Communication method and apparatus

Abstract

The present application provides a communication method and apparatus. The method comprises: a first apparatus generates first information; and the first apparatus sends the first information to a second apparatus. The first information comprises native data of N targets, N being a positive integer. A first target is any one of the N targets, and native data of the first target comprises native data of M1 data types, M1 being a positive integer. The native data of the M1 data types is one or more of artificial intelligence data, sensing data, and channel data. By using the above-described method, the sending of native data of one or more targets can be supported, so that support for various data types possibly existing in RAN native data of next-generation mobile communication technologies is facilitated, thereby flexibly supporting data transmission in different scenarios and different tasks.

Description

Communication method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on March 29, 2024, with application number 202410383677.1 and invention name "A Communication Method and Device", the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of communication technology, and in particular to a communication method and device. Background Art

[0004] As wireless communication application scenarios become increasingly diverse, the next generation of wireless communications will generate a large amount of data for new scenarios. For example, new application scenarios such as Integrated Sensing and Communication (ISAC), wireless technologies enabled by artificial intelligence (AI), and terahertz communications will generate massive amounts of data and signaling. Therefore, in the next generation of mobile communication technology radio access network (RAN) systems, multiple data types may exist, requiring the transmission of different data types in different scenarios or tasks.

[0005] Therefore, for the next generation of wireless communication systems, how to effectively and flexibly support data transmission of multiple different data types is an issue worthy of attention. Summary of the Invention

[0006] The embodiments of the present application provide a communication method and apparatus, which are used to effectively and flexibly support data transmission of multiple different data types by defining data formats corresponding to data of multiple data types.

[0007] In a first aspect, the present application provides a communication method, comprising: a first device generating first information, and the first device sending the first information to a second device. The first information includes native data of N targets, where N is a positive integer, and the first target is one of the N targets. The native data of the first target includes native data of M1 data types, where M1 is a positive integer, and the native data of the M1 data types is one or more of artificial intelligence data, perception data, and channel data.

[0008] The above method can support the sending of native data of one or more targets. In addition, it has good scalability and maintainability, which makes it easy to support various data types that may exist in the native data of the next generation mobile communication technology RAN, thereby flexibly supporting data transmission in different scenarios and different tasks.

[0009] In one possible design, when the first device sends the first information to the second device, the first device sends the first information through one or more layers of the physical PHY layer, the medium access control MAC layer, the radio link layer control protocol RLC layer, the packet data convergence protocol PDCP layer, the radio resource control RRC layer or the application layer.

[0010] In one possible design, corresponding to a wireless communication scenario where artificial intelligence is applicable, the native data of the N targets include artificial intelligence data corresponding to N artificial intelligence models collected by the first device, and the N artificial intelligence models correspond to N wireless communication tasks respectively; or, the native data of the N targets include artificial intelligence data corresponding to the N targets collected by the first device, and the N targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data. In another possible design, corresponding to a perception scenario, the native data of the N targets include perception data of N perception devices collected by the first device. In one possible design, corresponding to a scenario where communication tasks are processed, the native data of the N targets include channel data of N user devices collected by the first device.

[0011] The above design supports native data transmission in multiple different scenarios. The first information can include native data of the same data type for multiple targets, so that the second device can obtain more, more comprehensive, and more accurate native data of the same data type, thereby improving the accuracy of tasks related to the data type.

[0012] In one possible design, the first target is the first device, and the native data of the first target includes two or more of the perception data of the first target, the channel data of the first target, or the artificial intelligence data of the first target.

[0013] With the above design, the native data of the first target may include native data of multiple data types, so that the second device can determine more accurate and more suitable configuration parameters by combining the native data of multiple data types.

[0014] In one possible design, the native data of some or all of the N targets includes two or more types of native data; the two or more types of native data include perception data and channel data, and the perception data is used to assist in communication tasks of one or more targets. In another possible design, the native data of some or all of the N targets includes two or more types of native data; the two or more types of native data include artificial intelligence data and perception data, and the artificial intelligence data is used to assist in perception of one or more targets.

[0015] By adopting the above design, the second device can determine more accurate and suitable configuration parameters by combining native data of multiple data types.

[0016] In a possible design, the first data type is any one of the M1 data types, and the native data of the first data type includes native data of K data subtypes, where K is a positive integer.

[0017] In a possible design, the native data of the first data type further includes identifiers of the K data subtypes, and the identifiers of the K data subtypes respectively correspond to the native data of the K data subtypes.

[0018] In one possible design, the data type or data subtype of the perception data includes one or more of reflection point information, patch information, environmental map information, radio frequency map information, imaging data, or original perception signals; the data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data, or performance data; the data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data.

[0019] In one possible design, before generating the first information, the first device sends first capability information to the second device, where the first capability information includes S data types supported by the first device, where S is an integer greater than or equal to M1.

[0020] In one possible design, the first capability information also includes a data subtype supported by the first device in each of the S data types.

[0021] In one possible design, before generating the first information, the first device receives second capability information from the second device, where the second capability information includes Q data types supported by the second device, where Q is an integer greater than or equal to M1.

[0022] In one possible design, the second target is one of the N targets that is different from the first target, and the native data of the second target includes native data of M2 data types, where M2 is a positive integer and M1 is not equal to M2.

[0023] In one possible design, the first information also includes identifiers of the N targets, and the identifiers of the N targets correspond to the N targets respectively.

[0024] In one possible design, the first information also includes indication information, where the indication information is used to indicate the number of targets.

[0025] In one possible design, the native data of the first target includes identifiers of the M1 data types, and the identifiers of the M1 data types respectively correspond to the native data of the M1 data types.

[0026] In a second aspect, the present application provides a communication method, which includes: a second device receives first information from a first device, wherein the first information includes native data of N targets, N is a positive integer, and the first target is one of the N targets, and the native data of the first target includes native data of M1 data types, M1 is a positive integer, and the native data of the M1 data types are one or more of artificial intelligence data, perception data, and channel data; the second device parses the first information and performs corresponding operations based on the native data of the N targets included in the first information.

[0027] The above method can support the transmission of native data to one or more targets. Furthermore, it has good scalability and maintainability, facilitating support for the diverse data types that may exist in native data of next-generation mobile communication technologies such as RAN, thereby flexibly supporting data transmission in different scenarios and tasks. Because the first information may include more, more comprehensive, and more accurate native data, after obtaining the first information, the second device can perform corresponding operations based on the native data included in the first information, thereby improving communication performance.

[0028] In one possible design, corresponding to a wireless communication scenario where artificial intelligence is applicable, the native data of the N targets include artificial intelligence data corresponding to N artificial intelligence models collected by the first device, and the N artificial intelligence models correspond to N wireless communication tasks respectively; or, the native data of the N targets include artificial intelligence data corresponding to the N targets collected by the first device, and the N targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data. In another possible design, corresponding to a perception scenario, the native data of the N targets include perception data of N perception devices collected by the first device. In yet another possible design, corresponding to a scenario where communication tasks are processed, the native data of the N targets include channel data of N user devices collected by the first device.

[0029] In one possible design, the first target is the first device, and the native data of the first target includes two or more of the perception data of the first target, the channel data of the first target, or the artificial intelligence data of the first target.

[0030] In one possible design, the native data of some or all of the N targets includes two or more types of native data; the two or more types of native data include perception data and channel data, and the perception data is used to assist in communication tasks of one or more targets. In another possible design, the native data of some or all of the N targets includes two or more types of native data; the two or more types of native data include artificial intelligence data and perception data, and the artificial intelligence data is used to assist in perception of one or more targets.

[0031] In a possible design, the first data type is any one of the M1 data types, and the native data of the first data type includes native data of K data subtypes, where K is a positive integer.

[0032] In a possible design, the native data of the first data type further includes identifiers of the K data subtypes, and the identifiers of the K data subtypes respectively correspond to the native data of the K data subtypes.

[0033] In one possible design, the data type or data subtype of the perception data includes one or more of reflection point information, patch information, environmental map information, radio frequency map information, imaging data, or original perception signals; the data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data, or performance data; the data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data.

[0034] In one possible design, before the second device receives the first information from the first device, the second device receives first capability information from the first device, where the first capability information includes S data types supported by the first device, where S is an integer greater than or equal to M1.

[0035] In one possible design, the first capability information also includes a data subtype supported by the first device in each of the S data types.

[0036] In one possible design, before the second device receives the first information from the first device, the second device sends second capability information to the first device, where the second capability information includes Q data types supported by the second device, where Q is an integer greater than or equal to M1.

[0037] In one possible design, the second target is one of the N targets that is different from the first target, and the native data of the second target includes native data of M2 data types, where M2 is a positive integer and M1 is not equal to M2.

[0038] In one possible design, the first information also includes identifiers of the N targets, and the identifiers of the N targets correspond to the N targets respectively.

[0039] In one possible design, the first information also includes indication information, where the indication information is used to indicate the number of targets.

[0040] In one possible design, the native data of the first target includes identifiers of the M1 data types, and the identifiers of the M1 data types respectively correspond to the native data of the M1 data types.

[0041] In a third aspect, the present application provides a communication method, comprising: a first device generating second information; the first device sending the second information to a second device, the second information including native data of X data types, where X is a positive integer; the native data of the X data types are one or more of artificial intelligence data, perception data, and channel data; wherein the first data type is any one of the X data types; the native data of the first data type includes native data of Y targets, where Y is a positive integer.

[0042] The above method can support the transmission of native data of one or more data types. In addition, it has good scalability and maintainability, which is convenient for supporting various data types that may exist in the native data of the next generation mobile communication technology RAN, thereby flexibly supporting data transmission in different scenarios and different tasks.

[0043] In one possible design, when the first device sends the first information to the second device, the first device sends the first information through one or more layers of the physical layer, MAC layer, RLC layer, PDCP layer, RRC layer or application layer.

[0044] In one possible design, corresponding to a wireless communication scenario where artificial intelligence is applicable, the native data of the first data type is artificial intelligence data, and the native data of the Y targets include artificial intelligence data corresponding to Y artificial intelligence models collected by the first device, and the Y artificial intelligence models correspond to Y wireless communication tasks respectively; or, the native data of the Y targets include artificial intelligence data corresponding to the Y targets collected by the first device, and the Y targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data. In another possible design, corresponding to a perception scenario, the native data of the first data type is perception data, and the native data of the Y targets include perception data of Y perception devices collected by the first device. In yet another possible design, corresponding to a scenario where communication tasks are processed, the native data of the first data type is channel data, and the native data of the Y targets include channel data of Y user devices collected by the first device.

[0045] The above design supports native data transmission in multiple different scenarios. The first information can include native data of the same data type for multiple targets, so that the second device can obtain more, more comprehensive, and more accurate native data of the same data type, thereby improving the accuracy of tasks related to the data type.

[0046] In one possible design, before generating the second information, the first device sends first capability information to the second device, where the first capability information includes S data types supported by the first device, where S is an integer greater than or equal to X.

[0047] In one possible design, the first capability information also includes a data subtype supported by the first device in each of the S data types.

[0048] In one possible design, before generating the second information, the first device receives second capability information from the second device, where the second capability information includes Q data types supported by the second device, where Q is an integer greater than or equal to X.

