WO2023184452A1 - 终端设备使用的模型的确定方法和装置 - Google Patents

终端设备使用的模型的确定方法和装置 Download PDF

Info

Publication number
WO2023184452A1
WO2023184452A1 PCT/CN2022/084687 CN2022084687W WO2023184452A1 WO 2023184452 A1 WO2023184452 A1 WO 2023184452A1 CN 2022084687 W CN2022084687 W CN 2022084687W WO 2023184452 A1 WO2023184452 A1 WO 2023184452A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
terminal device
indication information
access network
parameter
Prior art date
Application number
PCT/CN2022/084687
Other languages
English (en)
French (fr)
Inventor
朱亚军
Original Assignee
北京小米移动软件有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京小米移动软件有限公司 filed Critical 北京小米移动软件有限公司
Priority to CN202280000814.8A priority Critical patent/CN117178579A/zh
Priority to PCT/CN2022/084687 priority patent/WO2023184452A1/zh
Publication of WO2023184452A1 publication Critical patent/WO2023184452A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W8/00—Network data management
    • H04W8/22—Processing or transfer of terminal data, e.g. status or physical capabilities

Definitions

  • the present disclosure relates to the field of communication technology, and in particular, to a method and device for determining a model used by a terminal device.
  • AI Artificial Intelligence, artificial intelligence
  • Terminal devices can use AI models for performance prediction. For example: in the application of AI models and beam management, The terminal device can use the AI model to predict the best beam to use in the future, without the need for the terminal device to continuously perform beam measurements, which can reduce the complexity of the terminal device measurement and reduce signaling overhead.
  • Embodiments of the present disclosure provide a method and device for determining a model used by a terminal device.
  • the terminal device can determine a target model according to the model indication information of the access network device, enabling the terminal device to use different AI models, which can improve the performance of the terminal device.
  • embodiments of the present disclosure provide a method for determining a model used by a terminal device.
  • the method is executed by the terminal device.
  • the method includes: receiving model indication information sent by the access network device; determining the model based on the model indication information. Describes the target model used by the terminal device.
  • the model indication information sent by the access network device is received, and the target model used by the terminal device is determined based on the model indication information. Therefore, the terminal device can determine to use different AI models, which can improve the performance of the terminal device.
  • embodiments of the present disclosure provide another method for determining a model used by a terminal device.
  • the method is executed by an access network device.
  • the method includes: sending model indication information to the terminal device; wherein the model indication information is To indicate the target model used by the terminal device.
  • embodiments of the present disclosure provide a communication device that has some or all of the functions of the terminal device for implementing the method described in the first aspect.
  • the functions of the communication device may have some or all of the functions of the present disclosure.
  • the functions in the embodiments may also be used to independently implement any of the embodiments of the present disclosure.
  • the functions described can be implemented by hardware, or can be implemented by hardware executing corresponding software.
  • the hardware or software includes one or more units or modules corresponding to the above functions.
  • the structure of the communication device may include a transceiver module and a processing module, and the processing module is configured to support the communication device to perform corresponding functions in the above method.
  • the transceiver module is used to support communication between the communication device and other devices.
  • the communication device may further include a storage module coupled to the transceiver module and the processing module, which stores necessary computer programs and data for the communication device.
  • the processing module may be a processor
  • the transceiver module may be a transceiver or a communication interface
  • the storage module may be a memory
  • the communication device includes: a transceiver module, configured to receive model indication information sent by an access network device; and a processing module, configured to determine a target model used by the terminal device based on the model indication information.
  • embodiments of the present disclosure provide another communication device that has some or all of the functions of the network device in the method example described in the second aspect.
  • the functions of the communication device may have some of the functions in the present disclosure.
  • the functions in all the embodiments may also be provided to implement the functions of any one embodiment in the present disclosure independently.
  • the functions described can be implemented by hardware, or can be implemented by hardware executing corresponding software.
  • the hardware or software includes one or more units or modules corresponding to the above functions.
  • the structure of the communication device may include a transceiver module and a processing module, and the processing module is configured to support the communication device to perform corresponding functions in the above method.
