided in an embodiment of the present application;

[0186] Figure 28 is a schematic diagram of the hardware structure of another network-side device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0187] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0188] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0189] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication, implied indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result based on the judgment result.

[0190] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but 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 the present application are often used interchangeably, and the technology described can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) systems. thGeneration, 6G) communication system.

[0191] FIG1 is a block diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (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 (Wearable Device), an aircraft (Flight Vehicle), a vehicle-mounted device (VUE), a ship-mounted device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), a game console, a personal computer (PC), an ATM, or a self-service machine, or other terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit, etc. In addition to the above-mentioned terminal devices, it can also be a chip in the terminal, such as a modem chip, a system-on-chip (SoC). It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be called a radio access network (RAN) device, a radio access network function or a radio access network unit. The access network device may 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 can 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 Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home evolved Node B (home evolved Node B), Transmission Reception Point (TRP) or other appropriate terms in the relevant field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, the base station in the NR system is mainly introduced as an example, and the specific type of the base station is not limited.

[0192] The core network equipment may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (MME), access 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), location management function (LMF), network repository function (NRF), network exposure function (NEF), local NEF (L-NEF), binding support function (BSF), etc. Function, BSF), application function (Application Function, AF), etc. It should be noted that in the embodiment of the present application, the core network device in the NR system is mainly introduced as an example, and the specific type of the core network device is not limited.

[0193] The following is a brief introduction to the relevant technologies.

[0194] Related technology 1: AI technology and communication technology

[0195] 1) AI-based beam prediction

[0196] In millimeter-wave wireless communications, communication transceivers, such as base stations and user equipment (UE), are configured with multiple simulated beams. For the same UE, the measured channel quality varies when measuring different transmit and receive simulated beams. The key to transmission quality is how to quickly and accurately identify the transmit and receive beam combination with the highest channel quality from all possible transmit and receive simulated beam combinations. With the introduction of the AI ​​neural network model, the terminal can effectively predict the transmit simulated beam with the highest channel quality based on historical channel quality information and report it to the network.

[0197] In 5G, beam prediction primarily uses beam quality information derived from CSI measurements, measurement resource identifiers, or beam identification information as model inputs. In the AI-based beam prediction use case discussed in 5G, model inputs include beam quality derived from CSI measurements, beam identifiers / CSI resource identifiers, or measurement timestamps. The AI ​​unit's inference output is the strongest beam identifier or the beam quality of each beam.

[0198] 2) AI-based CSI prediction

[0199] In the AI-based CSI prediction use case discussed in 5G, the model input includes the historical channel matrix, precoding matrix indicator (PMI), channel eigenvectors / eigenvalues, or measurement timestamps obtained based on CSI measurements; the inference output of the AI ​​unit is the predicted channel matrix, PMI, or channel eigenvectors / eigenvalues.

[0200] 3) AI-based positioning

[0201] In the AI-based positioning use case discussed in 5G, the model input includes time-domain channel and positioning reference signal measurement results; the inference output of the AI ​​unit is the predicted distance or time of arrival (TOA) relative to the base station.

[0202] Related technology 2: Communication and perception integration

[0203] Mobile communication systems, such as Beyond 5G (B5G) or 6G systems, will possess not only communication capabilities but also perception capabilities. Perception refers to the ability of one or more devices to sense information such as the position, distance, or speed of a target object through the transmission and reception of wireless signals, or to detect, track, identify, or image a target object, event, or environment. With the deployment of small base stations with high-frequency and large-bandwidth capabilities such as millimeter-wave and terahertz signals in 6G networks, the perception resolution will be significantly improved compared to centimeter-wave signals, enabling 6G networks to provide more refined perception services. Typical perception functions and application scenarios are shown in Table 1.

[0204] Table 1

[0205] Communication and perception integration (abbreviated as synaesthesia integration) is to achieve the integrated design of communication and perception functions through spectrum sharing and hardware sharing in the same system. While transmitting information, the system can perceive information such as direction, distance, and speed, and detect, track, and identify target devices or events. The communication system and the perception system complement each other to achieve overall performance improvement and bring a better service experience.

[0206] The integration of communications and radar is a typical application of communication-perception integration (communication-perception fusion). In the past, radar and communication systems were strictly separated due to their different research objectives and focus, and in most scenarios, the two systems were studied independently. In reality, radar and communication systems are both typical means of transmitting, acquiring, processing, and exchanging information, and they share many similarities in their operating principles, system architecture, and frequency bands. The design of integrated communications and radar is highly feasible, primarily due to the following aspects: First, both communications and perception systems are based on electromagnetic wave theory, utilizing the transmission and reception of electromagnetic waves to acquire and transmit information. Second, both communications and perception systems possess antennas, transmitters, receivers, and signal processors, resulting in significant overlap in hardware resources. With technological advancement, the operating frequency bands between the two systems are increasingly overlapping. Furthermore, there are similarities in key technologies such as signal modulation, reception detection, and waveform design. The integration of communications and radar systems can bring many advantages, such as cost savings, size reduction, power consumption reduction, improved spectrum efficiency, and reduced mutual interference, thereby improving overall system performance.

[0207] Based on the difference between the sending and receiving nodes of the sensing signal, there are six basic sensing modes, as shown in Figure 2, 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) Inter-base station air interface sensing: In this sensing mode, base station B receives the sensing signal sent by base station A and performs sensing measurements.

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

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

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

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

[0214] It's worth noting that each perception mode in Figure 2 uses one sensing signal transmitting node and one sensing signal receiving node as examples. In actual systems, one or more different perception modes can be selected based on different sensing use cases and requirements, and each perception mode can have one or more transmitting and receiving nodes. The perception targets in Figure 2 use people and vehicles as examples, assuming neither person nor vehicle carries or has installed signal transceiver / receiver equipment. In actual scenarios, the range of perception targets will be much richer.

[0215] Here are three ways to get perception results:

[0216] A sends and B receives the perception result:

[0217] Node A sends a perception reference signal (or perception measurement signal), which is received by node B, and node B obtains a perception measurement value / perception result. Node A may be base station 1, and node B may be a target UE, a UE near the target UE, or base station 2.

[0218] Get the perception results spontaneously:

[0219] A sensing reference signal is sent by node A, node A receives the sensing reference signal, and node A obtains a sensing measurement quantity / sensing result. Node A may be the target UE, a UE near the target UE, a serving base station of the target UE, or another base station.

[0220] Get perception results through sensors:

[0221] Network nodes obtain perception measurements / perception results through sensor-type perception devices deployed on themselves or in the environment.

[0222] It should be noted that, unless otherwise specified, perception measurement quantities, perception measurement results, etc. can all be understood as perception results.

[0223] Sensor-based perception is a type of perception that performs perception services through methods other than communication-perception integrated systems. Typical equipment includes lidar, millimeter-wave radar, visual 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 model input, the reasoning accuracy of the AI ​​model (see explanation 1 below) 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 reasoning does not involve the acquisition of perception information, nor how to use perception information. Related technology 2 is a commonly used method for obtaining perception measurement quantities / perception results, which does not involve how to use them as reasoning data for AI models to improve the reasoning accuracy of AI models. At present, there is no mature solution for model reasoning using perception results and communication measurement results as model input data. In view of this, the embodiment of the present application proposes a perception-assisted model reasoning solution, so that network nodes, such as terminals, base stations, core network functions, etc., can obtain perception information as auxiliary information of the AI ​​model to perform model reasoning, which can improve the reasoning accuracy of the AI ​​model.

[0225] The embodiments of the present application involve the interaction of multiple communication devices, each of which can be represented by a variety of network nodes. The functions corresponding to each communication device and the network nodes representing each communication device can be found in Table 2.

[0226] Table 2

[0227] In the embodiments of the present application, a target signal refers to a dedicated signal used for sensing, 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 may be referred to as a sensing reference signal or a sensing measurement signal.

[0228] The model reasoning method provided in the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0229] FIG3 shows a flow chart of a model reasoning method provided in an embodiment of the present application. As shown in FIG3 , the model reasoning method includes the following steps:

[0230] Step 301: The first device obtains an inference sample, where the inference sample is determined based on communication measurement related data and perception measurement related data;

[0231] Step 302: The first device inputs the inference sample into the AI ​​unit to obtain an inference result.

[0232] Communication measurement-related data: data related to communication measurement, for example, communication measurement-related data includes one of the following: CSI measurement amount (or CSI measurement result), CSI measurement resource identifier, reference signal received power (RSRP) of the beam, reference signal received quality (RSRQ) of the beam, signal-to-noise and interference ratio (SINR) of the beam, RSRP of the cell channel, RSRQ of the cell channel, SINR of the cell channel, received signal strength indication (RSSI) of the cell channel, cell channel impulse response, precoding matrix indicator (PMI), rank indicator (RI), channel quality indicator (CQI), beam identifier, subband identifier.

[0233] Perception measurement related data: data related to perception measurement, such as perception measurement configuration, perception results (such as perception measurement quantity), perception performance, perception feature description information, etc.

[0234] The first device may obtain the communication measurement related data through communication measurement (such as CSI measurement, radio resource management (RRM) measurement).

[0235] There are many ways for the first device to obtain the perception measurement related data. It can be achieved by the first device performing perception measurement, or it can be obtained from other devices. For details, please refer to the embodiments provided below.

[0236] The first device obtains the inference sample, which can be understood as the first device performing sample synchronization on the communication measurement-related data and the perception measurement-related data to determine whether to combine the communication measurement-related data and the perception measurement-related data into a single inference sample. For example, the first device performs sample synchronization based on the communication measurement-related data to determine perception measurement-related data that can belong to the same inference sample as the communication measurement-related data.

[0237] The inference samples acquired by the first device may include both communication measurement-related data and perception measurement-related data, or may include only communication measurement-related data. The inference samples are model input data during the model inference process. That is, the model input data may include both communication measurement-related data and perception measurement-related data. This is not limited in the present embodiment.

[0238] In an embodiment of the present application, through sample synchronization, each acquired inference sample can 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 conducive to expanding the model inference data and thus helping to improve the model inference accuracy.

[0239] In this embodiment of the present application, a first device obtains an inference sample, which is determined based on communication measurement data and perception measurement data. The first device then inputs the inference sample into an AI unit to obtain an inference result. This inference sample includes multi-dimensional data from both communication measurement data and perception measurement data, expanding the data information used for model inference and improving model inference accuracy.

[0240] Optionally, the perception measurement related data includes at least one of the following information:

[0241] Perceptual measurement quantity;

[0242] an indication of the perceived measured quantity;

[0243] timestamps of perceived measurements;

[0244] Information about the sending device that senses the measured quantity;

[0245] Information about the receiving device that perceives the measured quantity;

[0246] Perceive the coordinate information of the measured quantity;

[0247] Information indicating a performance indicator of a perceptual measurement quantity;

[0248] Information indicating the source of the perceived measurement;

[0249] Information indicating the type of the perceptual measurement;

[0250] information indicating a perceptual mode of a perceptual measurement quantity;

[0251] Configuration information of the target signal;

[0252] Information about the device sending the target signal;

[0253] Information on the receiving equipment of the target signal;

[0254] The target signal is a signal used for perception.

[0255] In the embodiment of the present application, the types of the perception measurement amount can be referred to Explanation 2 below, and the configuration information of the target signal can be referred to Explanation 3 below.

[0256] The timestamp of the perception measurement quantity may refer to a measurement timestamp of the perception measurement quantity, or may refer to a reception timestamp of the perception measurement quantity, and its meaning may be flexibly determined according to specific circumstances.

[0257] In some embodiments, the method further comprises:

[0258] The first device sends a first request to the second device, where the first request is used to request perception measurement related data required for model inference.

[0259] For example, when the first device is a terminal, a first request may be sent to its serving base station. The first request can reflect the first device's demand for the perceptual information required for model inference data, which is beneficial for the first device to obtain model inference data that meets the demand, thereby improving the model inference effect.

[0260] Optionally, the first request includes at least one of the following information:

[0261] Information indicating that the model is in the inference phase;

[0262] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0263] Configuration identifier of the perception measurement quantity;

[0264] identification of perceptual measurement quantities;

[0265] Information indicating the perceptual characteristics of the target dataset;

[0266] The identifier of the target dataset;

[0267] Configuration information of perceptual measurements required for model inference;

[0268] Information indicating a threshold number of perceptual measurements required for model inference;

[0269] Information indicating the source of perceptual measurements required for model inference;

[0270] Information indicating the kind of perceptual measurements needed for model inference;

[0271] Information about perceptual patterns that indicate perceptual measurements required for model inference;

[0272] Information used to indicate perceived needs;

[0273] Configuration information of the target signal;

[0274] Information about the device sending the target signal;

[0275] Information on the receiving equipment of the target signal;

[0276] The target data set is the data set used by the AI ​​unit during the training phase;

[0277] The target signal is a signal used for perception.

[0278] The above-mentioned identifiers may all be pre-defined identifiers.

[0279] The above-mentioned indications may be either implicit or explicit, and the embodiments of the present application do not limit this.

[0280] It should be noted that the above-mentioned information used to indicate the perceptual characteristics of the target data set, as well as the above-mentioned identifier of the target data set, can both reflect the perceptual characteristics used by the target AI model during the training phase, thereby facilitating the first device to obtain model inference data that is more consistent with the perceptual characteristics of the training phase, which is beneficial to improving the accuracy of model inference.

[0281] In some embodiments, the first device obtains the inference sample, including at least one of the following:

[0282] The first device acquires an inference sample based on a timestamp of the communication measurement amount, a timestamp of the perception measurement amount, and a valid duration of the perception measurement amount;

[0283] The first device obtains an inference sample based on a timestamp corresponding to a prediction result of the target AI model, a timestamp of the perception measurement, and a valid duration of the perception measurement;

[0284] The first device obtains an inference sample based on the first indication and a timestamp of the communication measurement;

[0285] The first device obtains an inference sample based on the first indication and a timestamp corresponding to the prediction result of the target AI model;

[0286] The first device obtains an inference sample based on whether the second indication is received;

[0287] The first indication is used to indicate the failure time or failure time difference of the sensed measurement quantity;

[0288] The second indication is used to indicate that the perceived measurement quantity is invalid.

[0289] In this embodiment, the first device determines whether to synchronize the perception result and the communication measurement result into a single inference sample based on the invalidation time of the perception result. This ensures that the perception measurement-related data in the inference sample is timely, thereby improving the reliability of the inference sample and thus enhancing the model inference effect.

[0290] Optionally, at least one of the following is included:

[0291] In a case where a time corresponding to a timestamp of the communication measurement amount is earlier than the first time, the first device obtains an inference sample including communication measurement-related data and perception measurement-related data;

[0292] When the timestamp corresponding to 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 perception measurement-related data;

[0293] When the time corresponding to the timestamp of the communication measurement amount is earlier than the second time, the first device obtains an inference sample including communication measurement-related data and perception measurement-related data;

[0294] When the timestamp corresponding to 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 perception measurement-related data;

[0295] In a case where the first device does not receive the second indication, the first device obtains an inference sample including communication measurement related data and perception measurement related data;

[0296] The first time is the time corresponding to the timestamp of the perception measurement amount superimposed on the valid duration of the perception measurement amount;

[0297] The second time is an expiration time of the perception measurement quantity determined based on the first indication.

[0298] For details, please refer to the embodiments provided below.

[0299] Optionally, a method for determining the effective duration of the perception measurement value includes at least one of the following:

[0300] In the case where a first valid duration is pre-configured or defined, the valid duration of the perception measurement value is the first valid duration;

[0301] In a case where a second valid duration is preconfigured or defined and the target signal carries a time adjustment value, the valid duration of the perception measurement value is determined according to the second valid duration and the time adjustment value;

[0302] In the case where the target signal carries a third valid duration, the valid duration of the perception measurement value is the third valid duration;

[0303] The target signal is a signal used for perception.

[0304] For details, please refer to the embodiments provided below.

[0305] In some embodiments, the first device obtains the inference sample, including:

[0306] 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;

[0307] 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;

[0308] The historical data includes at least one of communication measurement related data and perception measurement related data.

[0309] This implementation is 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.

