Communication method and apparatus, and storage medium

Abstract

The present application provides a communication method and apparatus, and a storage medium, capable of obtaining AI / ML models meeting processing requirements. In the method, a network device sends first data to a terminal device, the first data being obtained by processing second data by means of a first processing mode, and the first processing mode comprising at least one of the following: modulation, encoding, or reference signal generation; the terminal device obtains third data on the basis of the first data and a first AI model, a processing mode of the first AI model for the first data corresponding to the first processing mode, and determines a first index on the basis of the third data and the second data; and when the first index meets a target index, the terminal device sends first information to the network device, the first information being used for indicating the first AI model.

Description

Communication method, apparatus, and storage medium

[0001] The present application claims priority to the Chinese patent application No. 202411097739.9, filed on August 9, 2024, and entitled "Communication method, apparatus, and storage medium", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication technology, and in particular to a communication method, an apparatus, and a storage medium. BACKGROUND

[0003] When artificial intelligence (AI) / machine learning (ML) technology is applied to a wireless communication system, it can be applied to a variety of use cases, such as modulation, coding, transmitters, receivers, multi-antenna technology, positioning technology, etc. The AI / ML technology can be applied in network devices and / or terminal devices, i.e., AI / ML models are deployed at the network side and / or the terminal device side.

[0004] Whether it is a network side model or a terminal side model, there may be a problem of insufficient training, which causes the processing result of AI / ML to fail to meet the demand. SUMMARY

[0005] The present application provides a communication method, an apparatus, and a storage medium to obtain an AI / ML model that meets the processing demand.

[0006] In a first aspect, the present application provides a communication method, which can be applied to a terminal device, or applied to a component (such as a chip, a chip system, etc.) configured in the terminal device, or can also be applied to a logic module or software capable of realizing all or part of the function of the terminal device, and the present application does not limit this. Hereinafter, for the convenience of understanding and description, the terminal device is taken as an example of the receiving end to describe the method.

[0007] Exemplarily, the method comprises: receiving first data, the first data being obtained by processing second data through a first processing manner, the first processing manner comprising at least one of the following: modulation, coding, or reference signal generation; obtaining third data based on the first data and a first AI model, the first AI model corresponding to the first processing manner in terms of processing manner of the first data; determining a first index based on the third data and the second data; and in a case where the first index meets a target index, sending first information, the first information being used to indicate the first AI model.

[0008] Optionally, the first processing manner can include an AI processing manner and a non-AI processing manner.

[0009] Optionally, the first AI model can implement a function of one or more AI modules.

[0010] The first index is used to represent the correlation between the second data and the third data, or the error between the two. The target index can be a threshold value, and the target index can be related to the first processing manner.

[0011] Based on this technical solution, after the terminal device receives the first data obtained by processing the second data through the first processing manner, the terminal device can process the first data through the first AI model to obtain the third data. Since the manner selected by the terminal device for processing the first data corresponds to the first processing manner, the third data obtained by the terminal device is the same as the second data in terms of the expected target. However, since the first AI model is obtained through training, the third data processed through the first AI model can not be the same as the second data. In this application, the terminal device obtains the first index based on the third data corresponding to the second data (i.e., the true value corresponding to the first data) obtained by the first data, compares the first index with the target index, and reports the first AI model to the network device when the target index is met. This way can determine whether the model for docking meets the requirements before the model docking, thereby effectively avoiding the situation that the model performance cannot meet the standard after the model docking is completed, effectively improving the success rate of model docking, and meeting the processing requirements of the communication system for AI / ML models.

[0012] In combination with the first aspect, in some implementations of the first aspect, the method further includes receiving second information, the second information being used to indicate the target index.

[0013] Optionally, the second information can be carried in a broadcast message, a unicast message, or a groupcast message.

[0014] Specifically, the first processing manner is modulation and / or encoding, and the target index can include one or more of the following: a block error rate within a first time period is less than or equal to a first value, a bit error rate within the first time period is less than or equal to a second value, a demodulation success rate within the first time period is greater than or equal to a third value, or a decoding success rate within the first time period is greater than or equal to a fourth value.

[0015] Specifically, the first processing manner is reference signal generation, and the target index can be a normalized mean squared error (NMSE) of a channel estimation result within a first time period and a true result of the channel, and the number of times that the NMSE is less than a preset threshold is a fifth value.

[0016] The first time length can be replaced by a data amount N (N is a positive integer, and N can be indicated by the network device) of the first data received by the terminal device, or a receiving number N (which can be a total receiving number or a successful or failed receiving number) of the first data received by the terminal device.

[0017] With reference to the first aspect, in some implementations of the first aspect, the second data is determined in a predefined manner.

[0018] Optionally, the second data is determined in a predefined manner, including that the second data is predefined, or the second data is one data indicated by the network side from a plurality of predefined data.

[0019] Design I: The second data can be a random sequence predefined by a protocol. The random sequence can be initialized based on known parameters such as a cell identity (ID), a slot number, a subframe number, or a frame number.

[0020] Design II: The second parameter can be data in a standardized / agreed data set.

[0021] Design III: The second data can be a sequence generated by a data generator.

[0022] Design IV: The second data can be an estimation result of an agreed reference signal.

[0023] With reference to the first aspect, in some implementations of the first aspect, the second data is indicated by the network side.

[0024] Optionally, the second data can be carried in high-layer signaling or physical layer signaling.

[0025] With reference to the first aspect, in some implementations of the first aspect, the method further includes receiving third information, the third information being used to determine the first AI model.

[0026] Optionally, the third information indicates a first processing manner.

[0027] Exemplarily, when the first processing manner is an AI processing manner, the third information indicates a second AI model. Specifically, the third information can indicate the second AI model by identification information of the second AI model, the identification information of the second AI model including an identity (ID) of the second AI model, or an ID of a training data set corresponding to the second AI model, or an associated ID.

[0028] Optionally, the third information can be carried in a broadcast message, a unicast message, or a groupcast message.

[0029] With reference to the first aspect, in some implementations of the first aspect, the method further includes: receiving fourth information, the fourth information being used to indicate a physical resource carrying the first data, the physical resource including one or more of: a time domain resource, a frequency domain resource, or a space domain resource.

[0030] Optionally, the fourth information can be carried in a broadcast message, a unicast message, or a groupcast message.

[0031] With reference to the first aspect, in some implementations of the first aspect, the method further includes: sending fifth information, the fifth information being used to indicate the first index.

[0032] Optionally, the fifth information can be carried in capability information of the terminal device, or in UE assistant information (UAI) or the like, or in uplink control information (UCI) signaling, or in a network-side configured triggering event.

[0033] Optionally, after sending the fifth information, the method further includes: receiving sixth information, the sixth information being used to indicate the first AI model or AI function.

[0034] It can be understood that the terminal device can report multiple AI models or AI functions through the first information, and can report multiple indexes corresponding to the multiple AI models or AI functions through the fifth information. In this way, the network device can select an AI model or AI function corresponding to an index with a smaller error with a target index based on the reported multiple indexes, and indicate the AI model or AI function to the terminal device as an AI model or AI function for interfacing the first processing mode. That is, the first index has a smaller error with the target index.

[0035] With reference to the first aspect, in some implementations of the first aspect, the method further includes: sending capability information, the capability information being used to indicate one or more of: a size of a data amount for pre-monitoring, a quantity of resources occupied by the data for pre-monitoring, a sending period of the data for pre-monitoring, whether pre-monitoring is supported, or one or more AI models supporting pre-monitoring, the one or more AI models including the first AI model, the data for pre-monitoring including the first data and / or the second data.

[0036] Based on this, the terminal device can obtain customized first data sent by the network device for different terminal devices by reporting the capability information.

[0037] With reference to the first aspect, in some implementations of the first aspect, the first data is obtained by processing the second data by using a first processing manner, including: the first data is obtained based on the second data and a first AI model, the first AI model corresponding to the second AI model.

[0038] For example, the second AI model is an AI modulation, and the first AI model corresponding to the second AI model is an AI demodulation; or the second AI model is an AI encoding, and the first AI model corresponding to the second AI model is an AI decoding; or the second AI model is an AI reference signal generation model, and the first AI model corresponding to the second AI model is an AI channel estimation model.

[0039] With reference to the first aspect, in some implementations of the first aspect, the first data is carried in a broadcast message, a unicast message or a groupcast message.

[0040] In a second aspect, the present application provides a communication method, which can be applied to a network device, or applied to a component (such as a chip, a chip system, etc.) configured in the network device, or can also be applied to a logic module or software capable of realizing all or part of the network device functions, and the present application does not limit this. In the following, for the convenience of understanding and description, the method is described by taking the network device as an example of a sending end.

[0041] For example, the method includes: obtaining first data by processing second data based on a first processing manner, the first processing manner including at least one of modulation, encoding, or reference signal generation; sending the first data; receiving first information, the first information being used to indicate a first AI model.

[0042] The description of the first processing manner and the first AI model can refer to the description of the first aspect, which will not be repeated here.

[0043] Based on the technical solution, after the network device sends the first data obtained by processing the second data through the first processing manner to the terminal device, the terminal device can process the first data through the first AI model to obtain third data. Since the manner selected by the terminal device for processing the first data corresponds to the first processing manner, the third data obtained by the terminal device is the same as the second data in terms of the expected target. However, since the first AI model is obtained through training, the third data processed through the first AI model may not be the same as the second data. In the present application, the terminal device obtains the first index based on the second data corresponding to the first data (i.e., the true value corresponding to the first data) of the obtained third data, compares the first index with the target index, and reports the first AI model to the network device when the target index is met. This manner can determine whether the model used for docking meets the requirements in advance before the model docking, thereby effectively avoiding the situation that the performance of the model cannot meet the requirements after the model docking is completed, effectively improving the success rate of the model docking, and meeting the processing requirements of the AI / ML model of the communication system.

[0044] With reference to the second aspect, in some implementations of the second aspect, the method further includes: sending second information, the second information being used to indicate the target index.

[0045] The description of the target index can refer to the description in the first aspect, which will not be repeated here.

[0046] With reference to the second aspect, in some implementations of the second aspect, the second data is determined through a predefined manner.

[0047] Optionally, the method further includes: sending information used to indicate the second data to the terminal device.

[0048] With reference to the second aspect, in some implementations of the second aspect, the method further includes: sending third information, the third information being used to determine the first AI model.

