Communication method and device, chip module, storage medium and program product

Abstract

The invention discloses a communication method and device, a chip module, a storage medium and a program product. The method comprises the steps that first information is acquired, the first information comprises a first attribute and at least one reference wireless data set, and each reference wireless data set in the at least one reference wireless data set comprises reference wireless data and attributes associated with the reference wireless data; and processing the first attribute and the at least one reference wireless data set based on a first model to obtain second information, the first model being used for predicting at least one wireless data, and the second information comprising predicted wireless data associated with the first attribute. Therefore, a multifunctional wireless prediction model is provided, the prediction of various attributes and various wireless data is supported, the model does not need to be designed for the prediction of each wireless data, and the prediction efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and in particular to a communication method and device, a chip module, a storage medium and a program product. BACKGROUND

[0002] Introducing artificial intelligence (AI) / machine learning (ML) technology into a wireless air interface can be used for compression and reconstruction of wireless channel information, beam management, and positioning enhancement.

[0003] Current AI models are respectively for each wireless AI task. Models for different tasks respectively collect data for training and subsequent model management, which will result in a large number of models in a wireless communication system and high complexity of model management. SUMMARY

[0004] The present application provides a communication method and device, a chip module, a storage medium and a program product to provide a multifunctional wireless prediction model that supports prediction of multiple attributes and multiple wireless data.

[0005] In a first aspect, a communication method is provided, the method comprising: obtaining first information, the first information comprising a first attribute and at least one reference wireless data set, each reference wireless data set in the at least one reference wireless data set comprising a reference wireless data and an attribute associated with the reference wireless data; and processing the first attribute and the at least one reference wireless data set based on a first model to obtain second information, the first model being used to predict at least one wireless data, the second information comprising a predicted wireless data associated with the first attribute.

[0006] In this aspect, by obtaining the first attribute and the at least one reference wireless data set and processing the first attribute and the at least one reference wireless data set based on the first model to obtain the predicted wireless data associated with the first attribute, the multifunctional wireless prediction model can support prediction of multiple attributes and multiple wireless data, without the need to design a model for each wireless data prediction, thereby improving prediction efficiency.

[0007] In combination with the first aspect, in a possible implementation, the attribute associated with the reference wireless data or the first attribute comprises at least one of the following: position, time, frequency.

[0008] In this implementation, prediction of wireless data of multiple attributes can be supported, improving prediction efficiency and management efficiency.

[0009] With reference to the first aspect, in a possible implementation of the first aspect, the type of the reference wireless data or the predicted wireless data comprises at least one of the following: path loss, channel quality indicator, angle of arrival, angle of departure, timing advance, signal to interference plus noise ratio, data rate.

[0010] In this implementation, prediction of multiple types of wireless data is supported, and prediction efficiency and management efficiency are improved.

[0011] With reference to the first aspect, in a possible implementation of the first aspect, the first information further comprises first indication information, the first indication information being used to indicate the type of the predicted wireless data and / or the type of the first attribute.

[0012] In this implementation, since the values of different attributes or different wireless data can be the same, the first indication information can accurately indicate which attribute and / or which wireless data is predicted this time. The first indication information can indicate the mapping relationship between the type of the predicted wireless data and the type of the first attribute.

[0013] With reference to the first aspect, in a possible implementation of the first aspect, the method further comprises: obtaining an identifier of the first model and at least one function supported by the first model, the at least one function supported by the first model being used to indicate that the first model supports prediction of at least one type of wireless data of at least one attribute.

[0014] In this implementation, the model can be managed, and the model can support at least one function, so that when the model is used to predict at least one type of wireless data of a certain attribute, the corresponding model can be selected for prediction according to the identifier of the model.

[0015] With reference to the first aspect, in a possible implementation of the first aspect, the method further comprises: receiving second indication information, the second indication information being used to indicate that processing is based on the first model, and the second indication information comprising the identifier of the first model.

[0016] In this implementation, the model can be managed, and the corresponding model can be selected for prediction according to the identifier of the model.

[0017] With reference to the first aspect, in a possible implementation of the first aspect, the method further comprises: sending third information, the third information indicating at least one function supported by the first model, the at least one function supported by the first model being used to indicate that the first model supports prediction of at least one type of wireless data of at least one attribute.

[0018] In this implementation, when prediction is based on the first model, the communication apparatus can indicate the identifier of the first model and at least one function supported by the first model.

[0019] With reference to the first aspect, in a further possible implementation of the first aspect, before the processing, based on the first model, the first attribute and the at least one set of reference wireless data to obtain the second information, the method further includes: processing the attribute associated with the reference wireless data or the first attribute included in each set of reference wireless data in the at least one set of reference wireless data to obtain an attribute of a first data length; and processing the reference wireless data included in each set of reference wireless data in the at least one set of reference wireless data to obtain reference wireless data of a second data length.

[0020] With reference to the first aspect, in a further possible implementation of the first aspect, before the processing, based on the first model, the first attribute and the at least one set of reference wireless data to obtain the second information, the method further includes: processing the attribute associated with the reference wireless data or the first attribute included in each set of reference wireless data in the at least one set of reference wireless data to obtain an attribute of a first data length; and processing the reference wireless data included in each set of reference wireless data in the at least one set of reference wireless data to obtain reference wireless data of a second data length.

[0021] In this implementation, since the first model has a data length requirement for the attribute associated with the reference wireless data or the first attribute, before the processing, based on the first model, the first attribute and the at least one set of reference wireless data to obtain the second information, the attribute associated with the reference wireless data or the first attribute included in each set of reference wireless data in the at least one set of reference wireless data can also be processed to obtain an attribute of a first data length.

[0022] The first model can also have a data length requirement for the reference wireless data, and therefore, before the processing, based on the first model, the first attribute and the at least one set of reference wireless data to obtain the second information, the reference wireless data included in each set of reference wireless data in the at least one set of reference wireless data can also be processed to obtain reference wireless data of a second data length.

[0023] With reference to the first aspect, in a further possible implementation of the first aspect, before the processing, based on the first model, the first attribute and the at least one set of reference wireless data to obtain the second information, the method further includes: adding a first vector to the attribute of the first data length, the first vector being used to identify the attribute associated with the reference wireless data; and adding a second vector to the reference wireless data of the second data length, the second vector being used to identify the reference wireless data.

[0024] In the implementation, each set of reference wireless data and the attribute associated with the reference wireless data share the same position embedding, which is used to identify whether the input is the attribute or the reference wireless data. Exemplarily, a first vector can be added to the attribute of the first data length obtained after the neural network processing, and the first vector is used to identify the attribute associated with the reference wireless data. A second vector can also be added to the reference wireless data of the second data length obtained after the neural network processing, and the second vector is used to identify the reference wireless data.

[0025] In a second aspect, a communication apparatus is provided for implementing the communication method in the first aspect or any of the implementations of the first aspect. The apparatus can be a device, or a module (for example, a processor, a chip, or a chip system, etc.) applied to the device, or a logic node, a logic module, or software capable of implementing all or part of the device functions.

[0026] In a possible implementation, the communication apparatus in the second aspect includes units for performing the method in the first aspect or any of the implementations of the first aspect.

[0027] The communication apparatus includes a processing unit, and can further include a transceiver unit.

[0028] The processing unit is configured to obtain first information, the first information including a first attribute and at least one set of reference wireless data, each set of reference wireless data including reference wireless data and an attribute associated with the reference wireless data; and the processing unit is configured to process the first attribute and the at least one set of reference wireless data based on a first model to obtain second information, the first model being used to predict at least one type of wireless data, and the second information including a predicted wireless data associated with the first attribute.

[0029] Optionally, the attribute associated with the reference wireless data or the first attribute includes at least one of the following: a position, a time, and a frequency.

[0030] Optionally, the type of the reference wireless data or the predicted wireless data includes at least one of the following: a path loss, a channel quality indicator, an angle of arrival, an angle of departure, a timing advance, a signal-to-interference-plus-noise ratio, and a data rate.

[0031] Optionally, the first information further includes first indication information, the first indication information being used to indicate the type of the predicted wireless data and / or the type of the first attribute.

[0032] Optionally, the processing unit is further configured to acquire the identifier of the first model and at least one function supported by the first model, the at least one function supported by the first model being used to indicate that the first model supports predicting at least one kind of wireless data of at least one attribute.

[0033] Optionally, the transceiver is configured to receive second indication information, the second indication information being used to indicate that processing is based on the first model, and the second indication information comprising the identifier of the first model.

[0034] Optionally, the transceiver is further configured to send third information, the third information being used to indicate the at least one function supported by the first model, the at least one function supported by the first model being used to indicate that the first model supports predicting at least one kind of wireless data of at least one attribute.

[0035] Optionally, the processing unit is further configured to acquire fourth information, the fourth information being used to indicate that at least one function supported by the first model is activated, or the fourth information being used to indicate that at least one function supported by the first model is deactivated.

[0036] Optionally, the processing unit is further configured to process the attribute associated with the reference wireless data or the first attribute included in each of the at least one set of reference wireless data to obtain a first data length of attribute, and process the reference wireless data included in each of the at least one set of reference wireless data to obtain a second data length of reference wireless data.

[0037] Optionally, the processing unit is further configured to add a first vector to the first data length of attribute, the first vector being used to identify the attribute associated with the reference wireless data, and add a second vector to the second data length of reference wireless data, the second vector being used to identify the reference wireless data.

[0038] In another possible implementation, the communication apparatus in the above second aspect comprises a processing circuit coupled with a memory; the processing circuit is configured to enable the apparatus to perform the corresponding functions in the above communication method. The memory is used to be coupled with the processing circuit, and stores the programs (instructions) and / or data necessary for the apparatus. Optionally, the communication apparatus can further comprise a communication interface, which is used to enable the apparatus to communicate with other network elements. Optionally, the memory can be located inside the communication apparatus, or located outside the communication apparatus. Exemplarily, the processing circuit can be a processor or a circuit for processing in the processor.