[0310] When the first information only includes communication measurement-related data, the first device can obtain an inference sample based on the first information and historical perception measurement-related data. Accordingly, when the first information only includes perception measurement-related data, the first device can obtain an inference sample based on the first information and historical communication measurement-related data. When the first information includes communication measurement-related data and perception measurement-related data, if the communication measurement-related data and the perception measurement-related data therein are data sample-synchronized by a third device, the first device can directly use the communication measurement-related data and the perception measurement-related data therein as an inference sample; if the communication measurement-related data and the perception measurement-related data therein are data that are not sample-synchronized by a third device, the first device can sample-synchronize the communication measurement-related data and the perception measurement-related data therein to obtain an inference sample.

[0311] Optionally, the first information includes at least one of the following:

[0312] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0313] Configuration identifier of the perception measurement quantity;

[0314] identification of perceptual measurement quantities;

[0315] Identification of the perception measurement link;

[0316] Identification of perceived services;

[0317] Identification of the perceived service type;

[0318] Perceptual measurement quantity;

[0319] timestamps of perceived measurements;

[0320] Information about the sending device that senses the measured quantity;

[0321] Perceive the coordinate information of the measured quantity;

[0322] Information indicating a performance indicator of a perceptual measurement quantity;

[0323] Information indicating the source of the perceived measurement;

[0324] Information indicating the type of the perceptual measurement;

[0325] Information indicating the purpose of the perceived measurement;

[0326] information indicating a perceptual mode of a perceptual measurement quantity;

[0327] Communication measurement quantities;

[0328] Communication measurement resource identifier;

[0329] Timestamps of communication measurements;

[0330] Information indicating the first time window;

[0331] Information indicating a first effective time;

[0332] Configuration identification of the target signal;

[0333] Configuration information of the target signal;

[0334] Information about the device sending the target signal;

[0335] Information on the receiving equipment of the target signal;

[0336] The target signal is a signal used for perception.

[0337] This embodiment may include the following four optional situations:

[0338] Case 1: The first information includes a perception measurement amount, a timestamp of the perception measurement amount, a communication measurement amount, and a timestamp of the communication measurement amount;

[0339] The first device obtains an inference sample based on the first information, including at least one of the following:

[0340] In a case where a time difference between a timestamp of the perception measurement amount and a timestamp of the communication measurement amount is less than or equal to a first time window indicated by the first information, the first device acquires an inference sample including communication measurement-related data and perception measurement-related data;

[0341] In a case where a time difference between a timestamp of the perception measurement amount and a timestamp of the communication measurement amount is less than or equal to a predefined second time window, the first device obtains an inference sample including communication measurement-related data and perception measurement-related data.

[0342] In this case, the first information includes communication measurement related data and perception 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.

[0343] For details, please refer to the embodiments provided below.

[0344] Case 2: the first information includes a target perception measurement value and a timestamp of the target perception measurement value;

[0345] The first device obtains an inference sample based on the first information and stored historical data, including:

[0346] The first device obtains an inference sample including a target communication measurement amount and the target perception measurement amount;

[0347] The target communication measurement amount includes at least one of the following:

[0348] The difference between the timestamp of the historical data and the timestamp of the target perception measurement amount is less than or equal to the communication measurement amount of the first time window indicated by the first information;

[0349] A difference between a timestamp of the historical data and a timestamp of the target perception measurement value is less than or equal to a communication measurement value of a predefined second time window.

[0350] It should be noted that in this case, the inference samples including the target communication measurement quantity and the target perception measurement quantity acquired by the first device are not limited to only the measurement quantity, and may also include other communication measurement related data and other perception measurement related data.

[0351] It should be noted that in this case, the first information includes the target perception measurement amount and the timestamp of the target perception measurement amount, which can be understood as follows: the first information may include only perception measurement-related data (such as the first information only includes the target perception measurement amount and the timestamp of the target perception measurement amount), and the first information includes both perception measurement-related data and communication measurement-related data (such as the first information includes, in addition to the target perception measurement amount and the timestamp of the target perception measurement amount, one or more communication measurement amounts (and the timestamp of the communication measurement amount)).

[0352] 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.

[0353] For details, please refer to the embodiments provided below.

[0354] Case 3: the first information includes a target communication measurement amount and a timestamp of the target communication measurement amount;

[0355] The first device obtains an inference sample based on the first information and stored historical data, including:

[0356] The first device obtains an inference sample including the target communication measurement amount and the target perception measurement amount;

[0357] The target perception measurement includes at least one of the following:

[0358] A time difference between a timestamp of the historical data and a timestamp of the target communication measurement amount is less than or equal to a perception measurement amount of a first time window indicated by the first information;

[0359] The timestamp of the historical data is less than or equal to the perception measurement quantity of the first valid time indicated by the first information;

[0360] The timestamp of the historical data is less than or equal to the perception measurement quantity of the predefined second validity time.

[0361] It should be noted that in this case, the first information includes the target communication measurement amount and the timestamp of the target communication measurement amount, which can be understood as follows: the first information may include only communication measurement-related data (such as the first information only includes the target communication measurement amount and the timestamp of the target communication measurement amount), or the first information includes both perception measurement-related data and communication measurement-related data (such as the first information includes, in addition to the target communication measurement amount and the timestamp of the target communication measurement amount, one or more perception measurement amounts (and the timestamp of the perception measurement amount)).

[0362] 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.

[0363] For details, please refer to the embodiments provided below.

[0364] Case 4: The first device obtains an inference sample based on the first information, including at least one of the following:

[0365] The first device obtains an inference sample including a target communication measurement amount and a target perception measurement amount;

[0366] The first information includes the target communication measurement amount and the target communication measurement amount; or

[0367] The first information includes the target communication measurement value and a third indication, and the target perception measurement value is the perception measurement value corresponding to the third indication; or

[0368] The first information includes the target communication measurement value, and the target perception measurement value is the perception measurement value of a most recent inference sample.

[0369] Optionally, the third instruction includes at least one of the following:

[0370] Identification of inference samples;

[0371] Identification of the resources used for the communication measurement results;

[0372] Communication measurement result reporting identifier;

[0373] Identification of the resources used to perceive the measured quantity;

[0374] Reporting flag of the perception measurement quantity;

[0375] The identification of the perceptual measurement quantity.

[0376] It should be noted that in this case, the inference samples including the target communication measurement quantity and the target perception measurement quantity acquired by the first device are not limited to only the measurement quantity, and may also include other communication measurement related data and other perception measurement related data.

[0377] In this case, the first information includes at least communication measurement related data, and the third device has performed sample synchronization, and the first device obtains the synchronized data based on the first information (or the first information and historical data) to obtain an inference sample.

[0378] For details, please refer to the embodiments provided below.

[0379] It should be noted that the perception measurement amount (or communication measurement amount) in the above-mentioned cases is any perception measurement amount (or communication measurement amount) and does not refer to a specific perception measurement amount (or communication measurement amount).

[0380] In some embodiments, the method further comprises:

[0381] 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;

[0382] The fourth indication is used to indicate at least one of the following:

[0383] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0384] Configuration identifier of the perception measurement quantity;

[0385] identification of perceptual measurement quantities;

[0386] Identification of the perception measurement link;

[0387] Identification of perceived services;

[0388] Identification of the perceived service type;

[0389] whether the inference sample uses perceptual measurements;

[0390] the perceptual measurement used by the inference sample;

[0391] the timeliness of the perceptual measurements used in the inference samples;

[0392] a sending device of the perceptual measurement quantity used by the inference sample;

[0393] a receiving device of the perceptual measurement quantity used by the inference sample;

[0394] coordinates of the perceptual measurements used by the inference sample;

[0395] the source of the perceptual measurements used in the inference sample;

[0396] a perceptual pattern of perceptual measurements used by the inference sample;

[0397] the level of processing of the perceptual measurements used by the inference samples;

[0398] the perceptual service of the perceptual measurement quantity used by the inference sample;

[0399] the purpose of the perceptual measurements used in the inference sample;

[0400] performance indicators of perceptual measurements used by the inference samples;

[0401] the number of perceptual measurements used by the inference sample;

[0402] the proportion of perceptual measurements used in the inference sample;

[0403] whether the number of perceptual measurements used by the inference sample meets a minimum number threshold;

[0404] whether the ratio of the perceptual measurements used in the inference sample meets a minimum ratio threshold;

[0405] The proportion of perceptual measurements used in the inference sample that meet timeliness requirements;

[0406] The number of perceptual measurements used in the inference sample that meet timeliness requirements;

[0407] Configuration information of the target signal;

[0408] The target signal is a target signal corresponding to the perceptual measurement quantity used by the inference sample.

[0409] 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 perceptual characteristics of the inference sample, so that the fourth device obtains the perceptual characteristics of the inference sample through the fourth indication.

[0410] The above items included in the fourth indication reflect the perceptual characteristics of the inference sample from two perspectives: the usage of the perceptual measurement quantity and the perceptual configuration.

[0411] It should be noted that the perceptual characteristics of inference samples can be used to assist in analyzing model inference results, which is beneficial for monitoring or subsequent optimization of model inference.

[0412] The above is the first device side embodiment of the present application. The second device side embodiment, the third device side embodiment and the fourth device side embodiment of the present application are described below respectively.

[0413] FIG4 shows a flow chart of a model reasoning method provided in an embodiment of the present application. As shown in FIG4 , the model reasoning method includes the following steps:

[0414] Step 401: The second device receives a first request from the first device, where the first request is for requesting perceptual measurement-related data required for model inference;

[0415] Step 402: The second device performs a first operation, where the first operation includes any one of the following:

[0416] The second device sends a target signal based on the first request;

[0417] The second device determines configuration information of the target signal based on the first request;

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

[0419] The second device sends the perception measurement related data based on the first request;

[0420] The target signal is a signal used for perception.

[0421] In the embodiment of the present application, the second device may represent not only the data request receiving device but also the target signal sending device, that is, the second device and the fifth device may be co-located in the same network node.

[0422] Specifically, when the first operation includes sending a target signal, the second device and the fifth device are jointly provided; when the first operation includes sending configuration information of the target signal, the device that receives the configuration information of the target signal can serve as the fifth device.

[0423] The first operation includes sending a target signal, and the recipient 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 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.

[0424] Accordingly, when the first operation includes sending the configuration information of the target signal, the recipient of the configuration information of the target signal is not unique.

[0425] In some embodiments, when the first operation includes sending perception measurement-related data, the second device represents both the second device and a third device (i.e., the perception result sending device), i.e., the second device and the third device are co-located on the same network node. The second device sends the perception measurement-related data based on the first request, and the second device may directly send the perception measurement-related data to the first device based on the first request.

[0426] Optionally, the first request includes at least one of the following information:

[0427] Information indicating that the AI ​​unit is in the inference phase;

[0428] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0429] Configuration identifier of the perception measurement quantity;

[0430] identification of perceptual measurement quantities;

[0431] Information indicating the perceptual characteristics of the target dataset;

[0432] The identifier of the target dataset;

[0433] Configuration information of perceptual measurements required for model inference;

[0434] Information indicating a threshold number of perceptual measurements required for model inference;

[0435] Information indicating the source of perceptual measurements required for model inference;

[0436] Information indicating the kind of perceptual measurements needed for model inference;

[0437] Information about perceptual patterns that indicate perceptual measurements required for model inference;

[0438] Information used to indicate perceived needs;

[0439] Configuration information of the target signal;

[0440] Information about the device sending the target signal;

[0441] Information on the receiving equipment of the target signal;

[0442] The target data set is the data set used by the AI ​​unit during the training phase;

[0443] The target signal is a signal used for perception.

[0444] For the relevant description of the embodiments of the present application, please refer to the relevant description of the method embodiment of Figure 3, and the same technical effects can be achieved. To avoid repetition, they will not be described in detail.

[0445] FIG5 shows a flow chart of a model reasoning method provided in an embodiment of the present application. As shown in FIG5 , the model reasoning method includes the following steps:

[0446] 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.

[0447] In the embodiment of the present application, the third device may or may not perform sample synchronization.

[0448] If the third device does not perform sample synchronization, the first information may include at least one of the following:

[0449] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0450] Configuration identifier of the perception measurement quantity;

[0451] identification of perceptual measurement quantities;

[0452] Identification of the perception measurement link;

[0453] Identification of perceived services;

[0454] Identification of the perceived service type;

[0455] Perceptual measurement quantity;

[0456] timestamps of perceived measurements;

[0457] Information about the sending device that senses the measured quantity;

[0458] Perceive the coordinate information of the measured quantity;

[0459] Information indicating a performance indicator of a perceptual measurement quantity;

[0460] Information indicating the source of the perceived measurement;

[0461] Information indicating the type of the perceptual measurement;

[0462] Information indicating the purpose of the perceived measurement;

[0463] information indicating a perceptual mode of a perceptual measurement quantity;

[0464] Communication measurement quantities;

[0465] Communication measurement resource identifier;

[0466] Timestamps of communication measurements;

[0467] Information indicating the first time window;

[0468] Information indicating a first effective time;

[0469] Configuration identification of the target signal;

[0470] Configuration information of the target signal;

[0471] Information about the device sending the target signal;

[0472] Information on the receiving equipment of the target signal;

[0473] The target signal is a signal used for perception.

[0474] In the case where the third device performs sample synchronization, the first information may include at least one of the following:

[0475] a target communication measurement amount and a target communication measurement amount, wherein the target communication measurement amount and the target communication measurement amount are determined to belong to the same inference sample;

[0476] a target communication measurement amount and a third indication, wherein the target communication measurement amount and the perception measurement amount indicated by the third indication are determined to belong to the same inference sample;

[0477] a target communication measurement amount, wherein the target communication measurement amount and a perception measurement amount of a most recent reasoning sample are determined to belong to the same reasoning sample;

[0478] Optionally, the third instruction includes at least one of the following:

[0479] Identification of inference samples;

[0480] Identification of the resources used for the communication measurement results;

[0481] Communication measurement result reporting identifier;

[0482] Identification of the resources used to perceive the measured quantity;

[0483] Reporting flag of the perception measurement quantity;

[0484] The identification of the perceptual measurement quantity.

[0485] It should be noted that regardless of whether the third device performs sample synchronization, the third device can be referred to as a perception result sending device. If the third device performs sample synchronization, the third device may not send both the communication measurement result and the perception result in the first message. However, because the third device can implicitly indicate that it has already sent the perception result through the third indication, the third device has actually previously sent the perception result, that is, the third device is a perception result sending device.

[0486] For the relevant description of the embodiments of the present application, please refer to the relevant description of the method embodiment of Figure 3, and the same technical effects can be achieved. To avoid repetition, they will not be described in detail.

[0487] FIG6 shows a flow chart of a model reasoning method provided in an embodiment of the present application. As shown in FIG6 , the model reasoning method includes the following steps:

[0488] Step 601: The fourth device receives second information from the first device, where the second information includes an inference result and a fourth indication, where the inference result is obtained by an AI unit using an inference sample.

[0489] The fourth indication is used to indicate at least one of the following:

[0490] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0491] Configuration identifier of the perception measurement quantity;

[0492] identification of perceptual measurement quantities;

[0493] Identification of the perception measurement link;

[0494] Identification of perceived services;

[0495] Identification of the perceived service type;

[0496] whether the inference sample uses perceptual measurements;

[0497] the perceptual measurement used by the inference sample;

[0498] the timeliness of the perceptual measurements used in the inference samples;

[0499] a sending device of the perceptual measurement quantity used by the inference sample;

[0500] a receiving device of the perceptual measurement quantity used by the inference sample;

[0501] coordinates of the perceptual measurements used by the inference sample;

[0502] the source of the perceptual measurements used in the inference sample;

[0503] a perceptual pattern of perceptual measurements used by the inference sample;

[0504] the level of processing of the perceptual measurements used by the inference samples;

[0505] the perceptual service of the perceptual measurement quantity used by the inference sample;

[0506] the purpose of the perceptual measurements used in the inference sample;

[0507] performance indicators of perceptual measurements used by the inference samples;

[0508] the number of perceptual measurements used by the inference sample;

[0509] the proportion of perceptual measurements used in the inference sample;

[0510] whether the number of perceptual measurements used by the inference sample meets a minimum number threshold;

[0511] whether the ratio of the perceptual measurements used in the inference sample meets a minimum ratio threshold;

[0512] The proportion of perceptual measurements used in the inference sample that meet timeliness requirements;

[0513] The number of perceptual measurements used in the inference sample that meet timeliness requirements;

[0514] Configuration information of the target signal;

[0515] The target signal is a target signal corresponding to the perceptual measurement quantity used by the inference sample.