[0049] In a possible design, the second information further includes identifiers of the X data types, and the identifiers of the X data types respectively correspond to native data of the X data types.

[0050] In one possible design, the second information also includes second indication information, and the second indication information is used to obtain the number of data types.

[0051] In a possible design, the native data of the first data type also includes identifiers of the Y targets, and the identifiers of the Y targets respectively correspond to the native data of the Y targets.

[0052] In a possible design, the second data type is any one of the X data types that is different from the first data type, and the native data of the second data type includes native data of W targets, where W is a positive integer and W is not equal to Y.

[0053] In one possible design, the native data of the first data type includes native data of Z data subtypes, where Z is a positive integer, and the native data of the Y targets belong to the native data of the Z data subtypes.

[0054] In a possible design, the native data of the first data type further includes identifiers of the Z data subtypes, and the identifiers of the Z data subtypes respectively correspond to the native data of the Z data subtypes.

[0055] In a possible design, the native data of the first data type further includes third indication information, where the third indication information is used to determine the number of data subtypes.

[0056] In one possible design, the data type or data subtype of the perception data includes one or more of reflection point information, patch information, environmental map information, radio frequency map information, imaging data, or original perception signals; the data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data, or performance data; the data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data.

[0057] In a fourth aspect, the present application provides a communication method, comprising: a second device receiving second information from a first device; the second information including native data of X data types, where X is a positive integer; the native data of the X data types being one or more of artificial intelligence data, perception data, and channel data; wherein the first data type is any one of the X data types; the native data of the first data type including native data of Y targets, where Y is a positive integer; the second device parsing the second information and performing corresponding operations based on the native data of the X data types included in the second information.

[0058] The above method can support the transmission of native data to one or more targets. Furthermore, it offers excellent scalability and maintainability, facilitating support for the diverse data types that may exist in native data of next-generation mobile communication technologies (RANs), thereby flexibly supporting data transmission in different scenarios and tasks. Because the second information can include more, more comprehensive, and more accurate native data, the second device, after obtaining the second information, can perform corresponding operations based on the native data included in the second information, thereby improving communication performance.

[0059] In one possible design, corresponding to a wireless communication scenario where artificial intelligence is applicable, the native data of the first data type is artificial intelligence data, and the native data of the Y targets include artificial intelligence data corresponding to Y artificial intelligence models collected by the first device, and the Y artificial intelligence models correspond to Y wireless communication tasks respectively; or, the native data of the Y targets include artificial intelligence data corresponding to the Y targets collected by the first device, and the Y targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data. In another possible design, corresponding to a perception scenario, the native data of the first data type is perception data, and the native data of the Y targets include perception data of Y perception devices collected by the first device. In yet another possible design, corresponding to a scenario where communication tasks are processed, the native data of the first data type is channel data, and the native data of the Y targets include channel data of Y user devices collected by the first device.

[0060] In one possible design, before the second device receives the second information from the first device, the second device receives first capability information from the first device, where the first capability information includes S data types supported by the first device, where S is an integer greater than or equal to M1.

[0061] In one possible design, the first capability information also includes a data subtype supported by the first device in each of the S data types.

[0062] In one possible design, before the second device receives the second information from the first device, the second device sends second capability information to the first device, where the second capability information includes Q data types supported by the second device, where Q is an integer greater than or equal to M1.

[0063] In a possible design, the second information further includes identifiers of the X data types, and the identifiers of the X data types respectively correspond to native data of the X data types.

[0064] In one possible design, the second information also includes second indication information, and the second indication information is used to obtain the number of data types.

[0065] In a possible design, the native data of the first data type also includes identifiers of the Y targets, and the identifiers of the Y targets respectively correspond to the native data of the Y targets.

[0066] In a possible design, the second data type is any one of the X data types that is different from the first data type, and the native data of the second data type includes native data of W targets, where W is a positive integer and W is not equal to Y.

[0067] In one possible design, the native data of the first data type includes native data of Z data subtypes, where Z is a positive integer, and the native data of the Y targets belong to the native data of the Z data subtypes.

[0068] In a possible design, the native data of the first data type further includes identifiers of the Z data subtypes, and the identifiers of the Z data subtypes respectively correspond to the native data of the Z data subtypes.

[0069] In a possible design, the native data of the first data type further includes third indication information, where the third indication information is used to determine the number of data subtypes.

[0070] In one possible design, the data type or data subtype of the perception data includes one or more of reflection point information, patch information, environmental map information, radio frequency map information, imaging data, or original perception signals; the data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data, or performance data; the data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data.

[0071] In a fifth aspect, the present application provides a communication device, which may be a first device, or a module or unit (for example, a chip, or a chip system, or a circuit) in the first device that corresponds one-to-one to the method / operation / step / action described in any one of the first or third aspects, or may be capable of being used in combination with the first device.

[0072] In the sixth aspect, the present application provides a communication device, which can be a second device, or a module or unit (for example, a chip, or a chip system, or a circuit) in the second device that corresponds one-to-one to the method / operation / step / action described in any one of the second or fourth aspects, or can be used in combination with the second device.

[0073] In the seventh aspect, the present application provides a communication device comprising at least one processing element, wherein at least one storage element is used to store programs and data, and the at least one processing element is used to read and execute the programs and data stored in the storage element so that the method described in any one of the above aspects of the present application is implemented.

[0074] In one possible design, the communication device further includes the at least one storage element.

[0075] In an eighth aspect, the present application further provides a computer program, which, when executed on a computer, enables the computer to execute any of the methods described in any of the above aspects.

[0076] In a ninth aspect, the present application provides a communication device comprising: an interface circuit and at least one processor; the interface circuit is used to provide input and / or output of programs or instructions to the at least one processor; the at least one processor is used to execute the programs or instructions so that the communication device can implement any of the methods described in any of the above aspects.

[0077] In a possible manner, the communication device includes the at least one memory, and the at least one memory is used to store the program or instruction.

[0078] In a tenth aspect, the present application provides a computer storage medium storing a software program. When the software program is read and executed by one or more processors, it can implement any of the methods described in any of the above aspects.

[0079] In an eleventh aspect, the present application provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the methods described in any of the above aspects.

[0080] In the twelfth aspect, the present application provides a chip system, which includes at least one chip and a memory, and the at least one chip is used to read and execute the program stored in the memory to implement any of the methods described in any of the above aspects.

[0081] In the thirteenth aspect, the present application provides a communication system, which includes at least one first device and at least one second device, the first device is used to execute the method described in any one of the first and third aspects, and the second device is used to execute the method described in any one of the second and fourth aspects.

[0082] In the fourteenth aspect, the present application provides a communication system, which includes at least one terminal and a base station, the terminal is used to execute the method described in any one of the first to fourth aspects, and the base station is used to execute the method described in any one of the first to fourth aspects.

[0083] Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] FIG1 shows a schematic diagram of the architecture of a possible communication system in this application;

[0085] 2A to 2C are schematic diagrams showing possible implementation scenarios of the present application;

[0086] FIG3 shows an overview flow chart of a communication method in the present application;

[0087] 4A to 4D are schematic diagrams showing the specific format of the native data of the first target in this application;

[0088] 5A to 5C are schematic diagrams showing a specific format of native data of the first data type in the present application;

[0089] 6A to 6E are schematic diagrams showing the specific format of the first information in this application;

[0090] FIG7 shows an overview flow chart of a communication method in the present application;

[0091] 8A to 8C are schematic diagrams showing the specific format of the second information in this application;

[0092] FIG9 shows a schematic structural diagram of a communication device in the present application;

[0093] FIG10 shows a schematic structural diagram of another communication device in the present application. DETAILED DESCRIPTION

[0094] The specific implementation of the present application is described below with reference to the accompanying drawings in the embodiments of the present application. The detailed description of the following embodiments should not be understood in a restrictive sense. The terms used in the examples section of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.

[0095] The embodiments of the present application can be applied to various communication systems, such as: global system for mobile communications (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, universal mobile telecommunication system (UMTS), world-wide interoperability for microwave access (WIMAX) communication system, 5G system or new radio (NR), or applied to future communication systems or other similar communication systems (such as 6G, etc.), or ultra wide band (UWB) system, or wireless fidelity (WiFi) system.

[0096] Figure 1 shows a possible, non-limiting system diagram. As shown in Figure 1 , the communication system 1000 includes a radio access network 100 and a core network 200. Optionally, the communication system 1000 may also include the Internet 300. The radio access network 100 may include at least one radio access network device (such as 110a and 110b in Figure 1 ) and at least one terminal (such as 120a-120j in Figure 1 ). The terminal is wirelessly connected to the radio access network device, and the radio access network device is wirelessly or wiredly connected to the core network. The core network device and the radio access network device may be independent, distinct physical devices, or the core network device's functions and the radio access network device's logical functions may be integrated into the same physical device, or a single physical device may integrate some of the core network device's functions and some of the radio access network device's functions. Terminals and radio access network devices may be interconnected via wired or wireless connections. Figure 1 is merely a schematic diagram. The communication system may also include other network devices, such as wireless relay devices and wireless backhaul devices, which are not shown in Figure 1 .

[0097] The radio access network device can be a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next generation NodeB (gNB) in a 5G mobile communication system, a next generation base station in a sixth generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. The radio access network device can also be an open access network (open RAN, O-RAN or ORAN) or a cloud radio access network (CRAN). The radio access network device can also be a communication system that integrates two or more of the above systems. The radio access network device can be a macro base station (such as 110a in Figure 1), a micro base station or an indoor station (such as 110b in Figure 1), a relay node or a donor node, etc.

[0098] In addition, the radio access network device may also be a module or unit that performs some of the functions of the base station, for example, a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU may also be called O-CU (Open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For convenience of description, this application uses CU, CU-CP, CU-UP, DU and RU as examples for description. Any of the CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0099] The embodiments of the present application do not limit the specific technology and specific device form adopted by the wireless access network equipment. For the convenience of description, the following description takes the base station as an example of the wireless access network equipment. It can be understood that the base station can be called a communication device. For example, the base station can be understood as a device with the function of a base station. For example, the device for implementing the function of the base station can be a base station; or some components in the base station, such as CU, DU, etc. It can also be a device that can support the base station to implement the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The device can be installed in the base station or can be used in conjunction with the base station. In the embodiment of the present application, the chip system can be composed of chips, or it can include chips and other discrete devices.

[0100] Terminals can also be referred to as terminal devices, user equipment (UE), mobile stations, or mobile terminals. They can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), the Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, and smart cities. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, and smart home appliances.

[0101] The embodiments of this application do not limit the specific technology and specific device form used by the terminal. It is understood that the terminal can be referred to as a communication device. For example, the terminal can be understood as a device having terminal functions. For example, the device used to implement the terminal function can be a terminal; it can also be a device that supports the terminal to implement the function, such as a chip system, hardware circuit, software module, or hardware circuit and software module, which can be installed in the terminal or can be used in conjunction with the terminal.

[0102] Base stations and terminals can be fixed or mobile. They can be deployed on land, indoors or outdoors, handheld or vehicle-mounted; on water; or on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of base stations and terminals.