[0039] When the communication apparatus in the second aspect is a chip, the sending unit can be an output unit such as an output circuit or a communication interface; the receiving unit can be an input unit such as an input circuit or a communication interface. When the communication apparatus is a terminal device, the sending unit can be a transmitter or a transmitter; the receiving unit can be a receiver or a receiver.

[0040] In a third aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program or instructions, when the computer program or instructions are executed, the method in the first aspect or any implementation of the first aspect is implemented.

[0041] In a fourth aspect, a computer program product containing instructions is provided, when the instructions are run on a communication apparatus, the communication apparatus is caused to execute the method in the first aspect or any implementation of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 A simplified schematic diagram of a wireless communication system provided by embodiments of the present application is provided;

[0043] Figure 2 An architecture schematic diagram of an open radio access network is provided;

[0044] Figures 3A-3D A schematic diagram of near real-time RIC, non-real-time RIC in network architecture is provided;

[0045] Figure 4 A schematic diagram of a neuron structure is provided;

[0046] Figure 5 A schematic diagram of a neural network is provided;

[0047] Figure 6 A schematic diagram of an AI application framework is provided;

[0048] Figure 7 An architecture schematic diagram of another communication system provided by embodiments of the present application is provided;

[0049] Figure 8 An AI / ML management architecture schematic diagram is provided;

[0050] Figure 9 A single-function model schematic diagram is provided;

[0051] Figure 10 A function management schematic diagram of a model is provided;

[0052] Figure 11 A flowchart schematic diagram of a communication method provided by embodiments of the present application is provided;

[0053] Figure 12A schematic diagram of a multifunctional wireless prediction model provided for an embodiment of the present application;

[0054] Figure 13 A schematic diagram of the internal structure of a multifunctional wireless prediction model provided for an embodiment of the present application;

[0055] Figure 14 A schematic diagram of the association between a model and a function provided for an embodiment of the present application;

[0056] Figure 15 A schematic diagram of a multifunctional wireless radio map model provided for an embodiment of the present application;

[0057] Figure 16 A schematic diagram of a multifunctional wireless information prediction model provided for an embodiment of the present application;

[0058] Figure 17 A schematic diagram of a time-domain wireless data prediction provided for an embodiment of the present application;

[0059] Figure 18A A schematic diagram of multiple attributes being independently processed and input into a model provided for an embodiment of the present application;

[0060] Figure 18B A schematic diagram of multiple attributes being cascaded and input into a model provided for an embodiment of the present application;

[0061] Figure 19 A schematic diagram of the structure of a communication device provided for an embodiment of the present application;

[0062] Figure 20 A schematic diagram of the structure of another communication device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0063] The embodiments of the present application will be described below with reference to the accompanying drawings.

[0064] The technology provided by the present application can be applied to various communication systems. For example, the communication system can be a fourth generation (4 th generation, 4G) communication system (for example, a long term evolution (LTE) system), a fifth generation (5 th generation, 5G) communication system, a worldwide interoperability for microwave access (WiMAX) system, a wireless local area network (WLAN) system, a satellite communication system, a converged system of multiple systems, or a future communication system, for example, a sixth generation (6 thThe communication system can be, for example, a 5G (5th Generation, 5G) or later mobile communication system (also referred to as 6G (6th Generation, 6G) communication system, etc. Among them, the 5G communication system can also be referred to as a new radio (NR) system.

[0065] A network element in a communication system can send a signal to another network element or receive a signal from another network element. Among them, the signal can include information, signaling, or data, etc. Among them, the network element can also be replaced by an entity, a network entity, a device, a terminal device, a communication module, a node, a communication node, etc. In this application, the network element is taken as an example for description. For example, the communication system can include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device. In addition, it can be understood that if the communication system includes multiple terminal devices, the multiple terminal devices can also send signals to each other, that is, the sending network element of the signal and the receiving network element of the signal can be terminal devices.

[0066] Referring to Figure 1 , Figure 1 A simplified schematic diagram of a wireless communication system provided by the embodiments of the present application is shown. As Figure 1 indicated, the wireless communication system includes a wireless access network 100. The wireless access network 100 can be a next-generation (e.g., 6G or higher) wireless access network, or a traditional (e.g., 5G, 4G) wireless access network. One or more terminal devices (120a-120j, collectively referred to as 120) can be connected to each other, or connected to one or more network devices (110a, 110b, collectively referred to as 110) in the wireless access network 100. Optionally, Figure 1 This is only a schematic diagram, and the wireless communication system can also include other devices, such as core network devices, wireless relay devices, and / or wireless backhaul devices, etc., which are not shown in Figure 1 .

[0067] Optionally, in actual applications, the wireless communication system can simultaneously include multiple network devices (also referred to as access network devices), and can also simultaneously include multiple terminal devices. One network device can simultaneously serve one or more terminal devices. One terminal device can also simultaneously access one or more network devices. The embodiments of the present application do not limit the number of terminal devices and network devices included in the wireless communication system.

[0068] The network device can be an entity for transmitting or receiving signals on the network side. The network device can be an access device through which a terminal device accesses the wireless communication system in a wireless manner. For example, the network device can be a base station. The base station can be referred to as a radio access network (RAN) node, a NodeB, an evolved NodeB (eNB), a next generation NodeB (gNB), a network device in an open radio access network (O-RAN), a relay station, an access point, a transmitting and receiving point (TRP), a transmitting point (TP), a master eNB (MeNB), a secondary eNB (SeNB), a multi-standard radio (MSR) node, a home base station, a network controller, an access node, a radio node, an access point (AP), a transmission node, a transceiver node, a building baseband unit (BBU), a remote radio unit (RRU), an active antenna unit (AAU), a remote radio head (RRH), a centralized unit (CU), a distributed unit (DU), a radio unit (RU), a CU control plane (CU-CP) node, a CU user plane (CU-UP) node, a positioning node, a RAN intelligent controller (RIC), and the like. The base station can be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. The network device can also refer to a communication module, a modem, or a chip for being disposed in the foregoing devices or apparatuses. The network device can also be a mobile switching center, a device-to-device (D2D) device, a vehicle-to-everything (V2X) device, a machine-to-machine (M2M) device, a device assuming a base station function in device-to-device (D2D) communication, a device assuming a base station function in vehicle-to-everything (V2X) communication, a device assuming a base station function in machine-to-machine (M2M) communication, a network side device in a 6G network, a device assuming a base station function in a future communication system, and the like.The network device can support networks of the same or different access technologies. Embodiments of the present application do not limit the specific technology and specific device form adopted by the network device.

[0069] The network device can be fixed or mobile. For example, the base stations 110a, 110b are stationary and are responsible for wireless transmission and reception in one or more cells from the terminal device 120. Figure 1 The helicopter or drone 120i shown in the middle can be configured to act as a mobile base station, and one or more cells can move according to the location of the mobile base station 120i. In other examples, the helicopter or drone (120i) can be configured to act as a terminal device that communicates with the base station 110b.

[0070] In the present application, the communication device for implementing the access network function as described above can be a network device, a network device with part of the function of the access network, or a device capable of supporting the implementation of the access network function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module, which can be installed in the network device or used in conjunction with the network device. In the method of the present application, the communication device for implementing the function of the network device is described by way of example of the network device.

[0071] The terminal device can be an entity on the user side for receiving or transmitting signals, such as a mobile phone. The terminal device can be used to connect people, things and machines. The terminal device can communicate with one or more core networks through a network device. The terminal device includes a handheld device with a wireless connection function, another processing device connected to a wireless modem, or a vehicle-mounted device, etc. The terminal device can be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device. The terminal device 120 can be widely used in various scenarios, such as cellular communication, D2D, V2X, point-to-point (P2P), machine-to-machine (M2M), machine type communication (MTC), internet of things (IoT), virtual reality (VR), augmented reality (AR), industrial control, autonomous driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, smart transportation, smart city, unmanned aerial vehicle, robot, remote sensing, passive sensing, positioning, navigation and tracking, autonomous delivery and mobile, etc.Some examples of the terminal device 120 are a user equipment (UE) of a 3GPP standard, a fixed device, a mobile device, a handheld device, a wearable device, a cellular phone, a smart phone, a session initiated protocol (SIP) phone, a notebook, a personal computer, a smart book, a vehicle, a satellite, a global positioning system (GPS) device, a target tracking device, a drone, a helicopter, an aircraft, a ship, a remote control device, a smart home device, an industrial device, a personal communication service (PCS) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a wireless webcam, a tablet, a palm computer, a mobile internet device (MID), a wearable device such as a smart watch, a VR device, an AR device, a wireless terminal in industrial control, a terminal in Internet of Vehicles system, a wireless terminal in self driving, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city such as a smart gas tank, a terminal device on a high-speed rail, and a wireless terminal in smart home such as a smart speaker, a smart coffee machine, a smart printer, etc. The terminal device 120 can be a wireless device in the above various scenarios or an apparatus for being arranged in a wireless device, e.g., a communication module, a modem, or a chip in the above devices. The terminal device can also be referred to as a terminal, a terminal device, a UE, a mobile station (MS), a mobile terminal (MT), etc. The terminal device can also be a terminal device in a future wireless communication system. The terminal device can be used in a dedicated network device or a general-purpose device. The embodiments of the present application do not limit specific technologies and specific device forms adopted by the terminal device.

[0072] Optionally, the terminal device can be used to act as a base station. For example, a UE can act as a scheduling entity which provides sidelink signals between UEs in V2X, D2D, or P2P, etc. As shown in FIG. 1, the cellular phone 120a and the car 120b communicate with each other using sidelink signals. The cellular phone 120a and the smart home device 120e communicate without relaying the communication signals through the base station 110b. Figure 1 As shown in FIG. 1, the cellular phone 120a and the car 120b communicate with each other using sidelink signals. The cellular phone 120a and the smart home device 120e communicate without relaying the communication signals through the base station 110b.