[0516] For the relevant description of the embodiments of the present application, please refer to the relevant description of the method embodiment of Figure 3, and the same technical effects can be achieved. To avoid repetition, they will not be described in detail.

[0517] The following provides specific examples to illustrate the interaction process involved in the embodiments of the present application.

[0518] Example 1: The serving base station (hereinafter referred to as the base station) sends a sensing reference signal, the UE receives the sensing reference signal, and the UE performs model inference

[0519] In this embodiment, the UE represents the first device and the sixth device (ie, the first device and the sixth device are collectively provided in the UE), and the base station represents the second device, the fourth device, and the fifth device (ie, the second device, the fourth device, and the fifth device are collectively provided in the base station).

[0520] As shown in Figure 7, the following steps are included:

[0521] 1. The base station sends a sensing reference signal to the UE;

[0522] 2. The UE receives the sensing reference signal sent by the base station, obtains the sensing measurement value, synchronizes the sensing measurement value with the CSI measurement result, obtains the inference sample for model inference, and performs model inference. (Note: An inference sample is the model input data for one model inference.)

[0523] 3. The UE reports the inference result to the base station.

[0524] Before step 1, the UE sends a first request to the base station to request the perception measurement quantity required for model inference.

[0525] The first request may reflect the UE's requirements, and may be implicit or explicit. The first request may include at least one of the following:

[0526] AI lifecycle management process indicators, such as indicating that the model is in the inference phase;

[0527] Data set identifier, which can implicitly indicate, for example, the configuration of a certain perceptual reference signal or perceptual measurement quantity used in the previous training process, or the reporting configuration of the perceptual measurement quantity used in the previous training process; (implicit indication)

[0528] An identifier of a predefined perceptual measurement quantity, which may implicitly indicate which perceptual measurement quantity or combination of perceptual measurements is required; (implicit indication)

[0529] A predefined configuration identifier for a perceptual measurement quantity, which may implicitly indicate the required processing level, configuration density, etc. of the perceptual measurement quantity; (implicit indication)

[0530] Information indicating the source of the required perceptual measurement quantity, for example, whether it is derived from the measurement of a perceptual reference signal (i.e., synaesthesia integration), or from sensor perception, or which perceptual mode (i.e., the six basic perceptual modes in Related Art 2) the measurement of the perceptual reference signal (i.e., synaesthesia integration) is derived from, or which type of sensor the sensor perception is derived from;

[0531] Information indicating the sending device of the perception reference signal (also understood as the source of the perception measurement quantity), such as the serving base station, neighboring base station, and nearby UE;

[0532] Information indicating the receiving device of the perception reference signal (also understood as the source of the perception measurement quantity), such as the serving base station, neighboring base station, nearby UE, and target UE;

[0533] Information indicating the type of sensory measurement required (see explanation 2 below);

[0534] Configuration information of the sensing reference signal (see explanation 3 below);

[0535] Information indicating the total number of required perceptual measurements;

[0536] Information indicating the minimum number of required perceptual measurements;

[0537] Information used to indicate perceived needs (see explanation 4 below).

[0538] In this embodiment, the combination of the perception measurement quantities corresponding to the identifications of the perception measurement quantities can be seen in Table 3.

[0539] Table 3

[0540] In this embodiment, if the UE's serving base station represents only the second device and not the fifth device, that is, the device sending the sensor reference signal is not the UE's serving base station, how does the UE's serving base station coordinate the configuration of the sensor reference signal with the fifth device? The following three coordination methods are provided:

[0541] Mode 1: The fifth device determines the configuration of the sensing reference signal by itself and notifies the serving base station of the UE after the determination. In this mode, the serving base station of the UE receives the configuration of the sensing reference signal sent by the fifth device.

[0542] Method 2: The UE's serving base station determines the corresponding CRS configuration based on the first request and then notifies (or forwards) it to the fifth device. In this method, the UE's serving base station receives feedback from the fifth device regarding the CRS configuration. For example, the fifth device agrees to the CRS configuration; or the fifth device disagrees with the CRS configuration and negotiates the CRS configuration with the UE's serving base station.

[0543] Mode 3: The fifth device first determines the configuration of the sensing reference signal and then sends it to the UE's serving base station for negotiation. In this mode, the UE's serving base station 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 desired configuration to the fifth device.

[0544] In step 2, the UE performs sample synchronization on the perception measurement quantity and the CSI measurement result, including the following two methods:

[0545] Method 1:

[0546] The UE determines whether to combine the perception measurement amount with the CSI measurement amount as an inference sample based on the timestamp of the perception reference signal measurement, the valid duration of the perception measurement amount, the CSI measurement amount (eg, L1-RSRP), and the timestamp of the CSI measurement.

[0547] Specifically, if the timestamp of the CSI measurement is earlier than the timestamp of the sensing measurement + the valid duration, the UE combines the sensing measurement value and the CSI measurement result as an inference sample. Or,

[0548] If the timestamp corresponding to the prediction result of the AI ​​unit is earlier than the timestamp + validity time of the perception measurement, the UE combines the perception measurement value and the CSI measurement result as an inference sample.

[0549] Method 2:

[0550] The UE determines whether to combine the perception reference signal measurement amount with the CSI measurement amount as an inference sample based on the perception reference signal measurement amount, the perception control message, the CSI measurement amount, and the timestamp of the CSI measurement.

[0551] Specifically, if the UE obtains the perception measurement amount and does not receive a message indicating that the perception result is invalid from the base station, the UE combines the perception measurement amount with the CSI measurement amount as an inference sample.

[0552] If the latest timestamp corresponding to the CSI measurement amount is earlier than the expiration time indicated by the first indication, the UE combines the perception measurement amount with the CSI measurement amount as an inference sample. The first indication is used to indicate the expiration of the perception result, or includes the time difference of the expiration of the perception result. The time difference can also be predefined. Or,

[0553] If the timestamp corresponding to the prediction result of the AI ​​unit is earlier than the expiration time indicated by the first indication, the UE combines the perception measurement value and the CSI measurement result as an inference sample.

[0554] In the above-mentioned method 1, the UE needs to obtain the timeliness (i.e., the effective duration) of the perception measurement quantity to synchronize the samples of the perception measurement quantity and the CSI measurement result. The UE can obtain the timeliness in the following three ways:

[0555] Method 1: Initially configure or predefine a valid duration of a sensing measurement variable (e.g., 1 second, which can be implicitly or explicitly indicated). Each time a sensing reference signal is sent, the valid duration is no longer carried.

[0556] Method 2: Initially configure or predefine the effective duration of a sensing measurement variable, and carry an adjustment value (e.g., -100ms, which can be implicitly or explicitly indicated) each time a sensing reference signal is sent.

[0557] Mode 3: Each time the perception reference signal is sent, the absolute effective duration (for example, 900 ms, which can be indicated implicitly or explicitly) is carried.

[0558] In step 3, in addition to reporting the inference result to the base station, the UE may also report a fourth indication indicating at least one of the following:

[0559] whether perceptual measures were used;

[0560] Perceptual measurement quantity indication (e.g., explicit indication of one of the path's Doppler, delay, power, angle, etc., or implicit indication of a corresponding combination, or indication of the processing level of the perceptual measurement quantity); (See Table 4)

[0561] An indication of the timeliness of the perceptual measurement quantity (for example, using 1 bit to indicate whether the inference sample uses a valid perceptual measurement quantity or an invalid perceptual measurement quantity).

[0562] Table 4

[0563] The above items reflect the perceptual characteristics of the inference samples from the perspective of the usage of perceptual measurement quantities.

[0564] The following examples illustrate how perceptual measures might be used in a sample.

[0565] Example 1: As shown in Figure 8, the latest timestamp corresponding to the prediction in step 7 is earlier than the expiration timestamp of the perception result corresponding to step 8, and the timestamp of the perception measurement quantity obtained in step 2 is earlier than the time of model inference in step 5. In step 6, when reporting the inference result, 1 bit is used to indicate that the perception result used is within the validity period, or no indication is given.

[0566] Example 2: As shown in Figure 9, if after the model is activated in step 3, the timestamp of the perception measurement obtained in step 2 is later than the time of model inference in step 5, the perception result is not used for model inference; then, in the inference result report in step 6, 1 bit is used to indicate that the perception result is not used.

[0567] Example 3: As shown in FIG10 , if the expiration timestamp of the perception result corresponding to step 8 is earlier than the timestamp corresponding to the prediction in step 7 , the perception measurement result may or may not be used as the model input during model inference in step 5 .

[0568] If the perception measurement amount is not used, then in step 6, in the inference result reporting, it is indicated that the perception measurement result is not used;

[0569] If the perception measurement amount is used, the inference result report in step 6 indicates that the perception measurement amount is used, or indicates that an expired perception measurement amount is used, or indicates the expiration time.

[0570] Example 2: The serving base station (hereinafter referred to as the base station) sends a sensing reference signal, the UE receives the sensing reference signal and feeds it back to the base station, and the base station performs model inference

[0571] In this embodiment, the base station represents the first device and the fifth device (ie, the first device and the fifth device are jointly provided in the base station), and the UE represents the third device and the sixth device (ie, the third device and the sixth device are jointly provided in the UE).

[0572] In this embodiment, the second device and the fourth device can be core network functions (such as AMF, LMF).

[0573] As shown in Figure 11, the following steps are included:

[0574] 1. The base station sends a sensing reference signal to the UE. The base station can also send a CSI-RS to the UE.

[0575] 2. The UE receives the sensing reference signal sent by the base station and performs sensing measurement to obtain a sensing measurement quantity or sensing result. The UE may also perform CSI measurement to obtain a CSI measurement result.

[0576] 3. The UE reports at least one of the following information to the base station:

[0577] Perceptual measurement quantity;

[0578] CSI measurement quantity;

[0579] Perception measurement resource indication (e.g., identification);

[0580] CSI measurement resource indication (e.g., identifier);

[0581] timestamps of perceived measurements;

[0582] Timestamp of CSI measurement;

[0583] associated perceptual measurement indications;

[0584] The timestamp of the associated sensory measurement.

[0585] In FIG11 , step 3 includes steps 3a and 3b, wherein step 3a is reporting of the perception measurement quantity and step 3b is reporting of the CSI measurement quantity.

[0586] 4. Based on the information reported by the UE (or the information reported by the UE and the stored historical data), the base station obtains inference samples for model inference and performs model inference.

[0587] In this embodiment, the information reported by the UE to the base station may be information that has undergone 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 information that has not undergone sample synchronization, that is, the sample synchronization is performed by the base station.

[0588] When sample synchronization is performed by the UE, the information reported by the UE may include at least one of the following:

[0589] After time alignment, the perceptual measurement and CSI measurement can be used for an inference sample;

[0590] After time alignment, the CSI measurement amount of an inference sample + a third indication, where the third indication is used to indicate the perception measurement amount that has been sent to the base station; wherein the third indication may include a sample indication (e.g., an identifier) ​​that has been sent to the base station, or a CSI measurement indication (e.g., a resource identifier / CSI reporting identifier) ​​that has been sent to the base station, or a perception measurement amount indication (e.g., an identifier) ​​that has been sent to the base station;

[0591] The CSI measurement of a reasoning sample, without a third indication, uses the perceptual measurement of the most recent reasoning sample by default.

[0592] When sample synchronization is performed by the base station, the information reported by the UE may include at least one of the following:

[0593] Perception measurement quantity and CSI measurement quantity. When the time difference between a certain perception measurement quantity reported by the UE and a certain CSI measurement quantity received is less than a certain time window, the base station may consider that the perception measurement quantity and the CSI measurement quantity belong to the same inference sample; or, when the difference between the timestamps of a certain perception measurement quantity reported by the UE and a certain CSI measurement quantity already received (or already stored) by the base station is within a certain time window, the base station may consider that the perception measurement quantity and the CSI measurement quantity belong to the same inference sample; or, when the difference between the timestamps of a certain CSI measurement quantity reported by the UE and a certain perception measurement quantity already received (or already stored) by the base station is within a certain time window, the base station may consider that the perception measurement quantity and the CSI measurement quantity belong to the same inference sample;

[0594] CSI measurement quantity and timestamp of CSI measurement quantity. When the difference between the timestamp of a CSI measurement quantity and the timestamp of a received (or stored) perception measurement quantity is within a certain time window, or when the received (or stored) perception measurement quantity is within the valid time, the base station may consider that the CSI measurement quantity and the received perception measurement quantity belong to the same inference sample;

[0595] Perception measurement quantity and its timestamp. When the difference between the timestamp of a perception measurement quantity and the timestamp of a received (or stored) CSI measurement quantity is within a certain time window, the base station may consider that the perception measurement quantity and the received (or stored) CSI measurement quantity belong to the same inference sample.

[0596] The above time window may be a predefined time window or a time window reported by the UE.

[0597] Example 3: The serving base station (hereinafter referred to as the base station) sends the sensor's perception measurement data to the UE, and the UE performs model inference

[0598] In this embodiment, the UE represents the first device, and the base station represents the second device, the third device, and the fourth device (ie, the second device, the third device, and the fourth device are collectively provided in the base station).

[0599] As shown in Figure 12, the following steps are included:

[0600] 1. The base station sends sensor-based perception measurements to the UE;

[0601] 2. The UE receives the sensor's perception measurement data sent by the base station, synchronizes the perception measurement data with the CSI measurement results, and obtains inference samples for model inference.

[0602] 3. The UE reports the inference result to the base station and may also report a fourth indication.

[0603] The sensor's sensory measurement may also include some auxiliary information (contained in the first information), such as:

[0604] Data set identifier, which can implicitly indicate, for example, the configuration of a certain perceptual reference signal or perceptual measurement quantity used in the previous training process, or the reporting configuration of the perceptual measurement quantity used in the previous training process; (implicit indication)

[0605] A predefined identification of a perceptual measurement quantity, which may implicitly indicate which perceptual measurement quantity or which combination of perceptual measurements is being used; (implicit indication)

[0606] A predefined configuration identifier of a perceptual measurement quantity, which may implicitly indicate the processing level, configuration density, etc. of the perceptual measurement quantity; (implicit indication)

[0607] Information indicating the source of the sensory measurement, for example, whether the measurement is derived from a sensory reference signal (i.e., synaesthesia integration), or whether the sensor is derived from sensory perception, or whether the sensor is derived from the sensory reference signal (i.e., synaesthesia integration).

[0608] Information indicating the type of the perceptual measurement;

[0609] Information indicating the total number of sensory measurements;

[0610] Information indicating the minimum number of perceptual measurements.

[0611] Before step 1, the UE sends a first request to the base station to request the perceptual measurement quantity required for model inference. (Same as in embodiment 1)

[0612] In step 2, the method in which the UE performs sample synchronization on the perception measurement amount and the CSI measurement result is similar to that in embodiment 1, including the following two methods:

[0613] Method 1:

[0614] The UE determines whether to combine the perception measurement amount and the CSI measurement amount as an inference sample based on the measurement timestamp or reception timestamp of the perception measurement amount of the sensor, the valid duration of the perception measurement amount, the CSI measurement amount (such as L1-RSRP), and the timestamp of the CSI measurement.

[0615] Specifically, if the timestamp of the CSI measurement is earlier than the timestamp of the sensory measurement value plus the valid duration, the UE combines the sensory measurement value and the CSI measurement result as an inference sample. Or,

[0616] If the timestamp of the CSI measurement is earlier than the reception timestamp of the sensory measurement value + the valid duration, the UE combines the sensory measurement value and the CSI measurement result as an inference sample. Or,

[0617] If the timestamp corresponding to the prediction result of the AI ​​model is earlier than the measurement timestamp + validity time of the perception measurement value, the UE combines the perception measurement value and the CSI measurement result as an inference sample. Or,

[0618] If the timestamp corresponding to the prediction result of the AI ​​model is earlier than the reception timestamp + validity time of the perception measurement value, the UE combines the perception measurement value and the CSI measurement result as an inference sample.

