Communication method and communication apparatus

Abstract

A communication method and a communication apparatus. The method comprises: receiving first information from a second communication device, the first information indicating a first artificial intelligence (AI) model or a first perception result, the first AI model being used for processing perception data, and the first perception result being a perception result required by the second communication device; and, on the basis of the first information, sending second information, the second information indicating a second perception result, and the second perception result being determined on the basis of the first AI model or the first perception result. In the method and apparatus provided in the embodiments of the present application, on one hand, a first communication device can determine the second perception result on the basis of the received first information, thus implementing AI model-based perception; on the other hand, the first communication device provides the existing first perception result to the second communication device, so that there is no need to perform inference again in response to the first information, thus saving resources occupied by inference, reducing the delay of obtaining the second perception result, and improving communication efficiency.

Description

Communication methods and communication devices

[0001] This application claims priority to Chinese Patent Application No. 202410710025.4, filed with the China National Intellectual Property Administration on May 31, 2024, entitled "Communication Method and Communication Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and more specifically, to a communication method and a communication device. Background Technology

[0003] With the improvement of data storage and computing power, artificial intelligence (AI) technology is being used more and more. AI technology can be applied to communication systems such as New Radio (NR) systems to improve network performance and user experience by intelligently collecting and analyzing data.

[0004] The 3rd generation partnership project (3GPP) has introduced several AI application scenarios, such as using AI for channel state information (CSI) compression and feedback, CSI prediction, beam management (BM), and positioning.

[0005] Expanding AI application scenarios and improving network performance and user experience in other application scenarios are urgent problems to be solved. Summary of the Invention

[0006] This application provides a communication method and a communication device that can perform AI-based perception of a target environment or target space.

[0007] Firstly, a communication method is provided. This method can be executed by a first communication device. Unless otherwise specified, the "first communication device" in this application can refer to the first communication device itself (e.g., a network device, or a terminal device), a component within the first communication device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the first communication device. For ease of description, the following explanation uses execution by a first communication device as an example.

[0008] The method includes: receiving first information from a second communication device, the first information indicating a first artificial intelligence (AI) model and / or a first perception result, the first AI model being used for perception data processing, and the first perception result being a perception result required by the second communication device; determining a second perception result based on the first AI model and / or the first perception result; and sending second information indicating the second perception result.

[0009] Based on the solution provided in the embodiments of this application, the first communication device can determine the second sensing result by receiving the first information from the second communication device, and send the second information indicating the second sensing result to the second communication device.

[0010] For example, if the first information is used to indicate the first AI model, the first communication device can determine the first AI model through the first information sent by the second communication device, and determine the second perception result based on the first AI model.

[0011] For example, if the first information is used to indicate a first sensing result, the first communication device can determine the first sensing result required by the second communication device through the first information sent by the second communication device, and provide the first sensing result to the second communication device. In this case, the aforementioned second sensing result is the same as the first sensing result. When the first information is used to indicate a first sensing result, if the first communication device has already determined a first sensing result before determining the first sensing result in response to the first information, it can provide the determined first sensing result as the aforementioned second sensing result to the second communication device; or, the first communication device determines the first sensing result in response to the first information and provides the first sensing result as the aforementioned second sensing result to the second communication device.

[0012] In summary, on the one hand, the first communication device can determine the second perception result based on the first AI model indicated by the received first information, and provide the second perception result to the second communication device, thereby realizing perception based on the AI ​​model. On the other hand, the first communication device can determine the perception result required by the second communication device based on the first perception result indicated by the received first information, and provide the required perception result to the second communication device. If the perception result required by the second communication device is the first perception result already determined by the first communication device, the first communication device can provide the existing first perception result to the second communication device without having to reason again in response to the first information, which can save the resources occupied by reasoning, reduce the latency of obtaining the second perception result, and improve communication efficiency.

[0013] In some possible implementations, perception includes: environmental perception, scene perception, or environmental reconstruction.

[0014] Based on the solution provided in the embodiments of this application, the second communication device can determine the perception result of the environment or scene or the perception result of environment reconstruction based on the second perception result indicated by the received second information, thus enriching the application scenarios of the AI ​​model.

[0015] In some possible implementations, the first information indicates a first AI model and / or a first perception result, including: the first information includes a first identifier, the first identifier and a first relationship used to determine the first AI model and / or the first perception result; wherein, the first identifier includes an identifier and / or a functional identifier of the first AI model, the functional identifier indicates the functions supported by the first AI model, the first relationship is the association between the first identifier and at least one of the following: input information, output information, area information, or at least one AI model; the input information indicates the input of the first AI model, the output information indicates the output of the first AI model, the area information indicates the area where the second communication device can acquire information for perception, and the first AI model is one of at least one AI model.

[0016] Based on the solution provided in the embodiments of this application, the first communication device can determine the first AI model through the first identifier in the first information and the known first relationship. The first relationship indicates the relationship between the first identifier and the information of the first AI model (such as the input information, the output information, or the information of the region, etc.), so that the first communication device can accurately determine the first AI model and improve the accuracy of the solution.

[0017] In some possible implementations, the input to the first AI model is obtained based on the geometric information of objects in the environment.

[0018] In some possible implementations, the input to the first AI model includes at least one of the following: point data, patch data, octree data, or voxel data.

[0019] In some possible implementations, the output of the first AI model includes at least one of the following: point data, patch data, bounding box location, or semantic label.

[0020] In some possible implementations, the method further includes: receiving inference requirement indication information, wherein the first identifier, the first relation, and the inference requirement indication information are used to determine the first AI model.

[0021] Based on the solution provided in the embodiments of this application, the first communication device can determine the first AI model through inference requirement indication information, a first identifier, and a known first relationship. The inference requirement indication information indicates the performance of the first AI model (e.g., the inference requirement indication information indicates that the first AI model is a model that focuses on latency among multiple AI models, or the first AI model is a model that focuses on performance among multiple AI models), so that the first communication device can determine the first AI model according to the inference requirements, thereby improving the rationality of the solution.

[0022] In some possible implementations, the first information also indicates the input and / or output of the first AI model.

[0023] Based on the solution provided in the embodiments of this application, the first communication device can determine the first AI model through the input and / or output of the first AI model, the first identifier and the known first relationship. The input and / or output of the first AI model and the first relationship together indicate the relationship between the first identifier and the information of the first AI model (such as the input information, the output information, or the information of the region, etc.), so that the first communication device can accurately determine the first AI model and improve the accuracy of the solution.

[0024] In some possible implementations, the method further includes, upon satisfying the first condition, sending a first instruction message, which instructs a second communication device to send input to a first AI model, the input of which is used to determine a second perception result based on the first AI model; wherein the first condition includes at least one of the following: the first perception result fails; or, a first performance value is greater than a first threshold, the first performance value being determined by the first communication device based on the first perception result and first data from the second communication device, the first data including at least one of the following: point data, patch data, or voxel data.

[0025] Based on the solution provided in this application embodiment, when the first communication device determines that the first perception result is invalid or the first performance value is greater than the first threshold, the first communication device instructs the second communication device to send the input of the first AI model through the first indication information. The first communication device determines the second perception result by receiving the input of the first AI model from the second communication device and the determined first AI model, thereby re-determining the perception result when the first perception result is not ideal, making the second perception result more reliable and improving the reliability of the solution.

[0026] In some possible implementations, the method also includes sending a second indication message indicating that the first condition is not met.

[0027] In some possible implementations, the method also includes storing the first or second perception result.

[0028] Secondly, a communication method is provided. This method can be executed by a second communication device. Unless otherwise specified, the "second communication device" in this application can refer to the second communication device itself (e.g., a network device, or a terminal device), a component within the second communication device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the second communication device. For ease of description, the following description uses execution by a second communication device as an example.

[0029] The method includes: sending first information, the first information indicating a first AI model and / or a first perception result, the first AI model being used for perception data processing, the first perception result being a perception result required by a second communication device; and receiving second information from the first communication device, the second information indicating a second perception result, the second perception result being determined based on the first AI model or the first perception result.

[0030] In some possible implementations, perception includes: environmental perception, scene perception, or environmental reconstruction.

[0031] In some possible implementations, the first information indicates a first AI model and / or a first perception result, including: the first information includes a first identifier, the first identifier and a first relationship used to determine the first AI model and / or the first perception result; wherein, the first identifier includes an identifier and / or a functional identifier of the first AI model, the functional identifier indicates the functions supported by the first AI model, the first relationship is the association between the first identifier and at least one of the following: input information, output information, area information, or at least one AI model; the input information indicates the input of the first AI model, the output information indicates the output of the first AI model, the area information indicates the area where the second communication device can acquire information for perception, and the first AI model is one of at least one AI model.

[0032] In some possible implementations, the input to the first AI model is obtained based on the geometric information of objects in the environment.

[0033] In some possible implementations, the input to the first AI model includes at least one of the following: point data, patch data, octree data, or voxel data.

[0034] In some possible implementations, the output of the first AI model includes at least one of the following: point data, patch data, bounding box location, or semantic label.

[0035] In some possible implementations, the method further includes: sending inference requirement indication information, wherein the first identifier, the first relationship, and the inference requirement indication information are used to determine the first AI model.

[0036] In some possible implementations, the first information also indicates the input and / or output of the first AI model.

[0037] In some possible implementations, the method further includes, upon satisfying the first condition, receiving first instruction information from a first communication device, the first instruction information instructing a second communication device to send input to a first AI model, the input to the first AI model being used to determine a second perception result based on the first AI model: wherein the first condition includes at least one of the following: the first perception result fails; or, a first performance value is greater than a first threshold, the first performance value being determined by the first communication device based on the first perception result and first data from the second communication device, the first data including at least one of the following: point data, patch data, or voxel data.

[0038] In some possible implementations, the method further includes receiving a second indication message indicating that the first condition is not met.

[0039] Among some possible implementations, the method also includes storing the second perception result.

[0040] Thirdly, a communication method is provided. This method can be executed by a first communication device or a second communication device. Unless otherwise specified, "first communication device or second communication device" in this application can refer to the first or second communication device itself (e.g., a network device, or a terminal device), a component within the first or second communication device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the first or second communication device. For ease of description, the following explanation uses execution by a first or second communication device as an example.

[0041] The method includes: deploying a first relationship, which, together with a first identifier, determines a first AI model and / or a first perception result, wherein the first AI model is used for perception data processing; wherein the first identifier includes an identifier and / or a function identifier of the first AI model, the function identifier indicating the function supported by the first AI model, the first relationship being an association between the first identifier and at least one of the following: input information, output information, region information, or at least one AI model; the input information indicating the input of the first AI model, the output information indicating the output of the first AI model, the region information indicating the region in which a second communication device can acquire information for perception, and the first AI model being one of at least one AI model.