[0073] In this application, the communication device for realizing the function of the terminal device can be a terminal device, can also be a terminal device with part of the function of the above terminal device, or can be a device capable of supporting the realization of the function of the above terminal device, such as a chip system, which can be installed in the terminal device or used with the terminal device. In this application, the chip system can be composed of a chip, or can include a chip and other discrete devices. In the technical solutions provided in this application, the communication device is taken as an example to describe the terminal device or UE.

[0074] Optionally, a wireless communication system is usually composed of a cell, a base station provides management of the cell, and the base station provides communication services to a plurality of mobile stations (MSs) in the cell. The base station includes a baseband unit (BBU) and a remote radio unit (RRU). The BBU and the RRU can be placed in different places, for example, the RRU is pulled away and placed in a high traffic area, and the BBU is placed in a central machine room. The BBU and the RRU can also be placed in the same machine room. The BBU and the RRU can also be different components under one rack. Optionally, one cell can correspond to one carrier or member carrier.

[0075] In some deployments, the network device mentioned in the embodiments of the present application can be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (centralized unit-control plane, CU-CP) and a user plane CU node (centralized unit-user plane, CU-UP) and a DU node. For example, the network device can include a gNB-CU-CP, a gNB-CU-UP and a gNB-DU.

[0076] In some deployments, a plurality of RAN nodes assist the terminal device to implement wireless access, and different RAN nodes respectively implement part of the functions of the base station. For example, the RAN node can be a CU, a DU, a CU-CP, a CU-UP, or an RU, etc. The CU and the DU can be separately arranged, or can be included in the same network element, such as a BBU. The RU can be included in a radio frequency device or a radio frequency unit, such as an RRU, an AAU or an RRH.

[0077] The RAN node can support one or more types of fronthaul interfaces, different fronthaul interfaces respectively corresponding to DUs and RUs having different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more of baseband functions, and the RU is configured to implement one or more of radio frequency functions. If the fronthaul interface between the DU and the RU is another interface, relative to the CPRI, one or more of the partial baseband functions of the downlink and / or uplink, such as, for the downlink, one or more of precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / add cyclic prefix (CP), are moved from the DU to the RU for implementation, and for the uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / remove cyclic prefix are moved from the DU to the RU for implementation. In a possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the splitting manner between the DU and the RU is different, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0078] Taking eCPRI Cat A as an example, for downlink transmission, with layer mapping as the cut, the DU is configured to implement layer mapping and one or more functions (i.e., one or more of encoding, rate matching, scrambling, modulation, layer mapping) before layer mapping, while other functions (e.g., one or more of resource element (RE) mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) after layer mapping are implemented in the RU. For uplink transmission, with de-RE mapping as the cut, the DU is configured to implement de-mapping and one or more functions (i.e., one or more of decoding, de-rate matching, de-scrambling, de-modulation, inverse discrete Fourier transform (IDFT), channel equalization, de-RE mapping) before de-mapping, while other functions (e.g., one or more of digital BF or FFT / CP removal) after de-mapping are implemented in the RU. It can be understood that the function description of the DU and the RU corresponding to various types of eCPRI can refer to the eCPRI protocol, which is not described here.

[0079] In a possible design, the processing unit in the BBU for implementing baseband functions is referred to as a baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is referred to as a baseband low (BBL) unit.

[0080] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, as Figure 2The illustrated open radio access network (O-RAN) architecture diagram includes at least a non-real-time RAN intelligent controller (RIC): it is a function in the service management and orchestration framework (SMO) that drives the content transmitted over the A1 interface. It consists of a non-real-time RIC framework and non-real-time RIC applications (rApps). Near-real-time RAN intelligent controller (Near-RT RIC): an O-RAN network function that enables near-real-time control and optimization of RAN elements and resources through fine-grained data collection and operations over the E2 interface. It can include AI / ML workflows, including model training, inference, and updating. Open Cloud (O-Cloud): a cloud computing platform that includes a series of physical infrastructure nodes that meet the requirements of O-RAN to host related O-RAN functions (such as Near-RT RIC, O-CU-CP, O-CU-UP, and O-DU), supported software components (such as operating systems, virtual machine monitors, container runtimes, etc.), and appropriate management and orchestration functions. In the ORAN system, the CU can also be referred to as the open-centralized unit (O-CU), the DU can also be referred to as the open-distributed unit (O-DU), the CU-CP can also be referred to as the O-CU-CP, the CU-UP can also be referred to as the O-CU-UP, and the RU can also be referred to as the O-RU. Any one of the CU (or CU-CP, CU-UP), DU, and RU in the present application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0081] In the embodiments of the present application, the device for implementing the function of the network device can be a network device; it can also be a device capable of supporting the network device 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 network device or used in combination with the network device. In the embodiments of the present application, only the device for implementing the function of the network device is taken as an example to illustrate the network device, and the scheme of the embodiments of the present application is not limited.

[0082] It can be understood that the present application can be applied between the network device and the terminal device.

[0083] Protocol layer structure between the network device and the terminal device:

[0084] The communication between the network device and the terminal device follows a certain protocol layer structure. The protocol layer structure can include a control plane protocol layer structure and a user plane protocol layer structure. For example, the control plane protocol layer structure can include the functions of protocol layers such as a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, a medium access control (MAC) layer, and a physical layer. For example, the user plane protocol layer structure can include the functions of protocol layers such as a PDCP layer, an RLC layer, a MAC layer, and a physical layer, and in a possible implementation, a service data adaptation protocol (SDAP) layer can be further included above the PDCP layer.

[0085] Optionally, the protocol layer structure between the network device and the terminal device can further include an artificial intelligence (AI) layer for transmitting AI function related data.

[0086] Taking the data transmission between the network device and the terminal device as an example, the data transmission needs to pass through the user plane protocol layers such as the SDAP layer, the PDCP layer, the RLC layer, the MAC layer, and the physical layer. Among them, the SDAP layer, the PDCP layer, the RLC layer, the MAC layer, and the physical layer can also be collectively referred to as an access layer. According to the transmission direction of the data, each layer is divided into a sending part and a receiving part. Taking the following line data transmission as an example, the PDCP layer obtains data from the upper layer, transmits the data to the RLC layer and the MAC layer, generates a transport block by the MAC layer, and then transmits the data through the physical layer. The data is encapsulated in each layer. For example, the data received by a layer from the upper layer of the layer is regarded as a service data unit (SDU) of the layer, and after encapsulation by the layer, it becomes a protocol data unit (PDU), which is then passed to the next layer.

[0087] Exemplarily, the terminal device can further have an application layer and a non-access layer. The application layer can be configured to provide services to applications installed in the terminal device, for example, the downlink data received by the terminal device can be sequentially transmitted to the application layer by the physical layer, and then provided to the applications by the application layer; for another example, the application layer can obtain data generated by the applications, and sequentially transmit the data to the physical layer to send to other communication devices. The non-access layer can be configured to forward user data, for example, forward the uplink data received from the application layer to the SDAP layer, or forward the downlink data received from the SDAP layer to the application layer.

[0088] It should be understood that Figure 1 The number and types of devices in the illustrated communication system are merely illustrative, and the application is not limited thereto. In actual applications, more terminal devices, more network devices, and other network elements, such as core network devices and / or network elements for implementing artificial intelligence functions, can also be included in the communication system.

[0089] It can be understood that all or part of the functions of one or more of the terminal device, the network device, the core network device, or the network element for implementing artificial intelligence functions can be virtualized, that is, implemented by one or more of a special processor or a general processor and a corresponding software module. Among them, the terminal device and the network device involve the interface of air interface transmission, and the transceiving function of the interface can be realized by hardware. The core network device, such as the operation administration and maintenance (OAM) network element, can be virtualized. Optionally, one or more functions of the virtualized terminal device, network device, core network device, or network element for implementing artificial intelligence functions can be implemented by a cloud device, such as a cloud device in an over the top (OTT) system.

[0090] In order to support AI technology in the wireless network, an AI node can also be introduced in the network.

[0091] Optionally, the AI node can be deployed in one or more of the following positions in the communication system: network device, terminal device, or core network device, etc., or the AI node can also be deployed separately, for example, deployed in a position other than any of the above devices, such as a host or a cloud server in an over the top (OTT) system. The AI node can communicate with other devices in the communication system, which can be one or more of the following: network device, terminal device, or network element of the core network, etc.

[0092] It can be understood that the number of AI nodes is not limited in the present application. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, e.g., different AI nodes are responsible for different functions.

[0093] It can also be understood that the AI nodes can be independent devices, can be integrated into the same device to implement different functions, or can be network elements in a hardware device, or can be software functions running on a dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform), and the specific form of the AI nodes is not limited in the present application.

[0094] The AI nodes can be AI network elements or AI modules.

[0095] These network element nodes, e.g., one or more devices in a core network device, an access network node (RAN node), a terminal, or an OAM, are provided with one or more AI modules. The access network node can be a separate RAN node, or can include multiple RAN nodes, e.g., including a CU and a DU. The CU and / or DU can also be provided with one or more AI modules. Optionally, the CU can also be split into a CU-CP and a CU-UP. The CU-CP and / or CU-UP are provided with one or more AI models.

[0096] The AI modules are used to implement corresponding AI functions. The AI modules deployed in different network elements can be the same or different. The AI modules can implement different functions according to different parameter configurations. The model of the AI module can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of neurons, the activation function of neurons, or the bias in the activation function), input parameters (e.g., the type of input parameters and / or the dimension of input parameters), or output parameters (e.g., the type of output parameters and / or the dimension of output parameters). The bias in the activation function can also be referred to as the bias of the neural network.

[0097] One AI module can have one or more models. One model can infer an output, which includes one parameter or multiple parameters. The learning process, training process, or inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0098] Still referring to Figure 2The RIC is included in the communication system. For example, the RIC can be the AI module described above, and is configured to implement AI-related functions. The RIC includes a near-real time RIC (near-RT RIC) and a non-real time RIC (Non-RT RIC). The Non-RT RIC is mainly configured to process non-real-time information, such as data that is not sensitive to latency, and the latency of the data can be seconds. The near-RT RIC is mainly configured to process near-real-time information, such as data that is relatively sensitive to latency, and the latency of the data is tens of milliseconds.