[0049] The description of the third information can refer to the description in the first aspect, which will not be repeated here.

[0050] With reference to the second aspect, in some implementations of the second aspect, the method further includes: sending fourth information, the fourth information being used to indicate a physical resource carrying the first data, the physical resource including one or more of the following: a time domain resource, a frequency domain resource, or a space domain resource.

[0051] With reference to the second aspect, in some implementations of the second aspect, the method further includes: receiving fifth information, the fifth information being used to indicate the first index.

[0052] The description of the fifth information can refer to the description in the first aspect, which will not be repeated here.

[0053] With reference to the second aspect, in some implementations of the second aspect, the method further includes: receiving capability information, the capability information being used to indicate one or more of: a size of a data amount for pre-monitoring, a number of resources occupied by the data for pre-monitoring, a transmission period of the data for pre-monitoring, whether pre-monitoring is supported, or one or more AI models supporting pre-monitoring, the one or more AI models including the first AI model, and the data for pre-monitoring including the first data and / or the second data.

[0054] Based on this, the network device sends customized first data to different terminal devices based on the capability information reported by the terminal device.

[0055] With reference to the second aspect, in some implementations of the second aspect, the processing of the second data based on the first processing mode to obtain the first data includes: obtaining the second data based on the second data and a second AI model, the first AI model corresponding to the second AI model.

[0056] The correspondence between the first AI model and the second AI model can refer to the description in the first aspect, which will not be repeated here.

[0057] With reference to the first and second aspects, in some implementations of the first and second aspects, the first processing mode is modulation and / or encoding, and the first index includes one or more of: a block error rate (BLER) in a first time period, a bit error rate (BER) in the first time period, a success rate of demodulation in the first time period, or a success rate of decoding in the first time period.

[0058] Optionally, the first processing mode is reference signal generation, and the first index can be a number of times that a NMSE of a channel estimation result and a real result of a channel in a first time period is less than a preset threshold.

[0059] With reference to the first and second aspects, in some implementations of the first and second aspects, the first data is carried in a broadcast message, a unicast message, or a groupcast message.

[0060] In a third aspect, the present application provides a communication apparatus, including modules or units for implementing the method in any of the above aspects and any possible implementation manner of the aspects. It should be understood that each module or unit can realize the corresponding function by executing a computer program.

[0061] In a fourth aspect, the present application provides a communication apparatus, including a processor, which is configured to implement the method in any of the preceding aspects and / or any of the possible implementation manners of the preceding aspects.

[0062] The apparatus can further include a memory for storing instructions and data. The memory is coupled to the processor, and the processor implements the method described in the preceding aspects when executing the instructions stored in the memory.

[0063] The apparatus can further include a communication interface for the apparatus to communicate with other devices. Exemplarily, the communication interface can be a transceiver, a circuit, a bus, a module or other types of communication interface.

[0064] In a fifth aspect, the present application provides a chip system, including at least one processor, which is configured to support the functions described in any of the preceding aspects and / or any of the possible implementation manners of the preceding aspects, such as receiving or processing the data and / or information described in the preceding methods.

[0065] In a possible design, the chip system further includes a memory for storing program instructions and data, and the memory is located in or outside the processor.

[0066] The chip system can be composed of a chip, or include a chip and other discrete devices.

[0067] In a sixth aspect, the present application provides a computer readable storage medium, including a computer program, which, when executed on a computer, causes the computer to implement the method in any of the preceding aspects and / or any of the possible implementation manners of the preceding aspects.

[0068] In a seventh aspect, the present application provides a computer program product, including a computer program (also referred to as code or instructions), which, when executed, causes a computer to perform the method in any of the preceding aspects and / or any of the possible implementation manners of the preceding aspects.

[0069] In an eighth aspect, the present application provides a communication system, including the terminal device and the network device described above. The terminal device is configured to execute the method in the first aspect and / or any of the possible implementation manners of the first aspect; and the network device is configured to execute the method in the second aspect and / or any of the possible implementation manners of the second aspect.

[0070] It should be understood that the third aspect to the eighth aspect of the present application correspond to the technical solutions of the first aspect or the second aspect of the present application, and the beneficial effects achieved by the aspects and the corresponding possible implementation manners are similar, which will not be described herein. BRIEF DESCRIPTION OF DRAWINGS

[0071] FIG. 1 is a schematic diagram of an architecture of a communication system suitable for the method provided by the embodiments of the present application;

[0072] FIG. 2 is a schematic block diagram of a conventional transceiver provided by the embodiments of the present application;

[0073] FIG. 3 is a schematic block diagram of an AI transceiver provided by the embodiments of the present application;

[0074] FIG. 4 is a schematic diagram of a joint training manner provided by the embodiments of the present application;

[0075] FIG. 5 is a schematic diagram of a separate training manner provided by the embodiments of the present application;

[0076] FIGS. 6 to 8 are schematic flow diagrams of a communication method provided by the embodiments of the present application;

[0077] FIG. 9 is a schematic block diagram of an apparatus provided by the embodiments of the present application;

[0078] FIG. 10 is another schematic block diagram of an apparatus provided by the embodiments of the present application. DETAILED DESCRIPTION

[0079] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0080] For the convenience of understanding the embodiments of the present application, the following points are first explained:

[0081] First, in the embodiments of the present application, the use of prefixes such as “first”, “second”, etc. is only for the convenience of distinguishing and describing different things belonging to the same name category, and does not constrain the order, size or quantity of the things. For example, “first information” and “second information” are only different information, and there is no time sequence, size relationship or priority relationship between them.

[0082] Second, in the embodiments of the present application, “sending” and “receiving” represent the direction of signal transmission. For example, “sending information to a network device” can be understood as that the destination of the information is the network device, which can include direct transmission through the air interface, or indirect transmission through the air interface by other units or modules. “Receiving capability information from a terminal device” can be understood as that the source of the capability information is the terminal device, which can include direct reception from the terminal device through the air interface, or indirect reception from the terminal device through the air interface from other units or modules. “Sending” can also be understood as the “output” of the chip interface, and “receiving” can also be understood as the “input” of the chip interface.

[0083] In other words, the sending and receiving can be between devices, such as between a terminal device and a network device, or can be within a device, such as between components, modules, chips, software modules or hardware modules within a device via a bus, wire or interface.

[0084] It can be understood that the information can be processed as necessary, such as encoding and modulation, before being sent from the source to the destination. The destination can also perform corresponding processing, such as decoding and demodulation, after receiving the information from the source, so as to interpret the effective information from the source. Similar expressions in this application can be similarly understood, and will not be repeated here.

[0085] Thirdly, in the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The association relationship between the associated objects is described by "and / or", which means that there can be three kinds of relationships, for example, A and / or B, which can represent the following cases: A exists alone, A and B exist together, B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it, but does not rule out the case that the associated objects before and after it represent an "and" relationship. The specific meaning can be understood in combination with the context. "At least one of the following" or similar expressions means any combination of these items, including single item or any combination of multiple items. For example, at least one of a, b or c can represent: a, b, c; a and b; a and c; b and c; or a and b and c. Where a, b, c can be single or multiple.

[0086] Fourthly, in the embodiments of the present application, "indication" can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by a certain information (the first information described below) is referred to as the to-be-indicated information. In the specific implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or the index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can be achieved by means of the arrangement order of each information agreed in advance (for example, protocol predefined), thereby reducing the indication overhead to a certain extent. The specific way of indication is not limited in the present application.

[0087] It can be understood that, for the sender of the indication information, the indication information can be used to indicate the to-be-indicated information, and for the receiver of the indication information, the indication information can be used to determine the to-be-indicated information.

[0088] Fifthly, in the embodiments of the present application, the descriptions such as "when", "in the case of", "if", and "whether" all refer to that the device (such as a network device or a terminal device) will make corresponding processing under certain objective circumstances, and are not limited in time, and do not require the device (such as a network device or a terminal device) to have a judgment action when implemented, nor does it mean that there are other limitations.

[0089] Sixthly, the predefinition in the present application can be understood as: definition, predefinition, storage, pre-storage, pre-negotiation, pre-configuration, solidification, or pre-burning.

[0090] Seventhly, the saving in the present application can refer to saving in one or more memories. The one or more memories can be separately arranged or integrated in the encoder or decoder, the processor, or the communication device. The one or more memories can be partially separately arranged and partially integrated in the decoder, the processor, or the communication device. The type of the memory can be any form of storage medium, which is not limited in the present application.

[0091] The technical solutions provided by the present application can be applied to various communication systems, such as a 5th generation (5G) or new radio (NR) system, a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD) system, a wireless local area network (WLAN) system, a satellite communication system, and a future communication network. The technical solutions provided by the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and internet of things (IoT) communication system or other communication systems.

[0092] A device in a communication system can send or receive a signal to or from another device. The signal can include information, signaling, or data, etc. The device can be replaced by an entity, a network entity, a communication device, a communication module, a node, a communication node, etc. The device is taken as an example for description in the disclosure. 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. It can be understood that the terminal device in the disclosure can be replaced by a first communication apparatus, and the network device can be replaced by a second communication apparatus, both of which perform the corresponding communication method in the disclosure.

[0093] The radio access network (RAN) device in the present application is a device with wireless transceiving function. The radio access network device can provide wireless communication function service and can access the terminal device to the wireless network. The radio access network device can refer to the radio access network (RAN) node (or device) applied to the cellular network (or mobile network) to access the terminal device to the wireless network, and can also be a zigbee base station, a master bluetooth (BT master), a master bluetooth low energy (BLE) bluetooth (BLE master), a Lora base station, and a Wi-Fi access point.

[0094] The network device can be a base station. The base station can broadly cover various names in the following or be replaced with the following names, such as: Node B (Node B), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), primary station, secondary station, multi-mode wireless (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. 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 base station can also refer to a communication module, modem, or chip for setting in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device assuming a base station function in D2D, V2X, M2M communication, a network side device in 6G network, a device assuming a base station function in future communication system, etc. The base station can support networks of the same or different access technologies. Alternatively, the RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in vehicle to everything (V2X) technology can be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network device. 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 (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the network device can include gNB-CU-CP, gNB-CU-UP and gNB-DU.