[0103] The roles of base stations and terminals can be relative. For example, the helicopter or drone 120i in Figure 1 can be configured as a mobile base station. To terminals 120j accessing the wireless access network 100 via 120i, drone 120i is a base station. However, to base station 110a, 120i is a terminal, meaning that communication between 110a and 120i occurs via a wireless air interface protocol. Of course, communication between 110a and 120i can also occur via a base station-to-base station interface protocol. In this case, 120i is also a base station relative to 110a. Therefore, base stations and terminals can be collectively referred to as communication devices. 110a and 110b in Figure 1 can be referred to as communication devices with base station functionality, while 120a-120j in Figure 1 can be referred to as communication devices with terminal functionality.

[0104] Communication between base stations and terminals, between base stations, and between terminals can be carried out through authorized spectrum, unauthorized spectrum, or both; communication can be carried out through spectrum below 6 gigahertz (GHz), spectrum above 6 GHz, or spectrum below 6 GHz and spectrum above 6 GHz. The embodiments of the present application do not limit the spectrum resources used for wireless communication.

[0105] Unless otherwise specified herein, the description will be based on the “first device” and the “second device” as the execution entities.

[0106] Among them, the "first device" can be understood as a terminal, or a device with terminal functions, or a device that implements terminal functions. For example, the first device is a terminal, or the first device can be a module in the terminal (for example, a chip or circuit, etc.). Alternatively, the "first device" can be understood as a base station, or a device with base station functions, or a device that implements base station functions. For example, the first device is a base station, or the second device can be a module in a base station (for example, a chip or circuit, etc.), or a module or unit (for example, CU, DU or RU), a logic module or software that fully or partially implements the functions of a base station. Alternatively, the "first device" can be understood as a device or apparatus with perception capabilities, or a device or apparatus capable of performing artificial intelligence tasks. Among them, a device with perception capabilities can also be called a perception device, and a device capable of performing artificial intelligence tasks can also be called an artificial intelligence task execution device.

[0107] The “second device” can be understood as a terminal, or a device with terminal functions, or a device that implements terminal functions. For example, the second device is a terminal, or the second device can be a module in the terminal (for example, a chip or circuit, etc.). Alternatively, the “second device” can be understood as a base station, or a device with base station functions, or a device that implements base station functions. For example, the first device is a base station, or the second device can be a module in a base station (for example, a chip or circuit, etc.), or a module or unit (for example, CU, DU or RU), a logic module or software that fully or partially implements the functions of a base station. Alternatively, the “second device” can be understood as a device or apparatus with perception capabilities, or a device or apparatus that can perform artificial intelligence tasks. Among them, a device with perception capabilities can also be called a perception device, and a device that can perform artificial intelligence tasks can also be called an artificial intelligence task execution device.

[0108] In addition, "first device" can also be replaced by "first equipment" or "first communication device", and "second device" can also be replaced by "second equipment" or "second communication device".

[0109] In some possible implementation scenarios, the "first device" may be a "terminal" and the "second device" may be a "base station". Alternatively, the "first device" may be a "base station" and the "second device" may be a "terminal". For example, in Figure 2A, one or more terminals may communicate with the base station respectively. The interface between the terminal and the base station is a Uu interface.

[0110] In some possible implementation scenarios, the "first device" may be a "first terminal" and the "second device" may be a "second terminal". For example, in Figure 2B, terminal 1 can communicate with terminal 3, and terminal 2 can communicate with terminal 3. Among them, terminal 3 and terminal 1 can communicate through a side link, and similarly, terminal 3 and terminal 2 can communicate through a side link. In addition, if terminal 3 sends the data received from terminal 1 and the data received from terminal 2, terminal 3 can also send the data received from terminal 1, the data received from terminal 2, and its own data (that is, the data of terminal 3) to the base station. At this time, terminal 3 can also be understood as a relay terminal. The interface between terminal 3 and the base station is the Uu interface.

[0111] In some possible implementation scenarios, the "first device" may be a "first base station" and the "second device" may be a "second base station." For example, in Figure 2C , base station 1 and base station 2 may communicate. The interface between base station 1 and base station 2 may be an X2 interface.

[0112] In this application, "sending" and "receiving" indicate the direction of signal transmission. For example, "sending information to XX" can be understood as the destination of the information is XX, and "sending information" can include direct sending, and also includes indirect sending through other units or modules. "Receiving information from YY" can be understood as the source of the information is YY, and "receiving information" can include receiving directly from YY, and also includes receiving indirectly from YY through other units or modules. In addition, "sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface. In other words, "sending" or "receiving" can be performed between devices, for example, the base station and the terminal send or receive respectively through the air interface, and "sending" or "receiving" can also be performed within the device, for example, sending or receiving between components, modules, chips, software modules or hardware modules within the device through a bus, a line or an interface.

[0113] Wireless communication application scenarios are becoming increasingly diverse. Future wireless communication systems will generate a wealth of data tailored to these new scenarios, and new requirements will arise for transmitting this data. For example, new application scenarios such as ISAC, AI-enabled wireless technologies, and terahertz communications will generate massive amounts of data and signaling. Therefore, in future 6G radio access network systems, for example, multiple data types may exist, requiring transmission of different data types for different scenarios or tasks.

[0114] In the future wireless communication process, a large amount of native data will be generated. Native data can be understood as data derived from emerging application scenarios in future wireless communication systems (such as 6G), especially the radio access network (RAN) data that requires air interface transmission, or local data generated in the RAN. Among them, native data can be simply referred to as data. Native data can include data of various data types (and possible data subtypes), such as perception data, artificial intelligence data, or channel data. Exemplarily, native data or native data types may include at least one of the following but not limited to the following examples:

[0115] The first type is perception data, such as 2D or 3D imaging data (e.g., acquired environmental reflection points, environmental patches), environmental reconstruction data, point cloud data, radio frequency maps, or positioning data;

[0116] The second type is artificial intelligence data or edge artificial intelligence data, such as AI model data, training data, gradient data, gradient update data, inference results, feature information extracted by neural networks, performance data, etc.

[0117] The third type is channel data, such as a channel matrix, channel information fed back by devices in a multi-antenna system, and channel status information (CSI) data.

[0118] For example, in one implementation, the native data or native data type transmitted is perception data. In another implementation, the native data or native data type transmitted is point cloud data. In another implementation, the native data or native data type transmitted is positioning data and inference results.

[0119] In order to flexibly support the transmission of native data of different data types, the present application provides a communication method, as shown in FIG3 , which includes:

[0120] Step 300: The first device generates first information.

[0121] Step 310: The first device sends first information to the second device. Correspondingly, the second device receives the first information from the first device.

[0122] Exemplarily, the first information includes native data of N targets, where N is a positive integer; wherein the first target is any one of the N targets, and the native data of the first target includes native data of M1 data types, where M1 is a positive integer, and the native data of the M1 data types are one or more of perception data, artificial intelligence data, and channel data.

[0123] Exemplarily, when a first device sends first information to a second device, the first device may send the first information through one or more layers of a physical layer (PHY), a medium access control (MAC) layer, a radio link control protocol (RLC) layer, a packet data convergence protocol (PDCP) layer, a radio resource control (RRC) layer, or an application layer.

[0124] Exemplarily, the perception data may be sent via the MAC layer and / or the RRC layer, and the artificial intelligence data may be sent via the application layer and / or the PDCP layer.

[0125] For example, an AI model can use a third-party model, and the third-party model is located at the application layer. Therefore, the AI ​​data can be sent at the application layer and / or encapsulated as PDCP data at the PDCP layer. In addition, AI-related data can also be carried by the physical layer, such as AI-related measurement information, part or all of the input / output of the AI ​​model, and can be carried in different layers (for example, one possible combination: PHY layer, MAC layer) depending on the different tasks and models.

[0126] For another example, the perception data may be acquired through radio frequency collection and does not need to be processed at the application layer. Therefore, the perception data can be sent at the MAC layer and / or the RRC layer. The control channel (PHY layer) can be considered for transmitting the perception data information. However, due to the large amount of perception data, in order to reduce the overhead of the uplink control channel, such as reducing the overhead of uplink control information (UCI), the perception data can also be sent at the MAC layer and / or the RRC layer.

[0127] For another example, channel data can be sent at the physical layer and fed back using the system's CSI feedback mechanism, such as type II, to achieve lower latency.

[0128] The above examples are for illustration only. This application does not limit the specific layer or layers at which the perception data, channel data, and artificial intelligence data are sent. In addition, the above data can also be sent at different layers or at the same layer.

[0129] Optionally, step 320: the second device parses the first information and performs corresponding operations according to the native data of the N targets included in the first information.

[0130] For details, please refer to the following scenarios A to D, the relevant descriptions in the perception scenario, the wireless communication scenario applicable to artificial intelligence, and the scenario for processing communication tasks.

[0131] The above method can support the sending of native data of one or more targets. In addition, it has good scalability and maintainability, which is convenient for supporting various data types that may exist in the native data of the next generation mobile communication technology RAN, thereby being able to flexibly support the transmission of native data in different scenarios and tasks. Since the first information can include more, more comprehensive and more accurate native data, after obtaining the first information, the second device can continue to perform corresponding operations based on the native data included in the first information, thereby improving communication performance.

[0132] The following describes two cases: N is 1 and N is an integer greater than 1.

[0133] Case 1: The value of N is 1, that is, the first information includes the native data of one target, or in other words, the first information only includes the native data of the first target.

[0134] In a possible implementation, if N=1, the first target may be the first device, or the first target may also be another device.

[0135] The following describes the first information in conjunction with specific scenarios:

[0136] Scenario A: The native data of the first target includes the artificial intelligence data of the first target and the perception data of the first target.

[0137] Exemplarily, the first target is the first device, the first device is the terminal, and the second device is the base station. The terminal can perform target tracking and positioning based on the artificial intelligence model to obtain artificial intelligence data (for example, inference results, which can be specifically position or border information, etc.), and the terminal can also obtain perception data (for example, reflection points or patches). The terminal can send first information to the base station, and the first information includes the terminal's perception data and the terminal's artificial intelligence data. The base station can then combine the terminal's perception data and the terminal's artificial intelligence data to improve the accuracy of target tracking and positioning.

[0138] Scenario B: The native data of the first target includes the artificial intelligence data of the first target and the channel data of the first target.

[0139] Exemplarily, the first target is a first device, the first device is a terminal, and the second device is a base station. The terminal can predict subsequent channels based on an artificial intelligence model to obtain artificial intelligence data (for example, the inference result of the channel prediction), and the terminal can also obtain channel data through channel measurement. Compared with the terminal only feeding back channel data, the terminal can send first information to the base station, and the first information includes the terminal's channel data and the terminal's artificial intelligence data. Then, the base station can combine the terminal's channel data and the terminal's artificial intelligence data to determine more accurate multiple-input multiple-output (MIMO) transmission parameters.

[0140] Scenario C: The native data of the first target includes the perception data of the first target and the channel data of the first target.

[0141] Exemplarily, the first target is the first device, the first device is the terminal, and the second device is the base station. The terminal can obtain channel data through channel measurement, and the terminal can also obtain perception data (such as reflection points or patches, etc.). Compared with the terminal only feeding back channel data, the terminal can send first information to the base station. The first information includes the terminal's channel data and the terminal's perception data. Then, the base station can combine the terminal's channel data and the terminal's perception data to determine more accurate MIMO transmission parameters.