[0099] The near-RT RIC is configured to perform model training and inference. For example, the near-RT RIC is configured to train an AI model and perform inference using the AI model. The near-RT RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., a CU, a CU-CP, a CU-UP, a DU, and / or a RU) and / or a terminal. The information can be used as training data or inference data. Optionally, the near-RT RIC can deliver inference results to the RAN node and / or the terminal. Optionally, the inference results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the near-RT RIC delivers the inference results to the DU, and the DU delivers the inference results to the RU.

[0100] The Non-RT RIC is also configured to perform model training and inference. For example, the Non-RT RIC is configured to train an AI model and perform inference using the AI model. The Non-RT RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., a CU, a CU-CP, a CU-UP, a DU, and / or a RU) and / or a terminal. The information can be used as training data or inference data, and inference results can be delivered to the RAN node and / or the terminal. Optionally, the inference results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the Non-RT RIC delivers the inference results to the DU, and the DU delivers the inference results to the RU.

[0101] The near-RT RIC and the Non-RT RIC can also be separately configured as a network element. Alternatively, the near-RT RIC and the Non-RT RIC can also be part of other devices. For example, the near-RT RIC can be configured in a RAN node (e.g., a CU, a DU), and the Non-RT RIC can be configured in an OAM, a cloud server, a core network device, or another network device.

[0102] For example, the configuration of the near-RT RIC and the Non-RT RIC in the network architecture can be as shown in Figures 3A-3D

[0103] As shown in (a) of Figure 3A , in a first possible implementation, the network device includes a near-RT RIC module configured to perform model learning and / or inference.​

[0104] As shown in (b) of Figure 3A , in a second possible implementation, in the communication system, a non-real-time RIC can be included in addition to the network device. Optionally, the non-real-time RIC can be located in the OAM or the core network device.

[0105] As shown in (c) of Figure 3A , in a third possible implementation, a near-real-time RIC is included in the network device, and a non-real-time RIC is included in addition to the network device. Optionally, the non-real-time RIC can be located in the OAM or the core network device.

[0106] In contrast to (c) of Figure 3A , Figure 3B , the CU is separated into a CU-CP and a CU-UP. The near-real-time RIC and the non-real-time RIC are set in the same way as (c) of Figure 3A .

[0107] As shown in (d) of Figure 3C , optionally, one or more AI entities can be included in the network device, and the AI entity has a function similar to the above-mentioned near-real-time RIC. Optionally, one or more AI entities can be included in the OAM, and the AI entity has a function similar to the above-mentioned non-real-time RIC. Optionally, one or more AI entities can be included in the core network device, and the AI entity has a function similar to the above-mentioned non-real-time RIC. When the OAM and the core network device both include AI entities, the models trained by their respective AI entities are different, and / or the models used for inference are different. In this application, the models being different can include at least one of the following: structural parameters of the model (such as the number of layers of the model, and / or weights, etc.), input parameters of the model, or output parameters of the model.

[0108] In contrast to Figure 3C , Figure 3D , the network device in (c) is separated into a CU and a DU. Optionally, the CU can include an AI entity, and the AI entity has a function similar to the above-mentioned near-real-time RIC. Optionally, the DU can include an AI entity, and the AI entity has a function similar to the above-mentioned near-real-time RIC. When the CU and the DU both include AI entities, the models trained by their respective AI entities are different, and / or the models used for inference are different. Optionally, the CU in (c) can be further split into a CU-CP and a CU-UP. Optionally, one or more AI models can be deployed in the CU-CP. And / or, one or more AI models can be deployed in the CU-UP. Figure 3D Figure 3C In (d) or (e), the OAM of the network device and the OAM of the core network device can be separately deployed independently. Figure 3D

[0109] ​​For ease of understanding, the AI technology involved in the present application will be introduced first. It can be understood that this introduction does not limit the present application.

[0110] (1) AI model

[0111] AI refers to the intelligence exhibited by machines made by humans. Artificial intelligence generally refers to a technology that presents human intelligence through ordinary computer programs. Artificial intelligence can be defined as a machine or computer that simulates humans and has cognitive functions related to human thinking, such as learning and problem solving. Artificial intelligence can learn from past experiences, make reasonable decisions, and respond quickly. The goal of artificial intelligence is to understand intelligence by building computer programs with symbolic reasoning or reasoning.

[0112] Machine learning (ML) is one way to achieve artificial intelligence, that is, to solve problems in artificial intelligence by means of machine learning. Machine learning theory mainly designs and analyzes some algorithms that allow computers to automatically "learn". Machine learning algorithms are a class of algorithms that automatically analyze rules from data and use rules to predict unknown data. Because learning algorithms involve a lot of statistical theory, machine learning is particularly closely related to inferential statistics, also known as statistical learning theory.

[0113] Machine learning can be divided into supervised learning, unsupervised learning, and reinforcement learning.

[0114] Supervised learning learns the mapping relationship from sample values to sample labels using machine learning algorithms according to the collected sample values and sample labels, and uses a machine learning model to express the learned mapping relationship. The process of training a machine learning model is the process of learning this mapping relationship. For example, in signal detection, the noisy received signal is the sample, and the true constellation point corresponding to the signal is the label. Machine learning expects to learn the mapping relationship between samples and labels through training, that is, to learn a signal detector. During training, the model parameters are optimized by calculating the error between the predicted value of the model and the true label. Once the mapping relationship is learned, the learned mapping can be used to predict the label of each new sample. The mapping relationship learned by supervised learning can include linear mapping and nonlinear mapping. According to the type of label, the learned task can be divided into classification tasks and regression tasks.

[0115] Unsupervised learning only uses the collected sample values to discover the internal pattern of the sample by using algorithms. In unsupervised learning, a class of algorithms uses the sample itself as a supervision signal, that is, the model learns the mapping relationship from the sample to the sample, which is called self-supervised learning. During training, the model parameters are optimized by calculating the error between the predicted value of the model and the sample itself. Self-supervised learning can be used for signal compression and decompression recovery applications. Common algorithms include autoencoders and generative adversarial networks.

[0116] Reinforcement learning is different from supervised learning and is an algorithm that learns a strategy to solve a problem by interacting with the environment. Unlike supervised and unsupervised learning, the reinforcement learning problem does not have clear "correct" action label data. The algorithm needs to interact with the environment to obtain the reward signal of the environmental feedback, and then adjust the decision action to obtain a larger reward signal value. In the following power control, the reinforcement learning model adjusts the downlink transmission power of each user according to the system total throughput rate fed back by the wireless network, and then expects to obtain a higher system throughput rate. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and the optimal decision action. However, because the "correct action" label cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action". Reinforcement learning training is achieved through iterative interaction with the environment.

[0117] An AI model is an algorithm or computer program that can implement an AI function, and is a specific implementation of an AI technology function. The AI model represents the mapping relationship between the input and output of the model. The type of AI model can be a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q-learning model, or other machine learning models.

[0118] (2) Deep neural network (DNN)

[0119] A deep neural network is a specific implementation form of AI or machine learning technology. According to the universal approximation theorem, a neural network can theoretically approximate any continuous function, thereby enabling the neural network to learn any mapping. Traditional communication systems need to rely on rich expert knowledge to design communication modules, while a deep learning communication system based on a DNN can automatically discover the implicit pattern structure from a large amount of data set, establish the mapping relationship between the data, and obtain better performance than traditional modeling methods.

[0120] The idea of a DNN comes from the neuron structure of the brain tissue. For example, each neuron performs a weighted sum operation on its input values and outputs the operation result through an activation function. Figure 4As shown, it is a schematic diagram of a neuron structure. Assume that the input of a neuron is x = [x0, x1, …, x n ], the weight corresponding to each input is w = [w0, w1, …, w n ], where w i is the weight of x i , used for weighting x i . The bias for weighted sum of input values according to weights is, for example, b. The form of an activation function can be various. Assuming that the activation function of a neuron is y = f(z) = max(0, z), the output of the neuron is:

[0121] For another example, the activation function of a neuron is y = f(z) = z, the output of the neuron is:

[0122] Wherein, b, w i , x i may be various possible values such as decimal, integer (for example, 0, positive integer or negative integer), or complex number. The activation functions of different neurons in a neural network can be the same or different.

[0123] A neural network generally includes multiple layers, and each layer can include one or more neurons. By increasing the depth and / or width of the neural network, the expression ability of the neural network can be improved, and the neural network can provide stronger information extraction and abstract modeling ability for complex systems. The depth of the neural network can refer to the number of layers included in the neural network, and the number of neurons included in each layer can be referred to as the width of the layer. In an implementation manner, the neural network includes an input layer and an output layer. The input layer of the neural network processes the received input information through neurons, and transmits the processing result to the output layer, and the output result of the neural network is obtained by the output layer. In another implementation manner, the neural network includes an input layer, a hidden layer and an output layer, which can refer to the schematic diagram of the neural network in Figure 5 . The input layer of the neural network processes the received input information through neurons, and transmits the processing result to the intermediate hidden layer. The hidden layer calculates the received processing result to obtain a calculation result, and transmits the calculation result to the output layer or the adjacent hidden layer, and finally the output result of the neural network is obtained by the output layer. The neural network can include one hidden layer, or include multiple sequentially connected hidden layers, which is not limited.

[0124] Depending on how the network is constructed, DNN can include feedforward neural networks (FNN), convolutional neural networks (CNN), and recurrent neural networks (RNN). Figure 5 The figure shows an FNN network, which is characterized by the neurons in adjacent layers being fully connected to each other. This means that FNN usually requires a large amount of storage space and leads to high computational complexity.

[0125] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time series data and image data can both be considered grid-like. CNNs don't use all input information at once for computation. Instead, they use a fixed-size window to intercept a portion of the information for convolution operations, significantly reducing the computational complexity of model parameters. Furthermore, depending on the type of information intercepted by the window (e.g., people and objects in an image represent different types of information), different convolution kernels can be used for each window, enabling CNNs to better extract features from the input data.