  • the transceiver module is used to support communication between the communication device and other devices.
  • the communication device may further include a storage module coupled to the transceiver module and the processing module, which stores necessary computer programs and data for the communication device.
  • the communication device includes: a transceiver module, configured to send model indication information to a terminal device; wherein the model indication information is used to indicate a target model used by the terminal device.
  • an embodiment of the present disclosure provides a communication device.
  • the communication device includes a processor.
  • the processor calls a computer program in a memory, it executes the method described in the first aspect.
  • an embodiment of the present disclosure provides a communication device.
  • the communication device includes a processor.
  • the processor calls a computer program in a memory, it executes the method described in the second aspect.
  • an embodiment of the present disclosure provides a communication device.
  • the communication device includes a processor and a memory, and a computer program is stored in the memory; the processor executes the computer program stored in the memory, so that the communication device executes The method described in the first aspect above.
  • an embodiment of the present disclosure provides a communication device.
  • the communication device includes a processor and a memory, and a computer program is stored in the memory; the processor executes the computer program stored in the memory, so that the communication device executes The method described in the second aspect above.
  • an embodiment of the present disclosure provides a communication device.
  • the device includes a processor and an interface circuit.
  • the interface circuit is used to receive code instructions and transmit them to the processor.
  • the processor is used to run the code instructions to cause the The device performs the method described in the first aspect.
  • an embodiment of the present disclosure provides a communication device.
  • the device includes a processor and an interface circuit.
  • the interface circuit is used to receive code instructions and transmit them to the processor.
  • the processor is used to run the code instructions to cause the The device performs the method described in the second aspect above.
  • an embodiment of the present disclosure provides a communication system, which includes the communication device described in the third aspect and the communication device described in the fourth aspect, or the system includes the communication device described in the fifth aspect and The communication device according to the sixth aspect, or the system includes the communication device according to the seventh aspect and the communication device according to the eighth aspect, or the system includes the communication device according to the ninth aspect and the communication device according to the tenth aspect. the above-mentioned communication device.
  • embodiments of the present invention provide a computer-readable storage medium for storing instructions used by the above-mentioned terminal equipment. When the instructions are executed, the terminal equipment is caused to execute the above-mentioned first aspect. method.
  • embodiments of the present invention provide a readable storage medium for storing instructions used by the access network equipment. When the instructions are executed, the access network equipment is caused to execute the second aspect. the method described.
  • the present disclosure also provides a computer program product including a computer program, which when run on a computer causes the computer to execute the method described in the first aspect.
  • the present disclosure also provides a computer program product including a computer program, which, when run on a computer, causes the computer to execute the method described in the second aspect.
  • the present disclosure provides a chip system, which includes at least one processor and an interface for supporting a terminal device to implement the functions involved in the first aspect, for example, determining or processing data involved in the above method. and information.
  • the chip system further includes a memory, and the memory is used to store necessary computer programs and data for the terminal device.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • the present disclosure provides a chip system.
  • the chip system includes at least one processor and an interface for supporting the access network device to implement the functions involved in the second aspect, for example, determining or processing the functions involved in the above method. at least one of data and information.
  • the chip system further includes a memory, and the memory is used to store necessary computer programs and data for the access network equipment.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • the present disclosure provides a computer program that, when run on a computer, causes the computer to execute the method described in the first aspect.
  • the present disclosure provides a computer program that, when run on a computer, causes the computer to perform the method described in the second aspect.
  • Figure 1 is an architectural diagram of a communication system provided by an embodiment of the present disclosure
  • Figure 2 is a flow chart of a method for determining a model used by a terminal device provided by an embodiment of the present disclosure
  • Figure 3 is a flow chart of another method for determining a model used by a terminal device provided by an embodiment of the present disclosure
  • Figure 4 is a flow chart of yet another method for determining a model used by a terminal device provided by an embodiment of the present disclosure
  • Figure 5 is a flow chart of yet another method for determining a model used by a terminal device provided by an embodiment of the present disclosure
  • Figure 6 is a structural diagram of a communication device provided by an embodiment of the present disclosure.
  • Figure 7 is a structural diagram of another communication device provided by an embodiment of the present disclosure.