[0042] In some possible implementations, perception includes: environmental perception, scene perception, or environmental reconstruction.

[0043] In some possible implementations, the input to the first AI model is obtained based on the geometric information of objects in the environment.

[0044] In some possible implementations, the input to the first AI model includes at least one of the following: point data, patch data, octree data, or voxel data.

[0045] In some possible implementations, the output of the first AI model includes at least one of the following: point data, patch data, bounding box location, or semantic label.

[0046] Fourthly, a communication device is provided, which may be a network device / terminal device, or a chip, circuit or chip system configured in a network device / terminal device, and the embodiments of this application do not limit this.

[0047] The device includes: a transceiver unit for receiving first information from a second communication device, the first information indicating a first artificial intelligence (AI) model and / or a first perception result, the first AI model being used for perception data processing, and the first perception result being a perception result required by the second communication device; a processing unit for determining a second perception result based on the first AI model and / or the first perception result; the transceiver unit is also used to send second information, the second information indicating the second perception result.

[0048] In some possible implementations, perception includes: environmental perception, scene perception, or environmental reconstruction.

[0049] In some possible implementations, the first information indicates a first AI model and / or a first perception result, including: the first information includes a first identifier, the first identifier and a first relationship used to determine the first AI model and / or the first perception result; wherein, the first identifier includes an identifier and / or a functional identifier of the first AI model, the functional identifier indicates the functions supported by the first AI model, the first relationship is the association between the first identifier and at least one of the following: input information, output information, area information, or at least one AI model; the input information indicates the input of the first AI model, the output information indicates the output of the first AI model, the area information indicates the area where the second communication device can acquire information for perception, and the first AI model is one of at least one AI model.

[0050] In some possible implementations, the input to the first AI model is obtained based on the geometric information of objects in the environment.

[0051] In some possible implementations, the input to the first AI model includes at least one of the following: point data, patch data, octree data, or voxel data.

[0052] In some possible implementations, the output of the first AI model includes at least one of the following: point data, patch data, bounding box location, or semantic label.

[0053] In some possible implementations, the transceiver unit is also used to receive inference requirement indication information, and the first identifier, the first relation, and the inference requirement indication information are used to determine the first AI model.

[0054] In some possible implementations, the first information also indicates the input and / or output of the first AI model.

[0055] In some possible implementations, if the first condition is met, the transceiver unit is further configured to send first indication information, which instructs the second communication device to send the input of the first AI model. The input of the first AI model is used to determine the second perception result based on the first AI model. The first condition includes at least one of the following: the first perception result fails; or, the first performance value is greater than a first threshold. The first performance value is determined by the first communication device based on the first perception result and first data from the second communication device. The first data includes at least one of the following: point data, patch data, or voxel data.

[0056] In some possible implementations, the transceiver unit is also used to: send a second indication message, which indicates that the first condition is not met.

[0057] In some possible implementations, the device also includes a storage unit, which is also used to store the first sensing result or the second sensing result.

[0058] Fifthly, a communication device is provided, which may be a network device / terminal device, or a chip, circuit or chip system configured in a network device / terminal device, and the embodiments of this application do not limit this.

[0059] The device includes: a transceiver unit for transmitting first information, the first information indicating a first AI model and / or a first perception result, the first AI model being used for perception data processing, and the first perception result being a perception result required by a second communication device; the transceiver unit is also used to receive second information from the first communication device, the second information indicating a second perception result, and the second perception result being determined based on the first AI model and / or the first perception result.

[0060] In some possible implementations, perception includes: environmental perception, scene perception, or environmental reconstruction.

[0061] In some possible implementations, the first information indicates a first AI model and / or a first perception result, including: the first information includes a first identifier, the first identifier and a first relationship used to determine the first AI model and / or the first perception result; wherein, the first identifier includes an identifier and / or a functional identifier of the first AI model, the functional identifier indicates the functions supported by the first AI model, the first relationship is the association between the first identifier and at least one of the following: input information, output information, area information, or at least one AI model; the input information indicates the input of the first AI model, the output information indicates the output of the first AI model, the area information indicates the area where the second communication device can acquire information for perception, and the first AI model is one of at least one AI model.

[0062] In some possible implementations, the input to the first AI model is obtained based on the geometric information of objects in the environment.

[0063] In some possible implementations, the input to the first AI model includes at least one of the following: point data, patch data, octree data, or voxel data.

[0064] In some possible implementations, the output of the first AI model includes at least one of the following: point data, patch data, bounding box location, or semantic label.

[0065] In some possible implementations, the transceiver unit is also used to send inference requirement indication information, wherein the first identifier, the first relationship, and the inference requirement indication information are used to determine the first AI model.

[0066] In some possible implementations, the first information also indicates the input and / or output of the first AI model.

[0067] In some possible implementations, if the first condition is met, the transceiver unit is further configured to receive first indication information from the first communication device, the first indication information instructing the second communication device to send the input of the first AI model, the input of the first AI model being used to determine the second perception result based on the first AI model: wherein the first condition includes at least one of the following: the first perception result fails; or, the first performance value is greater than a first threshold, the first performance value being determined by the first communication device based on the first perception result and first data from the second communication device, the first data including at least one of the following: point data, patch data, or voxel data.

[0068] In some possible implementations, the transceiver unit is also used to: receive second indication information, which indicates that the first condition is not met.

[0069] In some possible implementations, the device also includes a storage unit, which is also used to store the second sensing result.

[0070] In a sixth aspect, a communication device is provided, which may be a network device / terminal device, or a chip, circuit or chip system configured in a network device / terminal device, and the embodiments of this application do not limit this.

[0071] The device includes: a transceiver for receiving first information from a second communication device, the first information indicating a first artificial intelligence (AI) model and / or a first perception result, the first AI model being used for perception data processing, and the first perception result being a perception result required by the second communication device; a processor for determining a second perception result based on the first AI model and / or the first perception result; the transceiver is also used to transmit second information, the second information indicating the second perception result.

[0072] In some possible implementations, perception includes: environmental perception, scene perception, or environmental reconstruction.

[0073] In some possible implementations, the first information indicates a first AI model and / or a first perception result, including: the first information includes a first identifier, the first identifier and a first relationship used to determine the first AI model and / or the first perception result; wherein, the first identifier includes an identifier and / or a functional identifier of the first AI model, the functional identifier indicates the functions supported by the first AI model, the first relationship is the association between the first identifier and at least one of the following: input information, output information, area information, or at least one AI model; the input information indicates the input of the first AI model, the output information indicates the output of the first AI model, the area information indicates the area where the second communication device can acquire information for perception, and the first AI model is one of at least one AI model.

[0074] In some possible implementations, the input to the first AI model is obtained based on the geometric information of objects in the environment.

[0075] In some possible implementations, the input to the first AI model includes at least one of the following: point data, patch data, octree data, or voxel data.

[0076] In some possible implementations, the output of the first AI model includes at least one of the following: point data, patch data, bounding box location, or semantic label.

[0077] In some possible implementations, the transceiver is also used to receive inference requirement indication information, and the first identifier, the first relation, and the inference requirement indication information are used to determine the first AI model.

[0078] In some possible implementations, the first information also indicates the input and / or output of the first AI model.

[0079] In some possible implementations, if the first condition is met, the transceiver is further configured to send a first indication message, which instructs the second communication device to send the input of the first AI model. The input of the first AI model is used to determine the second perception result based on the first AI model. The first condition includes at least one of the following: the first perception result fails; or, the first performance value is greater than a first threshold. The first performance value is determined by the first communication device based on the first perception result and first data from the second communication device. The first data includes at least one of the following: point data, patch data, or voxel data.

[0080] In some possible implementations, the transceiver is also used to: send a second indication message indicating that the first condition is not met.

[0081] In some possible implementations, the device also includes a memory, which is also used to store the first sensing result or the second sensing result.

[0082] In a seventh aspect, a communication device is provided, which may be a network device / terminal device, or a chip, circuit or chip system configured in a network device / terminal device, and the embodiments of this application do not limit this.

[0083] The device includes: a transceiver for transmitting first information, the first information indicating a first AI model and / or a first perception result, the first AI model being used for perception data processing, and the first perception result being a perception result required by a second communication device; the transceiver is also used to receive second information from the first communication device, the second information indicating a second perception result, and the second perception result being determined based on the first AI model and / or the first perception result.

[0084] In some possible implementations, perception includes: environmental perception, scene perception, or environmental reconstruction.

[0085] In some possible implementations, the first information indicates a first AI model and / or a first perception result, including: the first information includes a first identifier, the first identifier and a first relationship used to determine the first AI model and / or the first perception result; wherein, the first identifier includes an identifier and / or a functional identifier of the first AI model, the functional identifier indicates the functions supported by the first AI model, the first relationship is the association between the first identifier and at least one of the following: input information, output information, area information, or at least one AI model; the input information indicates the input of the first AI model, the output information indicates the output of the first AI model, the area information indicates the area where the second communication device can acquire information for perception, and the first AI model is one of at least one AI model.

[0086] In some possible implementations, the input to the first AI model is obtained based on the geometric information of objects in the environment.

[0087] In some possible implementations, the input to the first AI model includes at least one of the following: point data, patch data, octree data, or voxel data.

[0088] In some possible implementations, the output of the first AI model includes at least one of the following: point data, patch data, bounding box location, or semantic label.

[0089] In some possible implementations, the transceiver is also used to send inference requirement indication information, the first identifier, the first relation, and the inference requirement indication information being used to determine the first AI model.

[0090] In some possible implementations, the first information also indicates the input and / or output of the first AI model.

[0091] In some possible implementations, if the first condition is met, the transceiver is further configured to receive first indication information from the first communication device, the first indication information instructing the second communication device to send the input of the first AI model, the input of the first AI model being used to determine the second perception result based on the first AI model: wherein the first condition includes at least one of the following: the first perception result fails; or, the first performance value is greater than a first threshold, the first performance value being determined by the first communication device based on the first perception result and first data from the second communication device, the first data including at least one of the following: point data, patch data, octree data, or voxel data.

[0092] In some possible implementations, the transceiver is also used to: receive a second indication message indicating that the first condition is not met.

[0093] In some possible implementations, the device also includes a memory, which is also used to store the second sensing result.

[0094] Eighthly, a communication device is provided, which has the function of implementing the methods in the first to third aspects and any possible implementation thereof. For example, the communication device includes a module, unit or means corresponding to the operation involved in performing the methods in the first to third aspects and any possible implementation thereof. The module or unit or means can be implemented by software, or by hardware, or by a combination of software and hardware.