[0619] Method 2:

[0620] The UE determines whether to combine the perception measurement amount and the CSI measurement amount as an inference sample based on the perception measurement amount of the sensor, the perception control message, the CSI measurement amount, and the timestamp of the CSI measurement.

[0621] Specifically, if the UE obtains the perception measurement amount and does not receive a message from the base station indicating that the perception result is invalid, the UE combines the perception measurement amount with the CSI measurement amount as an inference sample. Or,

[0622] If the latest timestamp corresponding to the CSI measurement value is earlier than the expiration time indicated by the first indication, the UE combines the perception measurement value with the CSI measurement value as an inference sample. Or,

[0623] If the timestamp corresponding to the prediction result of the AI ​​model is earlier than the expiration time indicated by the first indication, the UE combines the perception measurement amount and the CSI measurement amount as an inference sample.

[0624] The first indication is used to indicate that the sensing result is invalid, or includes a time difference before the sensing result is invalid. The time difference may also be predefined.

[0625] In the above-mentioned method 1, the UE needs to obtain the timeliness (i.e., effective duration) of the perception measurement quantity in order to synchronize the samples of the perception measurement quantity and the CSI measurement result. (Same as in embodiment 1)

[0626] For example, Table 5 lists the timeliness of perception measurements corresponding to various sensor types.

[0627] Table 5

[0628] The rest is the same as that of Example 1, and will not be described in detail to avoid repetition.

[0629] Example 4: UE sends sensor perception measurement data to the serving base station (hereinafter referred to as base station), and the base station performs model inference

[0630] In this embodiment, the base station represents the first device, and the UE represents the third device.

[0631] As shown in Figure 13, the following steps are included:

[0632] 1. The base station sends the reporting configuration of the sensor perception measurement quantity to the UE;

[0633] 2. The UE reports at least one of the following information to the base station:

[0634] Perceptual measurement quantity;

[0635] CSI measurement quantity;

[0636] timestamps of perceived measurements;

[0637] Timestamp of CSI measurement;

[0638] associated perceptual measurement indications;

[0639] The timestamp of the associated sensory measurement.

[0640] In FIG13 , step 2 includes steps 2a and 2b, wherein step 2a is the reporting of the sensor's perception measurement quantity, and step 2b is the reporting of the CSI measurement quantity.

[0641] 3. Based on the information reported by the UE (or the information reported by the UE and the stored historical data), the base station obtains inference samples for model inference and performs model inference.

[0642] In this embodiment, the information reported by the UE to the base station may be information that has undergone 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 information that has not undergone sample synchronization, that is, the sample synchronization is performed by the base station. (Same as Example 2)

[0643] Example 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 value to the UE, and the UE performs model inference

[0644] In this embodiment, the UE represents the first device, the second base station represents the third device and the sixth device (ie, the third device and the sixth device are collectively provided in the second base station), and the first base station represents the second device, the third device, the fourth device, and the fifth device.

[0645] As shown in Figure 14, the following steps are included:

[0646] 1. The first base station sends a sensing reference signal to the second base station;

[0647] 2. The second base station obtains a sensing measurement value or a sensing result based on the sensing reference signal;

[0648] 3. The second base station sends at least one of the following information to the first base station:

[0649] Perceptual measurement quantity;

[0650] Perception measurement resource indication (e.g., identification);

[0651] timestamps of perceived measurements;

[0652] The effective duration of the perceived measurement quantity;

[0653] Other relevant information about the perceptual measurement quantity.

[0654] 4. The first base station sends at least one of the following information to the UE:

[0655] Perceptual measurement quantity;

[0656] Perception measurement resource indication (e.g., identification);

[0657] timestamps of perceived measurements;

[0658] The effective duration of the perceived measurement quantity;

[0659] An indication from the perception reference signal receiving device (in this embodiment, an indication to the second base station, which may be an implicit indication or an explicit indication);

[0660] Other relevant information about the perceptual measurement quantity.

[0661] 5. Based on the information sent by the first base station, the UE obtains inference samples for model inference and performs model inference.

[0662] 6. The UE reports the inference result to the first base station and may also report a fourth indication.

[0663] In this embodiment, other relevant information of the perception measurement value (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:

[0664] Data set identifier, which can implicitly indicate, for example, the configuration of a certain perceptual reference signal or perceptual measurement quantity used in the previous training process, or the reporting configuration of the perceptual measurement quantity used in the previous training process; (implicit indication)

[0665] A predefined identification of a perceptual measurement quantity, which may implicitly indicate which perceptual measurement quantity or which combination of perceptual measurements is being used; (implicit indication)

[0666] A predefined configuration identifier of a perceptual measurement quantity, which may implicitly indicate the processing level, configuration density, etc. of the perceptual measurement quantity; (implicit indication)

[0667] Perception measurement link identification information (used to distinguish which perception link the perception measurement result comes from, and which device sends and which device receives it);

[0668] Sensing mode information (monostatic sensing mode or bistatic sensing mode, or at least one of the six sensing modes);

[0669] Perception signal configuration identification information (used to distinguish which perception signal the perception measurement result comes from);

[0670] Perceived business information (e.g., perceived business identity (ID));

[0671] Perception service type information (e.g., perception service type ID);

[0672] Data subscription ID;

[0673] Information on the use of measurement results (e.g., communication, perception, synaesthesia, AI reasoning, etc.);

[0674] Device information for sensing measurements (e.g., UE ID, device location, device orientation, and device motion information);

[0675] Coordinate information of the measurement result (measurement value), such as whether the result is based on the local coordinate system or the global coordinate system, and description information of the local coordinate system, such as the rotation angle relative to the global coordinate system: α (bearing angle), β (downtilt angle), and γ (tilt angle);

[0676] The measurement results correspond to performance indicator information, such as resolution (which can be delay resolution, ranging resolution, angular resolution, Doppler resolution, velocity resolution, imaging resolution, etc., that is, the granularity of the reported measurement value), SINR, perceived SINR (the ratio of the power of the path associated with the perceived target to the power of noise and interference), etc.

[0677] The performance indicator corresponding to the perception result (such as the perception SINR) can be used as a model input together with the result of the perception measurement. For example, in addition to the Doppler value of the path on the Doppler spectrum as input for training / inference, the ratio of the power of the path to the power of noise and interference is also used as input to indicate the accuracy or reliability of the Doppler value.

[0678] Before step 1, the UE sends a first request to the first base station for requesting the perception measurement quantity required for model inference. The first request may include information indicating which neighboring base stations the perception measurement quantity comes from, and the rest may be the same as in embodiment 1.

[0679] In step 5, the UE may perform sample synchronization based on the information sent by the first base station. The sample synchronization method is similar to that in embodiment 1, including the following two methods:

[0680] Method 1:

[0681] The UE determines whether to combine the perception measurement amount with the CSI measurement amount as an inference sample based on the measurement timestamp or reception timestamp of the perception measurement amount, the valid duration of the perception measurement amount, the CSI measurement amount (eg, L1-RSRP), and the timestamp of the CSI measurement.

[0682] Specifically, if the timestamp of the CSI measurement is earlier than the measurement timestamp + valid duration of the perception measurement value, the UE combines the perception measurement value and the CSI measurement result (including the model input and the true value) as an inference sample. Or,

[0683] If the timestamp of the CSI measurement is earlier than the reception timestamp of the sensory measurement value + the valid duration, the UE combines the sensory measurement value and the CSI measurement result (including the model input and the true value) as an inference sample. Or,

[0684] If the timestamp corresponding to the prediction result of the AI ​​model is earlier than the timestamp of the perception measurement + the validity period, the UE combines the perception measurement and the CSI measurement result (including the model input and the true value) as an inference sample. Or,

[0685] If the timestamp corresponding to the prediction result of the AI ​​model is earlier than the timestamp + validity time of the perception measurement amount received, the UE combines the perception measurement amount and the CSI measurement result (including the model input and the true value) as an inference sample.

[0686] Method 2:

[0687] The UE determines whether to combine the perception measurement amount and the CSI measurement amount as an inference sample based on the perception measurement amount, the perception control message, the CSI measurement amount, and the timestamp of the CSI measurement.

[0688] Specifically, if the UE obtains the perception measurement amount and does not receive a message from the base station indicating that the perception result is invalid, the UE combines the perception measurement amount with the CSI measurement amount as an inference sample. Or,

[0689] If the latest timestamp corresponding to the CSI measurement value is earlier than the expiration time indicated by the first indication, the UE combines the perception measurement value with the CSI measurement value as an inference sample. Or,

[0690] If the timestamp corresponding to the prediction result of the AI ​​model is earlier than the expiration time indicated by the first indication, the UE combines the perception measurement amount and the CSI measurement amount as an inference sample.

[0691] The first indication is used to indicate that the sensing result is invalid, or includes a time difference before the sensing result is invalid. The time difference may also be predefined.

[0692] In the above-mentioned method 1, the UE needs to obtain the timeliness (i.e., effective duration) of the perception measurement quantity in order to synchronize the samples of the perception measurement quantity and the CSI measurement result. (Same as in embodiment 1)

[0693] The rest is the same as that of Example 1, and will not be described in detail to avoid repetition.

[0694] Example 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 value to the UE, and the UE performs model inference

[0695] 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 collectively arranged in the second base station), and the first base station represents the second device, the fourth device and the fifth device (that is, the second device, the fourth device and the fifth device are collectively arranged in the first base station).

[0696] In this embodiment, the UE also establishes a connection with the second base station. Therefore, the second base station may directly send the perception measurement value to the UE.

[0697] It should be noted that how does the second base station know to send the perception measurement value to the UE? Specifically, when the first base station sends the perception reference signal to the second base station, or when configuring the perception reference signal, it needs to indicate the receiving device of the perception measurement value, that is, the UE.

[0698] As shown in Figure 15, the following steps are included:

[0699] 1. The first base station sends a sensing reference signal to the second base station;

[0700] 2. The second base station obtains a sensing measurement value or a sensing result based on the sensing reference signal;

[0701] 3. The second base station sends at least one of the following information to the UE:

[0702] Perceptual measurement quantity;

[0703] timestamps of perceived measurements;

[0704] The effective duration of the perceived measurement quantity;

[0705] Other relevant information about the perceived measurement quantity;

[0706] An indication from the perception reference signal receiving device (in this embodiment, an indication to the second base station, which may be an implicit indication or an explicit indication).

[0707] 4. Based on the information sent by the second base station, the UE synchronizes samples of the perception measurement quantity and the CSI measurement result, obtains inference samples for model inference, and performs model inference.

[0708] 5. The UE reports the inference result to the first base station and may also report a fourth indication.

[0709] Before step 1, the UE sends a first request to the first base station for requesting the perception measurement quantity required for model inference. The first request may include information indicating which neighboring base stations the perception measurement quantity comes from, and the rest may be the same as in embodiment 1.

[0710] The rest is the same as that of Example 5, and will not be described in detail to avoid repetition.

[0711] Example 7: The serving base station (hereinafter referred to as the base station) sends a perception reference signal, the second UE receives the perception reference signal, the base station sends the perception measurement value to the target UE (or the first UE), and the target UE performs model inference

[0712] 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 (that is, the second device, the third device, the fourth device and the fifth device are collectively provided in the base station), and the second UE represents the third device and the sixth device.

[0713] In this embodiment, the second UE is a UE near the target UE.

[0714] As shown in Figure 16, the following steps are included:

[0715] 1. The base station sends a perception reference signal to the second UE;

[0716] 2. The second UE obtains a perception measurement value or a perception result based on the perception reference signal;

[0717] 3. The second UE sends at least one of the following information to the base station:

[0718] Perceptual measurement quantity;

[0719] timestamps of perceived measurements;

[0720] The effective duration of the perceived measurement quantity;

[0721] Perception measurement resource indication (e.g., identification);

[0722] Other relevant information about the perceptual measurement quantity.

[0723] 4. The base station sends at least one of the following information to the target UE:

[0724] Perceptual measurement quantity;

[0725] timestamps of perceived measurements;

[0726] The effective duration of the perceived measurement quantity;

[0727] Other relevant information about the perceived measurement quantity;

[0728] An indication from the perceptual reference signal receiving device (in this embodiment, an indication to the second UE, which may be an implicit indication or an explicit indication).

[0729] 5. Based on the information sent by the base station, the target UE synchronizes the perception measurement quantity and the CSI measurement result samples, obtains the inference samples for model inference, and performs model inference.

[0730] 6. The UE reports the inference result to the base station and may also report the fourth indication.

[0731] It should be noted that the serving base station may receive information directly from the second UE or forward it through other devices. For example, if the second UE is a neighboring cell UE, the second UE first sends the information to the neighboring cell base station, which then forwards it to the serving base station.

[0732] Before step 1, the target UE sends a first request to the base station for requesting the perception measurement quantity required for model inference. The first request may include information indicating which neighboring UEs the perception measurement quantity comes from. The rest is the same as in embodiment 1.

[0733] In this embodiment, when the serving base station of the target UE represents only the second device and not the fifth device, that is, the device sending 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 in Example 1)

[0734] Specifically, see Figures 17 and 18. In Figure 17, 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. In Figure 18, 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.

[0735] The rest is the same as that of Example 5, and will not be described in detail to avoid repetition.

[0736] Example 8: The serving base station (also called the first base station) sends a perception reference signal, the second UE receives the perception reference signal, the second UE sends the perception measurement value to the target UE (also called the first UE), and the target UE performs model inference

[0737] 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.

[0738] In this embodiment, the second device and the fourth device may be serving base stations or core network functions.

[0739] In this embodiment, the second UE is a UE near the target UE, and the target UE establishes a sidelink with the second UE. The second UE can directly send the perception measurement value to the target UE.

[0740] The main process of this embodiment is similar to that of embodiment 6, except that the sensing reference signal receiving device is different.

[0741] In this embodiment, the serving base station sends a perception reference signal to the second UE. In embodiment 6, the serving base station sends a perception reference signal to the second base station.

[0742] As shown in Figure 19, the following steps are included:

[0743] 1. The base station sends a perception reference signal to the second UE;

[0744] 2. The second UE obtains a perception measurement value or a perception result based on the perception reference signal;

[0745] 3. The second UE sends at least one of the following information to the target UE:

[0746] Perceptual measurement quantity;

[0747] timestamps of perceived measurements;

[0748] The effective duration of the perceived measurement quantity;

[0749] Other relevant information about the perceived measurement quantity;

[0750] An indication from the perceptual reference signal receiving device (in this embodiment, an indication to the second UE, which may be an implicit indication or an explicit indication).

[0751] 4. Based on the information sent by the second UE, the target UE synchronizes samples of the perception measurement quantity and the CSI measurement result, obtains inference samples for model inference, and performs model inference.

[0752] 5. The target UE reports the inference result to the base station.

[0753] Before step 1, the target UE sends a first request to the base station for requesting the perception measurement quantity required for model inference. The first request may include information indicating which neighboring UEs the perception measurement quantity comes from. The rest is the same as in embodiment 1.

[0754] In step 5, 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:

[0755] whether perceptual measures were used;

[0756] Perceptual measurement quantity indication (e.g., explicit indication of one of the path's Doppler, delay, power, angle, etc., or implicit indication of a corresponding combination, or indication of the processing level of the perceptual measurement quantity); (See Table 4)

[0757] Indication of the timeliness of perceptual measurements (e.g., using 1 bit to indicate whether the inference sample uses a valid perceptual measurement or an invalid perceptual measurement);

[0758] The nearby UE from which the perception measurement amount comes (this may be indicated explicitly or implicitly (eg, a measurement identifier of the perception measurement amount)).

[0759] The rest is the same as that of Example 5, and will not be described in detail to avoid repetition.

[0760] Example 9: The base station sends a sensing reference signal, the base station receives the sensing reference signal, the base station sends the sensing measurement value to the UE, and the UE performs model inference

[0761] 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.

[0762] In this embodiment, the second device and the fourth device may also be core network functions (eg, AMF, LMF).

[0763] In this embodiment, the base station performing the self-transmission and self-reception operation may be a serving base station or a neighboring base station. In addition, the base station performing the self-transmission and self-reception operation may also be other nearby UEs, which will not be specifically described in this embodiment.

[0764] As shown in Figure 20, the following steps are included:

[0765] 1. The base station sends and receives a sensing reference signal to obtain a sensing measurement quantity or a sensing result.