[0142] Scenario D: The native data of the first target includes the artificial intelligence data of the first target, the perception data of the first target, and the channel data of the first target.

[0143] The above scenarios A to D are for example purposes only and are not intended to limit this application. By reporting the native data of multiple data types of the first target to the second device, at least one of the following technical effects can be achieved: improving the accuracy of artificial intelligence task execution, improving perception accuracy, and improving the accuracy of communication parameters (such as MIMO transmission parameters).

[0144] In addition, illustratively, the first information may further include an identifier of the first target, or the first information may not include the identifier of the first target. For example, if the second device notifies the first device to periodically send the native data of the first target, the first information may not include the identifier of the first target.

[0145] Exemplarily, the native data of the first target may include identifiers of M1 data types, or may not include identifiers of M1 data types. For example, the second device may configure the first device to periodically send native data corresponding to M1 data types, and then the native data of the first target may not include identifiers of M1 data types. Among them, the second device may also configure the packet arrangement order of M1 data types, or predefine the packet arrangement order of multiple data types through the protocol, and the first device determines the packet arrangement order of M1 data types according to the packet arrangement order of multiple data types predefined by the protocol. For example, the packet arrangement order of multiple data types may be channel data before perception data, and perception data before artificial intelligence data. If the native data corresponding to the M1 data types include perception data and channel data, the first device determines that channel data precedes perception data according to the packet arrangement order of the above-mentioned multiple data types. It can be understood that the present application does not limit the packet arrangement order of multiple data types.

[0146] The specific format of the native data of the first target is described below with reference to Figures 4A to 4D . In Figures 4A to 4D , Data Type 1 to Data Type M1 are used to identify M1 data types, and Data Content 1 to Data Content M1 are used to represent the native data corresponding to the M1 data types. Data Type 1 to Data Type M1 correspond one-to-one to Data Content 1 to Data Content M1.

[0147] In one possible implementation, the native data of the first target includes identifiers of M1 data types and the native data corresponding to each of the M1 data types, with the identifiers of the M1 data types corresponding to the native data of the M1 data types, as shown in FIG4A . For example, if the second device notifies the first device to send native data of data type 1 and native data of data type 2, the native data of the first target may not indicate the number of data types.

[0148] In another possible implementation, the native data of the first target may include the number of data types, identifiers of M1 data types, and native data corresponding to the M1 data types. As shown in FIG4B , the native data of the first target also includes the number of data types.

[0149] In another possible implementation, the native data of the first target may include M1 indicator bits, identifiers of M1 data types, and native data corresponding to the M1 data types. For example, the indicator bit may be a more flag, and the number of data types may be indirectly (or implicitly) indicated by multiple indicator bits. As shown in Figures 4C and 4D, the native data of the first target also includes M1 indicator bits. In Figure 4C, when the indicator bit indicates 1, it indicates that there are subsequent native data of other data types, and when the indicator bit indicates 0, it indicates that there are no subsequent native data of other data types. In Figure 4D, when the indicator bit indicates 1, it indicates that there are subsequent other data types, and when the indicator bit indicates 0, it indicates that there are no subsequent other data types.

[0150] Further, taking the first data type as an example, the first data type is any one of M1 data types, and the native data of the first data type may include native data of K data subtypes, where K is a positive integer.

[0151] It is understandable that the first data type may include multiple data subtypes, and the K data subtypes may be part or all of the multiple data subtypes included in the first data type. Exemplarily, the data type or data subtype of the perception data includes one or more of reflection point information, patch information, environmental map information, radio frequency map information, imaging data, or raw perception signals; the data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data, or performance data; the data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data. For details, please refer to the following Table 1. In addition, the data subtype of the perception data, the data subtype of the artificial intelligence data, or the data subtype of the channel data may also include other data subtypes, which are not limited in this application. As can be seen from Table 1, the data subtype may also include one or more data sub-subtypes. In addition, the data subtype may also include data sub-subtypes, which are not limited in this application. The following only uses the two dimensions of data type and data subtype as examples for explanation. The technical solution provided in this application can also be applied to scenarios involving data sub-subtypes or data sub-sub-subtypes.

[0152] Table 1

[0153] Example 1: If the first data type is perception data, the native data of the first data type may include reflection point information and environment map information.

[0154] Example 2: If the first data type is artificial intelligence data, the native data of the first data type may include performance data.

[0155] Example 3: Assume that M1=2, and the M1 data types include sensing data and channel data, wherein the sensing data may include reflection point information and the channel data includes channel state information data.

[0156] Example 4: Assume M1 = 2, and the M1 data types include perception data and artificial intelligence data. Perception data may include reflection point information and environment map information. Artificial intelligence data includes inference results and performance data.

[0157] The above examples 1 to 4 are merely examples and are not intended to limit the present application.

[0158] Exemplarily, the native data of the first data type may include identifiers of K data subtypes and native data corresponding to the K data subtypes. The identifiers of the K data subtypes correspond to the native data of the K data subtypes. Alternatively, the native data of the first data type may include native data corresponding to the K data subtypes, but not include identifiers of the K data subtypes. The order in which the data packets of the K data subtypes are arranged may be configured in advance or predefined by the protocol.

[0159] The specific format of the native data of the first data type is described below with reference to FIG. 5A to FIG. 5C :

[0160] Possible implementation method 1: The native data of the first target includes a first value and native data corresponding to M1 data types, wherein the native data of the first data type includes identifiers of K data subtypes and native data corresponding to the K data subtypes. The first value is the sum of the data subtypes corresponding to the M1 data types, and the identifiers of the K data subtypes correspond to the native data of the K data subtypes.

[0161] In FIG5A , assuming that M1=2, the M1 data types are respectively the first data type and the second data type, the native data of the first data type includes data of m data subtypes, and the native data of the second data type includes native data of n data subtypes, where m and n are positive integers. The first data type is denoted as data type 1, data types 1-1 to 1-m are used to represent the identifiers of the m data subtypes in the first data type, and data type 1-i is used to represent any one of the m data subtypes in the first data type, where i is an integer greater than or equal to 1 and less than or equal to m. Data content 1-1 to data content 1-m are used to represent the native data corresponding to the m data subtypes. Data types 1-1 to 1-m correspond one-to-one to data content 1-1 to data content 1-m.

[0162] The second data type is denoted as data type 2. Data types 2-1 through 2-n are used to identify the n data subtypes within the second data type. Data type 2-j is used to identify any one of the n data subtypes within the second data type, where j is an integer greater than or equal to 1 and less than or equal to n. Data contents 2-1 through 2-n are used to represent the native data corresponding to each of the n data subtypes. Data types 2-1 through 2-n correspond one-to-one to data contents 2-1 through 2-n.

[0163] The native data of the first target includes a first value (where the first value = n+m), data type 1-1 to data type 1-m, data content 1-1 to data content 1-m, data type 2-1 to data type 2-n, and data content 2-1 to data content 2-n.

[0164] Possible implementation method 2: The native data of the first target includes multiple indicator bits and native data corresponding to M1 data types, wherein the native data of the first data type includes identifiers of K data subtypes and native data corresponding to the K data subtypes. The number of the multiple indicator bits is the sum of the data subtypes corresponding to the M1 data types, and the identifiers of the K data subtypes correspond to the native data of the K data subtypes.

[0165] It is understandable that the first information may not directly indicate the first numerical value, but may indicate through an indicator bit whether there are subsequent native data of other data subtypes, or indicate through an indicator bit whether there are subsequent data subtypes, which will not be elaborated here.

[0166] Possible Implementation 3: Taking the example of native data of a first data type including native data of K data subtypes, the native data of the first data type may include the number K of data subtypes, identifiers of the K data subtypes, and native data corresponding to the K data subtypes, as shown in FIG5B . Alternatively, the native data of the first data type may include K indicator bits, identifiers of the K data subtypes, and native data corresponding to the K data subtypes, as shown in FIG5C . The identifiers of the K data subtypes correspond to the native data of the K data subtypes, respectively.

[0167] In Figures 5B through 5C , the first data type is designated as data type 1, the native data of the first data type is designated as data content 1, data subtypes 1 through K are used to identify K data subtypes, and the native data corresponding to data subtype 1 through K are used to represent the native data corresponding to the K data subtypes. Figure 5C also includes an indicator bit. In the upper diagram of Figure 5C , the indicator bit is used to indicate whether additional data subtypes will follow, and in the lower diagram of Figure 5C , the indicator bit is used to indicate whether additional data subtypes will follow.

[0168] Case 2: N is an integer greater than 1, that is, the first information includes native data of multiple targets.

[0169] Among them, the N targets may include the first device or may not include the first device, and this application does not limit this.

[0170] In one possible implementation, the second target is any one of the N targets that is different from the first target. The native data of the second target includes native data of M2 data types, where M2 is a positive integer. M1 may not be equal to M2, or M1 may be equal to M2. If M1 = M2, the M1 data type and the M2 data type may be the same or different.

[0171] For example, the N targets include terminal 1, terminal 2, terminal 3 and terminal 4, where the native data of terminal 1 includes perception data and artificial intelligence data, the native data of terminal 2 includes perception data, the native data of terminal 3 includes perception data and artificial intelligence data, and the native data of terminal 4 includes perception data and channel data.

[0172] In one example, some or all of the N targets include two or more types of native data, including perception data and channel data. The perception data is used to assist in communication tasks for one or more targets. Therefore, the second device can obtain the perception data and channel data, and can use the perception data to assist in communication tasks and improve communication performance.

[0173] In another example, some or all of the N targets include two or more types of native data, where the two or more native data include artificial intelligence data and perception data, with the artificial intelligence data used to assist in the perception of one or more targets. Therefore, the second device can obtain both artificial intelligence data and perception data, and can then use the artificial intelligence data to assist in the perception task and improve perception accuracy.

[0174] Through the above method, the second device can obtain the native data of multiple targets at one time, and then the second device can fuse the obtained native data of multiple targets.

[0175] The following describes the first information in conjunction with specific scenarios:

[0176] Perception scenario: The native data of N targets includes perception data from N sensing devices collected by a first device. A perception device can be understood as a device with perception capabilities, such as a terminal or base station. The N perception data may or may not include the first device.

[0177] Therefore, the second device can obtain the perception data of multiple perception devices at one time, and thus can alleviate the object occlusion problem in the perception scene to a certain extent and improve the perception accuracy.

[0178] In one example, as shown in Figure 2B , terminal 3 can receive the perception data of terminal 1 and terminal 2, and can send the perception data of terminal 1 and terminal 2 to the base station. Alternatively, terminal 3 can send the perception data of terminal 1, terminal 2, and terminal 3 to the base station. In this case, terminal 3 is the first device, the base station is the second device, terminal 3 can be understood as a relay terminal, and the perception devices can be terminal 1, terminal 2, and terminal 3, or terminal 1 and terminal 2.

[0179] In another example, a first base station receives sensing data from multiple terminals, and the first base station may send the sensing data of the multiple terminals to a second base station. In this case, the first base station is a first device, the second base station is a second device, and the sensing devices are multiple terminals.

[0180] Wireless communication scenarios applicable to artificial intelligence: the native data of N targets include artificial intelligence data corresponding to N artificial intelligence models collected by a first device, and the N artificial intelligence models correspond to N wireless communication tasks respectively; or, the native data of N targets include artificial intelligence data corresponding to N targets collected by a first device, and the N targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data.