[0095] A ninth aspect provides a communication device comprising one or more processors. The one or more processors are capable of executing part or all of a computer program or instructions stored in a memory necessary for implementing the functions involved in the methods of the first to third aspects and any possible implementations thereof, wherein, when the computer program or instructions are executed, the communication device implements the methods of the first to third aspects and any possible implementations thereof.

[0096] In some possible implementations, the communication device may also include interface circuitry, through which the processor communicates with other devices or components.

[0097] In some possible implementations, the communication device may also include the memory.

[0098] The aforementioned communication device may be a terminal, a communication module in a terminal, or a chip in a terminal that is responsible for communication functions, such as a modem chip (also known as a baseband chip) or a SoC or SIP chip that contains a modem module.

[0099] In a tenth aspect, a communication device is provided, the device comprising: a processor for executing computer instructions to cause the device to perform the methods of the first to third aspects and any possible implementation thereof.

[0100] In some possible implementations, the device also includes a memory.

[0101] In some possible implementations, the device also includes a communication interface coupled to the processor, which is used for inputting and / or outputting information.

[0102] In the eleventh aspect, a computer program product is provided, which, when executed by a communication device, implements the methods of the first to third aspects and any possible implementation thereof.

[0103] In a twelfth aspect, a computer-readable storage medium is provided, which stores a computer program or instructions that, when executed by a communication device, implement the methods of the first to third aspects and any possible implementation thereof.

[0104] In a thirteenth aspect, a chip (or chip system) is provided, including at least one processor for running a computer program that causes a device having the chip mounted to perform the methods described in the first to third aspects and any possible implementation thereof.

[0105] The chip may include an output circuit or interface for transmitting information or data, and an input circuit or interface for receiving information or data.

[0106] In a fourteenth aspect, a communication system is provided, comprising: a network device and a terminal device, wherein the network device is configured to perform the methods of the first or third aspect and any possible implementation thereof, and the terminal device is configured to perform the methods of the second aspect and any possible implementation thereof.

[0107] In a fifteenth aspect, a communication system is provided, comprising: a first network device and a second network device, wherein the first network device is configured to perform the method described in the first aspect or the third aspect and any possible implementation thereof, and the second network device is configured to perform the method described in the second aspect and any possible implementation thereof.

[0108] In a sixteenth aspect, a communication system is provided, comprising: a first terminal device and a second terminal device, wherein the first terminal device is configured to perform the method of the first aspect or the third aspect and any possible implementation thereof, and the second terminal device is configured to perform the method of the second aspect and any possible implementation thereof. Attached Figure Description

[0109] Figure 1 is a schematic diagram of a wireless communication system 100 applicable to an embodiment of this application.

[0110] Figure 2 is a schematic diagram of an AI application framework provided in an embodiment of this application.

[0111] Figure 3 is a schematic flowchart of a communication method 300 provided in an embodiment of this application.

[0112] Figure 4 is a schematic diagram of a polyhedron provided in an embodiment of this application.

[0113] Figure 5 is a schematic diagram of a communication device 400 provided in an embodiment of this application.

[0114] Figure 6 is a schematic diagram of another communication device 500 provided in an embodiment of this application.

[0115] Figure 7 is a schematic diagram of a chip system 600 provided in an embodiment of this application. Detailed Implementation

[0116] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0117] The technical solutions of this application embodiment can be applied to various communication systems, such as: Global System for Mobile Communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD) system, Wireless Fidelity (WIFI), Device to Device (D2D) communication system, Vehicle-to-Everything (V2X) communication system, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication system, Machine to Machine (M2M) system, Machine Type Communication (MTC) system, Internet of Things (IoT) system. IoT communication systems, non-terrestrial network (NTN) systems, 5G systems, New Radio (NR) systems, and other future wireless communication systems.

[0118] First, a brief introduction to the communication system applicable to the embodiments of this application is given below.

[0119] Figure 1 is a schematic diagram of a wireless communication system 100 applicable to an embodiment of this application. As shown in Figure 1, the wireless communication system includes a wireless access network 100. The wireless access network 100 may be a wireless access network for a future communication network or a traditional (e.g., 5G or 4G) wireless access network. One or more terminal devices (120a-120j, collectively referred to as 120) may be interconnected or connected to one or more network devices (110a, 110b, collectively referred to as 110) in the wireless access network 100. Figure 1 is only a schematic diagram; the wireless communication system may also include other devices, such as core network devices, wireless relay devices, and / or wireless backhaul devices, which are not shown in Figure 1.

[0120] In practical applications, this wireless communication system can include multiple network devices and multiple terminal devices simultaneously, without limitation. A network device can serve one or more terminal devices simultaneously. A terminal device can also access one or more network devices simultaneously. The embodiments of this application do not limit the number of terminal devices and network devices included in the wireless communication system.

[0121] The communication system described above for use in the embodiments of this application is merely an example. The communication system applicable to the embodiments of this application is not limited to this. Any communication system capable of implementing the functions of the above-described devices is applicable to the embodiments of this application.

[0122] The terminal device in this application embodiment can refer to user equipment, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device. The terminal device can also be a cellular phone, cordless phone, Session Initiation Protocol (SIP) phone, Wireless Local Loop (WLL) station, Personal Digital Assistant (PDA), handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, in-vehicle device, wearable device, terminal device in a 5G network, or terminal device in a future evolved Public Land Mobile Network (PLMN), etc., and this application embodiment does not limit this to these categories.

[0123] Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices; they achieve powerful functions through software support, data interaction, and cloud interaction. Broadly defined, wearable smart devices include those with comprehensive functions, large sizes, and the ability to perform complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses. They also include devices focused on a specific application function that require the use of other devices, such as smart bracelets and smart jewelry for vital sign monitoring.

[0124] Furthermore, terminal devices can also be terminal devices in Internet of Things (IoT) systems. IoT is an important component of future information technology development, and its main technical feature is connecting objects to networks through communication technologies, thereby realizing an intelligent network that enables human-machine interconnection and machine-to-machine interconnection.

[0125] It should be understood that this application does not limit the specific form of the terminal device.

[0126] Network equipment can be a device within a wireless network, and in this application, it can also be referred to as operator equipment. For example, network equipment can be a device deployed in a wireless network to provide wireless communication functions for terminal devices. For example, network equipment can be a radio access network (RAN) node that connects terminal devices to the wireless network. The RAN can be connected to the core network (e.g., the core network of Long Term Evolution (LTE) or the core network of 5G, etc.).

[0127] The network devices in this application embodiment can be access network devices, including but not limited to: various base stations, such as next-generation node B (gNodeB, gNB), evolved node B (eNB), or base station equipment in future evolved communication systems; they can also be servers, wearable devices, vehicle-mounted devices, wireless relay nodes, wireless backhaul nodes, transmission points (TP), or transmission and reception points (TRP), etc.; they can also be one or a group of antenna panels (including multiple antenna panels) of a base station; or they can be network nodes constituting a base station, such as baseband units (BBU) or distributed units (DU), etc. The base station can be a macro base station, micro base station, pico base station, small cell, relay station, or balloon station, etc.

[0128] The network device in this application embodiment can also be a core network device, including but not limited to: access and mobility management function (AMF) network element, session management function (SMF) network element, user plane function (UPF) network element, policy control function (PCF) network element, or unified data management function (UDM) network element, etc.

[0129] Application layer network elements refer to network devices in computer networks that are responsible for processing application layer protocols, including but not limited to: Data Collection Application Function (DCAF) network elements, Provisioning Application Function (PAF) network elements, Event Consumer Application Function (ECAF) network elements, etc.

[0130] It is understood that all or part of the functions of the network device or terminal device in this application can also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform (such as a cloud platform).

[0131] In some deployments, the network devices mentioned in the embodiments of this application may be devices including centralized units (CU), distributed units (DU), or devices including CU and DU, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes. For example, the network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0132] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or radio units (RUs). CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio equipment or radio units, such as remote radio units (RRUs), active antenna systems (AAUs), or remote radio heads (RRHs).

[0133] To support machine learning capabilities in wireless communication systems, AI nodes may also be introduced.

[0134] Optionally, the communication system also includes at least one AI node.

[0135] Optionally, the AI ​​node may be deployed on one or more of the following: network devices, terminal devices, core network, or positioning devices; alternatively, the AI ​​node may be deployed independently, such as in a location other than any of the aforementioned devices. The AI ​​node may communicate with other devices in the communication system, which may be, for example, one or more of the following: network devices, terminal devices, core network elements, or sensing devices.

[0136] Optionally, the AI ​​node is used to perform AI-related operations. As an example, AI-related operations may include one or more of the following: model failure testing, model performance testing, model training testing, or data acquisition.

[0137] For example, a network device can forward AI model-related data reported by a terminal device to an AI node, which then performs AI-related operations. As another example, a network device or terminal device can forward AI model-related data to an AI node, which then performs AI-related operations. As yet another example, an AI node can send one or more of the outputs of AI-related operations, such as a trained neural network model, model evaluation, or test results, to a network device and / or a terminal device. For example, an AI node can directly send the outputs of AI-related operations to a network device and a terminal device. As yet another example, an AI node can send the outputs of AI-related operations to a terminal device through a network device. As yet another example, an AI node can send the outputs of AI-related operations to a network device through a terminal device.

[0138] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0139] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0140] For example, an AI node can be an AI network element or an AI module.

[0141] To facilitate understanding of the embodiments of this application, the terminology involved in the embodiments of this application will be briefly explained below.

[0142] (1) Artificial Intelligence (AI):

[0143] Artificial intelligence (AI) aims to endow machines with learning capabilities, enabling them to accumulate experience and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. AI can be understood as the intelligence exhibited by machines created by humans. Typically, AI refers to the technology of using computer programs to represent human intelligence. The goals of AI include understanding intelligence by constructing computer programs that demonstrate symbolic reasoning or logical reasoning.

[0144] (2) Machine learning (ML):

[0145] Machine learning (ML) is one implementation of artificial intelligence. It's a method that endows machines with the ability to perform functions that are impossible through direct programming. In practical terms, machine learning is a method of training models using data and then using those models to make predictions. There are many machine learning methods, such as neural networks (NNs), decision trees, and support vector machines. Machine learning theory primarily involves designing and analyzing algorithms that allow computers to learn automatically. Machine learning algorithms are a class of algorithms that automatically analyze data to obtain patterns and use those patterns to predict unknown data.