[0126] RNNs are a type of DNN that utilizes feedback time series information. Their input consists of a new input value at the current moment and their own output value at the previous moment. RNNs are suitable for capturing temporally correlated sequence features and are particularly well-suited for applications such as speech recognition and channel coding.

[0127] The above-mentioned FNN, CNN, and RNN are common neural network structures, which are all constructed based on neurons. As mentioned above, each neuron performs a weighted sum operation on its input values, and the weighted summation result generates an output through a nonlinear function. We call the weights of the weighted summation operation of neurons in the neural network and the nonlinear function the parameters of the neural network. Taking the neuron with max{0,x} as the nonlinear function as an example, The parameters of the neuron to be operated are weights w=[w0,…,w n ], the weighted sum bias is b, and the nonlinear function max{0,x}. The parameters of all neurons in a neural network constitute the parameters of the neural network.

[0128] (3) Training dataset and inference data

[0129] The training dataset is used for training of the AI model, and the training dataset can include the input of the AI model or the input and target output of the AI model. The training dataset includes one or more training data, and the training data can be a training sample input to the AI model or a target output of the AI model. The target output can also be referred to as a label or a label sample. The training dataset is one of the important parts of machine learning. Model training is essentially learning some features from the training data, so that the output of the AI model is as close as possible to the target output, such as the difference between the output of the AI model and the target output is as small as possible. The composition and selection of the training dataset can determine the performance of the trained AI model to some extent.

[0130] In addition, a loss function can be defined in the training process of the AI model (such as a neural network). The loss function describes the gap or difference between the output value of the AI model and the target output value. The application does not limit the specific form of the loss function. The training process of the AI model is a process of adjusting the model parameters of the AI model so that the value of the loss function is less than a threshold or so that the value of the loss function meets the target requirement. For example, the AI model is a neural network, and adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers of the neural network, the width, the weight of the neuron, or the parameter of the activation function of the neuron.

[0131] The inference data can be input to the trained AI model as an input of the AI model for inference of the AI model. In the model inference process, the inference data is input to the AI model, and the corresponding output is obtained as the inference result.

[0132] (4) Design of AI model

[0133] The design of the AI model mainly includes the data collection link (such as collecting training data and / or inference data), the model training link, and the model inference link. Further, it can also include the inference result application link. See Figure 6, a kind of AI application framework is shown.In the foregoing data collection link, data source is used to provide training data set and inference data.In the model training link, AI model is obtained by analyzing or training the training data provided by data source.The AI model represents the mapping relationship between the input and output of the model.AI model is learned by model training node, which is equivalent to learning the mapping relationship between the input and output of the model using training data.In the model inference link, AI model trained by model training link is used to perform inference based on inference data provided by data source to obtain inference result.This link can also be understood as follows: inference data is input into AI model, and the output obtained by AI model is the inference result.The inference result can indicate the configuration parameter used (executed) by the execution object and / or the operation executed by the execution object.In the inference result application link, the inference result is published, for example, the inference result can be uniformly planned by execution entity, for example, execution entity can send inference result to one or more execution objects (for example, core network equipment, network equipment or terminal equipment, etc.) to execute.Again, execution entity can also feed back the performance of model to data source to facilitate subsequent implementation of model update training.

[0134] It can be understood that the network element with artificial intelligence function can be included in the communication system. The above-mentioned AI model design related links can be executed by one or more network elements with artificial intelligence function. In a possible design, the AI function (such as AI module or AI entity) can be configured in the existing network element in the communication system to implement the AI related operation, for example, the training and / or inference of the AI model. For example, the existing network element can be a network device (such as gNB), a terminal device, a core network device, or a network management device, etc. Among them, the network management device can divide the management work of the network into three categories according to the actual needs of the operator network operation: operation, administration, and maintenance. The network management device can also be called OAM network element, abbreviated as OAM. The operation mainly completes the analysis, prediction, planning and configuration work of the daily network and service; the maintenance mainly completes the daily operation activities of the test and fault management of the network and its service, and the network management device can detect the network running state, optimize the network connection and performance, improve the network running stability, and reduce the network maintenance cost. Or in another possible design, a separate network element can also be introduced in the communication system to execute the AI related operation, such as training the AI model. The separate network element can be called AI network element or AI node, etc., and the name is not limited in the present application. The AI network element can be directly connected with the network device in the communication system, or can be indirectly connected with the network device through a third party device and the network device. Among them, the third party device can be an authentication management function (AMF) network element, a user plane function (UPF) network element, an OAM, a cloud server or other network element, which is not limited. For example, see Figure 7 Another architecture schematic diagram of a communication system provided by the embodiment of the present application is provided, which includes a network device 710, a terminal device 720, 730, and an AI network element 740 is introduced in the communication system.

[0135] In the present application, one model can infer one parameter, or infer multiple parameters. The training processes of different models can be deployed in different devices or nodes, or can be deployed in the same device or node. The inference processes of different models can be deployed in different devices or nodes, or can be deployed in the same device or node.

[0136] Among them, the model parameters may include one or more of the following structural parameters of the model (such as the number of layers and / or weights of the model, etc.), the input parameters of the model (such as input dimension, number of input ports), or the output parameters of the model (such as output dimension, number of output ports). It can be understood that the input dimension may refer to the size of an input data. For example, when the input data is a sequence, the input dimension corresponding to the sequence may indicate the length of the sequence. The number of input ports may refer to the number of input data. Similarly, the output dimension may refer to the size of an output data. For example, when the output data is a sequence, the output dimension corresponding to the sequence may indicate the length of the sequence. The number of output ports may refer to the number of output data.

[0137] Introducing artificial intelligence / machine learning technology into wireless air interfaces can be used for compression and reconstruction of wireless channel information, beam management, and positioning enhancement. AI / ML based on neural networks uses data-driven training to improve the performance of wireless tasks. Figure 8 As shown in the AI / ML management architecture diagram, the AI / ML system includes data collection, model training, model management / performance monitoring, model inference, model storage, and model inference control (including activation, deactivation, fallback, switching, and selection).

[0138] The development of AI / ML technology has brought changes to AI in fields such as natural language processing: pre-trained large models can be applied to a variety of downstream tasks through pre-training on diverse massive data.

[0139] The current AI models are designed for each wireless AI task, such as Figure 9 The following single-function model diagram shows that Model 1 predicts the path loss between the transmitting and receiving devices based on the location information of the transmitting or receiving device; Model 2 predicts the communication rate based on the location information of the transmitting or receiving device; and Model K predicts the beam direction based on time information. Models used for different tasks collect data for training and subsequent model management.

[0140] like Figure 10 The diagram below shows how models can be managed. For different scenarios, a function may be implemented by multiple models, each with a specific scope of application. This can typically be achieved by managing the function, such as activating or deactivating it. The specific models under each function require model-related management before the function is activated.

[0141] Currently, models are designed for each function separately, which cannot utilize the correlation between data of functions. It will also lead to a large number of models in wireless communication systems and high complexity in model management.

[0142] In view of this, the present application provides a communication solution, which obtains predicted wireless data associated with the first attribute by obtaining a first attribute and at least one reference wireless data set, and processes the first attribute and at least one reference wireless data set based on a first model, thereby providing a multifunctional wireless prediction model that supports the prediction of multiple attributes and multiple wireless data. There is no need to design a model separately for the prediction of each type of wireless data, thereby improving the prediction efficiency.

[0143] The following describes in detail the communication method provided in the embodiment of the present application based on the above communication system.

[0144] like Figure 11 FIG. 1 is a flow chart of a communication method provided in an embodiment of the present application. Exemplarily, the method may include the following steps:

[0145] S1101. Obtain first information.

[0146] like Figure 12 FIG. 1 is a schematic diagram of a multifunctional wireless prediction model provided by an embodiment of the present application. Figure 12 The first model in the present invention is a multifunctional wireless prediction model. The first model supports at least one function, that is, the first model supports predicting at least one wireless data of at least one attribute. The first model includes two parts: input and output. The input includes at least one attribute and at least one reference wireless data set; the output includes predicted wireless data associated with at least one attribute. The attribute includes, but is not limited to, at least one of the following: position, time, frequency (e.g., resource block index (RB index)). Each reference wireless data set in the at least one reference wireless data set includes reference wireless data and attributes associated with the reference wireless data. The reference wireless data includes, but is not limited to, at least one of the following: path loss, channel quality indication (CQI), angle of arrival (AOA), angle of departure (AOD), timing advance (TA), signal to interference plus noise ratio (SINR), data rate, etc. The prediction of multiple attributes and multiple wireless data can be achieved based on the same model (or the same model parameters).

[0147] Therefore, when using the first model for training or inference, first, it is necessary to obtain the input information of the first model, that is, the first information.

[0148] As described above, the first model can obtain the predicted wireless data associated with the at least one attribute based on the at least one attribute and the at least one set of reference wireless data. This embodiment is described by taking an example of inputting the first attribute (one or more of any of the above attributes) and the at least one set of reference wireless data (the first information includes the first attribute and the at least one set of reference wireless data) to obtain the predicted wireless data associated with the first attribute, and obtaining the predicted wireless data associated with multiple attributes can refer to the method of this embodiment.

[0149] Exemplarily, the reference wireless data can be historical wireless data. Each set of reference wireless data in the at least one set of reference wireless data includes reference wireless data and an attribute associated with the reference wireless data. The attribute associated with the reference wireless data refers to the value of the attribute associated with the reference wireless data. For example, the attribute is a location, the at least one set of reference wireless data refers to at least one set of reference wireless data of at least one location, and the attribute associated with the reference wireless data refers to the location associated with the reference wireless data. For another example, the attribute is a time, the at least one set of reference wireless data refers to at least one set of reference wireless data of at least one time, and the attribute associated with the reference wireless data refers to the time associated with the reference wireless data.