[0095] In some deployments, wireless access is facilitated by a plurality of RAN nodes in cooperation to serve a terminal, different RAN nodes respectively implementing part of the functionalities of a base station. For example, a RAN node can be a CU, a DU, a CU-CP, a CU-UP, or a RU, etc. A CU and a DU can be separately arranged, or can also be included in the same network element, for example, in a BBU. A RU can be included in a radio frequency device or a radio frequency unit, for example, in a RRU, an AAU, or a RRH.

[0096] A 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 a DU and a RU is a common public radio interface (CPRI), the DU is configured to implement one or more of the baseband functions, and the RU is configured to implement one or more of the radio frequency functions. If the fronthaul interface between the DU and the RU is another interface, compared with the CPRI, part of the baseband functions of the downlink and / or the uplink, such as, for a downlink, one or more of precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / adding a cyclic prefix (CP), are implemented in the RU from the DU, and for an uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / removing the CP are implemented in the RU from the DU. 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.

[0097] Taking eCPRI Cat A as an example, for downlink transmission, the DU is configured to implement layer mapping and one or more functions (i.e., one or more of encoding, rate matching, scrambling, modulation, and layer mapping) before layer mapping, and other functions (e.g., one or more of resource element (RE) mapping, digital BF, or IFFT / add CP) after layer mapping are implemented in the RU. For uplink transmission, the DU is configured to implement demapping and one or more functions (i.e., one or more of decoding, de-rate matching, de-scrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping) before demapping, and other functions (e.g., one or more of digital BF or FFT / CP removal) after demapping are implemented in the RU. It can be understood that the function descriptions of the DU and the RU corresponding to various types of eCPRI can refer to the eCPRI protocol, which will not be described here.

[0098] In a possible design, the processing unit in the BBU for implementing baseband functions is referred to as a base band high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is referred to as a base band low (BBL) unit.

[0099] 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, in an open radio access network (open-RAN, O-RAN, or ORAN) system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. Any of the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module. That is, the network device in this application can be a virtualized device, which is implemented by general hardware and instantiated virtualized functions, or special hardware and instantiated virtualized functions. The general hardware can be a server, such as a cloud server.

[0100] The network device can include the foregoing access network device, and can also include an operation administration and maintenance (OAM) device and / or a core network (CN) device. For the CN device, at least one of a location management function (LMF), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), an application function (AF), a network data analytics function (NWDAF), a network exposure function (NEF), a network slice selection function (NSSF), and a policy control function (PCF) can be included; and for the OAM device, an element management system (EMS) can be included, and a network management system (NMS) can also be included.

[0101] It should be understood that the network device in the embodiments of the present application can also be referred to as a "network side" or a "network part".

[0102] In the embodiments of the present application, the apparatus for implementing the function of the network device can be the network device, or can be an apparatus 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 apparatus can be installed in the network device or used in matching with the network device. In the embodiments of the present application, only the apparatus for implementing the function of the network device is taken as an example for description, and the scheme of the embodiments of the present application is not limited.

[0103] The terminal device in the present application can also be referred to as a user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user apparatus.

[0104] The terminal device in the embodiments of the present application can include a terminal device, a chip or circuit in the terminal device, an entity associated with the terminal device.

[0105] The chip or circuit in the terminal device includes at least one of components inside the terminal device, such as a chip, a central processing unit (CPU), a network processing unit (NPU), and a terminal radio frequency module.

[0106] The entity associated with the terminal device includes a server on the terminal side, a computing / processing node, a computing / processing entity, a computing / processing unit, an over the top server (OTT server), etc. The terminal device interacts with relevant information (such as data) through communication with the associated network entity. For example, the associated network entity and the terminal device belong to the same manufacturer. Due to model training, model selection, etc., it can not be executed on the terminal device, but on the OTT server on the terminal side. Therefore, the "terminal device" in the embodiments of the present application also includes the OTT server on the terminal side.

[0107] It should be understood that the terminal device in the embodiments of the present application can also be referred to as "terminal side" (UE side) or "terminal part" (UE part).

[0108] The terminal device can be a device providing voice / data, for example, a handheld device with wireless connection function, a vehicle-mounted device, etc. At present, some examples of terminals are: mobile phone, tablet computer, notebook computer, palm computer, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication function, computing device or other processing device connected to a wireless modem, wearable device, terminal device in a 5G network, or terminal device in a future evolved public land mobile network (PLMN), etc., device in a zigbee network, device in a Lora network, Bluetooth (BT) slave, BLE slave, Wi-Fi station (STA), etc. The embodiments of the present application are not limited thereto.

[0109] The terminal device can also be a terminal device in an IoT system, also known as an IoT node. IoT is an important part of the future development of information technology, and its main technical feature is to connect objects through communication technology and network, so as to realize the intelligent network of man-machine interconnection and object-object interconnection. Connection can be through broadband technology or narrowband technology. IoT technology can achieve mass connection, deep coverage and terminal power saving through, for example, narrowband (NB) technology. IoT technology includes reflection communication technology, spread spectrum technology, ultra wide band (UWB), etc., which will not be described here.

[0110] In addition, the terminal device can further include a smart printer, a train detector, a gas station sensor, and the like, and the main functions include collecting data (part of the terminal device), receiving control information and downlink data of a network device, and transmitting electromagnetic waves to transmit uplink data to the network device.

[0111] By way of example and not limitation, in the embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing, and shoes. The wearable device is a portable device that is directly worn on the body or integrated into the clothes or accessories of the user. The wearable device is not only a hardware device, but also a powerful function realized through software support and data interaction and cloud interaction. The general wearable smart device includes a full function, a large size, and can realize complete or partial functions without relying on a smart phone, such as a smart watch or smart glasses, and focuses on a certain application function and needs to cooperate with other devices such as a smart phone, such as various smart wristbands and smart jewelry for monitoring vital signs.

[0112] In the embodiments of the present application, the device for realizing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to realize the function, such as a chip system, which can be installed in the terminal device or matched with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices. In the embodiments of the present application, only the device for realizing the function of the terminal device is taken as an example for description, and the scheme of the embodiments of the present application is not limited.

[0113] The terminal device in the present application can be a hardware device, a software function running on a special hardware, or a software function running on a general hardware, and can also be a virtualized device, such as a general hardware and an instantiated virtualization function, or a special hardware and an instantiated virtualization function. The general hardware can be a server, such as a cloud server.

[0114] The network device and / or the terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on the water surface; and can also be deployed on an airplane, a balloon, and a satellite in the air. The present application does not limit the scenario where the network device and the terminal device are located.

[0115] FIG. 1 is a schematic diagram of an architecture of a communication system 100 applicable to the method provided by the embodiments of the present application. As shown in FIG. 1, the communication system 100 includes a radio access network 10 and a core network 20, and optionally, the communication system 100 can also include an Internet 30. The radio access network 10 can include at least one radio access network device (e.g., 110a and 110b in FIG. 1), and can also include at least one terminal device (e.g., 120a-120j in FIG. 1).

[0116] The terminal device can be connected to the radio access network device in a wireless manner, and the radio access network device can be connected to the core network in a wireless or wired manner. The core network device and the radio access network device can be independent and different physical devices, or can be integrated into the same physical device with the functions of the core network device and the logical functions of the radio access network device, or can be a physical device integrated with part of the functions of the core network device and part of the functions of the radio access network device. The terminals can be connected to each other in a wired or wireless manner, and the radio access network devices can be connected to each other in a wired or wireless manner.

[0117] The radio access network device and the terminal, the radio access network devices, and the terminals can communicate through a licensed frequency spectrum, or through an unlicensed frequency spectrum, or through both the licensed frequency spectrum and the unlicensed frequency spectrum; can communicate through a frequency spectrum below 6 gigahertz (GHz), or through a frequency spectrum above 6 GHz, or through both the frequency spectrum below 6 GHz and the frequency spectrum above 6 GHz. The embodiments of the present application do not limit the frequency spectrum resources used for wireless communication.

[0118] The radio access network device can be a base station deployed in the air, such as a satellite base station 110a, or can be a base station deployed indoors, such as a micro base station or an indoor station 110b.

[0119] The terminal can be a terminal deployed in the air, such as a helicopter or a drone 120i in FIG. 1, or can be a terminal deployed on the ground, such as a mobile phone 120a, 120e, 120f and 120j, a vehicle 120b, a computer 110b, a printer 120h, etc.

[0120] The radio access network device and the terminal can be fixed in position or movable. For example, the radio access network device and the terminal can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can be deployed on the water surface; or can be deployed on an airplane, a balloon, and a man-made satellite in the air.

[0121] The roles of the wireless access network devices and the terminals can be relative. For example, the helicopter or the drone 120i in FIG. 1 can be configured as a mobile base station, and for 120j that accesses the wireless access network 10 through 120i, 120i is a base station; but for 110a, 120i is a terminal, that is, 110a and 120i communicate through a wireless air interface protocol. Of course, 110a and 120i can also communicate through an interface protocol between wireless access network devices, and in this case, 120i is also a base station relative to 110a. Therefore, the wireless access network devices and the terminals can be collectively referred to as communication devices, and 110a, 110b, and 120a-120j in FIG. 1 can be referred to as communication devices with their respective corresponding functions, such as a communication device with a base station function or a communication device with a terminal function.

[0122] It should be understood that FIG. 1 is only a schematic diagram, and other devices such as wireless relay devices and wireless backhaul devices can also be included in the communication system, which are not shown in FIG. 1.

[0123] The 3rd generation partnership project (3GPP) Release (R) 18 proposes research on air interface AI, including research on AI channel status information (CSI) feedback, AI beam management, AI positioning, and other use cases. At the same time, a framework for air interface AI lifecycle management (LCM) is determined, which is the control and management operation of the generation, deployment, management, monitoring, and other processes involved in the AI model. Among them, model monitoring refers to measuring the performance of the AI model, for example, comparing the output result of the model with the real true value to determine the performance of the current model, and the network device and the terminal device can determine whether to continue using the current AI model according to the result of model monitoring.

[0124] In the air interface AI model, there are two types of scenarios: single-end model and double-end model. Among them, the single-end model refers to an AI model that is located only on the network side or the terminal side, for example, AI beam management and AI positioning are both single-end model use cases, that is, the completion of the AI function can be completed at one end. The double-end model refers to an AI model that includes a network side model and a terminal side model, and the AI model of both ends needs to be used cooperatively to complete an AI function, for example, AI CSI feedback is a use case of a double-end model.