[0146] (3) AI:

[0147] An AI model is an algorithm or computer program that enables AI functionality. An AI model represents the mapping relationship between the model's input and output; in other words, it's a function model that maps an input of a certain dimension to an output of a certain dimension. The parameters of this function model can be obtained through machine learning training. For example, f(x) = mx 2 +n is a quadratic function model, which can be viewed as an AI model. m and n are the parameters of this AI model, and m and n can be obtained through machine learning training. For example, the AI ​​model mentioned in the following embodiments of this application is not limited to neural networks, linear regression models, decision tree models, support vector machines (SVM), Bayesian networks, Q-learning models, or other ML models.

[0148] AI model design mainly includes a data collection phase (e.g., collecting training data and / or inference data), a model training phase, and a model inference phase. It can further include an inference result application phase. In the aforementioned data collection phase, a data source provides the training dataset and inference data. In the model training phase, the AI ​​model is obtained by analyzing or training the training data provided by the data source. Learning the AI ​​model through model training nodes is equivalent to learning the mapping relationship between the AI ​​model's input and output using the training data. In the model inference phase, the AI ​​model trained in the model training phase is used to perform inference based on the inference data provided by the data source to obtain the inference result. This phase can also be understood as: inputting inference data into the AI ​​model, obtaining the output through the AI ​​model, which is the inference result. This inference result can indicate the configuration parameters used (executed) by the execution object, and / or the operations performed by the execution object. In the inference result application phase, the inference result is published. For example, the inference result can be uniformly planned by the actor entity, which can send the inference result to one or more execution objects (e.g., core network devices, access network devices, or terminal devices) for execution. For example, the executing entity can also provide feedback on the performance of the AI ​​model to the data source, which facilitates the subsequent updating and training of the AI ​​model.

[0149] It is understood that AI models can be implemented using hardware circuits, software, or a combination of both; there are no restrictions. Non-restrictive examples of software include: program code, program, subroutine, instructions, instruction sets, code, code segments, software modules, application programs, or software applications, etc.

[0150] The AI ​​module is a module with machine learning computing capabilities. In wireless communication systems, the AI ​​module can be located in operations, administration and maintenance (OAM), or in a gNB (e.g., in a separate architecture, it can be located in the CU / DU), in terminal equipment, or as a standalone network element entity, the RAN intelligent controller (RIC). The main function of the AI ​​module in a wireless communication system is to perform a series of AI calculations, including model building, training approximation, and reinforcement learning, based on input data (in wireless communication systems, input data generally refers to network operation data provided by access network equipment or monitored by OAM, such as network load, channel quality, or user plane data transmission provided by the core network). Currently, the trained models provided by the AI ​​module have predictive capabilities for changes in the RAN side network and can be used for load prediction, terminal equipment path prediction, CSI prediction, optimal beam prediction, and positioning prediction. Furthermore, the AI ​​module can also perform policy reasoning from the perspectives of network energy saving and mobility optimization based on the predicted RAN network performance results of the trained models, to obtain reasonable and efficient energy-saving strategies and mobility optimization strategies. When the AI ​​model resides in the CU, and the CU's control plane and user plane are separated, the CP can be responsible for receiving the AI ​​model and subsequent AI inference and policy generation functions. When the CU-CP is further divided into CU-CP1 and CU-CP2, CU-CP1 can be responsible for receiving the AI ​​model and subsequent AI model inference functions, and generating specific interactive signaling, which is then sent by CU-CP2. When the AI ​​module is located in the OAM, its communication with the RAN-side gNB can reuse the current northbound interface. When the AI ​​module is located in the gNB or CU, the current F1, Xn, Uu, etc. interfaces can be reused; when the AI ​​module becomes an independent network entity, a new communication link needs to be established with the OAM and RAN sides, for example, based on a wired link or a wireless link.

[0151] (4) Neural network (NN):

[0152] Neural networks are a specific implementation of AI or ML. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings.

[0153] A neural network can be composed of neural units, which can be operational units that take xs and an intercept of 1 as input. A neural network is a network formed by connecting many of these individual neural units together; that is, the output of one neural unit can be the input of another neural unit. The input of each neural unit can be connected to the local receptive field of the previous layer to extract features from the local receptive field, which can be a region composed of several neural units.

[0154] Taking neural networks as an example, the AI ​​model disclosed herein can be a deep neural network (DNN). Depending on the network construction method, DNN can include feedforward neural networks (FNN), convolutional neural networks (CNN), and recurrent neural networks (RNN), etc.

[0155] (5) Training dataset and inference data:

[0156] In the field of machine learning, ground truth usually refers to data that is considered accurate or real.

[0157] Training datasets are used to train AI models. A training dataset can include the input to the AI ​​model, or it can include both the input and the target output of the AI ​​model. Specifically, a training dataset includes one or more training data points, which can include training samples input to the AI ​​model or the target output of the AI ​​model. The target output can also be referred to as a label, sample label, or labeled sample. The label is the ground truth value.

[0158] In the field of communications, training datasets can include simulation data collected through simulation platforms, experimental data collected from experimental scenarios, or measured data collected in actual communication networks. Because the geographical environment and channel conditions where the data is generated vary—for example, indoor / outdoor conditions, movement speed, frequency bands, or antenna configurations—the collected data can be categorized during acquisition. For instance, data with the same channel propagation environment and antenna configuration can be grouped together.

[0159] Model training essentially involves learning certain features from training data. In training AI models (such as neural network models), the goal is to make the model's output as close as possible to the desired predicted value. This is achieved by comparing the network's current predictions with the target value and updating the weight vector of each layer based on the difference. (Of course, there's usually an initialization process before the first update, where parameters are pre-configured for each layer.) For example, if the network's prediction is too high, the weight vector is adjusted to predict a lower value. This adjustment continues until the AI ​​model can predict the target value or a value very close to it. Therefore, it's necessary to predefine "how to compare the difference between the predicted and target values," which is the loss function or objective function. These are important equations used to measure the difference between the predicted and target values. Taking the loss function as an example, a higher output value (loss) indicates a greater difference. Therefore, training the AI ​​model becomes a process of minimizing this loss, making the loss function value less than a threshold, or making the loss function value meet the target requirements. For example, if the AI ​​model is a neural network, adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers of the neural network, the width, the weights of the neurons, or the parameters in the activation function of the neurons.

[0160] Inference data can be used as input to a trained AI model for inference. During the model's inference process, the inference data is input into the AI ​​model, and the corresponding output, which is the inference result, is obtained.

[0161] Figure 2 is a schematic diagram of an AI application framework provided in an embodiment of this application. This AI application framework can be used to implement model lifecycle management (LCM). The core functions of LCM may include, as shown in Figure 2, a data acquisition module, a model training module, a model management module, a model inference module, and a model storage module. The model management module interacts with and manages the other modules, the model storage module is used to store and manage AI models, and the model training module and model inference module are examples of AI modules.

[0162] In the aforementioned data collection phase, the data source provides both training and inference datasets. In the model training phase, the AI ​​model is obtained by analyzing or training the training data provided by the data source. The AI ​​model represents the mapping relationship between the model's input and output.

[0163] For example, network devices, terminal devices, or gNB CUs, DUs, or other management entities, as shown in Figure 1, can input data into the data acquisition module. The data acquisition module can serve as a database for AI model training and data analysis inference. The model training module can analyze and train the data output by the data acquisition module, providing a usable AI model, which is then deployed to the model management module. The model inference module, based on the inference data output by the data acquisition module, provides reasonable predictions about network operation based on the AI ​​model (obtained through training), and feeds back the AI ​​model's performance data to the model training module. Subsequently, the model training module continues to train the model based on the feedback performance data and feeds back the updated AI model to the data acquisition module for storage.

[0164] It is understood that communication systems may include network elements with artificial intelligence (AI) capabilities. The AI ​​model design-related steps described above can be performed by one or more network elements with AI capabilities. In one possible design, AI functions (such as AI modules or AI entities) can be configured within existing network elements in the communication system to implement AI-related operations, such as AI model training and / or inference. For example, this existing network element could be a network device or a terminal device. Alternatively, in another possible design, an independent network element can be introduced into the communication system to perform AI-related operations, such as training an AI model. This independent network element can be called an AI network element or an AI node, etc., and this application embodiment does not limit the use of this name. Exemplarily, the AI ​​network element can be directly connected to network devices in the communication system, or it can be indirectly connected to network devices through a third-party network element. The third-party network element can be a core network element such as an authentication management function (AMF) network element or a user plane function (UPF) network element, an operation administration and maintenance (OAM) network element, a cloud server, or other network elements, without limitation. For example, the independent network element can be deployed on one or more of the following: the network device side, the terminal device side, or the core network side. Optionally, it can be deployed on a cloud server.

[0165] The training processes of different models can be deployed on different devices or nodes, or on the same device or node. Similarly, the inference processes of different models can be deployed on different devices or nodes, or on the same device or node. For example, the model parameters of an AI model may include one or more of the following: model structure parameters (e.g., the number of layers, and / or weights), model input parameters (e.g., input dimension, number of input ports), or model output parameters (e.g., output dimension, number of output ports). It can be understood that the input dimension refers to the size of an input data set; for example, when the input data is a sequence, the corresponding input dimension can indicate the length of the sequence. The number of input ports can refer to the quantity of input data. Similarly, the output dimension can refer to the size of an output data set; for example, when the output data is a sequence, the corresponding output dimension can indicate the length of the sequence. The number of output ports can refer to the quantity of output data.

[0166] In the description of the embodiments of this application, unless otherwise stated, "multiple" or "amounts" means two or more. Additionally, "at least one" can be replaced with "one or more". "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can represent: a, or b, or c, or a and b, or a and c, or b and c, or a, b, and c. Here, a, b, and c can be single or multiple.

[0167] The ordinal numbers such as "first" and "second" mentioned in the embodiments of this application are used to distinguish multiple objects, and are not used to limit the size, content, order, timing, priority, or importance of the multiple objects. For example, the first instruction information and the second instruction information can be the same information or different information, and such names do not indicate differences in the content, size, application scenario, sending / receiving end, priority, or importance of the two messages. In addition, the numbering of steps in the various embodiments described in this application is only to distinguish different steps and is not used to limit the order of steps.

[0168] In this application, the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion, such that a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or apparatus.

[0169] In this application, "for indicating" can include both direct and indirect indication. When describing indication information for indicating A, it can include either direct or indirect indication of A, but does not necessarily mean that the indication information carries A. Direct indication information A means including information A; implicit indication information A means indicating information A through the correspondence between information A and information B, and through direct indication information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0170] It is understood that some optional features in the various embodiments of this application may not depend on other features in some scenarios, or may be combined with other features in some scenarios, without limitation.