[0181] In the above scenario, the target can be at the device or entire device granularity, for example, the target is a terminal, base station, or other device. Alternatively, the target can be at the artificial intelligence model or wireless task granularity, for example, the target is an artificial intelligence model or wireless task.

[0182] For example, taking a terminal as an example, the terminal may include one or more AI models, and thus may perform one or more wireless tasks, wherein one or more wireless tasks correspond one to one with one or more AI models. When the terminal uses an AI model to perform a corresponding wireless task, the terminal generates artificial intelligence data corresponding to the AI ​​model (or the wireless task corresponding to the AI ​​model). In this case, the target can be understood as the terminal, or as the wireless task or the AI ​​model. When the terminal uses X AI models to perform a corresponding wireless task, the terminal generates artificial intelligence data corresponding to X AI models (or wireless tasks corresponding to X AI models). In this case, the target can be X, and the target is based on the granularity of wireless tasks or AI models, with X being greater than or equal to 2.

[0183] For example, in a mobile phone, AI model 1 is used to perform beam management tasks, and AI model 2 is used to perform assisted positioning tasks. If the mobile phone performs the above two tasks at the same time, the mobile phone can generate data corresponding to the two tasks respectively, that is, the data corresponding to AI model 1 and the data corresponding to AI model 2.

[0184] Therefore, the second device can obtain artificial intelligence data corresponding to multiple targets at one time, which is suitable for artificial intelligence to perform wireless tasks, thereby solving the problem of insufficient computing power of some devices and improving the execution accuracy of artificial intelligence tasks.

[0185] For example, in a scenario where the artificial intelligence task is distributed reasoning, each target can report its own reasoning results to the first device. The first device can fuse the collected reasoning results and send the fused reasoning results to the second device, or the first device can directly send the collected reasoning results to the second device.

[0186] Scenario for processing communication tasks: The native data of N targets include channel data of N user equipments collected by the first device.

[0187] Therefore, the second device can obtain channel data of multiple terminals at one time, and then the second device can schedule only the first device without scheduling multiple terminals, thereby saving signaling overhead.

[0188] In one possible implementation, the first information includes identifiers of N targets and native data corresponding to the N targets. The identifiers of the N targets correspond to the N targets. For example, if the targets are terminals, the identifiers of the N targets are identifiers of the N terminals, such as UE IDs. If the second device notifies the first device to periodically send native data for N targets, the first information may not include the number of targets.

[0189] As shown in Figure 6A, assuming that the N targets are N UEs, the first information includes N UE IDs and the native data corresponding to the N UE IDs. The specific format of the native data of each target can be referred to Figures 4A to 4D or Figures 5A to 5C above, and will not be repeated here.

[0190] In a possible implementation manner, the first information may further include first indication information, where the first indication information is used to obtain the number of targets.

[0191] Example a: The first indication information directly indicates the number of targets.

[0192] Exemplarily, the first information includes the number N of targets, identifiers of the N targets, and native data corresponding to the N targets, wherein the identifiers of the N targets correspond to the N targets respectively.

[0193] As shown in Figure 6B , assuming that the N targets are N UEs, the first information includes the number of UEs, N UE IDs, and the native data corresponding to the N UE IDs. The specific format of the native data for each target can be referred to Figures 4A to 4D or Figures 5A to 5C above, and will not be repeated here.

[0194] Example b: the first indication information indirectly indicates the number of targets, or implicitly indicates the number of targets.

[0195] The first information includes N first indication information, N target identifiers, and native data corresponding to the N targets. The N first indication information can be implemented using N indicator bits. The N target identifiers correspond to the N targets respectively.

[0196] As shown in FIG6C , assuming that the target is a UE, assuming that the N targets are N UEs, the first information includes N indicator bits, N UE IDs, and the native data corresponding to the N UE IDs. The specific format of the native data of each target can refer to FIG4A to FIG4D or FIG5A to FIG5C above, and will not be repeated here.

[0197] In the upper diagram of FIG6C , when the indicator bit indicates 1, it indicates that there will be native data corresponding to other UE IDs in the future. When the indicator bit indicates 0, it indicates that there will be no native data corresponding to other UE IDs in the future. In the lower diagram of FIG6B , when the indicator bit indicates 1, it indicates that there will be other UE IDs in the future. When the indicator bit indicates 0, it indicates that there will be no other UE IDs in the future.

[0198] Figure 6D is a schematic diagram of a possible data format of the first information, wherein the first information includes native data of N targets, where the N targets are N UEs, and the identifiers of the N UEs are recorded as UE ID1 to UE ID N. The native data corresponding to UE ID1 includes native data of M1 data types, and the native data corresponding to UE ID1 can use multiple formats. Among them, data type 1 to data type M1 are used to represent the identifiers of M1 data types, and data content 1 to data content M1 are used to represent the native data corresponding to the M1 data types. Among them, data type 1 to data type M1 correspond one-to-one with data content 1 to data content M1.

[0199] Figure 6E is a schematic diagram of another possible data format of the first information, wherein the first information includes native data of N targets, where the N targets are N UEs, and the identifiers of the N UEs are denoted as UE ID 1 to UE ID N. The native data corresponding to UE ID 1 includes native data of M1 data types, wherein data types 1 to data types M1 are used to represent the identifiers of the M1 data types, and data content 1 to data content M1 are used to represent the native data corresponding to the M1 data types. Data types 1 to data types M1 correspond one-to-one with data content 1 to data content M1. The native data of the M1 data types include native data of the first data type, and the native data of the first data type includes native data of K data subtypes. The native data of the first data type can adopt multiple formats. The first data type is denoted as data type 1, the native data of the first data type is denoted as data content 1, data subtype 1 to data subtype K are used to represent the identifiers of the K data subtypes, and the native data corresponding to data subtype 1 to data subtype K are used to represent the native data corresponding to the K data subtypes.

[0200] In order to flexibly support the transmission of native data of different data types, the present application also provides a communication method, as shown in FIG7 , which includes:

[0201] Step 700: The first device generates second information.

[0202] Step 710: The first device sends second information to the second device. Correspondingly, the second device receives the second information from the first device.

[0203] Exemplarily, the second information includes native data of X data types, where X is a positive integer; the native data of the X data types are one or more of perception data, artificial intelligence data, and channel data; wherein the first data type is any one of the X data types; the native data of the first data type includes native data of Y targets, where Y is a positive integer.

[0204] For example, when the first device sends the second information to the second device, the first device may send the second information via any one or more layers of the physical layer, the media access control layer, the radio link layer control protocol layer, the packet data convergence protocol layer, the radio resource control layer, or the application layer. For details, please refer to the relevant description in 710 above and will not be repeated here.

[0205] Optionally, step 720: the second device parses the second information, and performs corresponding operations according to the native data of the X data types included in the second information.

[0206] For details, please refer to the above scenarios A to D, the relevant descriptions in the perception scenario, the scenario applicable to artificial intelligence, and the scenario for processing communication tasks.

[0207] The above method can support the transmission of native data of one or more data types. In addition, it has good scalability and maintainability, which is convenient for supporting the various data types that may exist in the native data of the next generation mobile communication technology RAN, thereby being able to flexibly support the transmission of native data in different scenarios and tasks. Since the first information can include more, more comprehensive and more accurate native data, after obtaining the first information, the second device can continue to perform corresponding operations based on the native data included in the first information, thereby improving communication performance. In addition, the second device can transmit native data of different data types to the corresponding processing module (such as a perception module, an AI module, etc.) to reduce processing delays and improve task accuracy.

[0208] The following describes the specific format of the second information in combination with different situations:

[0209] Case A: Y = 1. The native data of the first data type includes the native data of the first target, and the native data of the other X-1 data types also only include the native data of the first target. That is, the native data of the X data types only include the native data of the first target. The native data of the first data type includes the native data of the first target, meaning that the native data of the first data type is the native data of the first data type of the first target. Case A can also be understood as the second information including native data of X data types, and the native data of the X data types is the native data of the X data types of the first target.

[0210] In this case, Case A is the same as Case 1 above. The specific content of Case A can refer to the relevant description of Case 1 above and will not be repeated here. For example, when no data subtype is involved, the specific format of the second information can refer to Figures 4A to 4D above. When data subtype is involved, the specific format of the second information can refer to Figures 5A to 5C above.

[0211] For example, assuming X = 2, the native data of the X data types are perception data and artificial intelligence data. The perception data is the perception data of the first target, and the artificial intelligence data is the artificial intelligence data of the first target. Therefore, the second information includes the perception data of the first target and the artificial intelligence data of the first target. Furthermore, the perception data of the first target and / or the artificial intelligence data of the first target may also include native data of multiple data subtypes.

[0212] Case B: Y is an integer greater than 1.

[0213] In case B, corresponding to different values ​​of X, it can be divided into two sub-cases:

[0214] Subcase 1: X=1, that is, X=1, and Y is an integer greater than 1.

[0215] In this case, Subcase 1 is a simplified version of Case 2. Specifically, the second information in this case is equivalent to the first information in Case 2, where it includes native data for multiple targets, and each target's native data only includes native data of the same data type. The details of Subcase 1 can be found in the description of Case 2 above and are not repeated here.

[0216] For example, the second information only includes perception data, and the perception data includes perception data of multiple targets, that is, the second information includes perception data of multiple targets.

[0217] Subcase 2: X is an integer greater than 1, that is, both X and Y are integers greater than 1.

[0218] Illustratively, the X data types may further include a second data type, where the second data type is any one of the X data types that is different from the first data type. The native data of the second data type includes native data of W targets, where W is a positive integer and may or may not be equal to Y. If W=Y, the W targets may be the same as or different from the Y targets.

[0219] For example, the second information includes perception data and artificial intelligence data, wherein the perception data includes perception data of three terminals, and the artificial intelligence data includes artificial intelligence data of two terminals.

[0220] For another example, the second information includes perception data and channel data, wherein the perception data includes the perception data of terminal A and the perception data of terminal B, and the channel data includes the channel data of terminal A and the channel data of terminal B.

[0221] The specific format of the second information is described below with reference to Figures 8A to 8C . In Figures 8A to 8C , Data Type 1 to Data Type X are used to represent X data types, and Data Content 1 to Data Content X are used to represent the native data corresponding to the X data types. The first data type is denoted as Data Type 1, and Data Content 1 is the native data of the first data type.

[0222] In one possible implementation, the second information includes raw data corresponding to each of the X data types, but does not include identifiers of the X data types. For example, the second device may configure the first device to periodically transmit raw data corresponding to each of the X data types, and the second information may not include identifiers of the X data types. The order in which the data packets of the X data types are arranged may be configured in advance or predefined by the protocol.

[0223] In a possible implementation, the second information includes identifiers of X data types and native data corresponding to the X data types, wherein the identifiers of the X data types correspond to the native data corresponding to the X data types.

[0224] The second information may not include the number of data types, for example, (1) or (2) in FIG. 8A .

[0225] Exemplarily, the second information may include second indication information, and the second indication information directly indicates the number of data types. Exemplarily, the second information may include the number of data types, for example, (3) or (4) in FIG. 8A .