[0125] In addition to the several use cases discussed in the current air interface AI standardization, some new research directions or new use cases have emerged, such as AI transceiver. AI transceiver can be considered as a dual-end model use case. For AI transceiver, the function modules of the receiving end and the sending end are replaced by AI modules. The following will compare and introduce the traditional transceiver and AI transceiver in combination with FIG. 2 and FIG. 3.

[0126] FIG. 2 is a schematic block diagram of a traditional transceiver provided by an embodiment of the present application. As shown in FIG. 2, the traditional transceiver can include the following modules: the sending module can include channel coding, modulation, resource mapping, and reference signal generation; and the receiving module can include resource demapping, channel estimation, equalization demodulation, and channel decoding.

[0127] FIG. 3 is a schematic block diagram of an AI transceiver provided by an embodiment of the present application. As shown in FIG. 3, the AI modules are used to replace the signal modulation and reference signal generation in the traditional sending module, and the equalization demodulation and channel estimation module in the traditional receiving module. Compared with the traditional transceiver, or the single-end AI transmitter or receiver, the joint optimization of the two ends of the transceiver can be equivalent to the global optimization result, and thus the performance is better.

[0128] It can be understood that as long as a set of function modules used in combination at the sending end and the receiving end are replaced by AI, it can be called an AI transceiver, which is not limited to the example in FIG. 3.

[0129] It can be understood that before using the model for inference, the model needs to be trained first. In R18, for the dual-end model, a type1 training method (i.e., a joint training method) is proposed, as shown in FIG. 4. Taking the AI CSI in R18 as an example, in the AI CSI feedback, the terminal side has an AI CSI compression model, and the network side has an AI CSI recovery model. The two models are used in combination to achieve AI compression and AI recovery of CSI information.

[0130] The above AI CSI feedback model is divided into two parts (i.e., including the AI CSI compression model at the terminal side and the AI CSI recovery model at the network side). In the type1 training method, taking the network side as an example, the network side trains the two models as a whole, and then sends the model required to be used by the terminal side to the terminal side. The network side uses the model at the network side. Thus, the deployment of the dual-end model is realized.

[0131] Since the whole model is trained by one node (e.g., the network side), as long as the node sends the trained model belonging to another node (e.g., the terminal side) to the other node after that, the docking of the two-end model is realized. That is, the docking of the model is actually completed through the model transmission; and the performance of the two-end model can be guaranteed by the node that performs the training, because the node that performs the training will send the model of the other node to the other node only when it considers that the model performance meets the standard. This way can effectively guarantee that the performance of the two-end model meets the standard, but the transmission of the model is relatively complex for air interface transmission; and the two-end model is completely developed by one end, and the other end lacks the possibility of self-design and optimization.

[0132] In order to reduce the complexity of air interface transmission model, some technologies mention the way of independent training of two-end model. Specifically, taking the type3 training mode based on data set transmission (i.e., independent training mode) as an example, in this training mode, the network side and the terminal side can design their own models, and there is no behavior of sending the model from one end to the other end, but the process of sending the training data set from one end to the other end is involved. Hereinafter, the network side sending the training data set to the terminal side is taken as an example for description.

[0133] The network side first trains an overall AI model according to the type1 mode, for example, an AI encoder and a decoder. Unlike sending the AI encoder to the terminal side, the network side inputs the existing training data set into the AI encoder based on the trained AI encoder, and obtains the output of the AI encoder. As shown in FIG. 5, Vin is the existing training data set, and Vq is the output of the AI encoder. The network side sends Vin and Vq as the input and the true value of the training data to the terminal side. The terminal side trains an AI model based on Vin and the true value Vq, and obtains an AI model equivalent to the AI encoder trained by the network side after the training is completed. Therefore, the terminal side can use the self-trained AI encoder in combination with the AI decoder trained by the network side.

[0134] When the data set is transmitted, the network side can add some labels, for example, the identity (ID) or the association ID of the data set. These labels can be used to represent different network side additional conditions or terminal side additional conditions, wherein the additional conditions can include scene type, channel type, antenna parameter, beam pattern, terminal speed, etc. The terminal side can train different terminal side models according to different data set IDs or association IDs, and form different model IDs. Therefore, when the models of the two ends need to be docked, the docking can be realized through the interaction of the data set ID, the model ID, the association ID and the like.

[0135] The model training method can avoid model transmission over the air interface, and can ensure that the two ends are designed respectively. However, in the model docking process, it is difficult to ensure that the performance meets the requirements. For example, the terminal side trains a dockable model based on the data set transmitted by the network side, but the model may not be trained sufficiently. In this case, when the model of the network side is docked with the model of the terminal side, the performance may still be poor. In this case, it can be considered that the terminal side selects an inappropriate model to participate in the docking. Similarly, the same problem also exists for the single-end terminal side model. For example, the terminal side selects a terminal side model that is not trained sufficiently, and the performance of the single-end model after being accessed to the network may not meet the network requirements, that is, the single-end model selected is not suitable for the network.

[0136] In the current standard discussion, it is assumed that the performance of the dockable model meets the requirements. Even if the performance of the docked model is problematic, it is currently considered that the problem can be found through model monitoring and the model can be closed in the case of poor performance. In independent training, whether the model of a certain end (such as the terminal side) is trained sufficiently is actually not guaranteed. If the docking is performed first, and then the model is monitored and closed when the performance is found to not meet the requirements, resource waste and power consumption waste will be caused to a certain extent.

[0137] Therefore, embodiments of the present application provide a communication method, device and storage medium. In the method, pre-monitoring of the model is realized through pre-monitoring, a suitable model is selected for docking according to the pre-monitoring result (i.e., the first index below), an AI / ML model meeting the processing requirements is obtained, the processing performance of the AI / ML is improved, and resource and power consumption waste is reduced.

[0138] The communication method provided by the embodiments of the present application will be described in detail below with reference to FIG. 6. The method provided by the present application can be applied to the communication system shown in FIG. 1, but the embodiments of the present application are not limited thereto.

[0139] FIG. 6 is a schematic flowchart of a communication method 600 provided by an embodiment of the present application. In the flowchart shown in FIG. 6, the method is shown from the perspective of interaction between a terminal device and a network device, but the present application does not limit the execution subject of the method. For example, the terminal device in FIG. 6 can be replaced by a chip, a chip system, or a processor supporting the terminal device to implement the method, and can also be a logic module or software capable of implementing all or part of the functions of the terminal device. The network device in FIG. 6 can be replaced by a chip, a chip system, or a processor supporting the network device to implement the method, and can also be a logic module or software capable of implementing all or part of the functions of the network device.

[0140] As shown in FIG. 6, the method 600 can include S601-S605. Details of each step in the method 600 are described below.

[0141] S601, the network device processes the second data based on a first processing manner to obtain first data. In other words, the first data is obtained by the network device processing the second data based on the first processing manner.

[0142] Optionally, in a scenario where the network device is a sending end, the first processing manner can include at least one of the following: modulation, encoding, or other processing manners such as reference signal generation; in a scenario where the network device is a receiving end, the first processing manner can include: demodulation, decoding, or other processing manners such as channel estimation. The encoding and decoding can include channel encoding and channel decoding.

[0143] The reference signal can be a demodulation reference signal (DMRS), a channel state information-reference signal (CSI-RS), a sounding reference signal (SRS), a phase tracking reference signal (PTRS), a tracking reference signal (TRS), a positioning reference signal (PRS), a preamble, and can also be a reference signal for sensing; the corresponding estimation can include channel estimation, CSI state estimation, phase noise estimation, time-frequency offset estimation, position estimation, sensing target estimation, etc. In this application, the reference signal is taken as the DMRS for channel estimation, and the corresponding estimation is taken as the channel estimation. It can be understood that the processing manner and the flow involved in the reference signal and the estimation based on the reference signal in this application can also be applied to the above-mentioned other reference signals.

[0144] The first processing manner can be a processing manner corresponding to a module included in the conventional transceiver shown in FIG. 2, and can be considered as a non-AI processing manner. In the non-AI processing manner, modulation is implemented by a modulation module in the conventional transceiver, for example, constellation modulation such as quadrature phase shift keying (QPSK) or quadrature amplitude modulation (QAM) in LTE / NR; encoding is implemented by an encoding module in the conventional transceiver, for example, by a low-density parity-check code (LDPC) encoding, Polar encoding, Turbo encoding, or the like; and reference signal generation is implemented by a reference signal generation module in the conventional transceiver, for example, a reference signal generated based on an m-sequence, a gold sequence, a zadoff-chu (ZC) sequence, or the like.

[0145] Alternatively, the first processing manner is a processing manner corresponding to an AI module included in the AI transceiver shown in FIG. 3, and can be considered as an AI processing manner. In the AI processing manner, modulation is implemented by an AI modulation module in the AI transceiver, for example, modulated constellation symbols are no longer uniformly distributed; encoding is implemented by an AI encoding module in the AI transceiver, for example, channel encoding is determined by an AI model; and reference signal generation is implemented by an AI reference signal generation module in the AI transceiver, for example, a reference signal generated based on a sequence determined by an AI manner.

[0146] Therefore, the network device processing the second data based on the first processing manner to obtain the first data can include: obtaining the first data based on the second data and a second AI model. Specifically, the network device can input the second data into the second AI model, and the output obtained or the data processed based on the output is the first data. The second AI model can implement the function of one or more AI modules, which is not limited in the present application.

[0147] It should be noted that when the first processing manner is AI-based reference signal generation, the network device can not include processing of the second data (i.e., the network device can not perform S601), and in this case, the network device can determine the first data according to the reference signal generated by the second AI model. This is because, in this case, the estimated result corresponding to the second data needs to be determined in the process of transmitting and receiving the data, and cannot be processed in advance.

[0148] The first data in the present application can be referred to as pre-monitoring data, pre-testing data, or data for pre-monitoring / pre-testing, or other names, which are not limited in the present application. The second data can be referred to as the true value of the first data.

[0149] S602, the network device sends the first data to the terminal device. Correspondingly, the terminal device receives the first data from the network device.

[0150] Optionally, the first data can be carried in a broadcast message, such as a system information block (SIB) message, or can be carried in a multicast message or a unicast message. The present application does not limit this.

[0151] Optionally, the first data described above can be sent by the network device to which the neighbor cell of the network device belongs using a broadcast message.