[0171] The technical solutions provided in this application can be applied to wireless communication between communication devices. Wireless communication between communication devices can include: wireless communication between network devices and terminals, wireless communication between network devices, and wireless communication between terminals. In this application, the term "wireless communication" can also be abbreviated as "communication," and the term "communication" can also be described as "data transmission," "information transmission," or "transmission."

[0172] The communication method provided in the embodiments of this application is described in detail below with reference to the accompanying drawings. The embodiments provided in this application can be applied to all or part of the modules of the communication system shown in FIG1 and the AI ​​application framework shown in FIG2, and the embodiments of this application do not limit this application.

[0173] In this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, and "send information" can include direct transmission or indirect transmission through other units or modules. "Receive information from YY" can be understood as the source of the information being YY, and "receive information" can include direct reception from YY or indirect reception from YY through other units or modules. Besides air interface transmission or reception signals implemented at the system level, such as network devices or terminal devices, "send" can also be understood as the "output" of a chip interface, and "receive" can also be understood as the "input" of a chip interface. For example, a modem or system-on-a-chip (SoC) chip or system-in-package (SIP) chip transmits or receives signals. "Send" or "receive" can also be performed through device components, for example, by using buses, traces, or interfaces to transmit or receive signals through several parts, modules, or chips of a device.

[0174] Figure 3 is a schematic flowchart of a communication method 300 provided in an embodiment of this application. As shown in Figure 3, method 300 may include the following steps. This method can be executed by a first communication device or a second communication device. For example, the method can be executed by a network device / terminal device, or by a communication module configured in the network device / terminal device, or by a circuit, chip, or chip system (such as a modem chip, also known as a baseband chip, or a SoC chip, processor, or SIP chip containing a modem core) responsible for communication functions in the network device / terminal device, or by a logic module or software capable of implementing all or part of the functions of the network device / terminal device. This application embodiment does not limit this.

[0175] It is understood that in the embodiments of this application, both the first communication device and the second communication device can be network devices; both the first communication device and the second communication device can also be terminal devices; when the first communication device is a network device, the second communication device can be a terminal device; or, when the first communication device is a terminal device, the second communication device can be a network device. The embodiments of this application do not limit this. For ease of description, the following example uses the first communication device as a network device and the second communication device as a terminal device.

[0176] S310, the network device receives the first information from the terminal device, and correspondingly, the terminal device sends the first information to the network device.

[0177] Wherein, the first information indicates the first artificial intelligence (AI) model and / or the first perception result, the first AI model is used for perception data processing, and the first perception result is the perception result required by the second communication device.

[0178] S315, the network device determines the second perception result based on the first AI model and / or the first perception result.

[0179] S320: The network device sends second information to the terminal device, and the corresponding terminal device receives the second information from the network device.

[0180] The second information indicates the second perception result.

[0181] In this embodiment, "AI model" refers to an AI model used for perceptual data processing, and "first AI model" refers to a specific AI model used for perceptual data processing. "First perceptual result" is a perceptual result inferred from data obtained through perceptualization of the environment using a specific AI model. This first perceptual result is the perceptual result required by the second communication device. It is understood that the specific AI model may be the same as or different from the first AI model.

[0182] Specifically, the terminal device sends first information to the network device. This first information may indicate a first AI model (used for sensing data processing) or a first sensing result (the first sensing result is the sensing result required by the second communication device). The network device can determine a second sensing result based on the first AI model indicated by the first information, or the network device can determine the second sensing result based on the first sensing result indicated by the first information. After determining the second sensing result, the network device can send second information to the terminal device, which indicates the second sensing result.

[0183] For example, the terminal device can send first information and information for reasoning by the first AI model to the network device. The information for reasoning by the first AI model can be obtained based on the geometric information of objects in the environment. The network device can determine the first AI model based on the first information and reason a second perception result based on the first AI model and the information for reasoning by the first AI model.

[0184] In some possible implementations, after the first communication device determines the second sensing result, it can send the second sensing result to the second communication device. For example, the second information may include the second sensing result. Alternatively, after the first communication device determines the second sensing result, it can send second information that can indicate the second sensing result to the second communication device, and the second communication device can obtain the second sensing result indicated by the second information based on the second information.

[0185] In some possible implementations, the information used for reasoning by the first AI model can be obtained by the second communication device through environmental perception and sent to the first communication device, or it can be obtained by the second communication device through other means or other communication devices and sent to the first communication device, or it can be stored in the first communication device. This application does not limit this aspect.

[0186] In some possible implementations, after determining the first sensing result, the network device can identify the first sensing result as the second sensing result.

[0187] For example, the first information indicates the first sensing result required by the terminal device. After receiving the first information, the network device confirms that it has stored the first sensing result, and the network device can send the first sensing result to the terminal device.

[0188] It is understood that the first perception result can be a perception result determined before the network device responds to the first information. For example, it could be a perception result pre-stored before the network device receives the first information, or a perception result pre-stored before the network device decodes the first information, or a perception result determined at the same time as the network device receives / decodes the first information. Any perception result that can be determined before the network device responds to the first information can be included in the embodiments of this application, and the embodiments of this application do not limit this.

[0189] Based on the solution provided in the embodiments of this application, the first communication device can determine the second sensing result by receiving the first information from the second communication device, and send the second information indicating the second sensing result to the second communication device.

[0190] For example, if the first information is used to indicate the first AI model, the first communication device can determine the first AI model through the first information sent by the second communication device, and determine the second perception result based on the first AI model.

[0191] For example, if the first information is used to indicate a first sensing result, the first communication device can determine the first sensing result required by the second communication device through the first information sent by the second communication device, and provide the first sensing result to the second communication device. In this case, the aforementioned second sensing result is the same as the first sensing result. When the first information is used to indicate a first sensing result, if the first communication device has already determined a first sensing result before determining the first sensing result in response to the first information, it can provide the determined first sensing result as the aforementioned second sensing result to the second communication device; or, the first communication device determines the first sensing result in response to the first information and provides the first sensing result as the aforementioned second sensing result to the second communication device.

[0192] In summary, on the one hand, the first communication device can determine the second perception result based on the first AI model indicated by the received first information, and provide the second perception result to the second communication device, thereby realizing perception based on the AI ​​model. On the other hand, the first communication device can determine the perception result required by the second communication device based on the first perception result indicated by the received first information, and provide the required perception result to the second communication device. If the perception result required by the second communication device is the first perception result already determined by the first communication device, the first communication device can provide the existing first perception result to the second communication device without having to reason again in response to the first information, which can save the resources occupied by reasoning, reduce the latency of obtaining the second perception result, and improve communication efficiency.

[0193] In some possible implementations, the first communication device is equipped with a model management module, which can determine the first AI model based on first information. For example, the first information includes the identifier (ID) of the first AI model, and the model management module can determine the first AI model based on the ID of the first AI model.

[0194] In some possible implementations, the first communication device is equipped with a model inference module that can determine the second perception result. For example, the model inference module infers the second perception result based on the first AI model.

[0195] In some possible implementations, the first communication device is equipped with a data acquisition module that can acquire data based on the geometric information of objects in the environment (e.g., the input of a first AI model, which may include point data, patch data, octree data, or voxel data).

[0196] It is understood that the model management module, model inference module and / or data acquisition module deployed in the first communication device may be the LCM-based model management module, model inference module and / or data acquisition module in Figure 2 above. However, the model management module, model inference module and / or data acquisition module deployed in the first communication device may also be limited to the LCM-based model management module, model inference module and / or data acquisition module in Figure 2 above.

[0197] The application of method 300 provided in this application embodiment in an LCM-based module can be an enhancement of the existing LCM, which can be implemented without making any changes to the existing LCM. The perception management scheme based on function ID and / or model ID can flexibly manage various tasks and models; the model management module can select a suitable model as the first AI model for inference based on the correspondence between function ID / model ID and inference input and inference results. In the above perception management scheme based on function ID and / or model ID, the design of the perception function ID and model ID, as well as the inference process, can all be based on the existing LCM framework, and will not be elaborated further here.

[0198] In some possible implementations, perception includes: environmental perception, scene perception, or environmental reconstruction.

[0199] Based on the solution provided in the embodiments of this application, the second communication device can determine the perception result of the environment or scene or the perception result of environment reconstruction based on the second perception result indicated by the received second information, thus enriching the application scenarios of the AI ​​model.

[0200] In some possible implementations, the first information indicates a first AI model and / or a first perception result, including: the first information includes a first identifier, and the first identifier and a first relationship are used to determine the first AI model; wherein, the first identifier includes an identifier and / or a functional identifier of the first AI model, the functional identifier indicates the functions supported by the first AI model, and the first relationship is the association between the first identifier and at least one of the following: input information, output information, area information, or at least one AI model; the input information indicates the input of the first AI model, the output information indicates the output of the first AI model, the area information indicates the area in which the second communication device can acquire information for perception, and the first AI model is one of at least one AI model.

[0201] Specifically, the first information may include a first identifier (e.g., the first identifier is an ID. This ID may be used to indicate one or more AI models supporting a class of functions (e.g., a function ID indicates one or more AI models with the same class of functions), and / or, this ID may be used to indicate a specific AI model (e.g., a model ID indicates a specific AI model). It is understood that one function ID corresponds to one inference task, and one or more model IDs correspond to one inference task. The network device can determine the first AI model based on the first identifier and the first relationship. The first identifier has an association relationship (i.e., the first relationship) with at least one of the following information: input information, output information, area information, or at least one AI model. The input information may include the perception data input to the first AI model, the type of the perception data input to the first AI model, and the identifier of the perception data / data type input to the first AI model; the output information may include the perception result data output by the first AI model, the type of the perception result data output by the first AI model, and the identifier of the perception result data / result data type output by the first AI model; at least one AI model includes two or more AI models that can support the function identifier indication; the area information may include the area where the terminal device can obtain the perception information and / or the area identifier of the area where the terminal device can obtain the perception information, or other information used to indicate the area where the terminal device can obtain the perception information.

[0202] In some possible implementations, the region information may include information indicating the region of interest to the terminal device. For example, if the terminal device is only interested in a portion of a region within which it can acquire sensing information, and only needs to acquire the sensing results for that portion, then the region information may include information indicating the region from which the sensing results need to be acquired.

[0203] Table 1

[0204] For example, the first identifier includes a function ID / model ID. The network device pre-stores a first relationship between the function ID / model ID and the input and output information. For example, the correspondence shown in Table 1 / Table 2 is one possible representation of the first relationship. The network device can determine the first AI model indicated by the function ID / model ID based on the pre-stored first relationship.