  • FIG. 8 is a schematic structural diagram of a chip provided by an embodiment of the present disclosure.
  • Figure 1 is a schematic diagram of a communication system provided by an embodiment of the present disclosure.
  • the communication system may include access network equipment, multiple terminal equipment, and core network equipment.
  • Access network equipment communicates with each other through wired or wireless means, for example, through the Xn interface in Figure 1.
  • Access network equipment can cover one or more cells.
  • access network equipment 1 covers cell 1.1 and cell 1.2
  • access network equipment 2 covers cell 2.1.
  • the terminal equipment can camp on the access network equipment in one of the cells and be in the connected state. Further, the terminal device can convert from the connected state to the inactive state through the RRC release process, that is, to the non-connected state.
  • the terminal device in the non-connected state can camp in the original cell, and perform uplink transmission and/or downlink transmission with the access network device in the original cell according to the transmission parameters of the terminal device in the original cell.
  • a terminal device in a non-connected state can also move to a new cell, and perform uplink transmission and/or downlink transmission with the access network device of the new cell according to the transmission parameters of the terminal device in the new cell.
  • Figure 1 is only an exemplary framework diagram, and the number of nodes, the number of cells and the status of the terminal included in Figure 1 are not limited.
  • other nodes may also be included, such as core network equipment, gateway equipment, application servers, etc., without limitation.
  • Access network equipment communicates with core network equipment through wired or wireless methods, such as through next generation (NG) interfaces.
  • NG next generation
  • the access network equipment is mainly used to implement at least one function of resource scheduling, radio resource management, and radio resource control of the terminal equipment.
  • the access network equipment may include any node among a base station, a wireless access point, a transmission reception point (TRP), a transmission point (TP), and some other access node.
  • the device for realizing the function of the access network device may be the access network device; it may also be a device that can support the access network device to realize the function, such as a chip system, and the device may be installed on the access network device.
  • the technical solution provided by the embodiments of the present disclosure is described by taking the device for realizing the functions of the access network equipment as an access network equipment as an example.
  • the core network device may include an AMF and/or a location management function network element.
  • the location management function network element includes a location server.
  • the location server can be implemented as any of the following: LMF (Location Management Function, location management network element), E-SMLC (Enhanced Serving Mobile Location Center, enhanced Service mobile location center), SUPL (Secure User Plane Location, secure user plane location), SUPL SLP (SUPL Location Platform, secure user plane location platform).
  • a terminal device is an entity on the user side that is used to receive or transmit signals, such as a mobile phone.
  • Terminal equipment can also be called terminal equipment (terminal), user equipment (user equipment, UE), mobile station (mobile station, MS), mobile terminal equipment (mobile terminal, MT), etc.
  • the terminal device can be a car with communication functions, a smart car, a mobile phone, a wearable device, a tablet computer (Pad), a computer with wireless transceiver functions, a virtual reality (VR) terminal device, an augmented reality (augmented reality (AR) terminal equipment, wireless terminal equipment in industrial control, wireless terminal equipment in self-driving, wireless terminal equipment in remote medical surgery, smart grid ( Wireless terminal equipment in smart grid, wireless terminal equipment in transportation safety, wireless terminal equipment in smart city, wireless terminal equipment in smart home, etc.
  • the embodiments of the present disclosure do not limit the specific technology and specific equipment form used by the terminal equipment.
  • the AMF network element is mainly responsible for the access authentication of terminal equipment, mobility management, signaling interaction between various functional network elements, etc., such as: user registration status, user connection status, user registration into the network, tracking area update, Cell switching user authentication and key security are managed.
  • the AIF network element is connected to the core network equipment (AMF network element) through a wired or wireless interface, and is mainly responsible for training artificial intelligence AI model parameters.
  • LTE long term evolution
  • 5th generation 5th generation
  • NR 5th generation new radio
  • side link in the embodiment of the present disclosure may also be called a side link or a through link.
  • the time unit may be a physical time unit or a logical time unit, for example, the unit is seconds, milliseconds, microseconds, frames, subframes, slots, mini-slots, Orthogonal frequency division multiplexing (OFDM) symbols, etc.