[0152] Exemplarily, the first data can be carried in high-layer signaling, such as medium access control (MAC)-control element (CE), radio link control (RLC), packet data convergence protocol (PDCP), radio resource control (RRC), or non-access-stratum (NAS); or the first data can be carried in physical layer signaling, such as downlink control information (DCI).

[0153] Exemplarily, the first data can be carried in a physical layer channel, such as a physical downlink shared channel (PDSCH), a physical downlink control channel (PDCCH), or a physical broadcast channel (PBCH). After the first data is generated, the network device can map the first data in the corresponding physical layer channel and send it to the terminal device in a unicast, multicast or broadcast manner.

[0154] Optionally, the first data can be periodically sent, and the first data sent in each period can be the same or different. At this time, the first data does not refer to a specific data, but refers to a type of data.

[0155] If the first data is periodically sent, the network side can also indicate the terminal device of the sending period of the first data.

[0156] S603, the terminal device obtains third data based on the first data and the first AI model. In other words, the third data is obtained by the terminal device processing the first data through the first AI model.

[0157] In a scenario where the terminal device is a sending end, the first processing manner can include at least one of the following: modulation, coding, or other processing manners such as reference signal generation; in a scenario where the terminal device is a receiving end, the first processing manner can include: demodulation, decoding, or other processing manners such as channel estimation.

[0158] In the present application, the processing manner of the first AI model on the first data corresponds to the first processing manner. It can be understood that, when the first processing manner is modulation / coding / reference signal generation, the first AI model can be an AI demodulation / AI decoding / AI channel estimation module; or, when the first processing manner is one or more combinations of modulation, coding, and reference signal generation (for example, the first processing manner is modulation + coding), the first AI model can be a module of one or more combinations of AI demodulation, AI decoding, and AI channel estimation (for example, the first AI is an AI demodulation + decoding module).

[0159] In combination with the description of the first processing manner in S601, the processing manner of the first AI model on the first data corresponds to the first processing manner, including: the first AI model corresponds to the second AI model. For example, the second AI model is AI modulation, and the first AI model is AI demodulation; or, the second AI model is AI coding, and the first AI model is AI decoding; or, the second AI model is an AI reference signal generation model, and the first AI model is an AI channel estimation model.

[0160] It can be understood that the AI model in the present application can also be replaced by an AI function. The AI function can be understood as an AI feature, or a configuration capable of enabling an AI feature, such as an RRC configuration. Different AI use cases (such as AI transceiver, AI receiver, AI CSI feedback, AI beam management, AI positioning, etc.) can be considered as different AI features, and an RRC configuration capable of enabling an AI feature can be understood as an AI function, for example, a PDSCH configuration in an RRC configuration, if associated with AI, for example, a model ID, a data set ID, and an association ID are added, it can be considered that this PDSCH configuration corresponds to an AI function, and the AI function can realize AI reception of downlink. In the LCM framework of air interface AI, the AI function or the AI model can be considered as different LCM granularities, and the management granularity of the AI function is larger than that of the AI model. Under the management granularity of the AI model, the network device can specifically manage the AI model required to be used by the terminal device, and under the management granularity of the AI function, the network device only manages the AI function possessed by the terminal device, without further controlling the specific AI model. The same AI function can correspond to one or more AI models. Different AI models can be trained by different training data sets on the same neural network model structure or different neural network model structures, that is, the AI model is determined based on the training data set, for example, the training data set is the data before and after encoding, and then the AI model can be an AI encoding model or an AI decoding model, or the AI function corresponding to the AI model is encoding or decoding.

[0161] Optionally, the third data can be a result output by the first AI model after the terminal device inputs the first data to the first AI model, or a result further processed based on the result output by the first AI model.

[0162] S604, the terminal device determines a first index based on the third data and the second data.

[0163] Optionally, the second data can be determined based on a predefined manner, or can be indicated by the network side. The second data will be described in detail below, so it is not described here.

[0164] The first index is used to represent the correlation between the second data and the third data, or the error between the two. It can be understood that since the processing manner of the first AI model corresponds to the first processing manner, under the condition that the first AI model is fully trained, the third data obtained by the terminal device can be the same as the second data, or the error between the third data and the second data is small.

[0165] S605, in a case where the first index meets a target index, the terminal device sends first information to the network device, the first information being used for indicating the first AI model. Correspondingly, the network device receives the first information from the terminal device.

[0166] The target index can be a threshold value, and the target index can be related to the first processing manner. For example, the first processing manner is modulation and / or encoding, and the target index can be a threshold value related to one or more of a block error rate (BLER), a bit error rate (BER), a demodulation success rate, or a decoding success rate.

[0167] Specifically, the first processing manner is modulation and / or encoding, and the target index can include one or more of: a BLER in a first time period being less than or equal to a first value, a BER in the first time period being less than or equal to a second value, a demodulation success rate in the first time period being greater than or equal to a third value, or a decoding success rate in the first time period being greater than or equal to a fourth value.

[0168] Specifically, the first processing manner is reference signal generation, and the target index can be a normalized mean squared error (NMSE) between a channel estimation result and a real channel result in a first time period, and the number of times that the NMSE is less than or equal to a preset threshold value is a fifth value. The target index can also be an average NMSE or a maximum NMSE between the channel estimation result and the real channel result in the first time period, and the number of times that the average NMSE or the maximum NMSE is less than or equal to a sixth value.

[0169] The first time period can be replaced by a data amount N (N is a positive integer, and N can be indicated by the network device) of the first data received by the terminal device, or a receiving number N (which can be a total receiving number or a successful or failed receiving number) of the first data received by the terminal device.

[0170] Optionally, the first information can indicate the first AI model through identification information of the first AI model. For example, the identification information of the first AI model includes an ID of the first AI model, or an ID of a training data set corresponding to the first AI model, or an association ID.

[0171] Optionally, the first information can be carried in capability information of the terminal device, or in UE assistant information (UAI) or the like, or in uplink control information (UCI) signaling, or in RRC information (for example, in an RRC configuration / reconfiguration completion message), or in medium access control-control element (MAC-CE) information, or in a trigger event configured by the network side. The trigger event can be a switching-like event, and the first information can be carried in a switching report when the condition is met.

[0172] The trigger event configured by the network side can be sent through a broadcast message (for example, an SIB message). It can be understood that the network device can also carry UAI configuration in the broadcast message to configure the reporting of the first AI model. The trigger event configured by the network side can also be sent through a unicast or groupcast message (for example, RRC configuration information).

[0173] In the embodiments of the present application, after receiving the first data obtained by processing the second data through the first processing manner, the terminal device can process the first data through the first AI model to obtain third data. Since the manner selected by the terminal device for processing the first data corresponds to the first processing manner, the third data obtained by the terminal device is the same as the second data in terms of the expected target. However, since the first AI model is obtained through training, the third data obtained through the first AI model may not be the same as the second data. In the present application, the terminal device obtains the first index based on the second data corresponding to the first data (i.e., the true value corresponding to the first data) of the obtained third data, compares the first index with the target index, and reports the first AI model to the network device when the target index is met. This way can determine whether the model for docking meets the requirements before the model docking, thereby effectively avoiding the situation that the model performance cannot meet the requirements after the model docking is completed, effectively improving the success rate of the model docking, and meeting the processing requirements of the AI / ML model of the communication system.

[0174] Optionally, before S604, the method 600 further includes: the network device sends second information to the terminal device, the second information being used to indicate the target index. Correspondingly, the terminal device receives the second information from the network device.

[0175] The description of the target index can refer to the description in S605, which will not be repeated here.

[0176] Optionally, the second information can be carried in a broadcast message, a unicast message or a groupcast message. The second information can be sent simultaneously with the first data or separately. For example, the second information and the first data can be sent in the same broadcast message or in different broadcast messages.

[0177] Exemplarily, the second information can be carried in high layer signaling or physical layer signaling.

[0178] Optionally, the first processing manner is modulation and / or encoding, and the first index includes one or more of the following: BLER in the first time length, error BER, demodulation success rate in the first time length or decoding success rate in the first time length.

[0179] The demodulation success rate in the first time length refers to the number of consecutive demodulation successes of the terminal device in the first time length. The decoding success rate in the first time length refers to the number of consecutive decoding successes of the terminal device in the first time length.

[0180] Optionally, the first processing manner is reference signal generation, and the first index can be the number of times that the NMSE of the channel estimation result and the real channel result in the first time length is less than a preset threshold.

[0181] Optionally, the first processing manner is reference signal generation, and the first index can be the average NMSE or the maximum NMSE of the channel estimation result and the real channel result in the first time length.

[0182] It can be understood that the first index determined by the terminal device can be determined according to the type of the target index, and the type of the target index can include BLER, BER, decoding success rate, demodulation success rate or NMSE of the channel estimation result and the real channel result. For example, the target index is the BLER in the first time length less than or equal to the first value (i.e., the type of the target index is BLER), and the terminal device determines the first index as BLER.

[0183] Optionally, the second data can be determined by a predefined manner or indicated by the network side.

[0184] In a possible implementation, the second data is determined by a predefined manner.

[0185] Optionally, the second data is determined by a predefined manner, including: the second data is predefined, or the second data is one data indicated by the network side from a plurality of predefined data.

[0186] Design one, the second data can be a protocol pre-defined random sequence, such as an m sequence, a gold sequence, etc., which can be initialized based on known parameters such as a cell identity (ID), a slot number, a subframe number, or a frame number. That is, the terminal device can initialize the second data based on the cell ID of the cell currently located in, the slot number corresponding to the slot in which the first data is received, the subframe number, or the frame number, etc. Similarly, the network device can initialize the second data based on the cell ID of the cell currently located in by the terminal device, the slot number corresponding to the slot in which the first data is transmitted, the subframe number, or the frame number, etc.

[0187] Design two, the second parameter can be data in a standardized / agreed data set. At this time, the network device can further indicate the second data to the terminal device. For example, the network device can indicate the second data used to the terminal device through the identifier corresponding to the second data.

[0188] Design three, the second data can be a sequence generated by a data generator. At this time, the network device can further indicate the data generator and / or other information for generating random data such as a random seed to the terminal device.

[0189] The data generator can be protocol-defined or defined by the network side and the terminal side in an offline state. The data generator can be considered as a higher form of a random sequence formula, that is, a formula of a random sequence with a formula expression form can be considered as a data generator.