[0205] Table 2

[0206] In some possible implementations, the input to the first AI model is obtained based on the geometric information of objects in the environment.

[0207] For example, a terminal device can obtain environmental information that reflects the geometric information of objects in the environment through sensors or other devices capable of sensing the environment. This environmental information can be used as data for sensing that the terminal device sends to the network device as input to the first AI model.

[0208] For example, other devices besides the terminal device can obtain environmental information that reflects the geometric information of objects in the environment through sensors or other devices capable of sensing the environment. Other devices besides the terminal device can send the environmental information to the terminal device, and the terminal device can use the received environmental information as data for sensing and inputting the first AI model to the network device.

[0209] For example, one or more of the following can be considered as the geometric information of an object: information representing the coordinates of an object's points, information representing a plane of the object, and information representing one side (e.g., a line) of the object.

[0210] In some possible implementations, the input to the first AI model can be raw data obtained from the geometric information of objects in the environment, or it can be compressed data obtained from the raw data obtained from the geometric information of objects in the environment after compression processing. This application does not limit this approach.

[0211] In some possible implementations, the input to the first AI model includes at least one of the following: point data, patch data, octree data, or voxel data.

[0212] For example, the input to the first AI model may include point data, patch data, octree data, voxel data, or any combination of point data, patch data, octree data, and voxel data (such combined data may also be called multimodal data).

[0213] For example, in the embodiments of this application, point data may include data that can represent three-dimensional coordinate points of an object or environment. For example, the coordinates of point P in a three-dimensional coordinate system can be represented as (a,b,c), and (a,b,c) can be a representation of point data. Patch data may be vertex data and index data representing a face. For example, a cube includes eight vertices, and the vertex data of a face represents the position information of the eight vertices. One face of the cube includes four vertices, and the index data represents the index of the four vertices of the face in the eight vertices of the cube. Based on the vertex data and the index data, one face of the cube can be determined. Voxel data may include data used to indicate whether there are points in the grid when the space is divided into very small grids (for example, 0 indicates that there are no points in the grid, and 1 indicates that there are points in the grid; or, 1 indicates that there are no points in the grid, and 0 indicates that there are points in the grid). Alternatively, other data capable of distinguishing whether a point exists in the grid can be used to represent whether a point exists or not (this application does not limit this). An octree is a tree-like data structure used to describe three-dimensional space. Each node in an octree represents a volume element of a cube. Each node has eight child nodes. The volume elements represented by the eight child nodes are added together to equal the volume of the parent node. Generally, the center point is used as the branching center of the node. If the octree is not an empty tree, any node in the tree has exactly eight or zero child nodes, that is, the number of child nodes will not be 0 or 8. When a child node is 0, it can represent a point that does not exist in space. When a child node is 1, it can represent a point that exists in space. Alternatively, other data capable of distinguishing whether a point exists in space corresponding to a child node can be used to represent whether a point exists or not (this application does not limit this).

[0214] For example, Figure 4 is a schematic diagram of a polyhedron provided in an embodiment of this application. After fixing the coordinate axes, the vertex data of the eight vertices of the polyhedron can be determined: {(x1,y1,z1),(x2,y2,z2),(x3,y3,z3),(x4,y4,z4),(x5,y5,z5),(x6,y6,z6),(x7,y7,z7),(x8,y8,z8)}, which correspond to points 1 to 8 respectively. An index is set for these eight vertices, and a certain plane of the polyhedron can be determined by using the index data and the vertex data. For example, when the index data is {123}, the plane formed by points 1, 2, and 3 can be determined using the index data and vertex data; or, when the index data is {2368}, the plane formed by points 2, 3, 6, and 8 can be determined using the index data and vertex data; or, when the index data is {45786}, the plane formed by points 4, 5, 6, 7, and 8 can be determined using the index data and vertex data.

[0215] In some possible implementations, the output of the first AI model includes at least one of the following: point data, patch data, bounding box location, or semantic label.

[0216] For example, the output of the first AI model may include point data, patch data, octree data, bounding box location, or semantic labels; or, the output of the first AI model may include any combination of point data, patch data, octree data, bounding box location, and semantic labels (such combined data may also be called multimodal data).

[0217] For example, both the input and output of an AI model can include point data. For instance, the input point data could be based on perception of objects in the environment, while the output point data could be obtained through simulation and reasoning based on the input point data.

[0218] For example, in the embodiments of this application, the target bounding box location may include data representing the vertex coordinates / center point of the target bounding box and the range data of the target bounding box, and the semantic label may include the index value of the category corresponding to each point. The target bounding box location may be a detection box of a two-dimensional (2D) perceptual data target, or it may be a detection box of a three-dimensional (3D) perceptual data target.

[0219] In some possible implementations, the first information also indicates the input and / or output of the first AI model.

[0220] For example, the first relationship pre-stored by the network device does not include input information. Before determining the AI ​​model indicated by the function ID based on the pre-stored first relationship, the network device also needs to receive the input information corresponding to the function ID sent by the terminal device. For example, the correspondence shown in Table 3 is another possible representation of the first relationship. The first relationship shown in Table 3 does not include input information. The network device also needs to receive the input information corresponding to the function ID sent by the terminal device so that the network device can determine the first AI model indicated by the function ID based on the pre-stored first relationship.

[0221] Table 3

[0222] For example, the first relationship pre-stored by the network device does not include output information. Before determining the AI ​​model indicated by the model ID based on the pre-stored first relationship, the network device also needs to receive the output information corresponding to the model ID sent by the terminal device. For example, taking the correspondence shown in Table 4 as another possible form of the first relationship, the first relationship shown in Table 4 does not include output information. The network device also needs to receive the output information corresponding to the model ID sent by the terminal device so that the network device can determine the first AI model indicated by the model ID based on the pre-stored first relationship.

[0223] Table 4

[0224] For example, the first relationship pre-stored by the network device does not include output information. Before determining the AI ​​model indicated by the function ID based on the pre-stored first relationship, the network device also needs to receive the input information corresponding to the function ID sent by the terminal device. For example, the correspondence shown in Table 5 is another possible representation of the first relationship. The first relationship shown in Table 5 does not include output information. One function ID can correspond to one or more input information. The network device also needs to receive the unique input information corresponding to the function ID sent by the terminal device, so that the network device can determine the first AI model indicated by the function ID based on the pre-stored first relationship.

[0225] Table 5

[0226] Table 6

[0227] For example, the first relation pre-stored by the network device does not include input information. Before determining the AI ​​model indicated by the model ID based on the pre-stored first relation, the network device also needs to receive the output information corresponding to the model ID sent by the terminal device. For example, the correspondence shown in Table 6 is another possible representation of the first relation. The first relation shown in Table 6 does not include input information, and one model ID can correspond to one or more output information. The network device also needs to receive the unique output information corresponding to the model ID sent by the terminal device, so that the network device can determine the first AI model indicated by the model ID based on the pre-stored first relation.

[0228] Based on the solution provided in the embodiments of this application, the first communication device can determine the first AI model through the input and / or output of the first AI model, the first identifier and the known first relationship. The input and / or output of the first AI model and the first relationship together indicate the relationship between the first identifier and the information of the first AI model (such as the input information, the output information, or the information of the region, etc.), so that the first communication device can accurately determine the first AI model and improve the accuracy of the solution.

[0229] When the first identifier includes a function ID / model ID, the network device can determine the first AI model based on the pre-stored first relationship and the function ID / model ID (for example, the network device can determine the first AI model based on Table 1 / Table 2, or the network device can determine the first AI model based on Table 3 / Table 4 / Table 5 / Table 6 and the input / output information corresponding to the function ID sent by the terminal device).

[0230] For example, as shown in Tables 1, 3, and 5, when the function ID is 0, the inference task corresponding to this function ID is 3D model reconstruction, the input information includes Point, and the output information includes polygon; when the function ID is 1, the inference task corresponding to this function ID is object detection, the input information includes Multimodal data, and the output information includes the position of the moving target bounding box; when the function ID is 2, the inference task corresponding to this function ID is semantic segmentation, the input information includes Point, and the output information includes the semantic label of each point. The network device can determine one or more AI models based on Table 1, or Tables 3 and 5, and the input information corresponding to the function ID sent by the terminal device. When the network device determines only one AI model based on the function ID and the first relation, this single AI model is the first AI model. For example, as shown in Table 7, the AI ​​model determined by the network device based on the first relation (Table 7) and the function ID (function ID is 0) is Kp-conv, and this Kp-conv is the first AI model.

[0231] Table 7

[0232] For example, as shown in Tables 2, 4, and 6, when the model ID is 0, the model corresponding to this model ID is PointNet, the input information includes Point, and the output information includes polygon; when the function ID is 1, the model corresponding to this function ID is OpenPcdet, the input information includes Point, and the output information includes the position of the moving target bounding box; when the function ID is 2, the model corresponding to this function ID is DGCNN, the input information includes Point, and the output information includes the semantic label of each point; when the function ID is 3, the model corresponding to this function ID is InvPT, the input information includes Multimodal data, and the output information includes the position of the moving target bounding box or the semantic label of each point. The network device can determine an AI model based on Table 2, or Tables 4 and 6, and the input information corresponding to the function ID sent by the terminal device. This AI model is the first AI model.

[0233] For example, the first identifier includes a function ID / model ID. The terminal device also sends region indication information indicating a sensing region L to the network device. The sensing region L is the region where the terminal device can obtain information for sensing when sending the region indication information. Before receiving the first information, the network device pre-stores inference results within the first region that correspond one-to-one with the function ID / model ID. The input information used to obtain the inference result is obtained by the terminal device within the first region. The network device pre-stores a first relationship between the function ID / model ID and the inference result within the first region. The first region includes the sensing region L. After receiving the first information and the region indication information indicating the sensing region L, the network device can determine whether there is an inference result within the first region that matches the ID included in the first identifier based on the pre-stored first relationship (i.e., when the function ID / model ID included in the first identifier matches the function ID / model ID that corresponds one-to-one with the inference result in the first relationship, the inference result corresponding to the matching function ID / model ID is determined to be the first sensing result). The network device can use this first sensing result as the second sensing result.

[0234] It is understood that the aforementioned first relationship may be deployed in the first communication device before receiving the first information, or it may be obtained by the first communication device through other means; the aforementioned first relationship may be deployed in the first communication device in the form of a table, or it may be deployed in the first communication device in the form of text or other means. This application embodiment does not limit this.