  • OFDM Orthogonal frequency division multiplexing
  • embodiments of the present disclosure provide a method and device for determining a model used by a terminal device, so as to at least solve the problems existing in related technologies.
  • FIG. 2 is a flow chart of a method for determining a model used by a terminal device provided by an embodiment of the present disclosure.
  • this method is applied to terminal equipment.
  • This method may include but is not limited to the following steps:
  • S21 Receive model indication information sent by the access network device.
  • artificial intelligence AI is a method of teaching the same things to computers. Artificial intelligence is the concept of imitating human abilities. Artificial intelligence can include a variety of models, such as machine learning models, deep learning models, federated learning models, etc. , each model also contains various sub-model types. For example, deep learning models include convolutional neural networks, recursive neural networks, etc. The model types here do not distinguish between models or sub-models.
  • the terminal device receives the model indication information sent by the access network device, where the model indication information may indicate information related to the model used by the terminal device.
  • the model indication information instructs the first terminal device to use a deep learning model, etc.
  • the model indication information indicates relevant parameters of the model used by the first terminal device, etc.
  • S22 Determine the target model used by the terminal device according to the model indication information.
  • the terminal device receives the model indication information sent by the access network device and can determine the target model used by the terminal device, where the model indication information can indicate relevant information of the model used by the terminal device.
  • the terminal device can determine that the target model used is a deep learning model.
  • the model pre-stored in the terminal device may be inherent to the terminal device, or predefined, or generated based on the model indication information last sent by the access network device, or obtained by training on the terminal device, or Obtained by joint training of terminal equipment and access network equipment.
  • the model indication information sent by the access network device instructs the first terminal device to use the parameter information of the deep learning model.
  • the terminal device receives the model indication information sent by the access network device and can use the deep learning model according to the model indication information. Carry out the initial configuration of the model based on the parameter information to obtain the deep learning model and serve it as the target model.
  • the model indication information includes model parameter information
  • the model parameter information includes at least one of the following:
  • the number of neuron nodes in each network layer is the number of neuron nodes in each network layer
  • the model indication information sent by the access network device to the terminal device includes model parameter information.
  • the model parameter information includes: model type parameters, the number of network layers, the number of neuron nodes in each network layer, and the number of neural nodes in each network layer.
  • the model type parameter is used to indicate the type of model used by the terminal device.
  • the terminal device can determine the target model to be used based on the model type parameter.
  • the number of network layers is used to indicate the number of network layers of the model used by the terminal device.
  • the terminal device can determine and select the corresponding number of network layers based on the number of network layers.
  • a combination of network layer structures is used as the target model.
  • the number of neuron nodes in each network layer is used to indicate the number of neuron nodes in each network layer of the model used by the terminal device; the calculation matrix parameters of the neuron nodes are used to indicate the model used by the terminal device.
  • the calculation parameter matrix of the neuron node; the deviation parameter of the neuron node is used to indicate the deviation of the neuron node of the model used by the terminal device;
  • the activation function parameter of the neuron node is used to indicate the activation of the neuron node of the model used by the terminal device function;
  • the sliding step size parameter is used to indicate the sliding step size of the model used by the terminal device;
  • the padding value parameter is used to indicate the padding value of the model used by the terminal device.
  • the model indication information sent by the access network device to the terminal device includes model parameter information.
  • the model parameter information includes: model type parameters and calculation matrix parameters of the neuron nodes.
  • the model can be configured according to the model type.
  • the parameters determine the type of the model, and further, determine the calculation matrix of the neuron node of the model.
  • the model type parameter indicates that the type of the model is a convolutional neural network model, and the calculation matrix parameter of the neuron node is the convolution kernel, then it can Determine the convolution kernel of the convolutional neural network model.
  • model parameter information may be different for different model types.
  • the above examples are only for illustration, and the embodiments of the present disclosure do not specifically limit this.
  • S21 Receive model indication information sent by the access network device, including:
  • the terminal device receives the model indication information sent by the access network device, and may receive the model indication information by receiving a broadcast message, a unicast message, or a multicast message from the access network device.