[0150] As Figure 13 shown, an internal structure diagram of a multifunctional wireless prediction model provided by an embodiment of the present application is shown, and input includes reference wireless data 1 and an attribute associated with the reference wireless data 1 (for example, assuming that the first attribute is a location, the attribute associated with the reference wireless data 1 is the location associated with the reference wireless data 1), reference wireless data 2 and an attribute associated with the reference wireless data 2 (the attribute associated with the reference wireless data 2 is the location associated with the reference wireless data 2). Two sets of reference wireless data are shown in the figure, and more reference wireless data and attributes associated with the reference wireless data can also be included. The first attribute, i.e., an attribute associated with the predicted wireless data, is also input, and the predicted wireless data, i.e., the predicted wireless data associated with the first attribute, is also input.

[0151] Further, the attribute associated with the reference wireless data can be a number, and the attribute values associated with the reference wireless data can be the same under different attributes (e.g., the first attribute is location, the attribute associated with the reference wireless data 1 is 1 (the location associated with the reference wireless data 1), and the attribute associated with the reference wireless data 2 is 2 (the location associated with the reference wireless data 2); the first attribute is time, the attribute associated with the reference wireless data 1 is also 1 (the time associated with the reference wireless data 1), and the attribute associated with the reference wireless data 2 is also 2 (the time associated with the reference wireless data 2)). Therefore, in order to distinguish the input reference wireless data and the attribute associated with the reference wireless data, a first indication information (i.e., the first information further includes the first indication information) can also be input, which is used to indicate the type of the predicted wireless data and / or the type of the first attribute, i.e., to indicate which attribute and / or which wireless data is predicted this time. Exemplarily, the first indication information can be a model index.

[0152] By configuring a set of model parameters for the first model, the prediction of at least one wireless data can be realized.

[0153] In some communication scenarios, the first model can be deployed at the base station side, and the base station can receive the first information reported by the UE. In other communication scenarios, the first model can be deployed at the UE side, and the UE can collect the first information by itself or receive the first information sent by the base station.

[0154] Exemplarily, the first model can be a decoder transformer, a recurrent neural network (RNN), a long short-term memory (LSTM), or other neural networks supporting sequence prediction tasks, etc.

[0155] When training the first model, different input lengths are predicted to minimize the average loss as the optimization objective.

[0156] S1102. Based on the first model, the first attribute and the at least one set of reference wireless data are processed to obtain second information.

[0157] After obtaining the first attribute and the at least one set of reference wireless data, the first attribute and the at least one set of reference wireless data are input to the first model. The first attribute and the at least one set of reference wireless data can be processed based on the first model to obtain second information. For example, the first attribute and the at least one set of reference wireless data can be processed based on the first model to obtain predicted wireless data associated with the first attribute. The second information includes the predicted wireless data associated with the first attribute.

[0158] For example, when the first attribute is a location, the first model can be used to input reference wireless data (such as path loss, CQI, AOA, AOD, TA, SINR, data rate, etc.) of multiple locations to predict predicted wireless data (such as path loss, CQI, AOA, AOD, TA, SINR, data rate, etc.) of a certain location. For another example, when the first attribute is a time, the first model can be used to input reference wireless data (such as path loss, CQI, AOA, AOD, TA, SINR, data rate, etc.) of multiple times to predict predicted wireless data (such as path loss, CQI, AOA, AOD, TA, SINR, data rate, etc.) of a certain time in the future. That is, the first model can support prediction of at least one type of wireless data of at least one attribute, or the first model supports at least one function.

[0159] Because the model in the embodiment can support multiple wireless functions, the model can be managed based on the model (rather than managing multiple models based on functions as shown in Figure 10 As shown in Figure 14 , a model and function association diagram provided by the embodiment of the present application is shown. The model is identified and assigned a model identifier, such as model 1 and model 2 in Figure 14 . The description or meta-information of the model 1 and the model 2 includes at least one function supported by the model (which can be a list of functions supported by the model). For example, the model 1 supports function 1 (such as location-associated path loss), function 2 (such as location-associated AOA), and function 3 (such as time-associated TA); and the model 2 supports function 4 (such as frequency-associated path loss) and function 5 (such as frequency-associated CQI).

[0160] In addition, because the first model has a data length requirement for the attribute associated with the reference wireless data or the first attribute, before the first attribute and the at least one set of reference wireless data are processed based on the first model to obtain the second information, the attribute associated with the reference wireless data or the first attribute included in each set of reference wireless data in the at least one set of reference wireless data can be processed to obtain a first data length attribute. Figure 13As shown, the attribute associated with the reference wireless data or the first attribute can be processed by a multilayer perceptron (MLP) to obtain an attribute of a first data length.

[0161] Similarly, the first model can also have a data length requirement for the reference wireless data, and therefore, before processing the first attribute and the at least one set of reference wireless data based on the first model to obtain the second information, the reference wireless data included in each set of reference wireless data in the at least one set of reference wireless data can also be processed to obtain reference wireless data of a second data length. For example, Figure 13 As shown, the reference wireless data can also be processed by an MLP to obtain reference wireless data of a second data length.

[0162] In addition, as shown, Figure 13 The reference wireless data and the attribute associated with the reference wireless data can be jointly embedded together with the first indication information as described above. That is, each set of reference wireless data and the attribute associated with the reference wireless data share the same position embedding, which is used to identify whether the input is an attribute or reference wireless data. For example, a first vector can be added to the attribute of a first data length obtained after MLP processing, and the first vector is used to identify the attribute associated with the reference wireless data. A second vector can also be added to the reference wireless data of a second data length obtained after MLP processing, and the second vector is used to identify the reference wireless data.

[0163] When predicting based on the first model, the communication apparatus can obtain the identifier of the first model and at least one function supported by the first model. If the model is deployed on the UE side, the base station can manage the model, and the base station can receive the identifier of at least one model and at least one function supported by each model in the at least one model reported by the UE. When the base station instructs the UE to predict the wireless data associated with the first attribute, the base station can send second indication information, for example, the second indication information can be used to instruct processing based on the first model, and the second indication information includes the identifier of the first model. If the model is deployed on the base station side, the base station can provide prediction services to the UE, and the base station can instruct the UE about the functions supported by different models. For example, the base station can send third information to the UE, and the third information indicates at least one function supported by the first model.

[0164] In addition, the model can also be updated / rolled back based on the model identifier. The rollback refers to, in some cases, when the performance of the model deteriorates, the model can be rolled back to a traditional algorithm or a default algorithm / model to process the data.

[0165] For any model, the function thereof can also be activated / deactivated. Specifically, fourth information can be acquired, the fourth information being used to indicate activation of at least one function supported by the first model; or the fourth information being used to indicate deactivation of at least one function supported by the first model. For example, the model is deployed at the UE side, and the base station can send the fourth information to the UE; for another example, the model is deployed at the base station side, and the UE can send the fourth information to the base station.

[0166] According to the communication method provided in the embodiments of the present application, the first attribute and the at least one reference wireless data set are acquired, and the first attribute and the at least one reference wireless data set are processed based on the first model to obtain predicted wireless data associated with the first attribute. Through the multifunctional wireless prediction model, prediction of multiple attributes and multiple wireless data can be supported, and a model does not need to be designed for each wireless data for prediction, thereby improving the prediction efficiency.

[0167] The following describes how to obtain predicted wireless data associated with an attribute through two examples:

[0168] In one example, multiple wireless data of a specific location are predicted through a multifunctional radio map model. As shown in Figure 15 FIG. 1 is a schematic diagram of a multifunctional radio map model according to an embodiment of the present application, wherein the input of the model includes location information and at least one reference wireless data set (for example, a first reference wireless data set and a second reference wireless data set). Figure 15 The first reference wireless data set includes reference wireless data 1 (for example, path loss, CQI, AOA, AOD, TA, SINR, data rate, etc.) and an attribute (for example, a first location) associated with the reference wireless data 1, and the second reference wireless data set includes reference wireless data 2 (for example, path loss, CQI, AOA, AOD, TA, SINR, data rate, etc.) and an attribute (for example, a second location) associated with the reference wireless data 2.

[0169] The location information and the at least one reference wireless data set can be processed based on the multifunctional radio map model to obtain multiple predicted wireless data (for example, path loss, CQI, AOA, AOD, TA, SINR, data rate, etc.) associated with the location information (for example, a third location).

[0170] Further, the location information, the location information associated with the reference wireless data 1, and the location information associated with the reference wireless data 2 can be processed through a neural network such as an MLP to obtain the location information, the location information associated with the reference wireless data 1, and the location information associated with the reference wireless data 2 with a unified data length, respectively.

[0171] Further, the reference wireless data 1 and the reference wireless data 2 can be processed by a neural network such as MLP to obtain the reference wireless data 1 and the reference wireless data 2 with unified data length, respectively.

[0172] In addition, the position information after the data length is unified, the position information associated with the reference wireless data 1, and the position information associated with the reference wireless data 2 can be added with a first vector for identifying the position information.

[0173] In addition, the reference wireless data 1 and the reference wireless data 2 after the data length is unified can be added with a second vector for identifying the reference wireless data 1 and the reference wireless data 2.

[0174] In addition, in order to distinguish the input reference wireless data and the attribute associated with the reference wireless data, a model index can be input to the multi-functional radio map model to indicate that the type and / or attribute of the predicted wireless data is the position information.

[0175] After the position information and the at least one set of reference wireless data are processed based on the multi-functional radio map model to obtain the predicted wireless data associated with the position information, the predicted wireless data can be processed by a neural network such as MLP to obtain the predicted wireless data with a required data length. For example, the multi-functional radio map model outputs a high-dimensional vector, and after processing by the neural network such as MLP, the high-dimensional vector can be mapped to a dimension with the required data length.

[0176] When training the multi-functional radio map model, the difference between the predicted wireless data of each position and the label (target wireless data, such as the true value of the wireless data or the measured wireless data) can be used as the loss function of the model, such as mean-square error (MSE) or mean absolute error loss (MAE).

[0177] When inferring based on the multi-functional radio map model, the number of the input set of reference wireless data can be determined according to performance requirements and the like.