[0235] It is understood that the aforementioned area indication information may be sent simultaneously with the first information or separately from the first information, and this application embodiment does not limit this.

[0236] It is understood that when the geographical location of the terminal device is fixed, the sensing area L can be a fixed area; when the terminal can move, the sensing area L can be a changing area. Any area that can acquire information for sensing when any terminal device sends area indication information can be considered the sensing area L; this application does not limit this.

[0237] Based on the solution provided in the embodiments of this application, the first communication device can determine the first AI model through the first identifier in the first information and the known first relationship. The first relationship indicates the relationship between the first identifier and the information of the first AI model (such as the input information, the output information, or the information of the region, etc.), so that the first communication device can accurately determine the first AI model and improve the accuracy of the solution.

[0238] In some possible implementations, before determining the first AI model, method 300 may also include:

[0239] The network device receives inference request indication information from the terminal device. Correspondingly, the terminal device sends inference request indication information to the network device. The first identifier, the first relationship, and the inference request indication information are used to determine the first AI model.

[0240] For example, when the network device determines multiple AI models based on the function ID and the first relationship, the first AI model is one of these multiple AI models. For instance, as shown in Table 7, the AI ​​model determined by the network device based on the function ID (function ID is 1) is PointNet and OpenPcdet; or, the network device determines the AI ​​model as PointNet and OpenPcdet based on function ID 1, input information including Multimodal data, and output information including the position of the moving target bounding box. The network device can choose either PointNet or OpenPcdet as the first AI model; or, the network device can determine either PointNet or OpenPcdet as the first AI model based on the indication of the inference requirement indication information.

[0241] For example, a network device may identify multiple AI models based on their function IDs. Among these models, model A has higher reliability in its inference results, model B has faster inference speed, model C requires less input information, and model D's output information is more universal or more suitable for the current application scenario. The terminal device can instruct the network device to select one of these AI models based on the characteristics of different models and the requirements of the current inference task. For instance, if faster inference speed is needed, the terminal device can instruct the network device to select model B, which has the faster inference speed. Other possible model selection scenarios are not elaborated here.

[0242] For example, a terminal device can instruct a network device to select one of multiple AI models as the first AI model using 1 bit of information. For instance, the terminal device sends inference requirement indication information; when this indication information is 0, it instructs the network device to select an AI model that prioritizes latency performance as the first AI model; when the indication information is 1, it instructs the network device to select an AI model that prioritizes the reliability of the inference result as the first AI model. It should be understood that the terminal device can also instruct the network device to select one of multiple AI models as the first AI model using other information, and this embodiment does not limit this approach.

[0243] Based on the solution provided in the embodiments of this application, the first communication device can determine the first AI model through inference requirement indication information, a first identifier, and a known first relationship. The inference requirement indication information indicates the performance of the first AI model (e.g., the inference requirement indication information indicates that the first AI model is a model that focuses on latency among multiple AI models, or the first AI model is a model that focuses on performance among multiple AI models), so that the first communication device can determine the first AI model according to the inference requirements, thereby improving the rationality of the solution.

[0244] Optionally, in some possible implementations, if the first condition is met, the method further includes: the network device sending first indication information to the terminal device, and correspondingly, the terminal device receiving the first indication information from the network device.

[0245] The first instruction information instructs the second communication device to send the input of the first AI model, which is used to determine the second perception result based on the first AI model. The first condition includes at least one of the following: the first perception result fails; or, the first performance value is greater than the first threshold. The first performance value is determined by the first communication device based on the first perception result and the first data from the second communication device. The first data includes at least one of the following: point data, patch data, octree data, or voxel data.

[0246] For example, if the network device determines, based on a pre-stored first relationship, that there is no inference result matching the ID included in the first identifier within the first region; or if the network device determines that the first perception result is invalid (e.g., the time interval between the first moment and the second moment is greater than a first time threshold, where the first moment is the moment the network device determines the first perception result and the second moment is the moment the network device receives the first message; or, the first moment is the moment the network device determines the first perception result and the second moment is the moment the network device determines the first perception result), the network device can send a first indication message to the terminal device. The first indication message instructs the terminal device to send data for the AI ​​model to perform perception. The network device can perform inference based on the data sent by the terminal device for the AI ​​model to perform perception, and based on the first AI model determined according to any of the first relationships in Tables 1-7 above, and determine the result obtained from the inference as the second perception result.

[0247] For example, when a network device determines that a first performance value is greater than a first threshold (the first performance value is determined by the network device based on a first perception result and first data from a terminal device, the first data including at least one of the following: point data, patch data, octree data, or voxel data), the network device may send a first instruction information to the terminal device, the first instruction information instructing the terminal device to send data for the AI ​​model to perceive.

[0248] For example, in addition to sending first information and region indication information to the network device, the terminal device also sends first data (which may include at least point data, patch data, octree data, or voxel data). Based on this first data and the first perception result, the network device can determine a first performance value. For example, the first performance value may be the Chamfer distance (the closest distance from each sampling point to the polygon surface), or the Hausdorff distance (used to describe the similarity between two sets of points), or the first performance value may be obtained based on whether the categories detected by semantic detection are the same / the position IOU, or the first performance value may be the angle between the normal vectors on the surface of the region.

[0249] It is understood that the above-mentioned first performance value is a commonly used indicator to characterize the performance of the model. Any indicator that can be used to characterize the effect of the AI ​​model can be used in the embodiments of this application, and the embodiments of this application do not limit it.

[0250] Based on the solution provided in this application embodiment, when the first communication device determines that the first perception result is invalid or the first performance value is greater than the first threshold, the first communication device instructs the second communication device to send the input of the first AI model through the first indication information. The first communication device determines the second perception result by receiving the input of the first AI model from the second communication device and the determined first AI model, thereby re-determining the perception result when the first perception result is not ideal, making the second perception result more reliable and improving the reliability of the solution.

[0251] In some possible implementations, the first identifier includes a function ID and a model ID. The network device can determine the first AI model based on the pre-stored first relationship and the function ID and model ID (for example, the network device can determine the unique input information based on the function ID and the aforementioned first relationship, and determine the unique output information and the unique AI model based on the model ID and the aforementioned first relationship, thereby determining the first AI model).

[0252] In some possible implementations, the network device can send a second sensing result determined based on the first sensing result to the terminal device. After receiving the second sensing result, the terminal device can determine whether the second sensing result satisfies the first condition.

[0253] In some possible implementations, if the terminal device does not receive the second perception result sent by the network device within a certain period of time, the terminal device can send the second data to the network device. The second data can indicate the input information. The network device can obtain the second perception result based on the input information and the first AI model (the first AI model is determined according to any of the above possible methods) through reasoning of the first AI model, and then send the second perception result to the terminal device.

[0254] Optionally, in some possible implementations, the first indication information may also indicate that the first perception result is invalid or that the first performance value is greater than the first threshold.

[0255] For example, the terminal device can determine that the first condition is met by receiving the first instruction information. The terminal device needs to send input information to the network device so that the network device can obtain the second perception result based on the input information and the first AI model and through the reasoning of the first AI model.

[0256] Optionally, in some possible implementations, method 300 further includes: the network device sending second indication information to the terminal device, the second indication information indicating that the first condition is not met. Correspondingly, the terminal device receives the second indication information from the network device, the second indication information indicating that the first condition is not met.

[0257] Specifically, the network device can send a second indication information to the terminal device, the second indication information indicating that the first condition is not met, that is, the first sensing result is not invalid, or the first performance value satisfies: the first performance value is less than or equal to the first threshold.

[0258] For example, the terminal device can determine the second perception result by receiving a second inference instruction: the second perception result is the first perception result pre-stored by the network device.

[0259] The communication method 300 provided in the embodiments of this application has been described in detail above with reference to Figure 3. The communication device provided in the embodiments of this application will be described below with reference to Figures 5-7.

[0260] Figure 5 is a schematic diagram of a communication device 400 provided in an embodiment of this application. As shown in Figure 5, the device 400 can be a terminal device or a network device, or a component (e.g., a unit, module, chip, or chip system) configured in a terminal device or network device. The device 400 includes a transceiver unit 410, and optionally, a processing unit 420. The transceiver unit 410 can be used to implement corresponding communication functions. The transceiver unit 410 can also be called a communication interface or communication unit. The processing unit 420 can be used to perform processing.

[0261] Optionally, the device 400 may further include a storage unit, which can be used to store instructions and / or data, and the processing unit 420 can read the instructions and / or data in the storage unit to enable the device to implement the aforementioned method embodiments.

[0262] For example, the communication device 400 may be a first communication device / second communication device, or a communication device applied to or used in conjunction with the first communication device / second communication device and capable of implementing the method executed by the first communication device / second communication device, such as a chip, chip system or circuit. For details, please refer to the relevant description of the chip system shown in FIG7.

[0263] As a design, the device 400 is used to execute the steps or processes performed by the first communication device / second communication device in the method embodiment of FIG3 above. The transceiver unit 410 is used to execute the transceiver-related operations on the first communication device / second communication device side in the method embodiment above (e.g., receiving or sending first information, second information, inference requirement indication information, first indication information, or second indication information). The processing unit 420 is used to execute the processing-related operations on the first communication device / second communication device side in the method embodiment of FIG3 above (e.g., determining the second sensing result, determining whether the first sensing result is invalid, or determining whether the first performance value is greater than the first threshold).

[0264] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0265] It should also be understood that the device 400 here is embodied in the form of a functional unit. The term "unit" here may refer to application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memories for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functions.

[0266] The apparatus 400 of each of the above-described schemes has the function of implementing the corresponding steps performed by the first communication device / second communication device in the above-described methods. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions; for example, the transceiver unit can be replaced by a transceiver (e.g., the transmitting unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as processing units, can be replaced by processors, each executing the transceiver operations and related processing operations in each method embodiment.

[0267] In addition, the transceiver unit 410 described above can also be a transceiver circuit (for example, it may include a receiving circuit and a transmitting circuit), and the processing unit can be a processing circuit.

[0268] It should be noted that the device in Figure 5 can be a network element as described in the preceding embodiments, or it can be a chip or a chip system, such as a system on a chip (SoC). The transceiver unit can be an input / output circuit or a communication interface; the processing unit is a processor, microprocessor, or integrated circuit integrated on the chip. No limitations are imposed here.

[0269] Figure 6 is a schematic diagram of another communication device 500 provided in an embodiment of this application. As shown in Figure 6, the device 500 includes a transceiver 530, which is used for receiving and / or transmitting signals. For example, a processor 510 is used to control the transceiver 530 to receive and / or transmit signals.