[0766] 2. The base station sends at least one of the following information to the UE:

[0767] Perceptual measurement quantity;

[0768] timestamps of perceived measurements;

[0769] The effective duration of the perceived measurement quantity;

[0770] Other relevant information about the perceived measurement quantity;

[0771] An indication from the perception reference signal receiving device (in this embodiment, an indication from a base station, which may be an implicit indication or an explicit indication).

[0772] 3. Based on the information sent by the base station, the UE synchronizes the perception measurement quantity and the CSI measurement result samples, obtains the inference samples for model inference, and performs model inference.

[0773] 4. The UE reports the inference result to the base station.

[0774] Before step 1, the UE sends a first request to the base station to request the perceptual measurement quantity required for model inference. The first request may include:

[0775] Information indicating that the perceived measurement quantity comes from several fifth devices;

[0776] Used to indicate the category of the fifth device (serving cell, neighboring cell, nearby UE) or category combination (for example, serving cell, 3 neighboring cells, 4 nearby UEs).

[0777] The rest of the content of the first request may be the same as in Example 1.

[0778] 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:

[0779] whether perceptual measures were used;

[0780] Perceptual measurement quantity indication (e.g., explicit indication of one of the path's Doppler, delay, power, angle, etc., or implicit indication of a corresponding combination (see Table 3), or indication of the processing level of the perceptual measurement quantity);

[0781] Indication of the timeliness of perceptual measurements (e.g., using 1 bit to indicate whether the inference sample uses a valid perceptual measurement or an invalid perceptual measurement);

[0782] The receiving device (serving cell, neighboring cell, nearby UE) or receiving device combination (for example, serving cell, 3 neighboring cells, 4 nearby UEs) of the perceived measurement amount (may be indicated explicitly or implicitly (for example, a measurement identifier of the perceived measurement amount, an identifier of the sixth device / receiving device combination)).

[0783] For example, the explicit indication of the timeliness of the perceptual measurement quantity can be seen in Table 6.

[0784] Table 6

[0785] For example, the implicit indication of the timeliness of the perceptual measurement quantity can be seen in Table 7.

[0786] Table 7

[0787] The rest is the same as that of Example 5, and will not be described in detail to avoid repetition.

[0788] The above are specific embodiments provided in the embodiments of this application.

[0789] The relevant terms of this application are explained as follows:

[0790] Explanation 1: AI Model

[0791] An AI model may also be referred to as an AI unit, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI feature, a neural network, a neural network function, a neural network function, etc. Alternatively, an AI unit / AI model may refer to a processing unit that can implement specific AI-related algorithms, formulas, processing flows, capabilities, etc. Alternatively, an AI unit / AI model may be a processing method, algorithm, function, module, or unit for a specific data set, or an AI unit / AI model may be a processing method, algorithm, function, module, or unit running on AI / ML-related hardware such as a GPU, NPU, TPU, or ASIC. This application does not specifically limit this.

[0792] Optionally, the specific data set includes input or output of the AI ​​unit / AI model.

[0793] Optionally, the identifier of the AI ​​unit / AI model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, etc., or an identifier of a specific data set associated with the AI ​​unit / AI model, or an identifier of a specific scenario, environment, channel characteristics, equipment, etc. related to the AI / ML, or an identifier of a function, feature, capability or module related to the AI / ML. This application does not make any specific limitations on this.

[0794] Explanation 2: Types of Perceptual Measurements

[0795] Perceptual measurements related to synaesthesia integration include the following:

[0796] (1) First-level measurement quantities (received signal / original channel information), including: received signal / channel response complex results, amplitude / phase, I-channel / Q-channel and their operation results (operations include addition, subtraction, multiplication and division, matrix addition, subtraction, multiplication and division, matrix transposition, trigonometric operations, square root operations and power operations, as well as threshold detection results and maximum / minimum value extraction results 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 operation, wavelet transform and digital filtering, as well as threshold detection results and maximum / minimum value extraction results of the above operation results);

[0797] Here, H is not limited to the channel between the serving base station and the UE. It also includes the perceived channels generated by other base stations through autonomous transmission and reception. This encompasses multiple scenarios. The H perceived by the base station through autonomous transmission and reception differs from the H measured by the UE itself. For example, it is unclear whether a moving object in the environment is caused by the movement of an obstacle or by the UE's own movement. This enables interference cancellation and facilitates 3D environment reconstruction.

[0798] It should be noted that the above H represents the received signal / original channel information.

[0799] The validity period of sensory measurements can be long or short. If the sensory information is relatively static (for example, unchanged for several years), it can be sent directly. If it is obtained from real-time measurements, it is necessary to configure which devices send and receive sensory signals. This can improve prediction accuracy.

[0800] (2) Second-level measurement quantities (basic measurement quantities), including: delay, Doppler, angle, intensity, and their multi-dimensional combination representations; for example, they can be delay values, Doppler values, or delay power spectrum, Doppler power spectrum, velocity power spectrum, angle power spectrum, delay-Doppler spectrum, delay-angle spectrum, Doppler-angle spectrum, delay-Doppler-angle spectrum, etc.

[0801] (3) Third-level measurement: perception results / perception intermediate results

[0802] Basic attributes / states, including: distance, speed, direction, spatial position, acceleration;

[0803] Advanced attributes / status, including: target presence, trajectory, movement, expression, vital signs, quantity, imaging results, weather, air quality, shape, material, and composition;

[0804] Environmental reconstruction results,trajectory.

[0805] The measurement quantities perceived by sensors include the following:

[0806] (1) LiDAR-related measurements, including at least one of the following:

[0807] LiDAR point cloud data, each point in the LiDAR point cloud data includes: X / Y / Z position information, and,additional information;

[0808] The angle and distance of the target obtained based on the lidar point cloud data;

[0809] Visual features of objects identified from LiDAR point cloud data, such as people and vehicles;

[0810] The number of objects identified from the LiDAR point cloud data.

[0811] The additional information in the lidar point cloud data includes at least one of the following:

[0812] Intensity: The return intensity of the laser pulse that generated the lidar point;

[0813] Echo number: Echo number is the total number of echoes for a given pulse;

[0814] Point classification: Each post-processed lidar point can have a classification that defines the type of object that reflected the lidar pulse. LiDAR points can be divided into many categories, such as ground, bare earth, top of tree canopy, and water.

[0815] RGB: RGB bands can be used as attributes of lidar data. This attribute usually comes from the effects collected during lidar measurement.

[0816] Global Positioning System (GPS) time: GPS timestamp of the laser point emitted from the aircraft;

[0817] Scan angle;

[0818] Scan direction: The direction of travel of the laser scanning mirror. A value of 1 represents a positive scanning direction and a value of 0 represents a negative scanning direction.

[0819] (2) Vision-related measurements, including at least one of the following:

[0820] visual images;

[0821] the luminosity of the image pixels;

[0822] RGB values ​​of image pixels;

[0823] Visual features of objects identified from images, such as people and vehicles;

[0824] The angle and distance of the target identified from the image (especially for binocular vision);

[0825] The number of objects identified in the image.

[0826] (3) Radar-related measurements, including at least one of the following:

[0827] Radar point cloud, each point in the point cloud includes: at least one of range / velocity / azimuth / elevation angle, or at least one of X / Y / Z / velocity;

[0828] The distance, speed, and angle of the identified target;

[0829] radar imaging;

[0830] The number of targets.

[0831] (4) Inertial measurement unit-related measurements, including at least one of the following:

[0832] Acceleration: at least one of the three directions X / Y / Z;

[0833] Speed: at least one of the three directions X / Y / Z;

[0834] Angular velocity: around at least one of the three axes X / Y / Z.

[0835] (5) Measurements from position sensors such as the Global Navigation Satellite System (GNSS), including the device’s location information and the relative distance / angle between the device and a specific object.

[0836] (6) Other measurement quantities, including at least one of the following: target presence, trajectory, movement, expression, vital signs, quantity, imaging results, weather, air quality, shape, material, composition, etc.

[0837] Explanation 3: Signal configuration information (can be called target signal configuration information, perception reference signal configuration information, etc.)

[0838] Signal configuration information, including at least one of the following:

[0839] Signal resource identification (ID), used to distinguish different signal resource configurations;

[0840] Signal usage indicates whether the signal is used for communication (e.g., channel measurement, channel estimation, synchronization, or carrying data information), for sensing, or for both communication and sensing. Specifically, it may also indicate which sensing service the signal is used for, or which type of sensing service the signal is used for. For definitions of sensing services and sensing service types, refer to Explanation 3.

[0841] Waveforms, such as Orthogonal Frequency Division Multiplex (OFDM), Single-Carrier Frequency-Division Multiple Access (SC-FDMA), Orthogonal Time Frequency Space (OTFS), Chirp waveform, Frequency Modulated Continuous Wave (FMCW), pulse signals, etc.

[0842] Subcarrier spacing, for example, the subcarrier spacing of the OFDM system is 30KHz.

[0843] The guard interval is the time interval from the moment the signal ends to the moment the latest echo signal of the signal is received; this parameter is proportional to the maximum perception distance; for example, it can be calculated by c / (2R max ) is calculated, R max is the maximum perception distance (belonging to the perception demand information), for example, for the self-transmitted and self-received perception signal, R max Represents the maximum distance between the perceived signal receiving and transmitting point and the signal transmitting point; in some cases, the OFDM signal cyclic prefix (CP) can serve as the minimum guard interval; c is the speed of light.

[0844] The starting frequency domain position, i.e., the starting frequency point, can also be the starting resource element (RE) or resource block (RB) index;

[0845] The starting time domain position, i.e. the starting time point, can also be the starting symbol index, time slot index, or frame index;

[0846] The ending frequency domain position, i.e., the ending frequency point, can be represented by the ending RE and RB index;

[0847] The termination time domain position, i.e., the termination time point, can be represented by the termination RE and RB index;

[0848] Frequency domain resource length, i.e., frequency domain bandwidth, where the frequency domain bandwidth is inversely proportional to the range resolution, and the frequency domain bandwidth B of each first signal is ≥ c / (2ΔR), where c is the speed of light and ΔR is the range resolution;

[0849] Time domain resource length, also known as burst duration, is inversely proportional to the Doppler resolution.

[0850] Frequency domain resource spacing, which indicates the spacing between adjacent signal frequency domain resource units, can be expressed as the number of REs or RBs, or as a density value (Density). For example, Density = 1 means that there is one RE in each RB used to carry the signal. The frequency domain resource spacing is inversely proportional to the maximum unambiguous distance / delay. For OFDM systems, when subcarriers are continuously mapped, the frequency domain spacing is equal to the subcarrier spacing.

[0851] A time domain resource interval, where the time domain resource interval is a time interval between two adjacent signal resource units, and the time domain resource interval is associated with a maximum unambiguous Doppler frequency shift or a maximum unambiguous velocity;

[0852] Time domain resource characteristics, periodic transmission, semi-continuous transmission, and aperiodic transmission;

[0853] Signal power, for example, from -20dBm to 23dBm, with a value of 2dBm;

[0854] Sequence information, including sequence type information (ZC sequence, PN sequence, etc.), sequence generation method, sequence length, etc.;

[0855] Signal direction, angle information or beam information of signal transmission;

[0856] Quasi-Co-Location (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;

[0857] Antenna port information, such as the maximum number of antenna ports and antenna port index;

[0858] Cyclic prefix (CP) information, including CP type (e.g., Normal Cyclic Prefix (NCP), Extended Cyclic Prefix (ECP), or a newly designed CP dedicated to perception measurement), CP length, etc.

[0859] Explanation 4: Perceived Need

[0860] Perceived demand information includes at least one of the following:

[0861] Perception services or perception service types, the perception services may be, for example, detection of target presence, 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 recognition, gait recognition, expression recognition, facial recognition, respiration monitoring, heart rate monitoring, pulse monitoring, humidity / brightness / temperature / atmospheric pressure monitoring, air quality monitoring, weather condition monitoring, environmental reconstruction, topography, building / vegetation distribution detection, pedestrian or vehicle flow detection, crowd density, vehicle density detection, etc.; the perception service type may be to classify a plurality of different perception services according to certain characteristics, for example, according to function, it may be divided into detection-type perception services (for example, including intrusion detection, fall detection), parameter estimation, etc. The sensing services include metering services (distance, angle, speed calculation), recognition services (motion recognition, identity recognition), etc., or target detection and tracking services (including target presence, target distance measurement / distance measurement / angle measurement / positioning / trajectory tracking), environmental monitoring services (including rainfall detection, flood monitoring, etc.), motion detection services (including gesture / motion recognition, breathing / heartbeat detection, fall detection), etc. They can also be divided according to the range of perception (close-range perception, medium-range perception, long-range perception), the degree of perception refinement (coarse-grained perception, fine force perception, etc.), power consumption / energy consumption, and resource occupancy.

[0862] Perception target area: refers to the location area where the perception object may exist, or the location area where imaging or environmental reconstruction is required;

[0863] Perception object type: Classify the perception object according to its possible motion characteristics. Each perception object type contains information such as the motion speed, motion acceleration, and typical RCS of a typical perception object.

[0864] Perception QoS: Performance indicators for perceiving the target area or object.

[0865] Perceived QoS includes at least one of the following:

[0866] Perception resolution (can be divided into: ranging resolution, angular resolution, velocity resolution, imaging resolution), etc.

[0867] Perception accuracy (can be divided into: ranging accuracy, angle measurement accuracy, speed measurement accuracy, positioning accuracy, etc.);

[0868] Perception range (can be divided into: ranging range, speed measurement range, angle measurement range, imaging range, etc.);

[0869] Perception latency (the time interval from the sending of the perception signal to the acquisition of the perception result, or the time interval from the initiation of the perception request to the acquisition of the perception result);

[0870] Perception update rate (the time interval between two consecutive perception operations and the acquisition of perception results);

[0871] Detection probability (the probability of correctly detecting the perceived object when it exists);

[0872] False alarm probability (the probability of incorrectly detecting a perceived target when the perceived target does not exist);

[0873] The maximum number of targets that can be perceived.

[0874] In summary, in the embodiments of the present application, by proposing a perception-assisted model reasoning method, network nodes can expand the data information used for model reasoning by acquiring perception information, thereby improving the reasoning accuracy of the AI ​​model.

[0875] The model reasoning method provided in the embodiment of the present application can be executed by a model reasoning device. The model reasoning method provided in the embodiment of the present application can be executed by a model reasoning device. In the embodiment of the present application, the model reasoning device provided in the embodiment of the present application is illustrated by taking the execution of the model reasoning method by a model reasoning device as an example.

[0876] FIG21 shows a structural diagram of a model reasoning device provided in an embodiment of the present application, which can be applied to a first device. As shown in FIG21 , the model reasoning device 910 includes:

[0877] A first processing module 911 is configured to obtain an inference sample, where the inference sample is determined based on communication measurement related data and perception measurement related data;

[0878] The second processing module 912 is used to input the reasoning sample into the artificial intelligence AI unit to obtain the reasoning result.

[0879] Optionally, the perception measurement related data includes at least one of the following information:

[0880] Perceptual measurement quantity;

[0881] an indication of the perceived measured quantity;

[0882] timestamps of perceived measurements;

[0883] Information about the sending device that senses the measured quantity;

[0884] Information about the receiving device that perceives the measured quantity;

[0885] Perceive the coordinate information of the measured quantity;

[0886] Information indicating a performance indicator of a perceptual measurement quantity;

[0887] Information indicating the source of the perceived measurement;

[0888] Information indicating the type of the perceptual measurement;

[0889] information indicating a perceptual mode of a perceptual measurement quantity;

[0890] Configuration information of the target signal;

[0891] Information about the device sending the target signal;

[0892] Information on the receiving equipment of the target signal;

[0893] The target signal is a signal used for perception.

[0894] Optionally, the device further comprises:

[0895] The first sending module is used to send a first request to the second device, where the first request is used to request perception measurement related data required for model inference.