[0226] Exemplarily, the second information may include second indication information, and the second indication information indirectly or implicitly indicates the number of data types. Exemplarily, the second indication information may be implemented by an indication bit, such as (5) or (6) in FIG8A , wherein, in (5) in FIG8A , the indication bit is used to indicate whether there is subsequent native data of other data types, and in (6) in FIG8A , the indication bit is used to indicate whether there is subsequent other data types.

[0227] In one possible implementation, the native data of the first data type includes native data of Y targets. The native data of the Y targets is also the native data of the first data type of the Y targets. Exemplarily, the native data of the first data type includes identifiers of the Y targets and the native data of the first data type of the Y targets. The identifiers of the Y targets correspond to the native data of the first data type of the Y targets, respectively.

[0228] Exemplarily, the native data of the first data type may not include the number of targets, for example, (1) or (2) in FIG8B . In FIG8B , assuming that the Y targets are Y UEs, UE ID1 to UE ID Y are used to represent the identifiers of the Y UEs, and the native data of the first data type of UE ID1 to the native data of the first data type of UE ID Y are used to identify the native data of the first data type of the Y UEs.

[0229] Exemplarily, the native data of the first data type also includes the number of targets, for example, (3) or (4) in FIG. 8B .

[0230] Exemplarily, the native data of the first data type can implicitly indicate the number of targets through an indicator bit, for example, the number of targets can be indirectly or implicitly indicated through an indicator bit, for example, (5) or (6) in Figure 8B, wherein, in (5) in Figure 8B, the indicator bit is used to indicate whether there are other UEs with native data of the first data type subsequently, and in (6) in Figure 8B, the indicator bit is used to indicate whether there are other UEs subsequently.

[0231] In another possible implementation, the native data of the first data type includes native data of Z data subtypes, where Z is a positive integer, and the native data of Y targets belong to the native data of Z data subtypes. Alternatively, it can be understood that the native data of the first data type includes native data of Z data subtypes, and the native data of each data subtype includes native data of the corresponding data subtype of one or more targets.

[0232] Exemplarily, the native data of the first data type includes identifiers of Z data subtypes and data corresponding to the Z data subtypes. The identifiers of the Z data subtypes correspond to the data corresponding to the Z data subtypes. Alternatively, the native data of the first data type includes data corresponding to the Z data subtypes but does not include identifiers of the Z data subtypes. The order in which data packets of the Z data subtypes are arranged can be configured in advance or predefined by the protocol.

[0233] In addition, the native data of the first data type may further include third indication information, and the third indication information is used to determine the number of data subtypes. Exemplarily, the native data of the first data type may further include the number of data subtypes, or the native data of the first data type may indirectly or implicitly indicate the number of data subtypes, for example, by using an indicator bit. This is similar to Figures 5B and 5C above and will not be repeated here.

[0234] The first data subtype is any one of the Z data subtypes, and the data corresponding to the first data subtype includes native data of the first data subtype of L targets, where L is a positive integer.

[0235] Exemplarily, the data corresponding to the first data subtype includes the identifiers of L targets and the native data of the first data subtype of the L targets. The identifiers of the L targets correspond to the native data of the first data subtype of the L targets, respectively. The data corresponding to the first data subtype may not include the number of targets, for example, (1) or (2) in Figure 8C. As shown in Figure 8C, data subtype 1 to data type Z are used to represent Z types of data subtypes, and data content 1 to data content X are used to represent the native data corresponding to X types of data types, respectively. The first data class is denoted as data type 1, and data content 1 is the native data of the first data type. Assuming that the L targets are L UEs, UE ID1 to UE ID L are used to represent the identifiers of L UEs, and the native data of the first data subtype of UE ID1 to the native data of the first data subtype of UE ID L are used to identify the native data of the first data subtype of L UEs.

[0236] Exemplarily, the data corresponding to the first data subtype may include the number of targets, for example, (3) or (4) in FIG. 8C .

[0237] Exemplarily, the data corresponding to the first data subtype can indirectly or implicitly indicate the number of targets. For example, the indirect or implicit indication of the number of targets can be achieved through an indicator bit, such as (5) or (6) in Figure 8C, wherein, in (5) in Figure 8C, the indicator bit is used to indicate whether there are other UE's native data in the future, and in (6) in Figure 8C, the indicator bit is used to indicate whether there are other UEs in the future.

[0238] With respect to the embodiments shown in FIG. 3 and FIG. 7 , in one possible design, the first device may further send first capability information to the second device, where the first capability information includes S data types supported by the first device, where S is a positive integer. Furthermore, the first capability information may further include data subtypes supported by the first device for each of the S data types.

[0239] Exemplarily, before step 300, the first device may further send first capability information to the second device. For the embodiment shown in FIG. 3 , S is greater than or equal to M1, and S is a positive integer.

[0240] Exemplarily, before step 700, the first device may further send first capability information to the second device. For the embodiment shown in FIG. 7 , S is greater than or equal to X.

[0241] For example, the first capability information may indicate the data types and / or data subtypes supported by the first device in an enumerated manner or a bitmap manner. Alternatively, the first capability information may include the names of the data types and data subtypes supported by the first device.

[0242] For example, taking enumeration as an example, assuming that 0 represents support for perception data-reflection points, 1 represents support for perception data-patches, 2 represents support for perception data-environmental maps, 3 represents support for perception data-radio frequency maps, 4 represents support for artificial intelligence data-training data, 5 represents support for artificial intelligence data-model data, etc., then if the first device supports reflection points and training data, the first capability information indicates 0 and 4.

[0243] For example, taking the bit map method as an example, assuming that the first bit indicates support for perception data-reflection point, the second bit indicates support for perception data-pattern, the third bit indicates support for perception data-environmental map, the fourth bit indicates support for perception data-radio frequency map, the fifth bit indicates artificial intelligence data-training data, and the sixth bit indicates artificial intelligence data-model data, then if the first device supports reflection points and training data, the first capability information can be expressed as 100010.

[0244] In another possible implementation, the first device may further receive second capability information from the second device, where the second capability information includes Q data types supported by the second device, where Q is a positive integer. Furthermore, the second capability information also includes data subtypes supported by the second device for each of the Q data types.

[0245] Exemplarily, before step 300 , the first device may further receive second capability information from the second device. For the embodiment shown in FIG. 3 , Q is greater than or equal to M1.

[0246] Exemplarily, before step 700 , the first device may further receive second capability information from the second device. For the embodiment shown in FIG. 7 , Q is greater than or equal to X.

[0247] The specific implementation method of the second capability information may refer to the implementation method of the first capability information mentioned above.

[0248] Exemplarily, the second device may send the second capability information via broadcast, multicast, or unicast.

[0249] Exemplarily, the first device may send native data based on the second capability information, that is, the first device may send native data of some or all data types supported by the second device.

[0250] In one possible implementation, after a first device receives the second capability information from a second device, the first device may send third capability information to the second device. The third capability information includes the data types supported by the first device among the Q data types. In other words, the first device may select a subset of the data types and / or data subtypes supported by the first device from the set of data types and / or data subtypes supported by the second device, and notify the second device of the subset.

[0251] For example, the base station broadcasts second capability information, and the second capability information indicates the reflection points, patches, and training data supported by the base station. Assuming that the first bit indicates support for perception data-reflection points, the second bit indicates support for perception data-patterns, the third bit indicates support for perception data-environmental maps, the fourth bit indicates support for perception data-radio frequency maps, the fifth bit indicates artificial intelligence data-training data, and the sixth bit indicates artificial intelligence data-model data, the second capability information can be represented as 110010, that is, the second device supports a total of three data subtypes. Furthermore, terminal 1 and terminal 2 can select the data subtype they support from the above three data subtypes and report it. For example, if terminal 1 supports patches and training data among the above three data subtypes, terminal 1 sends capability information 1 to the base station, and capability information 1 can be represented as 011; for another example, if terminal 2 supports reflection points and patches among the above three data subtypes, terminal 2 sends capability information 2 to the base station, and capability information 2 can be represented as 110.

[0252] In addition, for uplink or downlink native data, the data type and / or data subtype supported by the first device and / or the data type and / or data subtype supported by the second device can be indicated respectively.

[0253] The following is a brief introduction to the data content that may be included in native data:

[0254] It will be understood that the following data types and / or data subtypes, as well as the different specific contents of the corresponding data contents, are merely examples and are not intended to limit the present application.

[0255] 1. The data content of the perception data can be referred to as shown in Table 2 below

[0256] Table 2

[0257] 2. The data content of artificial intelligence data can be referred to as shown in Table 3 below:

[0258] Table 3

[0259] Among them, the data format of artificial intelligence data is strongly related to specific scenarios / artificial intelligence tasks, especially model / gradient data, inference results, feature data, etc.

[0260] 3. Channel data:

[0261] For example, the original channel data can be a high-dimensional matrix Each matrix element is a complex number, or expressed as (amplitude, phase), etc.

[0262] In addition, the present application does not limit the order of the native data in the first information or the second information. For native data of a data type or data subtype, part of the data content in the native data can also be extracted and placed at the beginning of the native data to facilitate searching and improve reading efficiency. For example, the radio frequency map can be represented by an M×N grid map, and the channel state information corresponding to each grid is multipath information. Among them, the multipath information corresponding to the grid indexed by i can be expressed as (K i ,P i,0 ,P i,1 …P i,Ki-1 ), where i is the index of the grid, and K i It is the number of multipaths included in the grid with index i. The information of each path is (power, delay, AOA, AOD). The multipath numbers K0, K1, K2, etc. of all grids in the radio frequency map can be merged and placed at the beginning of the native data content of the radio frequency map, which is also called subheader information. Among them, all powers, all delays, all AOAs and AODs are merged and placed after the subheader information as the remaining information of the radio frequency map data content.

[0263] For another example, the model data includes a set of weight parameters, each of which includes dimension size, data type, specific parameter value, etc. The dimension sizes, data types, etc. corresponding to multiple weight parameters can be combined into sub-header information of the data content of the model data, and the specific parameter values ​​corresponding to all weight parameters can be combined into the remaining information of the data content of the model data.

[0264] It is understandable that in order to implement the functions in the above embodiments, the first device and the second device include hardware structures and / or software modules corresponding to the execution of each function. It should be readily apparent to those skilled in the art that, in combination with the units and method steps of each example described in the embodiments disclosed in this application, this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in hardware or in a manner driven by computer software depends on the specific application scenario and design constraints of the technical solution.

[0265] Figures 9 and 10 are schematic diagrams of possible communication devices provided in embodiments of the present application. These communication devices can be used to implement the functions of the first device or the second device in the above method embodiments, thereby also achieving the beneficial effects of the above method embodiments.

[0266] As shown in Figure 9, a communication device 900 includes a processing unit 910 and a transceiver unit 920. The communication device 900 is used to implement the first device or the second device in the above method embodiment.

[0267] When the communication device 900 is used to implement the function of the first device in the method embodiment shown in FIG3 :

[0268] The processing unit 910 is configured to generate first information, and the transceiver unit 920 is configured to send the first information to the second device. The first information includes native data of N targets, where N is a positive integer, and the first target is one of the N targets. The native data of the first target includes native data of M1 data types, where M1 is a positive integer, and the native data of the M1 data types is one or more of artificial intelligence data, perception data, and channel data.