[0270] Optionally, the device 500 further includes a processor 510 and a memory 520, with the processor 510 coupled to the memory 520. The memory 520 is used to store computer programs or instructions and / or data. The processor 510 is used to execute the computer programs or instructions stored in the memory 520, or to read the data stored in the memory 520, to perform the methods in the above-described method embodiments. For example, the processor 510 is used to control the transceiver 530 to receive and / or transmit signals.

[0271] Optionally, there may be one or more processors 510.

[0272] Optionally, the memory 520 may be one or more.

[0273] Optionally, the memory 520 can be integrated with the processor 510, or it can be set separately.

[0274] As an example, processor 510 may have the functions of processing unit 420 shown in FIG. 5, memory 520 may have the functions of storage unit, and transceiver 530 may have the functions of transceiver unit 410 shown in FIG. 5.

[0275] For example, the communication device 500 may be a first communication device / second communication device, or a communication device applied to or used in conjunction with the first communication device / second communication device and capable of implementing the method executed by the first communication device / second communication device, such as a chip, chip system or circuit. For details, please refer to the relevant description of the chip system shown in FIG7.

[0276] As a design, the device 500 is used to execute the steps or processes performed by the first communication device / second communication device in the method embodiment of FIG3 above, the transceiver 530 is used to execute the transmission and reception related operations on the first communication device / second communication device side in the method embodiment above (e.g., receiving or sending first information, second information, inference requirement indication information, first indication information, or second indication information), and the processor 510 is used to execute the processing related operations on the first communication device / second communication device side in the method embodiment of FIG3 above (e.g., determining the second sensing result, determining whether the first sensing result is invalid, or determining whether the first performance value is greater than the first threshold).

[0277] Optionally, the processor 510 is used to execute computer programs or instructions stored in the memory 520 to implement the relevant operations of the first communication device / second communication device in the various method embodiments described above.

[0278] It should be understood that the processor mentioned in the embodiments of this application can be one of the following devices or a portion of the circuitry used for processing functions: a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0279] In this embodiment, the method described in FIG3 can be executed by a first communication device / second communication device, or by a chip, chip system, or circuit of the first communication device / second communication device, which can be installed in the first communication device / second communication device. The chip system in the first communication device / second communication device will now be described with reference to FIG7.

[0280] Figure 7 is a schematic diagram of a chip system 600 provided in an embodiment of this application. The chip system 600 (or may also be called a processing system) includes logic circuitry 610 and an input / output interface 620.

[0281] The logic circuit 610 can be a processing circuit in the chip system 600. The logic circuit 610 can be coupled to a memory unit, calling instructions from the memory unit, enabling the chip system 600 to implement the methods and functions of the embodiments of this application. The input / output interface 620 can be an input / output circuit in the chip system 600, outputting processed information or inputting data or signaling information to be processed into the chip system 600 for processing.

[0282] For example, if the first device is equipped with the chip system 600, the logic circuit 610 is coupled to the input / output interface 620. The input / output interface 620 can input the input information to the logic circuit 610 for processing, such as processing the input information to obtain the second sensing result.

[0283] As one approach, the chip system 600 is used to implement the operations performed by the device (such as the first communication device / second communication device) in the various method embodiments described above.

[0284] This application provides a computer-readable storage medium storing computer instructions for implementing the methods executed by a device (such as a first communication device / second communication device) in the above-described method embodiments.

[0285] For example, when the computer program is executed by a computer, it enables the computer to implement the methods performed by the device (such as the first communication device / second communication device) in the various embodiments of the above methods.

[0286] This application provides a computer program product containing instructions that, when executed by a computer, implement the methods described above, which are executed by a device (such as a first communication device / second communication device).

[0287] This application provides a communication system that includes a first communication device / second communication device from the embodiments described above. For example, the system includes the first communication device / second communication device from the embodiment shown in FIG3.

[0288] The explanations and beneficial effects of the relevant contents in any of the devices provided above can be found in the corresponding method embodiments provided above, and will not be repeated here.

[0289] To facilitate understanding of the above embodiments provided in this application, the following points are made:

[0290] In this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0291] It is also understood that the solutions in the various embodiments of this application can be used in reasonable combinations, and the explanations or descriptions of the various terms appearing in the embodiments can be referenced or explained to each other in the various embodiments, without limitation.

[0292] It is also understood that, in the above-described method embodiments, the methods and operations implemented by the first device or the positioning device can also be implemented by components (such as chips or circuits) of the first device or the positioning device, without limitation.

[0293] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0294] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0295] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0296] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0297] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0298] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0299] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, Applied to a first communication device, the method includes: Receive first information from a second communication device, the first information indicating a first artificial intelligence (AI) model and / or a first perception result, the first AI model being used for perception data processing, and the first perception result being the perception result required by the second communication device; Determine the second perception result based on the first AI model and / or the first perception result; Send a second message, which indicates the second perception result.

2. The method according to claim 1, characterized in that, The first information indicates the first AI model and / or the first perception result, including: The first information includes a first identifier, and the first identifier and the first relationship are used to determine the first AI model and / or the first perception result; Wherein, the first identifier includes the identifier and / or function identifier of the first AI model, the function identifier indicating the functions supported by the first AI model, and the first relationship is the association between the first identifier and at least one of the following information: Input information, output information, region information, or at least one AI model; The input information indicates the input of the first AI model, the output information indicates the output of the first AI model, the area information indicates the area in which the second communication device can acquire information for perception, and the first AI model is one of the at least one AI model.

3. The method according to claim 2, characterized in that, The input to the first AI model is obtained based on the geometric information of objects in the environment.

4. The method according to claim 2 or 3, characterized in that, The input to the first AI model includes at least one of the following: Point data, patch data, octree data, or voxel data.

5. The method according to any one of claims 2-4, characterized in that, The output of the first AI model includes at least one of the following: Point data, polygon data, bounding box positions, or semantic labels.

6. The method according to any one of claims 2-5, characterized in that, The method also includes: The first AI model is determined by receiving inference requirement indication information, wherein the first identifier, the first relationship, and the inference requirement indication information are used to determine the first AI model.

7. The method according to any one of claims 1-6, characterized in that, The first information also indicates the input and / or output of the first AI model.

8. The method according to any one of claims 1-7, characterized in that, If the first condition is met, the method further includes: Send a first instruction message, which instructs the second communication device to send the input of the first AI model, the input of the first AI model being used to determine the second perception result based on the first AI model; The first condition includes at least one of the following: The first sensing result is invalid; or, The first performance value is greater than a first threshold, and the first performance value is determined by the first communication device based on the first sensing result and first data from the second communication device, wherein the first data includes at least one of the following: Point data, patch data, octree data, or voxel data.

9. A communication method, characterized in that, Applied to a second communication device, the method includes: Send a first message, the first message indicating a first AI model and / or a first perception result, the first AI model being used for perception data processing, the first perception result being the perception result required by the second communication device; Receive second information from a first communication device, the second information indicating a second perception result, the second perception result being determined based on the first AI model and / or the first perception result.

10. The method according to claim 9, characterized in that, The first information indicates the first AI model and / or the first perception result, including: The first information includes a first identifier, and the first identifier and the first relationship are used to determine the first AI model and / or the first perception result; Wherein, the first identifier includes the identifier and / or function identifier of the first AI model, the function identifier indicating the functions supported by the first AI model, and the first relationship is the association between the first identifier and at least one of the following information: Input information, output information, region information, or at least one AI model; The input information indicates the input of the first AI model, the output information indicates the output of the first AI model, the area information indicates the area where the second communication device can acquire information for perception, and the first AI model is one of the at least one AI model.

11. The method according to claim 10, characterized in that, The input to the first AI model is obtained based on the geometric information of objects in the environment.

12. The method according to claim 10 or 11, characterized in that, The input to the first AI model includes at least one of the following: Point data, patch data, octree data, or voxel data.

13. The method according to any one of claims 10-12, characterized in that, The output of the first AI model includes at least one of the following: Point data, polygon data, bounding box positions, or semantic labels.

14. The method according to any one of claims 10-13, characterized in that, The method also includes: Send inference requirement indication information, wherein the first identifier, the first relationship, and the inference requirement indication information are used to determine the first AI model.

15. The method according to any one of claims 9-14, characterized in that, The first information also indicates the input and / or output of the first AI model.

16. The method according to any one of claims 9-15, characterized in that, If the first condition is met, the method further includes: The system receives a first instruction from a first communication device, which instructs the second communication device to send the input of the first AI model. The input of the first AI model is used to determine the second perception result based on the first AI model. The first condition includes at least one of the following: The first sensing result is invalid; or, The first performance value is greater than a first threshold, and the first performance value is determined by the first communication device based on the first sensing result and first data from the second communication device, wherein the first data includes at least one of the following: Point data, patch data, octree data, or voxel data.

17. A communication device, characterized in that, It includes a transceiver unit and a processing unit for performing the method according to any one of claims 1-8, or it includes a transceiver unit for performing the method according to any one of claims 9-16.

18. The apparatus according to claim 17, characterized in that, The transceiver unit is a transceiver, and / or the processing unit is a processor.

19. A communication device, characterized in that, include: A processor for executing computer instructions stored in memory to cause the apparatus to perform: the method of any one of claims 1-8, or the method of any one of claims 9-16.

20. The apparatus according to claim 19, characterized in that, The device also includes the memory.

21. The apparatus according to claim 19 or 20, characterized in that, The device also includes a communication interface coupled to the processor. The communication interface is used for inputting and / or outputting information.

22. The apparatus according to any one of claims 19-21, characterized in that, The device is a chip.

23. A computer program product, characterized in that, When the computer program in the computer program product is executed by a communication device, it implements the method as described in any one of claims 1-8, or the method as described in any one of claims 9-16.

24. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions, which, when executed by a communication device, implement the method as described in any one of claims 1-8, or the method as described in any one of claims 9-16.

25. A communication system, characterized in that, The communication system includes a terminal device and a network device, wherein the network device is configured to perform the method as described in any one of claims 1-8, and the terminal device is configured to perform the method as described in any one of claims 9-16; or... The communication system includes a terminal device and a network device, wherein the terminal device is used to perform the method as described in any one of claims 1-8, and the network device is used to perform the method as described in any one of claims 9-16; or... The communication system includes a first terminal device and a second terminal device, wherein the first terminal device is used to execute the method as described in any one of claims 1-8, and the second terminal device is used to execute the method as described in any one of claims 9-16; or... The communication system includes a first network device and a second network device, wherein the first network device is used to perform the method as described in any one of claims 1-8, and the second network device is used to perform the method as described in any one of claims 9-16.

Images