[0896] Optionally, the first request includes at least one of the following information:

[0897] Information indicating that the AI ​​unit is in the inference phase;

[0898] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0899] Configuration identifier of the perception measurement quantity;

[0900] identification of perceptual measurement quantities;

[0901] Information indicating the perceptual characteristics of the target dataset;

[0902] The identifier of the target dataset;

[0903] Configuration information of perceptual measurements required for model inference;

[0904] Information indicating a threshold number of perceptual measurements required for model inference;

[0905] Information indicating the source of perceptual measurements required for model inference;

[0906] Information indicating the kind of perceptual measurements needed for model inference;

[0907] Information about perceptual patterns that indicate perceptual measurements required for model inference;

[0908] Information used to indicate perceived needs;

[0909] Configuration information of the target signal;

[0910] Information about the device sending the target signal;

[0911] Information on the receiving equipment of the target signal;

[0912] The target data set is the data set used by the AI ​​unit during the training phase;

[0913] The target signal is a signal used for perception.

[0914] Optionally, the first processing module is specifically configured to perform at least one of the following:

[0915] Acquire an inference sample based on a timestamp of the communication measurement amount, a timestamp of the perception measurement amount, and a valid duration of the perception measurement amount;

[0916] Acquire an inference sample based on a timestamp corresponding to a prediction result of the AI ​​unit, a timestamp of the perception measurement quantity, and a valid duration of the perception measurement quantity;

[0917] Obtaining an inference sample based on the first indication and a timestamp of the communication measurement;

[0918] Obtaining an inference sample based on the first indication and a timestamp corresponding to the prediction result of the AI ​​unit;

[0919] obtaining an inference sample based on whether the second indication is received;

[0920] The first indication is used to indicate the failure time or failure time difference of the sensed measurement quantity;

[0921] The second indication is used to indicate that the perceived measurement quantity is invalid.

[0922] Optionally, a method for determining the effective duration of the perception measurement value includes at least one of the following:

[0923] In the case where a first valid duration is pre-configured or defined, the valid duration of the perception measurement value is the first valid duration;

[0924] In a case where a second valid duration is preconfigured or defined and the target signal carries a time adjustment value, the valid duration of the perception measurement value is determined according to the second valid duration and the time adjustment value;

[0925] In the case where the target signal carries a third valid duration, the valid duration of the perception measurement value is the third valid duration;

[0926] The target signal is a signal used for perception.

[0927] Optionally, the first processing module is specifically configured to perform at least one of the following:

[0928] When the time corresponding to the timestamp of the communication measurement amount is earlier than the first time, obtaining an inference sample including communication measurement related data and perception measurement related data;

[0929] When the timestamp corresponding to the prediction result of the AI ​​unit is earlier than the first time, obtaining an inference sample including communication measurement-related data and perception measurement-related data;

[0930] When the time corresponding to the timestamp of the communication measurement amount is earlier than the second time, obtaining an inference sample including communication measurement related data and perception measurement related data;

[0931] When the timestamp corresponding to the prediction result of the AI ​​unit is earlier than the second time, obtaining an inference sample including communication measurement-related data and perception measurement-related data;

[0932] In a case where the first device does not receive the second indication, obtaining an inference sample including communication measurement related data and perception measurement related data;

[0933] The first time is the time corresponding to the timestamp of the perception measurement amount superimposed on the valid duration of the perception measurement amount;

[0934] The second time is an expiration time of the perception measurement quantity determined based on the first indication.

[0935] Optionally, the first processing module includes:

[0936] 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 perception measurement-related data;

[0937] a processing unit, configured to obtain an inference sample based on the first information; or to obtain an inference sample based on the first information and stored historical data;

[0938] The historical data includes at least one of communication measurement related data and perception measurement related data.

[0939] Optionally, the first information includes at least one of the following:

[0940] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0941] Configuration identifier of the perception measurement quantity;

[0942] identification of perceptual measurement quantities;

[0943] Identification of the perception measurement link;

[0944] Identification of perceived services;

[0945] Identification of the perceived service type;

[0946] Perceptual measurement quantity;

[0947] timestamps of perceived measurements;

[0948] Information about the sending device that senses the measured quantity;

[0949] Perceive the coordinate information of the measured quantity;

[0950] Information indicating a performance indicator of a perceptual measurement quantity;

[0951] Information indicating the source of the perceived measurement;

[0952] Information indicating the type of the perceptual measurement;

[0953] Information indicating the purpose of the perceived measurement;

[0954] information indicating a perceptual mode of a perceptual measurement quantity;

[0955] Communication measurement quantities;

[0956] Communication measurement resource identifier;

[0957] Timestamps of communication measurements;

[0958] Information indicating the first time window;

[0959] Information indicating a first effective time;

[0960] Configuration identification of the target signal;

[0961] Configuration information of the target signal;

[0962] Information about the device sending the target signal;

[0963] Information on the receiving equipment of the target signal;

[0964] The target signal is a signal used for perception.

[0965] Optionally, the first processing module is specifically configured to perform at least one of the following:

[0966] When a time difference between a timestamp of the perception measurement amount and a timestamp of the communication measurement amount is less than or equal to a first time window indicated by the first information, acquiring an inference sample including communication measurement-related data and perception measurement-related data;

[0967] In a case where a time difference between a timestamp of the perception measurement amount and a timestamp of the communication measurement amount is less than or equal to a predefined second time window, an inference sample including communication measurement related data and perception measurement related data is acquired.

[0968] Optionally, the first information includes a target perception measurement and a timestamp of the target perception measurement;

[0969] The first processing module is specifically configured to:

[0970] Acquiring an inference sample including a target communication measurement and the target perception measurement;

[0971] The target communication measurement amount includes at least one of the following:

[0972] The difference between the timestamp of the historical data and the timestamp of the target perception measurement amount is less than or equal to the communication measurement amount of the first time window indicated by the first information;

[0973] A difference between a timestamp of the historical data and a timestamp of the target perception measurement value is less than or equal to a communication measurement value of a predefined second time window.

[0974] Optionally, the first information includes a target communication measurement amount and a timestamp of the target communication measurement amount;

[0975] The first processing module is specifically configured to:

[0976] Acquiring an inference sample including the target communication measurement quantity and the target perception measurement quantity;

[0977] The target perception measurement includes at least one of the following:

[0978] A time difference between a timestamp of the historical data and a timestamp of the target communication measurement amount is less than or equal to a perception measurement amount of a first time window indicated by the first information;

[0979] The timestamp of the historical data is less than or equal to the perception measurement quantity of the first valid time indicated by the first information;

[0980] The timestamp of the historical data is less than or equal to the perception measurement quantity of the predefined second validity time.

[0981] Optionally, the first processing module is specifically configured to:

[0982] obtaining an inference sample including a target communication measurement and a target perception measurement;

[0983] The first information includes the target communication measurement amount and the target communication measurement amount; or

[0984] The first information includes the target communication measurement value and a third indication, and the target perception measurement value is the perception measurement value corresponding to the third indication; or

[0985] The first information includes the target communication measurement value, and the target perception measurement value is the perception measurement value of a most recent inference sample.

[0986] Optionally, the third instruction includes at least one of the following:

[0987] Identification of inference samples;

[0988] Identification of the resources used for the communication measurement results;

[0989] Communication measurement result reporting identifier;

[0990] Identification of the resources used to perceive the measured quantity;

[0991] Reporting flag of the perception measurement quantity;

[0992] The identification of the perceptual measurement quantity.

[0993] Optionally, the device further comprises:

[0994] 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;

[0995] The fourth indication is used to indicate at least one of the following:

[0996] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[0997] Configuration identifier of the perception measurement quantity;

[0998] identification of perceptual measurement quantities;

[0999] Identification of the perception measurement link;

[1000] Identification of perceived services;

[1001] Identification of the perceived service type;

[1002] whether the inference sample uses perceptual measurements;

[1003] the perceptual measurement used by the inference sample;

[1004] the timeliness of the perceptual measurements used in the inference samples;

[1005] a sending device of the perceptual measurement quantity used by the inference sample;

[1006] a receiving device of the perceptual measurement quantity used by the inference sample;

[1007] coordinates of the perceptual measurements used by the inference sample;

[1008] the source of the perceptual measurements used in the inference sample;

[1009] a perceptual pattern of perceptual measurements used by the inference sample;

[1010] the level of processing of the perceptual measurements used by the inference samples;

[1011] the perceptual service of the perceptual measurement quantity used by the inference sample;

[1012] the purpose of the perceptual measurements used in the inference sample;

[1013] performance indicators of perceptual measurements used by the inference samples;

[1014] the number of perceptual measurements used by the inference sample;

[1015] the proportion of perceptual measurements used in the inference sample;

[1016] whether the number of perceptual measurements used by the inference sample meets a minimum number threshold;

[1017] whether the ratio of the perceptual measurements used in the inference sample meets a minimum ratio threshold;

[1018] The proportion of perceptual measurements used in the inference sample that meet timeliness requirements;

[1019] The number of perceptual measurements used in the inference sample that meet timeliness requirements;

[1020] Configuration information of the target signal;

[1021] The target signal is a target signal corresponding to the perceptual measurement quantity used by the inference sample.

[1022] FIG22 shows a structural diagram of a model reasoning device provided in an embodiment of the present application, which can be applied to a second device. As shown in FIG22 , the model reasoning device 920 includes:

[1023] A receiving module 921 is configured to receive a first request from a first device, where the first request is for requesting perceptual measurement related data required for model inference;

[1024] The processing module 922 is configured to perform a first operation, where the first operation includes any one of the following:

[1025] Based on the first request, sending a target signal;

[1026] Determining configuration information of a target signal based on the first request;

[1027] Sending configuration information of the target signal based on the first request;

[1028] Sending perception measurement related data based on the first request;

[1029] The target signal is a signal used for perception.

[1030] Optionally, the first request includes at least one of the following information:

[1031] Information indicating that the AI ​​unit is in the inference phase;

[1032] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[1033] Configuration identifier of the perception measurement quantity;

[1034] identification of perceptual measurement quantities;

[1035] Information indicating the perceptual characteristics of the target dataset;

[1036] The identifier of the target dataset;

[1037] Configuration information of perceptual measurements required for model inference;

[1038] Information indicating a threshold number of perceptual measurements required for model inference;

[1039] Information indicating the source of perceptual measurements required for model inference;

[1040] Information indicating the kind of perceptual measurements needed for model inference;

[1041] Information about perceptual patterns that indicate perceptual measurements required for model inference;

[1042] Information used to indicate perceived needs;

[1043] Configuration information of the target signal;

[1044] Information about the device sending the target signal;

[1045] Information on the receiving equipment of the target signal;

[1046] The target data set is the data set used by the AI ​​unit during the training phase;

[1047] The target signal is a signal used for perception.

[1048] Figure 23 shows a structural diagram of a model inference device provided in an embodiment of the present application, which can be applied to a third device. As shown in Figure 23, the model inference device 930 includes:

[1049] A sending module 931 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;

[1050] The first information includes at least one of the following:

[1051] a target communication measurement amount and a target communication measurement amount, wherein the target communication measurement amount and the target communication measurement amount are determined to belong to the same inference sample;

[1052] a target communication measurement amount and a third indication, wherein the target communication measurement amount and the perception measurement amount indicated by the third indication are determined to belong to the same inference sample;

[1053] a target communication measurement amount, wherein the target communication measurement amount and a perception measurement amount of a most recent reasoning sample are determined to belong to the same reasoning sample;

[1054] or,

[1055] The first information includes at least one of the following:

[1056] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[1057] Configuration identifier of the perception measurement quantity;

[1058] identification of perceptual measurement quantities;

[1059] Identification of the perception measurement link;

[1060] Identification of perceived services;

[1061] Identification of the perceived service type;

[1062] Perceptual measurement quantity;

[1063] timestamps of perceived measurements;

[1064] Information about the sending device that senses the measured quantity;

[1065] Perceive the coordinate information of the measured quantity;

[1066] Information indicating a performance indicator of a perceptual measurement quantity;

[1067] Information indicating the source of the perceived measurement;

[1068] Information indicating the type of the perceptual measurement;

[1069] Information indicating the purpose of the perceived measurement;

[1070] information indicating a perceptual mode of a perceptual measurement quantity;

[1071] Communication measurement quantities;

[1072] Communication measurement resource identifier;

[1073] Timestamps of communication measurements;

[1074] Information indicating the first time window;

[1075] Information indicating a first effective time;

[1076] Configuration identification of the target signal;

[1077] Configuration information of the target signal;

[1078] Information about the device sending the target signal;

[1079] Information on the receiving equipment of the target signal;

[1080] The target signal is a signal used for perception.

[1081] Optionally, the third instruction includes at least one of the following:

[1082] Identification of inference samples;

[1083] Identification of the resources used for the communication measurement results;

[1084] Communication measurement result reporting identifier;

[1085] Identification of the resources used to perceive the measured quantity;

[1086] Reporting flag of the perception measurement quantity;

[1087] The identification of the perceptual measurement quantity.

[1088] FIG24 shows a structural diagram of a model reasoning device provided in an embodiment of the present application, which can be applied to the fourth device. As shown in FIG24 , the model reasoning device 940 includes:

[1089] a receiving module 941 configured to receive second information from the first device, where the second information includes an inference result and a fourth indication, where the inference result is obtained by the AI ​​unit using the inference sample;

[1090] The fourth indication is used to indicate at least one of the following:

[1091] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[1092] Configuration identifier of the perception measurement quantity;

[1093] identification of perceptual measurement quantities;

[1094] Identification of the perception measurement link;

[1095] Identification of perceived services;

[1096] Identification of the perceived service type;

[1097] whether the inference sample uses perceptual measurements;

[1098] the perceptual measurement used by the inference sample;

[1099] the timeliness of the perceptual measurements used in the inference samples;

[1100] a sending device of the perceptual measurement quantity used by the inference sample;

[1101] a receiving device of the perceptual measurement quantity used by the inference sample;

[1102] coordinates of the perceptual measurements used by the inference sample;

[1103] the source of the perceptual measurements used in the inference sample;

[1104] a perceptual pattern of perceptual measurements used by the inference sample;

[1105] the level of processing of the perceptual measurements used by the inference samples;

[1106] the perceptual service of the perceptual measurement quantity used by the inference sample;

[1107] the purpose of the perceptual measurements used in the inference sample;

[1108] performance indicators of perceptual measurements used by the inference samples;

[1109] the number of perceptual measurements used by the inference sample;

[1110] the proportion of perceptual measurements used in the inference sample;

[1111] whether the number of perceptual measurements used by the inference sample meets a minimum number threshold;

[1112] whether the ratio of the perceptual measurements used in the inference sample meets a minimum ratio threshold;

[1113] The proportion of perceptual measurements used in the inference sample that meet timeliness requirements;

[1114] The number of perceptual measurements used in the inference sample that meet timeliness requirements;

[1115] Configuration information of the target signal;

[1116] The target signal is a target signal corresponding to the perceptual measurement quantity used by the inference sample.

[1117] The above-mentioned device in the embodiments of the present application can 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 chip. The electronic device can be a terminal, or it can be other devices other than a terminal. For example, the terminal can include but is not limited to the types of terminals listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiments of the present application.

[1118] The above-mentioned device provided in the embodiment of the present application can implement the various processes implemented in the method embodiments of Figures 3 to 20 and achieve the same technical effects. To avoid repetition, they will not be described here.

[1119] As shown in Figure 25, an embodiment of the present application also provides a communication device 1100, including a processor 1101 and a memory 1102, and the memory 1102 stores a program or instruction that can be run on the processor 1101. When the program or instruction is executed by the processor 1101, it implements the various steps of the model reasoning method embodiment of the above-mentioned first device side, or implements the various steps of the model reasoning method embodiment of the above-mentioned second device side, or implements the various steps of the model reasoning method embodiment of the above-mentioned third device side, or implements the various steps of the model reasoning method embodiment of the above-mentioned fourth device side, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[1120] An embodiment of the present application also provides a communication device, including a processor and a communication interface, wherein the processor is used to: obtain an inference sample, the inference sample being determined based on communication measurement-related data and perception measurement-related data; and input the inference sample into an artificial intelligence (AI) unit to obtain an inference result.

[1121] An embodiment of the present application also provides a communication device, including a processor and a communication interface, wherein the communication interface is used 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 used to: perform a first operation, wherein the first operation includes any one of the following: based on the first request, sending a target signal; based on the first request, determining configuration information of the target signal; based on the first request, sending configuration information of the target signal; based on the first request, sending perception measurement-related data; wherein the target signal is a signal used for perception.