[0178] In the present example, when training the model / performance monitoring the model, the communication device can collect reference wireless data of different positions in the same scene. For example, when the model is deployed at the base station side, the base station can configure the UE to perform measurement and report of multiple reference wireless data. Alternatively, the UE can actively report the position information and at least one reference wireless data measured at different positions.

[0179] When using this model for inference, if the model is deployed on the base station side, the UE can report location information and at least one reference wireless data measured at different locations. The base station can collect the location information reported by the UE and at least one reference wireless data measured at different locations as input, and the base station can predict the wireless data associated with a certain location. If the model is deployed on the UE side, the UE can use its own collected location information and at least one reference wireless data measured at different locations as model input, or request at least one reference wireless data at a specific location from the base station as model input to predict the wireless data associated with the certain location. Furthermore, the UE can report the predicted wireless data to the base station.

[0180] The multifunctional radio map model provided in this example supports predictions for various wireless data types, that is, supports multiple radio map functions. This fully utilizes the correlation between various wireless data types and reduces the complexity of model management.

[0181] In another example, a multifunctional wireless information prediction model is used to predict various wireless data at a specific time. Figure 16 As shown, a schematic diagram of a multifunctional wireless information prediction model exemplified by an embodiment of the present application, wherein the input of the model includes time information and at least one reference wireless data set (two reference wireless data sets are exemplified in the figure: the first reference wireless data set includes reference wireless data 1 (such as path loss, CQI, AOA, AOD, TA, SINR, data rate, etc.) and attributes associated with reference wireless data 1 (such as the first time), and the second reference wireless data set includes reference wireless data 2 (such as path loss, CQI, AOA, AOD, TA, SINR, data rate, etc.) and attributes associated with reference wireless data 2 (such as the second time).

[0182] The time information and at least one reference wireless data set can be processed based on the multifunctional wireless information prediction model to obtain multiple predicted wireless data associated with the time information (such as path loss, CQI, AOA, AOD, TA, SINR, data rate, etc. at the third time).

[0183] Furthermore, the time information, the time information associated with the reference wireless data 1, and the time information associated with the reference wireless data 2 can be processed by a neural network such as MLP to obtain time information with a uniform data length, time information associated with the reference wireless data 1, and time information associated with the reference wireless data 2, respectively.

[0184] Furthermore, the reference wireless data 1 and the reference wireless data 2 may be processed by a neural network such as an MLP to obtain the reference wireless data 1 and the reference wireless data 2 of uniform data length.

[0185] In addition, a first vector may be added to the time information after the data length is unified, the time information associated with the reference wireless data 1 , and the time information associated with the reference wireless data 2 , to identify the time information.

[0186] In addition, a second vector may be added to the reference wireless data 1 and the reference wireless data 2 after the data length is unified, so as to identify the reference wireless data 1 and the reference wireless data 2 .

[0187] In addition, in order to distinguish the input reference wireless data and attributes associated with the reference wireless data, a model index may be input to the multifunctional wireless information prediction model to indicate that the type and / or attribute of the predicted wireless data is time information.

[0188] After processing the time information and at least one reference wireless data set based on the multifunctional wireless information prediction model to obtain predicted wireless data associated with the time information, the predicted wireless data can be processed using a neural network, such as an MLP, to obtain predicted wireless data of the desired data length. For example, the multifunctional wireless information prediction model outputs a high-dimensional vector, which, after processing using a neural network, such as an MLP, can be mapped to the dimensions of the desired data length.

[0189] When training the multifunctional wireless information prediction model, the difference between the wireless data predicted at each time and the label (target wireless data, such as the true value of the wireless data or the measured wireless data) can be used as the loss function of the model, such as MSE or MAE.

[0190] When reasoning is performed based on the multifunctional wireless information prediction model, the number of input reference wireless data sets can be determined according to performance requirements and the like.

[0191] In this example, during model training / model performance monitoring, the communications device can collect reference wireless data at different times within the same scenario. For example, when the model is deployed on the base station side, the base station can configure the UE to measure and report multiple reference wireless data. Alternatively, the UE can proactively report time information and at least one reference wireless data item measured at different times.

[0192] When using this model for reasoning, Figure 17As shown in the time-domain wireless data prediction schematic diagram of the embodiment example of the present application, if the model is deployed at the base station side, the UE can report time information and at least one reference wireless data measured at different times, the base station can collect the time information and the at least one reference wireless data measured at different times reported by the UE as input, and the base station can predict wireless data associated with a certain time. If the model is deployed at the UE side, the UE can collect time information and at least one reference wireless data measured at different times as input of the model, or request the base station for at least one reference wireless data at a specific time as input of the model, to predict wireless data associated with a certain time. Further, the UE can report the predicted wireless data to the base station.

[0193] The multifunctional wireless information prediction model provided in the present example can support prediction of multiple wireless data, that is, support multiple wireless information prediction functions. The correlation of multiple wireless data is fully utilized, and the complexity of model management is reduced.

[0194] The above embodiment describes how to obtain predicted wireless data associated with a certain attribute based on at least one reference wireless data set of the attribute. In actual use, the above multifunctional model can be used to process at least one reference wireless data set of multiple attributes to obtain predicted wireless data associated with multiple attributes.

[0195] Specifically, each reference wireless data can include multiple attributes, such as location, time, frequency, etc., that is, wireless data can be predicted based on location, time, or frequency information at the same time. Multiple attributes can be input to the model after being processed independently or in cascade. For example, Figure 18A As shown in the schematic diagram of the embodiment example of the present application, multiple attributes are independently processed and input to the model, each attribute is independently processed by MLP, and then processed subsequently with at least one reference wireless data set; for example, Figure 18B As shown in the schematic diagram of the embodiment example of the present application, multiple attributes are independently processed and input to the model, each attribute is independently processed by MLP, and then processed subsequently with at least one reference wireless data set; for example,

[0196] Based on the same idea of the above communication method, the embodiments of the present application further provide a communication device for implementing the above method. The communication device can be the communication device in the above method embodiments, or a component applicable to the communication device. It can be understood that the communication device comprises the hardware structure and / or software module corresponding to each function in order to implement the above functions. Those skilled in the art should easily realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is implemented in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0197] The embodiments of the present application can divide the functions of the communication device according to the above method embodiments, for example, each function module can be divided according to each function, or two or more functions can be integrated in one processing unit. The integrated module can be realized in the form of hardware or software function module. It should be noted that the division of the modules in the embodiments of the present application is illustrative, and is only a logical function division. There can be another division method in actual implementation.

[0198] Based on the same idea of the above communication method, the present application further provides a communication device as follows:

[0199] As shown in Figure 19 Fig. 1 is a structural schematic diagram of a communication device provided by the embodiments of the present application. The communication device 1900 comprises a transceiver unit 1901 and a processing unit 1902; wherein:

[0200] The processing unit 1902 is configured to obtain first information, the first information comprising a first attribute and at least one reference wireless data set, each reference wireless data set in the at least one reference wireless data set comprising a reference wireless data and an attribute associated with the reference wireless data; and the processing unit 1902 is configured to process the first attribute and the at least one reference wireless data set based on a first model to obtain second information, the first model being used to predict at least one wireless data, the second information comprising a predicted wireless data associated with the first attribute.

[0201] Optionally, the attribute associated with the reference wireless data or the first attribute comprises at least one of the following: position, time, frequency.

[0202] Optionally, the type of the reference wireless data or the predicted wireless data comprises at least one of the following: path loss, channel quality indication, angle of arrival, angle of departure, timing advance, signal to interference plus noise ratio, data rate.

[0203] Optionally, the first information further comprises first indication information, the first indication information being used to indicate the type of the predicted wireless data and / or the type of the first attribute.

[0204] Optionally, the processing unit 1902 is further configured to acquire an identifier of the first model and at least one function supported by the first model, the at least one function supported by the first model being used to indicate that the first model supports predicting at least one type of wireless data of at least one attribute.

[0205] Optionally, the transceiver 1901 is configured to receive second indication information, the second indication information being used to indicate that processing is based on the first model, and the second indication information comprises the identifier of the first model.

[0206] Optionally, the transceiver 1901 is further configured to send third information, the third information indicating the at least one function supported by the first model, the at least one function supported by the first model being used to indicate that the first model supports predicting at least one type of wireless data of at least one attribute.

[0207] Optionally, the processing unit 1902 is further configured to acquire fourth information, the fourth information being used to indicate activating the at least one function supported by the first model, or the fourth information being used to indicate deactivating the at least one function supported by the first model.

[0208] Optionally, the processing unit 1902 is further configured to process the attribute associated with the reference wireless data or the first attribute included in each of the at least one set of reference wireless data to obtain a first data length of attribute, and the processing unit 1902 is further configured to process the reference wireless data included in each of the at least one set of reference wireless data to obtain a second data length of reference wireless data.

[0209] Optionally, the processing unit 1902 is further configured to add a first vector to the first data length of attribute, the first vector being used to identify the attribute associated with the reference wireless data, and the processing unit 1902 is further configured to add a second vector to the second data length of reference wireless data, the second vector being used to identify the reference wireless data.

[0210] The specific implementation of the transceiver 1901 and the processing unit 1902 can be referred to the description in the above method embodiments.

[0211] Further, it should be noted that the aforementioned transceiver and / or processing unit can be implemented by virtual modules, for example, the processing unit can be implemented by a software function unit or a virtual device, and the transceiver can be implemented by a software function or a virtual device. Alternatively, the processing unit or the transceiver can also be implemented by an entity circuit, for example, if the device is implemented by a chip / chip circuit, the transceiver can be an input / output circuit and / or a communication interface, which performs an input operation (corresponding to the aforementioned receiving operation) and an output operation (corresponding to the aforementioned sending operation); the processing unit is a processing circuit, such as an integrated processor or a microprocessor or an integrated circuit.

[0212] The division of modules in the present application is illustrative, and is only a logical functional division. In actual implementation, there can be another division manner. In addition, each functional module in each example of the present application can be integrated in one processor, or can be a separate physical existence, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module.