[0190] It can be understood that the data generator form can also be an AI model form, that is, data is generated through an AI model.

[0191] It can also be understood that the protocol pre-defined data generator or the data generator pre-defined by both ends in an offline state can be multiple, at which time the network side can indicate the currently used data generator to the terminal device through the identifier of the data generator.

[0192] Design four, the second data can be an estimated result of an agreed reference signal. That is, the terminal device can estimate according to the agreed reference signal, and take the estimated result as the second data. The estimation method can be a non-AI reference signal estimation method.

[0193] It should be noted that the true value based on the estimated result of the reference signal is usually difficult to agree in advance or obtain in advance. For example, in channel estimation, the true channel information is difficult to obtain, but in the case of meeting certain conditions, such as high signal-to-noise ratio and more wireless resources used by DMRS, the channel estimated by DMRS can be approximately equal to the true channel. Therefore, the network device can specify the estimated result of certain reference signal as the true value.

[0194] For example, the agreed reference signal can be a DMRS (located in a synchronization signal block (SSB)) of a physical broadcast channel (PBCH). At this time, the network device can further indicate to the terminal device a channel estimation result based on the agreed reference signal, which can be used as real channel information, i.e., the second data.

[0195] Based on this, the resource overhead for indicating the second data can be effectively saved.

[0196] It can be understood that the second data obtained through the above designs 1 to 4, if further processed by a pre-agreed processing manner between the network device and the terminal device, such as a predefined transformation, channel coding, etc., the data obtained can still be considered as predefined. At this time, the data processed by the pre-agreed processing manner can still be understood as the second data.

[0197] Another possible implementation, the second data is indicated by the network side. Illustratively, the second data can be carried in high layer signaling or physical layer signaling.

[0198] Illustratively, the second data can be carried in a physical layer channel, such as PDSCH, PDCCH, or PBCH.

[0199] Optionally, the network device can indicate the second data to the terminal device at the same time of sending the first data.

[0200] Optionally, before S603, the method 600 further includes: the network device sends third information to the terminal device, the third information being used to determine the first AI model. Correspondingly, the terminal device receives the third information from the network device.

[0201] Since the network side and the terminal side will determine the correspondence of the model in the model training process, the third information can indicate the first processing manner, so that the terminal device can determine the AI model corresponding to the first processing manner based on the third information. Specifically, the third information can indicate the second AI model. Similar to the first information, the third information can indicate the second AI model through identification information of the second AI model, the identification information of the second AI model including an ID of the second AI model, or an ID of a training data set corresponding to the second AI model, or an association ID.

[0202] Optionally, the third information can be carried in a broadcast message, a unicast message or a groupcast message. For example, the third information can be carried in high layer signaling or physical layer signaling.

[0203] Optionally, the third information can be transmitted simultaneously or separately with the first data, for example, the first data and the third information are carried in the same broadcast message or in different broadcast messages.

[0204] Optionally, before S601, the method 600 further includes: the network device transmits fourth information to the terminal device, the fourth information being used for indicating the physical resource carrying the first data. Correspondingly, the terminal device receives the fourth information from the network device.

[0205] The physical resource includes one or more of the following: time domain resource, frequency domain resource, or space domain resource.

[0206] Optionally, the fourth information can be carried in a broadcast message, a unicast message or a groupcast message. For example, the fourth information can be carried in high layer signaling or physical layer signaling.

[0207] It can be understood that the fourth information and the first data can be transmitted simultaneously or separately, which is not limited in the present application. For example, the fourth information and the first data are transmitted in the same broadcast message or in different broadcast messages.

[0208] Exemplarily, the fourth information includes a search space of a control channel corresponding to the first data. The search space can be understood as a time-frequency resource location corresponding to a group of control channels, for example, the search space can be associated with at least one control resource set (CORESET), and each CORESET corresponds to a group of time-frequency resources. The search space can be configured with a period, and the terminal device can periodically detect whether there is control channel information corresponding to the first data on the time-frequency resource corresponding to the associated CORESET.

[0209] Optionally, the fourth information can further include a scrambling manner and / or a scrambling identifier used for scrambling the control channel, for example, a radio network temporary identifier (RNTI) scrambling and / or a corresponding RNTI identifier, for checking after demodulating the control information, so as to determine whether the received information this time contains the first data.

[0210] Exemplarily, the physical resource carrying the first data can be indicated by control information in the control channel corresponding to the first data, for example, by DCI corresponding to the data channel carrying the first data.

[0211] Optionally, after S605, the method 600 further includes: the terminal device transmits fifth information to the network device, the fifth information being used for indicating the first index. Correspondingly, the network device receives the fifth information from the terminal device.

[0212] Optionally, the fifth information can be carried in the capability information of the terminal device, or in the UAI or other information, or in the UCI signaling, or in the RRC information (such as the RRC configuration / reconfiguration completion message), or in the MAC-CE information, or in the trigger event configured by the network side. It can be understood that the fifth information can be sent simultaneously with the first information, or separately. The present application does not limit this.

[0213] Optionally, after the network device receives the fifth information from the terminal device, the method 600 further includes: the network device sends the sixth information to the terminal device based on the first information, the sixth information being used to indicate the first AI model or the AI function. Correspondingly, the terminal device receives the sixth information from the network device; and based on the sixth information, selects the first AI model as the AI model interfaced with the first processing mode, or selects the AI function as the AI function interfaced with the first processing mode.

[0214] For example, the network device can indicate the first AI model or the AI function in the PDSCH configuration information, so that the terminal device knows that the first AI model can be used in the downlink data receiving process.

[0215] It can be understood that the terminal device can report multiple AI models through the first information, and multiple indicators corresponding to the multiple AI models can be reported through the fifth information. In this way, the network device can select an AI model corresponding to an indicator with a smaller target indication error based on the reported multiple indicators, and indicate the AI model to the terminal device as the AI model interfaced with the first processing mode.

[0216] Optionally, before S602, the method 600 further includes: the terminal device sends capability information to the network device, the capability information being used to indicate one or more of: the size of the data for pre-monitoring / pre-testing, the number of resources occupied by the data for pre-monitoring / pre-testing, the sending period of the data for pre-monitoring / pre-testing, whether to support pre-monitoring / pre-testing, or one or more AI models supporting pre-monitoring / pre-testing, the one or more AI models including the first AI model, the data for pre-monitoring / pre-testing including the first data and / or the second data. Correspondingly, the network device receives the capability information from the terminal device.

[0217] Based on this, the network device can send customized first data to different terminal devices according to the capability information of different terminal devices.

[0218] The method provided by the embodiments of the present application is described in detail below with reference to the embodiments shown in FIG. 6 in combination with FIG. 7 and FIG. 8. It should be noted that the steps in the embodiments shown in FIG. 7 and FIG. 8 that are the same as or similar to the steps in the embodiments shown in FIG. 6 can be referred to the relevant description of the method 600 above, and will not be described herein again.

[0219] The method provided by the embodiments of the present application is described in detail below with reference to the embodiments shown in FIG. 6 in combination with FIG. 7 and FIG. 8. It should be noted that the steps in the embodiments shown in FIG. 7 and FIG. 8 that are the same as or similar to the steps in the embodiments shown in FIG. 6 can be referred to the relevant description of the method 600 above, and will not be described herein again.

[0220] FIG. 7 is a schematic flowchart of another communication method provided by the embodiments of the present application. As shown in FIG. 7, the method 700 includes S701-S708. The steps in the method 700 are described in detail below.

[0221] S701, the network device sends a first configuration to the terminal device, the first configuration including at least one of the second information, the third information and the fourth information described above. Correspondingly, the terminal device receives the first configuration from the network device.

[0222] Optionally, the first configuration can further include information for indicating the second data.

[0223] Optionally, the first configuration can be periodically sent. The period of sending the first configuration can be carried in a broadcast message, and the broadcast message can be different from the broadcast message carrying the first configuration. For example, the first configuration is carried in a SIB message, and the period of sending the first configuration is carried in a MIB message.

[0224] S702, the network device obtains the first data based on the second data and the second AI model.

[0225] Taking the second AI model as an AI modulation for example, the second data can be data that has been channel encoded in a non-AI manner (such as low density parity check code (LDPC) encoding / polar encoding), and the first data is AI-modulated data generated by the second AI model of the network device.

[0226] S703, the network device sends the first data to the terminal device. Correspondingly, the terminal device receives the first data from the network device.

[0227] S704, the terminal device obtains at least one third data based on the first data and at least one AI model.

[0228] The at least one AI model includes the first AI model. The at least one AI model corresponds to a second AI model. That is, the terminal device includes at least one AI model corresponding to the second AI model.

[0229] Taking the first AI model as AI demodulation, the third data can be data after AI demodulation.

[0230] At S705, the terminal device obtains at least one index based on the second data and the at least one third data. The at least one index corresponds to the at least one third data one by one, the at least one third data corresponds to the at least one AI model one by one, and thus the at least one index corresponds to the at least one AI model one by one.

[0231] Since the at least one AI model includes the first AI model, the at least one index includes the first index.

[0232] Taking the first AI model as AI demodulation, the terminal device can generate the second data based on a predefined manner, for example, through the manner described in Design 1, generate a predefined random sequence, and then further perform known channel coding on the random sequence to generate the second data.

[0233] The relevant information of the known channel coding, such as code rate, can be determined through DCI information corresponding to the first data. The index can be BER obtained by N (N is a positive integer) third data and the second data. At this time, based on the N third data and the second data, N BERs or a total BER can be calculated.

[0234] At S706, in a case where one or more indexes in the at least one index satisfy a target index, the terminal device sends first information to the network device, the first information being used to indicate one or more AI models. The one or more AI models correspond to the one or more indexes one by one. Correspondingly, the network device receives the first information from the terminal device.

[0235] The one or more indexes include the first index, and the one or more AI models include the first AI model.

[0236] Taking the first AI model as AI demodulation, the index as BER, and the target index as a BER threshold, for example, when the total BER is lower than the BER threshold, the terminal device sends the first information.

[0237] At S707, the terminal device sends fifth information to the network device, the fifth information being used to indicate the one or more indexes. Correspondingly, the network device receives the fifth information from the terminal device.

[0238] Optionally, in a case where the number of the one or more indicators is 1, S707 can not be performed.