[1122] An embodiment of the present application further provides a communication device, comprising a processor and a communication interface, wherein the communication interface is configured to: send first information to a first device, the first information comprising at least one of communication measurement-related data and perception measurement-related data; the first information comprising at least one of the following: a target communication measurement amount and a target communication measurement amount, the target communication measurement amount and the target communication measurement amount being determined to belong to the same inference sample; a target communication measurement amount and a third indication, the target communication measurement amount and the perception measurement amount indicated by the third indication being determined to belong to the same inference sample; a target communication measurement amount, the target communication measurement amount and the perception measurement amount of the most recent inference sample being determined to belong to the same inference sample; or, the first information comprising at least one of the following: a data set identifier, the data set corresponding to the data set identifier comprising perception measurement-related data; a perception measurement amount. 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 the perception measurement quantity; information of a sending device of the perception measurement quantity; coordinate information of the perception measurement quantity; information for indicating a performance indicator of the perception measurement quantity; information for indicating a source of the perception measurement quantity; information for indicating a type of the perception measurement quantity; information for indicating a purpose of the perception measurement quantity; information for indicating a perception mode of the perception measurement quantity; a communication measurement quantity; a communication measurement resource identifier; a timestamp of the communication measurement quantity; information for indicating a first time window; information for indicating a first valid time; a configuration identifier of a target signal; configuration information of the target signal; information of a sending device of the target signal; information of a receiving device of the target signal; wherein the target signal is a signal used for perception.

[1123] An embodiment of the present application further provides a communication device, comprising a processor and a communication interface, wherein the communication interface is used to: receive second information from a first device, the second information comprising an inference result and a fourth indication, the inference result being obtained by an AI unit using an inference sample; wherein the fourth indication is used to indicate at least one of the following: a data set identifier, the data set corresponding to the data set identifier comprising perception measurement-related data; a configuration identifier of the perception measurement quantity; an identifier of the perception measurement quantity; an identifier of the perception measurement link; an identifier of the perception service; an identifier of the perception service type; whether the perception measurement quantity is used in the inference sample; the perception measurement quantity used by the inference sample; the timeliness of the perception measurement quantity used by the inference sample; a sending device of the perception measurement quantity used by the inference sample; a 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 inference The source of the perceptual measurement quantity used by the reasoning sample; the perceptual mode of the perceptual measurement quantity used by the reasoning sample; the processing level of the perceptual measurement quantity used by the reasoning sample; the perceptual service of the perceptual measurement quantity used by the reasoning sample; the purpose of the perceptual measurement quantity used by the reasoning sample; the performance indicator of the perceptual measurement quantity used by the reasoning sample; the number of perceptual measurement quantities used by the reasoning sample; the proportion of the perceptual measurement quantities used by the reasoning sample; whether the number of perceptual measurement quantities used by the reasoning sample meets the minimum number threshold; whether the proportion of the perceptual measurement quantities used by the reasoning sample meets the minimum proportion threshold; the proportion of the perceptual measurement quantities used by the reasoning sample that meet timeliness; the number of the perceptual measurement quantities used by the reasoning sample that meet timeliness; configuration information of the target signal; wherein, the target signal is the target signal corresponding to the perceptual measurement quantity used by the reasoning sample.

[1124] The processor of the above-mentioned communication device is used to run programs or instructions to implement the steps in the method embodiments shown in Figures 3 to 20, and can achieve the same technical effects.

[1125] The above-mentioned communication device can be a terminal or a network-side device.

[1126] Specifically, Figure 26 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

[1127] The terminal 1200 includes but is not limited to: 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 at least some of the components of the processor 1210.

[1128] Those skilled in the art will appreciate that the terminal 1200 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 1210 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system. The terminal structure shown in Figure 26 does not constitute a limitation of the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be described in detail here.

[1129] It should be understood that in an embodiment of the present application, the input unit 1204 may include a graphics processing unit (GPU) 12041 and a microphone 12042, and the graphics processor 12041 processes the image data of a static picture or video 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 a touch panel 12071 and at least one of 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. 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, and a joystick, which will not be repeated here.

[1130] In the embodiment of the present application, after receiving downlink data from a network-side device, the RF unit 1201 may transmit the data to the processor 1210 for processing. Furthermore, the RF unit 1201 may send uplink data to the network-side device. Typically, the RF unit 1201 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.

[1131] 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, wherein the first storage area may store an operating system, applications 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 a volatile memory or a 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 random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 1209 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[1132] Processor 1210 may include one or more processing units. Optionally, processor 1210 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 1210.

[1133] The processor 1210 is configured to:

[1134] Acquire an inference sample, where the inference sample is determined based on communication measurement related data and perception measurement related data;

[1135] The reasoning sample is input into the artificial intelligence AI unit to obtain the reasoning result.

[1136] Optionally, the perception measurement related data includes at least one of the following information:

[1137] Perceptual measurement quantity;

[1138] an indication of the perceived measured quantity;

[1139] timestamps of perceived measurements;

[1140] Information about the sending device that senses the measured quantity;

[1141] Information about the receiving device that perceives the measured quantity;

[1142] Perceive the coordinate information of the measured quantity;

[1143] Information indicating a performance indicator of a perceptual measurement quantity;

[1144] Information indicating the source of the perceived measurement;

[1145] Information indicating the type of the perceptual measurement;

[1146] information indicating a perceptual mode of a perceptual measurement quantity;

[1147] Configuration information of the target signal;

[1148] Information about the device sending the target signal;

[1149] Information on the receiving equipment of the target signal;

[1150] The target signal is a signal used for perception.

[1151] Optionally, the radio frequency unit 1201 is configured to:

[1152] A first request is sent to the second device, where the first request is used to request perception measurement-related data required for model inference.

[1153] Optionally, the first request includes at least one of the following information:

[1154] Information indicating that the AI ​​unit is in the inference phase;

[1155] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[1156] Configuration identifier of the perception measurement quantity;

[1157] identification of perceptual measurement quantities;

[1158] Information indicating the perceptual characteristics of the target dataset;

[1159] The identifier of the target dataset;

[1160] Configuration information of perceptual measurements required for model inference;

[1161] Information indicating a threshold number of perceptual measurements required for model inference;

[1162] Information indicating the source of perceptual measurements required for model inference;

[1163] Information indicating the kind of perceptual measurements needed for model inference;

[1164] Information about perceptual patterns that indicate perceptual measurements required for model inference;

[1165] Information used to indicate perceived needs;

[1166] Configuration information of the target signal;

[1167] Information about the device sending the target signal;

[1168] Information on the receiving equipment of the target signal;

[1169] The target data set is the data set used by the AI ​​unit during the training phase;

[1170] The target signal is a signal used for perception.

[1171] Optionally, the processor 1210 is further configured to perform at least one of the following:

[1172] Acquire an inference sample based on a timestamp of the communication measurement amount, a timestamp of the perception measurement amount, and a valid duration of the perception measurement amount;

[1173] Acquire an inference sample based on a timestamp corresponding to a prediction result of the AI ​​unit, a timestamp of the perception measurement quantity, and a valid duration of the perception measurement quantity;

[1174] Obtaining an inference sample based on the first indication and a timestamp of the communication measurement;

[1175] Obtaining an inference sample based on the first indication and a timestamp corresponding to the prediction result of the AI ​​unit;

[1176] obtaining an inference sample based on whether the second indication is received;

[1177] The first indication is used to indicate the failure time or failure time difference of the sensed measurement quantity;

[1178] The second indication is used to indicate that the perceived measurement quantity is invalid.

[1179] Optionally, a method for determining the effective duration of the perception measurement value includes at least one of the following:

[1180] In the case where a first valid duration is pre-configured or defined, the valid duration of the perception measurement value is the first valid duration;

[1181] In a case where a second valid duration is preconfigured or defined and the target signal carries a time adjustment value, the valid duration of the perception measurement value is determined according to the second valid duration and the time adjustment value;

[1182] In the case where the target signal carries a third valid duration, the valid duration of the perception measurement value is the third valid duration;

[1183] The target signal is a signal used for perception.

[1184] Optionally, the processor 1210 is further configured to perform at least one of the following:

[1185] When the time corresponding to the timestamp of the communication measurement amount is earlier than the first time, obtaining an inference sample including communication measurement related data and perception measurement related data;

[1186] When the timestamp corresponding to the prediction result of the AI ​​unit is earlier than the first time, obtaining an inference sample including communication measurement-related data and perception measurement-related data;

[1187] When the time corresponding to the timestamp of the communication measurement amount is earlier than the second time, obtaining an inference sample including communication measurement related data and perception measurement related data;

[1188] When the timestamp corresponding to the prediction result of the AI ​​unit is earlier than the second time, obtaining an inference sample including communication measurement-related data and perception measurement-related data;

[1189] In a case where the first device does not receive the second indication, obtaining an inference sample including communication measurement related data and perception measurement related data;

[1190] The first time is the time corresponding to the timestamp of the perception measurement amount superimposed on the valid duration of the perception measurement amount;

[1191] The second time is an expiration time of the perception measurement quantity determined based on the first indication.

[1192] Optionally, the radio frequency unit 1201 is configured to:

[1193] receiving first information from a third device, where the first information includes at least one of communication measurement-related data and perception measurement-related data;

[1194] The processor 1210 is further configured to:

[1195] Acquire an inference sample based on the first information; or acquire an inference sample based on the first information and stored historical data;

[1196] The historical data includes at least one of communication measurement related data and perception measurement related data.

[1197] Optionally, the first information includes at least one of the following:

[1198] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[1199] Configuration identifier of the perception measurement quantity;

[1200] identification of perceptual measurement quantities;

[1201] Identification of the perception measurement link;

[1202] Identification of perceived services;

[1203] Identification of the perceived service type;

[1204] Perceptual measurement quantity;

[1205] timestamps of perceived measurements;

[1206] Information about the sending device that senses the measured quantity;

[1207] Perceive the coordinate information of the measured quantity;

[1208] Information indicating a performance indicator of a perceptual measurement quantity;

[1209] Information indicating the source of the perceived measurement;

[1210] Information indicating the type of the perceptual measurement;

[1211] Information indicating the purpose of the perceived measurement;

[1212] information indicating a perceptual mode of a perceptual measurement quantity;

[1213] Communication measurement quantities;

[1214] Communication measurement resource identifier;

[1215] Timestamps of communication measurements;

[1216] Information indicating the first time window;

[1217] Information indicating a first effective time;

[1218] Configuration identification of the target signal;

[1219] Configuration information of the target signal;

[1220] Information about the device sending the target signal;

[1221] Information on the receiving equipment of the target signal;

[1222] The target signal is a signal used for perception.

[1223] Optionally, the processor 1210 is further configured to perform at least one of the following:

[1224] When a time difference between a timestamp of the perception measurement amount and a timestamp of the communication measurement amount is less than or equal to a first time window indicated by the first information, acquiring an inference sample including communication measurement-related data and perception measurement-related data;

[1225] In a case where a time difference between a timestamp of the perception measurement amount and a timestamp of the communication measurement amount is less than or equal to a predefined second time window, an inference sample including communication measurement related data and perception measurement related data is acquired.

[1226] Optionally, the first information includes a target perception measurement and a timestamp of the target perception measurement;

[1227] The processor 1210 is further configured to:

[1228] Acquiring an inference sample including a target communication measurement and the target perception measurement;

[1229] The target communication measurement amount includes at least one of the following:

[1230] The difference between the timestamp of the historical data and the timestamp of the target perception measurement amount is less than or equal to the communication measurement amount of the first time window indicated by the first information;

[1231] A difference between a timestamp of the historical data and a timestamp of the target perception measurement value is less than or equal to a communication measurement value of a predefined second time window.

[1232] Optionally, the first information includes a target communication measurement amount and a timestamp of the target communication measurement amount;

[1233] The processor 1210 is further configured to:

[1234] Acquiring an inference sample including the target communication measurement quantity and the target perception measurement quantity;

[1235] The target perception measurement includes at least one of the following:

[1236] A time difference between a timestamp of the historical data and a timestamp of the target communication measurement amount is less than or equal to a perception measurement amount of a first time window indicated by the first information;

[1237] The timestamp of the historical data is less than or equal to the perception measurement quantity of the first valid time indicated by the first information;

[1238] The timestamp of the historical data is less than or equal to the perception measurement quantity of the predefined second validity time.

[1239] Optionally, the processor 1210 is further configured to:

[1240] obtaining an inference sample including a target communication measurement and a target perception measurement;

[1241] The first information includes the target communication measurement amount and the target communication measurement amount; or

[1242] The first information includes the target communication measurement value and a third indication, and the target perception measurement value is the perception measurement value corresponding to the third indication; or

[1243] The first information includes the target communication measurement value, and the target perception measurement value is the perception measurement value of a most recent inference sample.

[1244] Optionally, the third instruction includes at least one of the following:

[1245] Identification of inference samples;

[1246] Identification of the resources used for the communication measurement results;

[1247] Communication measurement result reporting identifier;

[1248] Identification of the resources used to perceive the measured quantity;

[1249] Reporting flag of the perception measurement quantity;

[1250] The identification of the perceptual measurement quantity.

[1251] Optionally, the radio frequency unit 1201 is further configured to:

[1252] Sending second information to a fourth device, where the second information includes the inference result of the AI ​​unit and a fourth indication;

[1253] The fourth indication is used to indicate at least one of the following:

[1254] A data set identifier, where the data set corresponding to the data set identifier includes perception measurement related data;

[1255] Configuration identifier of the perception measurement quantity;

[1256] identification of perceptual measurement quantities;

[1257] Identification of the perception measurement link;

[1258] Identification of perceived services;

[1259] Identification of the perceived service type;

[1260] whether the inference sample uses perceptual measurements;

[1261] the perceptual measurement used by the inference sample;

[1262] the timeliness of the perceptual measurements used in the inference samples;

[1263] a sending device of the perceptual measurement quantity used by the inference sample;

[1264] a receiving device of the perceptual measurement quantity used by the inference sample;

[1265] coordinates of the perceptual measurements used by the inference sample;

[1266] the source of the perceptual measurements used in the inference sample;

[1267] a perceptual pattern of perceptual measurements used by the inference sample;

[1268] the level of processing of the perceptual measurements used by the inference samples;

[1269] the perceptual service of the perceptual measurement quantity used by the inference sample;

[1270] the purpose of the perceptual measurements used in the inference sample;

[1271] performance indicators of perceptual measurements used by the inference samples;

[1272] the number of perceptual measurements used by the inference sample;

[1273] the proportion of perceptual measurements used in the inference sample;

[1274] whether the number of perceptual measurements used by the inference sample meets a minimum number threshold;

[1275] whether the ratio of the perceptual measurements used in the inference sample meets a minimum ratio threshold;

[1276] The proportion of perceptual measurements used in the inference sample that meet timeliness requirements;

[1277] The number of perceptual measurements used in the inference sample that meet timeliness requirements;

[1278] Configuration information of the target signal;

[1279] The target signal is a target signal corresponding to the perceptual measurement quantity used by the inference sample.

[1280] In summary, in the embodiments of the present application, by proposing a perception-assisted model reasoning data collection method, network nodes can expand the data information used for model reasoning by acquiring perception information, thereby improving the reasoning accuracy of the AI ​​model.

[1281] It can be understood that the implementation process of each implementation method mentioned in this embodiment can be the relevant description of the method embodiments of Figures 3 to 20, and achieve the same or corresponding technical effects. To avoid repetition, they will not be repeated here.

[1282] Specifically, embodiments of the present application also provide a network-side device. As shown in Figure 27, 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 via 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 transmitted and sends it to the radio frequency device 132. The radio frequency device 132 processes the received information and then sends it through the antenna 131.

[1283] The methods performed by the first device, the second device, the third device, and the fourth device in the above embodiments can all be implemented in the baseband device 133, which includes a baseband processor.

[1284] The baseband device 133 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in Figure 27, one of which 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 network device operations shown in the above method embodiment.

[1285] The network side device may further include a network interface 136 , which is, for example, a Common Public Radio Interface (CPRI).

[1286] Specifically, the network side device 1300 of the embodiment of the present application also includes: instructions or programs stored in the memory 135 and can be run on the processor 134. The processor 134 calls the instructions or programs in the memory 135 to execute the methods executed by the modules shown in Figures 21 to 24 and achieve the same technical effects. To avoid repetition, they will not be repeated here.