[0213] As shown in FIG. 1, the communication device 1000 includes one or more processing circuits 1001 (one processing circuit is shown in the figure). Optionally, the communication device 1000 can also include a memory 1003 (indicated by a dashed line in the figure). The memory 1003 is used to store instructions executed by the processing circuit 1001, or to store input data required by the processing circuit 1001 to execute instructions, or to store data generated after the processing circuit 1001 executes instructions. Optionally, the communication device 1000 can also include an interface circuit 1002 (indicated by a dashed line in the figure), and the processing circuit 1001 and the interface circuit 1002 are coupled to each other. It can be understood that the interface circuit 1002 can be a transceiver or an input / output interface. Figure 20

[0214] Wherein, the processing circuit can be a processor or a circuit in the processor for processing.

[0215] Wherein, the processing circuit 2001 is configured to obtain first information, the first information including a first attribute and at least one reference wireless data set, each reference wireless data set in the at least one reference wireless data set including a reference wireless data and an attribute associated with the reference wireless data; and the processing circuit 2001 is configured to process the first attribute and the at least one reference wireless data set based on a first model to obtain second information, the first model being used to predict at least one wireless data, and the second information including a predicted wireless data associated with the first attribute.

[0216] ​Optionally, the reference wireless data is associated with at least one of the following: a location, a time, a frequency.

[0217] Optionally, the type of the reference wireless data or the predicted wireless data comprises at least one of the following: a path loss, a channel quality indication, an angle of arrival, an angle of departure, a timing advance, a signal to interference plus noise ratio, a data rate.

[0218] Optionally, the first information further comprises first indication information, the first indication information being used to indicate the type of the predicted wireless data and / or the type of the first attribute.

[0219] Optionally, the processing circuit 2001 is further configured to obtain an identification of the first model and at least one function supported by the first model, the at least one function supported by the first model being used to indicate that the first model supports predicting at least one type of wireless data of at least one attribute.

[0220] Optionally, the interface circuit 2002 is configured to receive second indication information, the second indication information being used to indicate that processing is based on the first model, the second indication information comprising the identification of the first model.

[0221] Optionally, the interface circuit 2002 is further configured to send third information, the third information indicating the at least one function supported by the first model, the at least one function supported by the first model being used to indicate that the first model supports predicting at least one type of wireless data of at least one attribute.

[0222] Optionally, the processing circuit 2001 is further configured to obtain fourth information, the fourth information being used to indicate activating the at least one function supported by the first model; or the fourth information being used to indicate deactivating the at least one function supported by the first model.

[0223] Optionally, the processing circuit 2001 is further configured to process the attribute associated with the reference wireless data or the first attribute included in each of the at least one set of reference wireless data to obtain a first data length of attribute; and the processing circuit 2001 is further configured to process the reference wireless data included in each of the at least one set of reference wireless data to obtain a second data length of reference wireless data.

[0224] Optionally, the processing circuit 2001 is further configured to add a first vector to the first data length of attribute, the first vector being used to identify the attribute associated with the reference wireless data; and the processing circuit 2001 is further configured to add a second vector to the second data length of reference wireless data, the second vector being used to identify the reference wireless data.

[0225] The embodiment of the present application further provides a computer readable storage medium, wherein a computer program or instructions are stored in the computer readable storage medium, and the computer program or instructions are executed to implement the method in the above embodiment.

[0226] The embodiment of the present application further provides a computer program product containing instructions, which, when executed on a computer, cause the computer to perform the method in the above embodiment.

[0227] The embodiment of the present application further provides a communication system, comprising the communication device.

[0228] The embodiment of the present application further provides a circuit, which is coupled with a memory, and is used to execute the method shown in the above embodiment. The circuit can include a chip circuit.

[0229] Optionally, the embodiment of the present application further provides a chip system, comprising at least one processor and an interface, wherein the at least one processor is coupled with a memory through the interface, and when the at least one processor executes a computer program or instructions in the memory, the chip system executes the method in any method embodiment. Optionally, the chip system can be composed of a chip, or can include a chip and other discrete devices, and the embodiment of the present application does not make a specific limitation.

[0230] The memory in the present application can also be a circuit or other any device capable of realizing a storage function, used to store program instructions and / or data. The memory can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but is not limited to this. For example, the memory can be a non-volatile memory, such as a digital versatile disc (DVD), a hard disk drive (HDD) or a solid-state drive (SSD), etc., and can also be a volatile memory, such as a random-access memory (RAM).

[0231] In the following description of the present application, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a list of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device.

[0232] It should be understood that, in the description of the present application, unless otherwise specified, " / " represents that the objects associated in front and back are in an "or" relationship, for example, A / B can represent A or B; wherein A, B can be singular or plural. And, in the description of the present application, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or the like means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c can be single or multiple. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, the same items or similar items with basically the same function and role are distinguished by using "first", "second", etc. The skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. do not necessarily mean different. At the same time, in the embodiments of the present application, "exemplary" or "for example" means to serve as an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner, for understanding.

[0233] In the above embodiments, all or part can be realized by software, hardware, firmware or any combination thereof. When realized by software, all or part can be realized in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode.

[0234] Although the present application is described in conjunction with the preferred embodiments thereof, numerous modifications and alterations are possible without departing from the scope and spirit of the present application as described in the following claims. In the claims, the article "a", "an" is intended in the alternative (i.e., "one or more") unless otherwise indicated. The use of the term "including" and / or "containing" does not exclude the presence of elements other than those listed. The use of the term "one" does not exclude the presence of more than one, unless otherwise indicated. The use of the term "at least one" does not exclude the presence of more than one, unless otherwise indicated. The use of the terms "first", "second", "third", etc. does not limit the quantity and / or order of those named. These terms are used to distinguish between two or more members of a group. The use of the term "if" does not exclude the presence of additional or other conditions that could make the presence of the stated condition possible or appropriate. Other expressions of possibility are used in a like manner.

[0235] It is to be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and do not limit the scope of the embodiments of the present application. The size of the serial numbers of the above processes does not mean the order of execution, and the execution order of the processes should be determined according to its function and inherent logic.

[0236] In the above embodiments, the description of each embodiment is focused on, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0237] The components in the device of the embodiments of the present application can be combined, divided and deleted according to actual needs. Those skilled in the art can combine or combine the features of different embodiments and different embodiments described in the specification.

[0238] In the present application, each example can be mutually quoted without logical contradiction, for example, the methods and / or terms between the method embodiments can be mutually quoted, for example, the functions and / or terms between the device embodiments can be mutually quoted, for example, the functions and / or terms between the device examples and the method examples can be mutually quoted.

Claims

1. A communication method characterized by comprising: The method comprises: obtaining first information, the first information comprising a first attribute and at least one reference wireless data set, each reference wireless data set in the at least one reference wireless data set comprising a reference wireless data and an attribute associated with the reference wireless data; processing the first attribute and the at least one reference wireless data set based on a first model to obtain second information, the first model being used to predict at least one wireless data, the second information comprising a predicted wireless data associated with the first attribute.

2. The method of claim 1, wherein, The attribute associated with the reference wireless data or the first attribute comprises at least one of the following: position, time, frequency.

3. The method of claim 1 or 2, wherein, The type of the reference wireless data or the predicted wireless data comprises at least one of the following: path loss, channel quality indicator, angle of arrival, angle of departure, timing advance, signal to interference plus noise ratio, data rate.

4. The method according to any one of claims 1 to 3, characterized in that, The first information further comprises first indication information, the first indication information being used to indicate the type of the predicted wireless data and / or the type of the first attribute.

5. The method of any one of claims 1-4, wherein, The method further comprises: obtaining an identifier of the first model and at least one function supported by the first model, the at least one function supported by the first model being used to indicate that the first model supports predicting at least one wireless data of at least one attribute.

6. The method of claim 5, wherein, The method further comprises: receiving second indication information, the second indication information being used to indicate that processing is based on the first model, the second indication information comprising the identifier of the first model.

7. The method of any one of claims 1-5, wherein, The method further comprises: sending third information, the third information indicating the at least one function supported by the first model, the at least one function supported by the first model being used to indicate that the first model supports predicting at least one wireless data of at least one attribute.

8. The method of claim 5 or 7, wherein, The method further comprises: obtaining fourth information, the fourth information being used to indicate activating the at least one function supported by the first model; or the fourth information being used to indicate deactivating the at least one function supported by the first model.

9. The method of any one of claims 1-8, wherein, Before the processing of the first attribute and the at least one reference wireless data set based on the first model to obtain the second information, the method further comprises: processing the attribute associated with the reference wireless data or the first attribute comprised in each reference wireless data set in the at least one reference wireless data set to obtain a first data length of attribute; processing the reference wireless data comprised in each reference wireless data set in the at least one reference wireless data set to obtain a second data length of reference wireless data.

10. The method of claim 9, wherein, Before the processing of the first attribute and the at least one reference wireless data set based on the first model to obtain the second information, the method further comprises: adding a first vector to the first data length of attribute, the first vector being used to identify the attribute associated with the reference wireless data; adding a second vector to the second data length of reference wireless data, the second vector being used to identify the reference wireless data.

11. A communications device, characterized by A device comprising means for performing the method of any one of claims 1-10.

12. A communications device, characterized by comprising processing circuitry and interface circuitry for receiving signals from and transmitting signals to other communication devices other than the communication device, and the processing circuitry is configured to implement the method of any one of claims 1-10 by means of logic circuitry or by means of executing code instructions.

13. The communication apparatus according to claim 12, wherein The communication device is a chip.

14. A chip module, characterized by comprising a transceiver component and a chip, the chip being configured to implement the method of any one of claims 1-10.

15. A computer readable storage medium having stored thereon a computer program, characterized in that, The program, when executed by a processor, implements the method of any one of claims 1-10.

16. A computer program product, characterised in that, The computer program product comprises program instructions involved, which, when executed, implement the method of any one of claims 1-10.

Images