[0239] Taking the first AI model as an AI demodulation, the indicator as a BER, and the target indicator as a BER threshold as an example, when the BER is lower than the BER threshold, the terminal device sends the overall BER calculated based on the N third data and the second data.

[0240] S708, the network device sends sixth information to the terminal device, and the sixth information is used to indicate the first AI model.

[0241] The first indicator corresponding to the first AI model can be one of the one or more indicators with a smaller difference from the target indicator.

[0242] It should be noted that the sixth information needs to be sent only when the network device needs the terminal device to use the first AI model, and therefore S708 is an optional step.

[0243] The embodiments of the present application can enable the terminal device to determine that the AI model available for docking of the terminal device can meet the performance requirements of the network side before reporting the AI model information to the network side, which can effectively avoid the situation that the model performance cannot meet the requirements after the model docking is completed. Moreover, the first data is sent through the broadcast message, which can enable the terminal device to autonomously determine and select the AI model meeting the requirements of the network side.

[0244] In a possible scenario, the serving cell notifies the pre-monitoring information of the neighboring cell (i.e., the first configuration in method 800), so that the terminal device obtains the related pre-monitoring information sent by the neighboring cell through the broadcast message, and then the terminal device can complete the pre-monitoring required by the neighboring cell in the serving cell in advance. The pre-monitoring configuration information of the neighboring cell is sent by the serving cell.

[0245] The method provided by the present application is described in detail below with reference to FIG. 8 taking the example that the neighboring cell sends the pre-monitoring information through the broadcast message. It can be understood that the terminal device can be in the connected state when the pre-monitoring information is sent through the broadcast message.

[0246] FIG. 8 is a schematic flowchart of another communication method provided by an embodiment of the present application. As shown in FIG. 8, the method 800 includes S801 to S808. The steps in method 800 are described in detail below.

[0247] S801, the serving cell of the network device sends a first configuration to the terminal device, and the first configuration includes at least one of the second information, the third information, and the fourth information. Correspondingly, the terminal device receives the first configuration from the network device.

[0248] Optionally, the first configuration can be carried in a switching measurement configuration in an RRC configuration message. Other descriptions about the first configuration can refer to the description in S701, which will not be repeated here.

[0249] The difference between S801 and S701 is that the first configuration in S701 is related to the pre-monitoring information of the serving cell, and the first configuration in S801 is related to the pre-monitoring information of the neighboring cell.

[0250] S802, the neighboring cell of the network device obtains the first data based on the second data and the second AI model.

[0251] Taking the generation of the AI DMRS based on the second AI model as an example, the first data includes the AI DMRS generated by the second AI model of the network device and the non-AI DMRS on the PBCH. It should be noted that in this case, the second data is the estimated result of the agreed non-AI DMRS on the PBCH, which can be determined only after channel estimation on the PBCH DMRS.

[0252] S803, the neighboring cell of the network device sends the first data to the terminal device. Correspondingly, the terminal device receives the first data from the network device.

[0253] S804, the terminal device obtains at least one third data based on the first data and at least one AI model.

[0254] The at least one AI model herein includes the first AI model described above. The at least one AI model corresponds to the second AI model. That is, the terminal device side includes at least one AI model corresponding to the second AI model.

[0255] Taking the AI channel estimation based on the first AI model as an example, the third data can be the channel estimation information obtained by processing the AI DMRS in the first data by the first AI model.

[0256] S805, the terminal device obtains at least one index based on the second data and the at least one third data.

[0257] The at least one index corresponds to the at least one third data one by one, the at least one third data corresponds to the at least one AI model one by one, and therefore the at least one index corresponds to the at least one AI model one by one.

[0258] Since the at least one AI model includes the first AI model, the at least one index includes the first index.

[0259] Taking the first AI model as an example of AI channel estimation, the terminal device can perform non-AI channel estimation based on the DMRS on the non-AI PBCH in the first data to obtain a channel estimation result as the second data. The indicator can be a normalized mean square error (NMSE) of the N third data and the second data. At this time, based on the N third data and the second data, the average NMSE can be calculated.

[0260] S806, in a case where one or more indicators in the at least one indicator meet the target indicator, the terminal device sends first information to a serving cell of the network device, the first information being used to indicate one or more AI models. The one or more AI models correspond to the one or more indicators in a one-to-one manner. Correspondingly, the network device receives the first information from the terminal device.

[0261] The one or more indicators include a first indicator, and the one or more AI models include a first AI model.

[0262] Taking the first AI model as an example of AI channel estimation, the indicator is NMSE, and the target indicator is an NMSE threshold. When the average NMSE is lower than the NMSE threshold, the terminal device sends the first information.

[0263] S807, the terminal device sends fifth information to the network device, the fifth information being used to indicate the one or more indicators. Correspondingly, the network device receives the fifth information from the terminal device.

[0264] Optionally, in a case where the number of the one or more indicators is 1, S807 can not be performed.

[0265] Taking the first AI model as an example of AI channel estimation, the indicator is NMSE, and the target indicator is an NMSE threshold. When the average NMSE is lower than the NMSE threshold, the terminal device sends the NMSE calculated based on the N third data and the second data.

[0266] After S806 or S807, the terminal device switches from the serving cell to a neighbor cell. After the switching is completed, the network device continues to perform S808.

[0267] It can be understood that before or during the switching, the serving cell of the network device can send the one or more AI models to the neighbor cell; optionally, the serving cell of the network device can send the one or more indicators to the neighbor cell.

[0268] S808, the neighbor cell of the network device sends sixth information to the terminal device, the sixth information being used to indicate the first AI model.

[0269] The first indicator corresponding to the first AI model can be one of the one or more indicators that has a smaller difference from the target indicator.

[0270] It is to be noted that the sixth information needs to be sent only when the neighboring cell of the network device requires the terminal device to use the first AI model, and thus S808 is an optional step.

[0271] The embodiments of the present application can enable the terminal device to determine the AI model that can meet the requirements of the neighboring cell in advance, and thus can effectively reduce the latency required for selecting / determining the AI model that meets the performance requirements.

[0272] The method provided by the embodiments of the present application is described in detail above in combination with FIGS. 1 to 8, and the apparatus provided by the embodiments of the present application is described in detail below in combination with FIGS. 9 and 10.

[0273] FIGS. 9 and 10 are schematic diagrams of possible apparatuses provided by the embodiments of the present application. These apparatuses can be used to implement the functions of the terminal device or the network device in the above method embodiments, and thus can also achieve the beneficial effects possessed by the above method embodiments.

[0274] FIG. 9 is a schematic block diagram of an apparatus provided by the embodiments of the present application. As shown in FIG. 9, the apparatus 900 includes a transceiver module 910 and a processing module 920.

[0275] A possible design is that the apparatus 900 is used to implement the functions of the terminal device in the above method embodiments shown in FIGS. 6 to 8.

[0276] Exemplarily, the transceiver module 910 is configured to receive first data, the first data being obtained by processing second data through a first processing manner, the first processing manner including at least one of modulation, encoding, or reference signal generation; the processing module 920 is configured to obtain third data based on the first data and a first AI model, the first AI model corresponding to the first processing manner; and determine a first index based on the third data and the second data; and the transceiver module 910 is further configured to send first information in a case where the first index meets a target index, the first information being used to indicate the first AI model.

[0277] Optionally, the transceiver module 910 is further configured to receive second information, the second information being used to indicate the target index.

[0278] Optionally, the transceiver module 910 is further configured to receive third information, the third information being used to determine the first AI model.

[0279] Optionally, the transceiver module 910 is further configured to receive fourth information, the fourth information being used to indicate a physical resource carrying the first data, the physical resource including one or more of a time domain resource, a frequency domain resource, or a space domain resource.

[0280] Optionally, the transceiver 910 is further configured to send fifth information, where the fifth information is used to indicate the first indicator.

[0281] Optionally, the transceiver 910 is further configured to send capability information, where the capability information is used to indicate one or more of: a size of a data amount for pre-monitoring, a number of resources occupied by the data for pre-monitoring, a transmission period of the data for pre-monitoring, whether pre-monitoring is supported, or one or more AI models supporting pre-monitoring, the one or more AI models including the first AI model, and the data for pre-monitoring including the first data and / or the second data.

[0282] More detailed descriptions of the transceiver 910 and the processing module 920 can be directly obtained by referring to the descriptions of the embodiments shown in FIGS. 6-8, which will not be repeated here.

[0283] Another possible design is that the apparatus 900 is configured to implement the functions of the network device in the method embodiments shown in FIGS. 6-8.

[0284] Optionally, the processing module 920 is configured to process the second data based on a first processing manner to obtain the first data, where the first processing manner includes at least one of: modulation, encoding, or reference signal generation; the transceiver 910 is configured to send the first data; and the transceiver 910 is configured to receive first information, where the first information is used to indicate the first AI model.

[0285] Optionally, the transceiver 910 is further configured to send second information, where the second information is used to indicate the target indicator.

[0286] Optionally, the transceiver 910 is further configured to send third information, where the third information is used to determine the first AI model.

[0287] Optionally, the transceiver 910 is further configured to send fourth information, where the fourth information is used to indicate physical resources carrying the first data, and the physical resources include one or more of: time domain resources, frequency domain resources, or space domain resources.

[0288] Optionally, the transceiver 910 is further configured to receive fifth information, where the fifth information is used to indicate the first indicator.

[0289] Optionally, the transceiver 910 is further configured to receive capability information, the capability information being used to indicate one or more of a size of a data amount for pre-monitoring, a number of resources occupied by the data for pre-monitoring, a transmission period of the data for pre-monitoring, whether pre-monitoring is supported, or one or more AI models supporting pre-monitoring, the one or more AI models including the first AI model, and the data for pre-monitoring including the first data and / or the second data.

[0290] Optionally, the processing module 920 is specifically configured to obtain the second data based on the second data and a second AI model, the first AI model corresponding to the second AI model.

[0291] More detailed descriptions of the transceiver 910 and the processing module 920 can be directly obtained by referring to the related descriptions in the embodiments shown in FIGS. 6-8, which will not be repeated here.

[0292] It should be noted that the apparatus 900 can include a sending module but not a receiving module. Alternatively, the apparatus 900 can include a receiving module but not a sending module. Specifically, whether the apparatus 900 includes a sending action and a receiving action in the above-mentioned schemes can be determined. It can be understood that, since the apparatus 900 has a communication function, it can also be referred to as a communication apparatus.