[1287] Specifically, the embodiment of the present application further provides a network side device. As shown in FIG28 , the network side device 1400 includes: a processor 1401, a network interface 1402, and a memory 1403. The network interface 1402 is, for example, a common public radio interface (CPRI).

[1288] Specifically, the network side device 1400 of the embodiment of the present application also includes: instructions or programs stored in the memory 1403 and executable on the processor 1401. The processor 1401 calls the instructions or programs in the memory 1403 to execute the methods executed by the modules shown in Figures 21 to 24 and achieve the same technical effect. To avoid repetition, they will not be elaborated here.

[1289] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the method embodiments of Figures 3 to 20 are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[1290] The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[1291] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the method embodiments of Figures 3 to 20, and can achieve the same technical effects. To avoid repetition, they will not be repeated here.

[1292] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[1293] An embodiment of the present application further provides a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the method embodiments of Figures 3 to 20, and can achieve the same technical effects. To avoid repetition, they are not described here.

[1294] An embodiment of the present application also provides a communication system, including: a first device and a second device, wherein the first device can be used to execute the steps of the model reasoning method on the first device side as described above, and the second device can be used to execute the steps of the model reasoning method on the second device side as described above.

[1295] 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.

[1296] Optionally, the communication system also 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.

[1297] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the 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 the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[1298] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.

[1299] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. A model reasoning method, comprising: The first device acquires an inference sample, where the inference sample is determined based on communication measurement related data and perception measurement related data; The first device inputs the reasoning sample into an artificial intelligence (AI) unit to obtain a reasoning result.

2. The method according to claim 1, wherein: The perception measurement related data includes at least one of the following information: Perceptual measurement quantity; an indication of the perceived measured quantity; timestamps of perceived measurements; Information about the sending device that senses the measured quantity; Information about the receiving device that perceives the measured quantity; Perceive the coordinate information of the measured quantity; information indicating a performance indicator of a perceptual measurement quantity; Information indicating the origin of the perceived measurement quantity; Information indicating the type of the perceptual measurement; information indicating a perceptual mode of a perceptual measurement quantity; Configuration information of the target signal; Information about the device sending the target signal; Information on the receiving equipment of the target signal; The target signal is a signal used for perception.

3. The method according to claim 1 or 2, wherein: The method further comprises: The first device sends a first request to the second device, where the first request is used to request perception measurement related data required for model reasoning.

4. The method according to claim 3, wherein: The first request includes at least one of the following information: Information indicating that the AI ​​unit is in the inference phase; A data set identifier, wherein the data set corresponding to the data set identifier includes perception measurement related data; Configuration identifier of the perception measurement quantity; the identification of the perceived measurement quantity; Information indicating the perceptual characteristics of the target dataset; The identifier of the target dataset; Configuration information of perceptual measurements required for model reasoning; Information indicating a threshold number of perceptual measurements required for model inference; Information indicating the source of perceptual measurements needed for model inference; Information indicating the kind of perceptual measurements needed for model inference; Information about perceptual patterns that indicate perceptual measurements needed for model inference; Information used to indicate perceived needs; Configuration information of the target signal; Information about the device sending the target signal; Information on the receiving equipment of the target signal; 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.

5. The method according to any one of claims 1 to 4, wherein: The first device obtains the inference sample, including at least one of the following: The first device acquires an inference sample based on a timestamp of the communication measurement amount, a timestamp of the perception measurement amount, and a valid duration of the perception measurement amount; The first device acquires an inference sample based on a timestamp corresponding to a prediction result of the AI ​​unit, a timestamp of the perception measurement amount, and a valid duration of the perception measurement amount; The first device acquires an inference sample based on the first indication and a timestamp of the communication measurement amount; The first device acquires an inference sample based on the first indication and a timestamp corresponding to the prediction result of the AI ​​unit; The first device obtains an inference sample based on whether the second indication is received; The first indication is used to indicate the failure time or failure time difference of the perceived measurement quantity; The second indication is used to indicate that the perceived measurement quantity is invalid.

6. The method according to claim 5, wherein: The method for determining the effective duration of the perception measurement quantity includes at least one of the following: In the case where a first valid duration is preconfigured or defined, the valid duration of the perception measurement quantity is the first valid duration; In a case where a second effective duration is preconfigured or defined, and the target signal carries a time adjustment value, the effective duration of the perception measurement value is determined according to the second effective duration and the time adjustment value; In the case where the target signal carries a third valid duration, the valid duration of the perception measurement amount is the third valid duration; The target signal is a signal used for perception.

7. The method according to claim 5 or 6, wherein: The first device acquires the inference sample based on the timestamp of the communication measurement amount, the timestamp of the perception measurement amount, and the effective duration of the perception measurement amount, including: In a case where the time corresponding to the timestamp of the communication measurement amount is earlier than the first time, the first device acquires an inference sample including communication measurement related data and perception measurement related data; The first device acquires an inference sample based on a timestamp corresponding to a prediction result of the AI ​​unit, a timestamp of the perception measurement amount, and a valid duration of the perception measurement amount, including: In a case where a timestamp corresponding to a prediction result of the AI ​​unit is earlier than a first time, the first device acquires an inference sample including communication measurement-related data and perception measurement-related data; The first device obtains the inference sample based on the first indication and the timestamp of the communication measurement amount, including: In a case where the time corresponding to the timestamp of the communication measurement amount is earlier than the second time, the first device acquires an inference sample including communication measurement related data and perception measurement related data; The first device acquires an inference sample based on the first indication and a timestamp corresponding to the prediction result of the AI ​​unit, including: In a case where a timestamp corresponding to a prediction result of the AI ​​unit is earlier than a second time, the first device acquires an inference sample including communication measurement-related data and perception measurement-related data; The first device obtains the inference sample based on whether the second indication is received, including: In a case where the first device does not receive the second indication, the first device acquires an inference sample including communication measurement related data and perception measurement related data; The first time is the time corresponding to the timestamp of the perception measurement amount superimposed on the effective duration of the perception measurement amount; The second time is an expiration time of the perception measurement quantity determined based on the first indication.

8. The method according to any one of claims 1 to 4, wherein: The first device obtains an inference sample, including: 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; The first device acquires the inference sample based on the first information; or the first device acquires the inference sample based on the first information and stored historical data; The historical data includes at least one of communication measurement related data and perception measurement related data.

9. The method according to claim 8, wherein: The first information includes at least one of the following: A data set identifier, wherein the data set corresponding to the data set identifier includes perception measurement related data; Configuration identifier of the perception measurement quantity; the identification of the perceived measurement quantity; Identification of the sensing measurement link; Perceive the identity of the business; Identification of perceived business type; Perceptual measurement quantity; timestamps of perceived measurements; Information about the sending device that senses the measured quantity; Perceive the coordinate information of the measured quantity; information indicating a performance indicator of a perceptual measurement quantity; Information indicating the origin of the perceived measurement quantity; Information indicating the type of the perceptual measurement; Information indicating the purpose of the perceived measurement; information indicating a perceptual mode of a perceptual measurement quantity; Communication measurements; Communication measurement resource identifier; Timestamps of communication measurements; Information for indicating the first time window; Information for indicating a first effective time; Configuration identification of the target signal; Configuration information of the target signal; Information about the device sending the target signal; Information on the receiving equipment of the target signal; The target signal is a signal used for perception.

10. The method according to claim 8 or 9, wherein: The first device obtains the inference sample, including at least one of the following: In a case where a time difference between a timestamp of the perception measurement amount and a timestamp of the communication measurement amount is less than or equal to a first time window indicated by the first information, the first device acquires an inference sample including communication measurement related data and perception measurement related data; In a case where a time difference between a timestamp of the perception measurement amount and a timestamp of the communication measurement amount is less than or equal to a predefined second time window, the first device acquires an inference sample including communication measurement related data and perception measurement related data.

11. The method according to claim 8 or 9, wherein: The first information includes a target perception measurement and a timestamp of the target perception measurement; The first device obtains an inference sample based on the first information and the stored historical data, including: The first device obtains an inference sample including a target communication measurement amount and the target perception measurement amount; The target communication measurement amount includes at least one of the following: The difference between the timestamp of the historical data and the timestamp of the target perception measurement amount is less than or equal to the communication measurement amount of the first time window indicated by the first information; A difference between a timestamp of the historical data and a timestamp of the target perception measurement amount is less than or equal to a communication measurement amount of a predefined second time window.

12. The method according to claim 8 or 9, wherein: The first information includes a target communication measurement amount and a timestamp of the target communication measurement amount; The first device obtains an inference sample based on the first information and the stored historical data, including: The first device obtains an inference sample including the target communication measurement amount and the target perception measurement amount; The target perception measurement includes at least one of the following: The time difference between the timestamp of the historical data and the timestamp of the target communication measurement amount is less than or equal to the perception measurement amount of the first time window indicated by the first information; The timestamp of the historical data is less than or equal to the perceived measurement quantity of the first valid time indicated by the first information; The timestamp of the historical data is less than or equal to the perception measurement quantity of the predefined second validity time.

13. The method according to claim 8 or 9, wherein: The first device acquires an inference sample based on the first information, including: The first device obtains an inference sample including a target communication measurement amount and a target perception measurement amount; The first information includes the target communication measurement amount and the target communication measurement amount; or, The first information includes the target communication measurement amount and a third indication, and the target perception measurement amount is the perception measurement amount corresponding to the third indication; or, The first information includes the target communication measurement value, and the target perception measurement value is a perception measurement value of a most recent inference sample.

14. The method according to claim 13, wherein: The third instruction includes at least one of the following: Identification of inference samples; Identification of resources used for communication measurements; Communication measurement result reporting mark; Identification of the resources used to sense the measured quantity; Reporting flag of the perception measurement quantity; The identification of the perceptual measurement quantity.

15. The method according to any one of claims 1 to 14, wherein: The method further comprises: 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; The fourth indication is used to indicate at least one of the following: A data set identifier, wherein the data set corresponding to the data set identifier includes perception measurement related data; Configuration identifier of the perception measurement quantity; the identification of the perceived measurement quantity; Identification of the sensing measurement link; Perceive the identity of the business; Identification of perceived business type; whether the inference sample uses perceptual measurements; the perceptual measurement used by the inference sample; the timeliness of the perceptual measurements used by the inference samples; a sending device of the perceptual measurement quantity used by the inference sample; a receiving device of the perceptual measurements used by the inference samples; coordinates of the perceptual measurements used by the inference sample; the source of the perceptual measurements used by the inference sample; a perceptual pattern of perceptual measurements used by the inference sample; a level of processing of the perceptual measurements used by the inference samples; the perceptual service of the perceptual measurement quantity used by the inference sample; the purpose of the perceptual measurements used by the inference sample; a performance indicator of the perceptual measurement used by the inference sample; the number of perceptual measurements used by the inference sample; the proportion of perceptual measurements used by the inference sample; Whether the number of perceptual measurements used by the inference sample meets a minimum number threshold; Whether the ratio of the perceptual measurements used by the inference sample meets a minimum ratio threshold; The proportion of perceptual measurements used by the inference sample that meet timeliness; The number of perceptual measurements used by the inference sample that meet timeliness requirements; Configuration information of the target signal; The target signal is a target signal corresponding to the perceptual measurement quantity used by the inference sample.

16. A model reasoning method, comprising: The second device receives a first request from the first device, where the first request is used to request perceptual measurement related data required for model inference; The second device performs a first operation, wherein 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 configuration information of the target signal based on the first request; The second device sends configuration information of the target signal based on the first request; The second device sends the perception measurement related data based on the first request; 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 indicating that the AI ​​unit is in the inference phase; A data set identifier, wherein the data set corresponding to the data set identifier includes perception measurement related data; Configuration identifier of the perception measurement quantity; the identification of the perceived measurement quantity; Information indicating the perceptual characteristics of the target dataset; The identifier of the target dataset; Configuration information of perceptual measurements required for model reasoning; Information indicating a threshold number of perceptual measurements required for model inference; Information indicating the source of perceptual measurements needed for model inference; Information indicating the kind of perceptual measurements needed for model inference; Information about perceptual patterns that indicate perceptual measurements needed for model inference; Information used to indicate perceived needs; Configuration information of the target signal; Information about the device sending the target signal; Information on the receiving equipment of the target signal; 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 reasoning device, applied to a first device, comprising: A first processing module, configured to obtain an inference sample, wherein the inference sample is determined based on communication measurement related data and perception measurement related data; The second processing module is used to input the reasoning sample into the artificial intelligence AI unit to obtain the reasoning result.

19. The device according to claim 18, wherein: Also includes: The first sending module is used to send a first request to the second device, where the first request is used to request perception measurement related data required for model reasoning.

20. The device according to claim 18 or 19, wherein: The first processing module is specifically used for at least one of the following: Acquire an inference sample based on a timestamp of the communication measurement amount, a timestamp of the perception measurement amount, and a valid duration of the perception measurement amount; Acquire an inference sample based on a timestamp corresponding to a prediction result of the AI ​​unit, a timestamp of the perception measurement quantity, and a valid duration of the perception measurement quantity; Obtaining an inference sample based on the first indication and a timestamp of the communication measurement; Acquire an inference sample based on the first indication and a timestamp corresponding to the prediction result of the AI ​​unit; acquiring an inference sample based on whether the second indication is received; The first indication is used to indicate the failure time or failure time difference of the perceived measurement quantity; The second indication is used to indicate that the perceived measurement quantity is invalid.

21. The device according to claim 18 or 19, wherein: The first processing module comprises: A receiving unit, configured to receive first information from a third device, wherein the first information includes at least one of communication measurement related data and perception measurement related data; A processing unit, configured to obtain an inference sample based on the first information; or to obtain an inference sample based on the first information and stored historical data; The historical data includes at least one of communication measurement related data and perception measurement related data.

22. The device according to any one of claims 18 to 21, wherein Also includes: A second sending module, configured to send second information to a fourth device, wherein the second information includes an inference result of the AI ​​unit and a fourth indication; The fourth indication is used to indicate at least one of the following: A data set identifier, wherein the data set corresponding to the data set identifier includes perception measurement related data; Configuration identifier of the perception measurement quantity; the identification of the perceived measurement quantity; Identification of the sensing measurement link; Perceive the identity of the business; Identification of perceived business type; whether the inference sample uses perceptual measurements; the perceptual measurement used by the inference sample; the timeliness of the perceptual measurements used by the inference samples; a sending device of the perceptual measurement quantity used by the inference sample; a receiving device of the perceptual measurements used by the inference samples; coordinates of the perceptual measurements used by the inference sample; the source of the perceptual measurements used by the inference sample; a perceptual pattern of perceptual measurements used by the inference sample; a level of processing of the perceptual measurements used by the inference samples; the perceptual service of the perceptual measurement quantity used by the inference sample; the purpose of the perceptual measurements used by the inference sample; a performance indicator of the perceptual measurement used by the inference sample; the number of perceptual measurements used by the inference sample; the proportion of perceptual measurements used by the inference sample; Whether the number of perceptual measurements used by the inference sample meets a minimum number threshold; Whether the ratio of the perceptual measurements used by the inference sample meets a minimum ratio threshold; The proportion of perceptual measurements used by the inference sample that meet timeliness; The number of perceptual measurements used by the inference sample that meet timeliness requirements; Configuration information of the target signal; The target signal is a target signal corresponding to the perceptual measurement quantity used by the inference sample.

23. A model reasoning device, applied to a second device, comprising: A receiving module, configured to receive a first request from a first device, wherein the first request is used to request perceptual measurement related data required for model reasoning; A processing module is used to perform a first operation, wherein 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 configuration information of the target signal based on the first request; The second device sends configuration information of the target signal based on the first request; The second device sends the perception measurement related data based on the first request; The target signal is a signal used for perception.

24. A communication device, comprising a processor and a memory, wherein the memory stores a program or instruction executable on the processor, wherein the program or instruction implements the steps of the method according to any one of claims 1 to 17 when executed by the processor.

25. A readable storage medium storing a program or an instruction, wherein the program or the instruction is executed by a processor to implement the steps of the method according to any one of claims 1 to 17.

Images