[0269] In one possible design, the transceiver unit 920 is used to send the first information to the second device through one or more layers of the physical PHY layer, the medium access control MAC layer, the radio link layer control protocol RLC layer, the packet data convergence protocol PDCP layer, the radio resource control RRC layer or the application layer.

[0270] In one possible design, corresponding to a wireless communication scenario where artificial intelligence is applicable, the native data of the N targets include artificial intelligence data corresponding to N artificial intelligence models collected by the first device, and the N artificial intelligence models correspond to N wireless communication tasks respectively; or, the native data of the N targets include artificial intelligence data corresponding to the N targets collected by the first device, and the N targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data. In another possible design, corresponding to a perception scenario, the native data of the N targets include perception data of N perception devices collected by the first device. In one possible design, corresponding to a scenario where communication tasks are processed, the native data of the N targets include channel data of N user devices collected by the first device.

[0271] In one possible design, the first target is the first device, and the native data of the first target includes two or more of the perception data of the first target, the channel data of the first target, or the artificial intelligence data of the first target.

[0272] In one possible design, the native data of some or all of the N targets includes two or more types of native data; the two or more types of native data include perception data and channel data, and the perception data is used to assist in communication tasks of one or more targets. In another possible design, the native data of some or all of the N targets includes two or more types of native data; the two or more types of native data include artificial intelligence data and perception data, and the artificial intelligence data is used to assist in perception of one or more targets.

[0273] In a possible design, the first data type is any one of the M1 data types, and the native data of the first data type includes native data of K data subtypes, where K is a positive integer.

[0274] In a possible design, the native data of the first data type further includes identifiers of the K data subtypes, and the identifiers of the K data subtypes respectively correspond to the native data of the K data subtypes.

[0275] In one possible design, the data type or data subtype of the perception data includes one or more of reflection point information, patch information, environmental map information, radio frequency map information, imaging data, or original perception signals; the data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data, or performance data; the data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data.

[0276] In one possible design, the transceiver unit 920 is used to send first capability information to the second device before generating the first information, where the first capability information includes S data types supported by the first device, where S is an integer greater than or equal to M1.

[0277] In one possible design, the first capability information also includes a data subtype supported by the first device in each of the S data types.

[0278] In one possible design, the transceiver unit 920 is used to receive second capability information from the second device before generating the first information, where the second capability information includes Q data types supported by the second device, where Q is an integer greater than or equal to M1.

[0279] In one possible design, the second target is one of the N targets that is different from the first target, and the native data of the second target includes native data of M2 data types, where M2 is a positive integer and M1 is not equal to M2.

[0280] In one possible design, the first information also includes identifiers of the N targets, and the identifiers of the N targets correspond to the N targets respectively.

[0281] In one possible design, the first information also includes indication information, where the indication information is used to indicate the number of targets.

[0282] In one possible design, the native data of the first target includes identifiers of the M1 data types, and the identifiers of the M1 data types respectively correspond to the native data of the M1 data types.

[0283] When the communication device 900 is used to implement the function of the second device in the method embodiment shown in FIG3 :

[0284] The transceiver unit 920 is used to receive first information from a first device, wherein the first information includes native data of N targets, N is a positive integer, the first target is one of the N targets, and the native data of the first target includes native data of M1 data types, M1 is a positive integer, and the native data of the M1 data types are one or more of artificial intelligence data, perception data, and channel data; the processing unit 910 is used to parse the first information and perform corresponding operations according to the native data of the N targets included in the first information.

[0285] In one possible design, corresponding to a wireless communication scenario where artificial intelligence is applicable, the native data of the N targets include artificial intelligence data corresponding to N artificial intelligence models collected by the first device, and the N artificial intelligence models correspond to N wireless communication tasks respectively; or, the native data of the N targets include artificial intelligence data corresponding to the N targets collected by the first device, and the N targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data. In another possible design, corresponding to a perception scenario, the native data of the N targets include perception data of N perception devices collected by the first device. In yet another possible design, corresponding to a scenario where communication tasks are processed, the native data of the N targets include channel data of N user devices collected by the first device.

[0286] In one possible design, the first target is the first device, and the native data of the first target includes two or more of the perception data of the first target, the channel data of the first target, or the artificial intelligence data of the first target.

[0287] In one possible design, the native data of some or all of the N targets includes two or more types of native data; the two or more types of native data include perception data and channel data, and the perception data is used to assist in communication tasks of one or more targets. In another possible design, the native data of some or all of the N targets includes two or more types of native data; the two or more types of native data include artificial intelligence data and perception data, and the artificial intelligence data is used to assist in perception of one or more targets.

[0288] In a possible design, the first data type is any one of the M1 data types, and the native data of the first data type includes native data of K data subtypes, where K is a positive integer.

[0289] In a possible design, the native data of the first data type further includes identifiers of the K data subtypes, and the identifiers of the K data subtypes respectively correspond to the native data of the K data subtypes.

[0290] In one possible design, the data type or data subtype of the perception data includes one or more of reflection point information, patch information, environmental map information, radio frequency map information, imaging data, or original perception signals; the data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data, or performance data; the data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data.

[0291] In one possible design, the transceiver unit 920 is used to receive first capability information from the first device before receiving first information from the first device, where the first capability information includes S data types supported by the first device, where S is an integer greater than or equal to M1.

[0292] In one possible design, the first capability information also includes a data subtype supported by the first device in each of the S data types.

[0293] In one possible design, the transceiver unit 920 is used to send second capability information to the first device before receiving the first information from the first device, where the second capability information includes Q data types supported by the second device, where Q is an integer greater than or equal to M1.

[0294] In one possible design, the second target is one of the N targets that is different from the first target, and the native data of the second target includes native data of M2 data types, where M2 is a positive integer and M1 is not equal to M2.

[0295] In one possible design, the first information also includes identifiers of the N targets, and the identifiers of the N targets correspond to the N targets respectively.

[0296] In one possible design, the first information also includes indication information, where the indication information is used to indicate the number of targets.

[0297] In one possible design, the native data of the first target includes identifiers of the M1 data types, and the identifiers of the M1 data types respectively correspond to the native data of the M1 data types.

[0298] When the communication device 900 is used to implement the function of the first device in the method embodiment shown in FIG3 :

[0299] The processing unit 910 is configured to generate second information; the transceiver unit 920 is configured to send the second information to the second device, where the second information includes native data of X data types, where X is a positive integer; the native data of the X data types is one or more of artificial intelligence data, perception data, and channel data; wherein the first data type is any one of the X data types; and the native data of the first data type includes native data of Y targets, where Y is a positive integer.

[0300] In one possible design, the transceiver unit 920 is used to send the first information to the second device through one or more layers of the physical layer, MAC layer, RLC layer, PDCP layer, RRC layer or application layer.

[0301] In one possible design, corresponding to a wireless communication scenario where artificial intelligence is applicable, the native data of the first data type is artificial intelligence data, and the native data of the Y targets include artificial intelligence data corresponding to Y artificial intelligence models collected by the first device, and the Y artificial intelligence models correspond to Y wireless communication tasks respectively; or, the native data of the Y targets include artificial intelligence data corresponding to the Y targets collected by the first device, and the Y targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data. In another possible design, corresponding to a perception scenario, the native data of the first data type is perception data, and the native data of the Y targets include perception data of Y perception devices collected by the first device. In yet another possible design, corresponding to a scenario where communication tasks are processed, the native data of the first data type is channel data, and the native data of the Y targets include channel data of Y user devices collected by the first device.

[0302] In one possible design, the transceiver unit 920 is used to send first capability information to the second device before generating the second information, where the first capability information includes S data types supported by the first device, where S is an integer greater than or equal to X.

[0303] In one possible design, the first capability information also includes a data subtype supported by the first device in each of the S data types.

[0304] In one possible design, the transceiver unit 920 is used to, before generating the second information, enable the first device to receive second capability information from the second device, where the second capability information includes Q data types supported by the second device, where Q is an integer greater than or equal to X.

[0305] In a possible design, the second information further includes identifiers of the X data types, and the identifiers of the X data types respectively correspond to native data of the X data types.

[0306] In one possible design, the second information also includes second indication information, and the second indication information is used to obtain the number of data types.

[0307] In a possible design, the native data of the first data type also includes identifiers of the Y targets, and the identifiers of the Y targets respectively correspond to the native data of the Y targets.

[0308] In a possible design, the second data type is any one of the X data types that is different from the first data type, and the native data of the second data type includes native data of W targets, where W is a positive integer and W is not equal to Y.

[0309] In one possible design, the native data of the first data type includes native data of Z data subtypes, where Z is a positive integer, and the native data of the Y targets belong to the native data of the Z data subtypes.

[0310] In a possible design, the native data of the first data type further includes identifiers of the Z data subtypes, and the identifiers of the Z data subtypes respectively correspond to the native data of the Z data subtypes.

[0311] In a possible design, the native data of the first data type further includes third indication information, where the third indication information is used to determine the number of data subtypes.

[0312] In one possible design, the data type or data subtype of the perception data includes one or more of reflection point information, patch information, environmental map information, radio frequency map information, imaging data, or original perception signals; the data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data, or performance data; the data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data.

[0313] When the communication device 900 is used to implement the function of the first device in the method embodiment shown in FIG7 :

[0314] The transceiver unit 920 is configured to receive second information from the first device; the second information includes native data of X data types, where X is a positive integer; the native data of the X data types is one or more of artificial intelligence data, perception data, and channel data; the first data type is any one of the X data types; and the native data of the first data type includes native data of Y targets, where Y is a positive integer. The processing unit 910 is configured to parse the second information and perform corresponding operations based on the native data of the X data types included in the second information.

[0315] In one possible design, corresponding to a wireless communication scenario where artificial intelligence is applicable, the native data of the first data type is artificial intelligence data, and the native data of the Y targets include artificial intelligence data corresponding to Y artificial intelligence models collected by the first device, and the Y artificial intelligence models correspond to Y wireless communication tasks respectively; or, the native data of the Y targets include artificial intelligence data corresponding to the Y targets collected by the first device, and the Y targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data. In another possible design, corresponding to a perception scenario, the native data of the first data type is perception data, and the native data of the Y targets include perception data of Y perception devices collected by the first device. In yet another possible design, corresponding to a scenario where communication tasks are processed, the native data of the first data type is channel data, and the native data of the Y targets include channel data of Y user devices collected by the first device.

[0316] In one possible design, the transceiver unit 920 is used to receive first capability information from the first device before receiving second information from the first device, where the first capability information includes S data types supported by the first device, where S is an integer greater than or equal to M1.

[0317] In one possible design, the first capability information also includes a data subtype supported by the first device in each of the S data types.

[0318] In one possible design, the transceiver unit 920 is used to send second capability information to the first device before receiving second information from the first device, where the second capability information includes Q data types supported by the second device, where Q is an integer greater than or equal to M1.

[0319] In a possible design, the second information further includes identifiers of the X data types, and the identifiers of the X data types respectively correspond to native data of the X data types.

[0320] In one possible design, the second information also includes second indication information, and the second indication information is used to obtain the number of data types.

[0321] In a possible design, the native data of the first data type also includes identifiers of the Y targets, and the identifiers of the Y targets respectively correspond to the native data of the Y targets.