[0293] FIG. 10 is another schematic block diagram of an apparatus according to an embodiment of the present application. As shown in FIG. 10, the apparatus 1000 includes one or more processors 1010. The processor 1010 can be a general-purpose processor or a special-purpose processor, etc. For example, it can be a baseband processor or a central processing unit. The baseband processor can be used to process a communication protocol and communication data, and the central processing unit can be used to control the apparatus (e.g., a terminal device, a network device, or a chip, etc.), execute a software program, and process data of the software program.

[0294] Optionally, in one design, the processor 1010 can include a program (which can also be referred to as code or instructions) that can be run on the processor 1010, so that the apparatus 1000 performs the method performed by the terminal device or the network device in the above method embodiments. In another possible design, the apparatus 1000 includes a circuit (not shown in FIG. 10) for implementing the functions of the terminal device or the network device in the above method embodiments.

[0295] For example, the processor 1010 can be used to execute a computer program or instructions in the memory to implement the steps performed by the terminal device or the network device in the method embodiments shown in any one of the embodiments shown in FIGS. 6-8.

[0296] Optionally, one or more memories 1020 can be included in the apparatus 1000, on which programs (sometimes also referred to as codes or instructions) are stored, which can be run on the processor 1010, so that the apparatus 1000 performs the method performed by the terminal device or the network device in the above embodiments.

[0297] Optionally, an artificial intelligence (AI) module can be included in the processor 1010 and / or the memory 1020, which is used to implement AI-related functions. The AI module can be implemented in software, hardware, or a combination of software and hardware. For example, the AI module can include a radio intelligent controller (RIC) module. For example, the AI module can be a near-real-time RIC or a non-real-time RIC.

[0298] Optionally, data can also be stored in the processor 1010 and / or the memory 1020. The processor and the memory can be separately arranged or integrated together.

[0299] Optionally, the apparatus 1000 can also include a communication interface 1030. The processor 1010 can also be referred to as a processing unit, which controls the apparatus (such as a terminal device or a network device). The communication interface 1030 can also be referred to as a transceiver unit, a transceiver, a transceiver circuit, or a transceiver, which is used to implement the transceiving function of the apparatus.

[0300] Optionally, the apparatus 1000 also includes a communication interface 1030. The processor 1010 and the communication interface 1030 are coupled to each other. It can be understood that the communication interface 1030 can be a transceiver or an input / output interface.

[0301] It can be understood that since the apparatus 1000 has a communication function, it can also be referred to as a communication apparatus.

[0302] When the apparatus 1000 is used to implement the method of FIGS. 6 to 8, the processor 1010 is used to perform the functions of the above processing unit, and the communication interface 1030 is used to perform the functions of the above transceiver module. Whether the communication interface 1030 is used for transmission or reception can be determined according to whether the apparatus 1000 performs a transmission action or a reception action in the scheme.

[0303] When the apparatus 1000 is a chip applied to a terminal device, the chip implements the functions of the terminal device in the method embodiments. The chip of the terminal device receives a signal from other modules (such as a radio frequency module or an antenna) in the terminal device, and the signal can be sent by a network device to the terminal device. Alternatively, the chip of the terminal device sends a signal to other modules (such as a radio frequency module or an antenna) in the terminal device, and the signal can be sent by the terminal device to the network device.

[0304] When the apparatus 1000 is a chip applied to a network device, the chip implements the functions of the network device in the method embodiments. The chip of the network device receives a signal from other modules (such as a radio frequency module or an antenna) in the network device, and the signal can be sent by a terminal device to the network device. Alternatively, the chip of the network device sends a signal to other modules (such as a radio frequency module or an antenna) in the network device, and the signal can be sent by the network device to the terminal device.

[0305] It can be understood that when the apparatus 1000 is a terminal device or a network device, the communication interface 1030 can be a transceiver, which can specifically include a transmitter and a receiver. The transmitter is configured to send a signal, and the receiver is configured to receive a signal. When the apparatus 1000 is a chip applied to a terminal device or a network device, the communication interface 1030 can be an input / output circuit. The input circuit can be used for receiving, and the output interface can be used for sending.

[0306] It should be noted that the method embodiments described above can be applied to a processor or implemented by a processor. The processor can be an integrated circuit chip having a signal processing capability. In the implementation process, each step of the method embodiments described above can be completed by an integrated logic circuit or an instruction in the form of software in the processor.

[0307] The processor described above can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or any combination thereof. The general processor can be a microprocessor, or any conventional processor, etc.

[0308] The steps of the method disclosed in the embodiments of the present application can be directly embodied as hardware code processing executed by a processor, or a combination of hardware and software modules in the code processing. The software module can be located in a storage medium such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, register, or the like. The storage medium is located in the storage, and the processor reads information in the storage and combines hardware to complete the steps of the above method.

[0309] The memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM). It should be noted that the memory of the system and method described herein is intended to include, but not limited to, these and any other suitable types of memory.

[0310] The method provided by the above embodiments can be implemented by software, hardware, firmware, or any combination thereof, in whole or in part. When implemented by software, the method can be implemented in whole or in part in the form of a computer program product. The computer program product can include one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. 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 computer-readable storage medium, 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 a wired (such as coaxial cable, optical fiber, digital subscriber (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic disk), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0311] The present application also provides a computer program product, which, when running on a processor, can implement the method shown in the above method embodiments.

[0312] The present application also provides a computer-readable storage medium, which includes computer instructions, and the computer instructions, when running on a processor, can implement the method shown in the above method embodiments.

[0313] The present application also provides a communication system, the terminal device and the network device.

[0314] Those skilled in the art can understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0315] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0316] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0317] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments.

[0318] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0319] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk.

[0320] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: The method comprises: receiving first data, the first data being obtained by processing second data through a first processing manner, the first processing manner comprising at least one of modulation, encoding, or reference signal generation; obtaining third data based on the first data and a first artificial intelligence (AI) model, the first AI model corresponding to the first processing manner; determining a first index based on the third data and the second data; in a case where the first index meets a target index, sending first information, the first information being used for indicating the first AI model.

2. The method of claim 1, wherein, The method further comprises: receiving second information, the second information being used for indicating the target index.

3. The method according to claim 1 or 2, characterized in that, The first processing manner is modulation and / or encoding, and the first index comprises one or more of a block error rate (BLER) within a first time length, a bit error rate (BER), a success rate of demodulation within the first time length, or a success rate of decoding within the first time length.

4. The method according to any one of claims 1 to 3, characterized in that, The second data is determined through a predefined manner or is indicated by a network side.

5. The method according to any one of claims 1 to 4, characterized in that, The method further comprises: receiving third information, the third information being used for determining the first AI model.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: receiving fourth information, the fourth information being used for indicating physical resources carrying the first data, the physical resources comprising one or more of time domain resources, frequency domain resources, or space domain resources.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: sending fifth information, the fifth information being used for indicating the first index.

8. The method according to any one of claims 1 to 7, characterized in that, The method further comprises: sending capability information, the capability information being used for indicating one or more of a size of data used for pre-monitoring, a number of resources occupied by the data used for pre-monitoring, a transmission period of the data used for pre-monitoring, whether pre-monitoring is supported, or one or more AI models supporting pre-monitoring, the one or more AI models comprising the first AI model, and the data used for pre-monitoring comprising the first data and / or the second data.

9. The method according to any one of claims 1 to 8, characterized in that, The first data is obtained by processing the second data through the first processing manner, comprising: The first data is obtained based on the second data and a second AI model, the first AI model corresponding to the second AI model.

10. The method according to any one of claims 1 to 9, characterized in that, The first data is carried in a broadcast message, a unicast message, or a groupcast message.

11. A communication method, comprising: The method comprises: processing second data through a first processing manner to obtain first data, the first processing manner comprising at least one of modulation, encoding, or reference signal generation; sending the first data; receiving first information, the first information being used for indicating a first artificial intelligence (AI) model.

12. The method of claim 11, wherein, The method further comprises: sending second information, the second information being used for indicating a target index.

13. The method according to claim 11 or 12, characterized in that, The second data is determined through a predefined manner.

14. The method according to any one of claims 11 to 13, characterized in that, The method further comprises: sending third information, the third information being used for determining the first AI model.

15. The method according to any one of claims 11 to 14, characterized in that, The method further comprises: sending fourth information, the fourth information being used for indicating physical resources carrying the first data, the physical resources comprising one or more of time domain resources, frequency domain resources, or space domain resources.

16. The method according to any one of claims 11 to 15, characterized in that, The method further comprises: receiving fifth information, the fifth information being used for indicating a first index.

17. The method of claim 16, wherein, The first processing manner is modulation and / or encoding, and the first index comprises one or more of the following: a block error rate (BLER) in a first time length, a bit error rate (BER), a success rate of demodulation in the first time length, or a success rate of decoding in the first time length.

18. The method according to any one of claims 11 to 17, characterized in that, The method further comprises: receiving capability information, the capability information being used to indicate one or more of the following: a size of a data amount for pre-monitoring, a number of resources occupied by the data for pre-monitoring, a transmission period of the data for pre-monitoring, whether pre-monitoring is supported, or one or more AI models supporting pre-monitoring, the one or more AI models comprising the first AI model, and the data for pre-monitoring comprising the first data and / or the second data.

19. The method according to any one of claims 11 to 18, characterized in that, The processing of the second data based on the first processing manner to obtain the first data comprises: obtaining the second data based on the second data and a second AI model, the first AI model and the second AI model corresponding to each other.

20. The method of any one of claims 11 to 19, wherein, The first data is carried in a broadcast message, a unicast message, or a groupcast message.

21. A communications device, characterized by The method comprises a module for implementing the method of any one of claims 1 to 10; or a module for implementing the method of any one of claims 11 to 20.

22. A communications device, characterized by The communication device comprises a processor for enabling the communication device to implement the method of any one of claims 1 to 10 by executing a computer program and / or by a logic circuit; or for enabling the communication device to implement the method of any one of claims 11 to 20.

23. A computer-readable storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor, and the method of any one of claims 1 to 10 is executed; or the method of any one of claims 11 to 20 is executed.

24. A computer program product, characterised in that, The computer program is executed by the processor, and the method of any one of claims 1 to 10 is executed; or the method of any one of claims 11 to 20 is executed.

Images