[0322] In a possible design, the second data type is any one of the X data types that is different from the first data type, and the native data of the second data type includes native data of W targets, where W is a positive integer and W is not equal to Y.

[0323] In one possible design, the native data of the first data type includes native data of Z data subtypes, where Z is a positive integer, and the native data of the Y targets belong to the native data of the Z data subtypes.

[0324] In a possible design, the native data of the first data type further includes identifiers of the Z data subtypes, and the identifiers of the Z data subtypes respectively correspond to the native data of the Z data subtypes.

[0325] In a possible design, the native data of the first data type further includes third indication information, where the third indication information is used to determine the number of data subtypes.

[0326] In one possible design, the data type or data subtype of the perception data includes one or more of reflection point information, patch information, environmental map information, radio frequency map information, imaging data, or original perception signals; the data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data, or performance data; the data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data.

[0327] A more detailed description of the processing unit 910 and the transceiver unit 920 can be directly obtained by referring to the relevant description in the above method embodiment, and will not be repeated here.

[0328] As shown in Figure 10, communication device 10000 includes a processor 1010 and an interface circuit 1020. Processor 1010 and interface circuit 1020 are coupled to each other. It will be appreciated that interface circuit 1020 may be a transceiver or an input / output interface. Optionally, communication device 10000 may further include a memory 1030 for storing instructions executed by processor 1010, input data required by processor 1010 to execute instructions, or data generated by processor 1010 after executing instructions.

[0329] The memory 1030 may be integrated into the processor 1010. In one possible case, the communication device 10000 may include at least one processor 1010 integrated with the memory 1030, and another memory.

[0330] When the communication device 10000 is used to implement the method shown in FIG3 , the processor 1010 is used to implement the functions of the processing unit 910 , and the interface circuit 1020 is used to implement the functions of the transceiver unit 920 .

[0331] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0332] In this application, another example of a device is provided, wherein the notification device includes at least one processor and at least one memory, the at least one processor and the at least one memory being coupled, the at least one memory being used to store instructions. When the instructions are executed by the at least one processor, the communication device performs the method in the above-described embodiment. For example, as shown in FIG10 , a communication device 10000 includes a processor 1010 and a memory 1030. The processor 1010 and the memory 1030 are coupled, and the memory 1030 stores instructions. When the instructions stored in the memory 1030 are executed by the processor 1010, the communication device 10000 performs the method performed by the first or second device in the above-described embodiment.

[0333] The method steps in the embodiments of the present application can be implemented in hardware or in software instructions that can be executed by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disk, mobile hard disk, CD-ROM or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. The storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in the first device or the second device mentioned above. The processor and the storage medium can also exist in the first device or the second device as discrete components.

[0334] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are performed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, or other programmable device. The computer program or instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a digital video disk; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage media.

[0335] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0336] In this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In the text description of this application, the character " / " generally indicates that the previous and next associated objects are in an "or" relationship; in the formula of this application, the character " / " indicates that the previous and next associated objects are in a "division" relationship. "Including at least one of A, B and C" can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B and C.

[0337] It is understood that the various numbers used in the embodiments of this application are merely for ease of description and are not intended to limit the scope of the embodiments of this application. The order of the sequence numbers of the above-mentioned processes does not necessarily imply a specific order of execution; the order of execution of the processes should be determined by their functions and inherent logic.

Claims

1. A communication method, characterized in that: The method includes: The first device generates first information, wherein The first information includes native data of N targets, where N is a positive integer, and the first target is one of the N targets. The native data of the first target includes native data of M1 data types, where M1 is a positive integer, and the native data of the M1 data types are one or more of artificial intelligence data, perception data, and channel data; The first device sends the first information to the second device.

2. The method according to claim 1, wherein The first device sending the first information to the second device includes: The first device sends the first information through one or more layers of a physical PHY layer, a medium access control MAC layer, a radio link layer control protocol RLC layer, a packet data convergence protocol PDCP layer, a radio resource control RRC layer or an application layer.

3. The method according to claim 1 or 2, wherein: Corresponding to a wireless communication scenario applicable to artificial intelligence, the native data of the N targets include artificial intelligence data corresponding to the N artificial intelligence models collected by the first device, and the N artificial intelligence models correspond to N wireless communication tasks respectively; or, the native data of the N targets include artificial intelligence data corresponding to the N targets collected by the first device, and the N targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data.

4. The method according to any one of claims 1 to 3, wherein Corresponding to the perception scenario, the native data of the N targets include perception data of N perception devices collected by the first apparatus.

5. The method according to any one of claims 1 to 4, characterized in that Corresponding to the scenario of processing communication tasks, the native data of the N targets include channel data of N user equipments collected by the first device.

6. The method according to any one of claims 1 to 5, wherein: The first target is the first device, The native data of the first target includes two or more of the perception data of the first target, the channel data of the first target, or the artificial intelligence data of the first target.

7. The method according to any one of claims 1 to 6, wherein: The native data of some or all of the N targets include two or more types of native data; The two or more types of native data include perception data and channel data, and the perception data is used to assist communication tasks of one or more targets.

8. The method according to any one of claims 1 to 6, wherein: The native data of some or all of the N targets include two or more types of native data; The two or more native data include artificial intelligence data and perception data, and the artificial intelligence data is used to assist in the perception of one or more targets.

9. The method according to any one of claims 1 to 8, wherein The first data type is any one of the M1 data types. The native data of the first data type includes native data of K data subtypes, where K is a positive integer.

10. The method according to claim 9, wherein The native data of the first data type further includes identifiers of the K data subtypes, and the identifiers of the K data subtypes respectively correspond to the native data of the K data subtypes.

11. The method according to claim 9 or 10, wherein: The data type or data subtype of the perception data includes one or more of reflection point information, patch information, environment map information, radio frequency map information, imaging data or original perception signal; The data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data or performance data; The data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data.

12. The method according to any one of claims 1 to 11, wherein: Before generating the first information, the method further includes: The first device sends first capability information to the second device, where the first capability information includes S data types supported by the first device, where S is an integer greater than or equal to M1.

13. The method according to claim 12, wherein: The first capability information also includes data subtypes supported by the first device in each of the S data types.

14. The method according to any one of claims 1 to 13, wherein: Before generating the first information, the method further includes: The first device receives second capability information from the second device, where the second capability information includes Q data types supported by the second device, where Q is an integer greater than or equal to M1.

15. The method according to any one of claims 1 to 14, wherein: The second target is one of the N targets that is different from the first target. The native data of the second target includes native data of M2 data types, where M2 is a positive integer and M1 is not equal to M2.

16. The method according to any one of claims 1 to 15, wherein: The first information also includes identifiers of the N targets, and the identifiers of the N targets correspond to the N targets respectively.

17. The method according to any one of claims 1 to 16, wherein: The first information further includes indication information, where the indication information is used to indicate the number of targets.

18. The method according to any one of claims 1 to 17, wherein: The native data of the first target includes identifiers of the M1 data types, and the identifiers of the M1 data types correspond to the native data of the M1 data types respectively.

19. A communication method, characterized in that: The method includes: The second device receives the first information from the first device, wherein: The first information includes native data of N targets, where N is a positive integer, and the first target is one of the N targets. The native data of the first target includes native data of M1 data types, where M1 is a positive integer, and the native data of the M1 data types are one or more of artificial intelligence data, perception data, and channel data; The second device parses the first information and performs corresponding operations according to the native data of the N targets included in the first information.

20. The method according to claim 19, wherein Corresponding to a wireless communication scenario applicable to artificial intelligence, the native data of the N targets include artificial intelligence data corresponding to the N artificial intelligence models collected by the first device, and the N artificial intelligence models correspond to N wireless communication tasks respectively; or, the native data of the N targets include artificial intelligence data corresponding to the N targets collected by the first device, and the N targets perform communication tasks based on the artificial intelligence models corresponding to the artificial intelligence data.

21. The method according to claim 19 or 20, wherein: Corresponding to the perception scenario, the native data of the N targets include perception data of N perception devices collected by the first apparatus.

22. The method according to any one of claims 19 to 21, wherein: Corresponding to the scenario of processing communication tasks, the native data of the N targets include channel data of N user equipments collected by the first device.

23. The method according to any one of claims 19 to 22, wherein: The first target is the first device, The native data of the first target includes two or more of the perception data of the first target, the channel data of the first target, or the artificial intelligence data of the first target.

24. The method according to any one of claims 19 to 23, wherein: The native data of some or all of the N targets include two or more types of native data; The two or more types of native data include perception data and channel data, and the perception data is used to assist communication tasks of one or more targets.

25. The method according to any one of claims 19 to 23, wherein: The native data of some or all of the N targets include two or more types of native data; The two or more native data include artificial intelligence data and perception data, and the artificial intelligence data is used to assist in the perception of one or more targets.

26. The method according to any one of claims 19 to 25, wherein: The first data type is any one of the M1 data types. The native data of the first data type includes native data of K data subtypes, where K is a positive integer.

27. The method according to claim 26, wherein The native data of the first data type further includes identifiers of the K data subtypes, and the identifiers of the K data subtypes respectively correspond to the native data of the K data subtypes.

28. The method according to claim 26 or 27, wherein The data type or data subtype of the perception data includes one or more of reflection point information, patch information, environment map information, radio frequency map information, imaging data or original perception signal; The data type or data subtype of the artificial intelligence data includes one or more of training data, model data, gradient data, inference results, feature data or performance data; The data type or data subtype of the channel data includes one or more of channel matrix data, channel state information data, and channel precoding data.

29. The method according to any one of claims 19 to 28, wherein: Before the second device receives the first information from the first device, the method further includes: The second device receives first capability information from the first device, where the first capability information includes S data types supported by the first device, where S is an integer greater than or equal to M1.

30. The method of claim 29, wherein: The first capability information also includes data subtypes supported by the first device in each of the S data types.

31. The method according to any one of claims 19 to 30, wherein: Before the second device receives the first information from the first device, the method further includes: The second device sends second capability information to the first device, where the second capability information includes Q data types supported by the second device, where Q is an integer greater than or equal to M1.

32. The method according to any one of claims 19 to 31, wherein: The second target is one of the N targets that is different from the first target. The native data of the second target includes native data of M2 data types, where M2 is a positive integer and M1 is not equal to M2.

33. The method according to any one of claims 19 to 32, wherein: The first information also includes identifiers of the N targets, and the identifiers of the N targets correspond to the N targets respectively.

34. The method according to any one of claims 19 to 33, wherein: The first information further includes indication information, where the indication information is used to indicate the number of targets.

35. The method according to any one of claims 19 to 34, wherein: The native data of the first target includes identifiers of the M1 data types, and the identifiers of the M1 data types correspond to the native data of the M1 data types respectively.

36. A communication device, characterized in that The communication device includes at least one processor; the at least one processor is configured to execute the method according to any one of claims 1 to 35.

37. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a program, and when the program is executed, the method according to any one of claims 1 to 35 is implemented.

38. A computer program product, characterized in that The computer program product comprises a program or instructions, which, when executed, causes the method according to any one of claims 1 to 35 to be implemented.

39. A communication system, characterized in that: The communication system includes at least one first device and at least one second device, wherein the first device is configured to execute the method according to any one of claims 1 to 18, and the second device is configured to execute the method according to any one of claims 19 to 35.

Images