  • the access network device can send a unicast message to the terminal device which is the specific terminal.
  • the access network device can send a unicast message to the terminal device which belongs to the specific terminal group.
  • the terminal equipment sends the multicast message, so that the terminal equipment can receive the model indication information sent by the access network equipment.
  • receiving a broadcast message from an access network device includes: receiving a System Information Block (SIB) of the access network device; where the SIB includes model indication information.
  • SIB System Information Block
  • the system information block SIB of the access network device may be an existing SIB or a newly set SIB.
  • the newly set SIB is used to send model indication information.
  • the broadcast message of the access network device may be SIB, and the terminal device may obtain the model indication information by receiving the SIB.
  • receiving unicast messages or multicast messages from access network devices includes:
  • receive downlink control information DCI signaling of the access network device includes model indication information.
  • the unicast message of the access network device may be MAC CE (Mediaaccess Control Control Element, Media Access Control Element) signaling, RRC (Radio Resource Control, Radio Resource Control) signaling or DCI (Downlink ControlInformation, downlink control information) signaling
  • the terminal device can obtain the model indication information after receiving MAC CE signaling, RRC signaling or DCI signaling.
  • the method for determining the model used by the terminal device provided by the embodiment of the present disclosure also includes: determining the effective time of the target model; wherein the effective time is the time when the model indication information of the access network device is received plus N time units; N is greater than or equal to 0.
  • the terminal device after receiving the model indication information sent by the access network device, the terminal device determines the target model to be used, and further, can determine the effective time of the target model.
  • the terminal device receives the model indication information sent by the access network device, determines the target model to be used, and determines that the target model takes effect immediately.
  • the terminal device determines that the effective time of the target model is after receiving the target model sent by the access network device.
  • the model indicates the timing of the information.
  • the terminal device receives the model indication information sent by the access network device, determines the target model to be used, and determines that the target model will take effect immediately after N time units, for example, the N time units are 2 hours. slot, the terminal device determines that the effective time of the target model is the time X when the model indication information sent by the access network device is received plus 2 time slots.
  • the terminal device receives the unicast message, multicast message or broadcast message including the model indication information sent by the access network device, determines the target model to be used, and determines that the target model takes effect immediately.
  • the terminal device determines the target model.
  • the effective time is the time X plus N time units when the unicast message, multicast message or broadcast message sent by the access network device is received.
  • the N time units may be predefined, or determined based on relevant information of the access network device, or determined based on the communication protocol.
  • the embodiment of the present disclosure does not impose specific limitations on this.
  • the broadcast message can be SIB
  • the unicast message and multicast message can be MAC CE signaling, RRC signaling or DCI signaling.
  • the terminal device receives the SIB including the model indication information sent by the access network device, determines the target model to be used, and determines that the target model takes effect immediately.
  • the terminal device determines that the effective time of the target model is after receiving the SIB sent by the access network device.
  • the terminal device receives the MAC CE signaling including the model indication information sent by the access network device, determines the target model to be used, and determines that the target model takes effect immediately.
  • the terminal device determines that the effective time of the target model is after receiving the access The time X of the MAC CE signaling sent by the network device plus N time units.
  • the method for determining the model used by the terminal device also includes: determining the effective time of the target model; determining the effective time of the target model; wherein the effective time is when the terminal device sends a feedback MAC CE message The first time after the time of the confirmation character ACK of signaling, RRC signaling, or DCI signaling plus the preset duration.
  • the terminal device after receiving the model indication information sent by the access network device, the terminal device determines the target model to be used, and further, can determine the effective time of the target model.
  • the terminal device After the terminal device receives the MAC CE signaling including the model indication information sent by the access network device, it will provide feedback and send the confirmation character ACK to the access network device.
  • the terminal device can determine the target model.
  • the effective time is the first moment after the time when the confirmation character ACK is sent plus the preset time period.
  • the terminal device After the terminal device receives the DCI signaling including the model indication information sent by the access network device, it will perform HARQ (Hybrid Automatic Repeat Request, hybrid automatic repeat request)-ACK feedback and send the confirmation character ACK to the access network device.
  • HARQ Hybrid Automatic Repeat Request, hybrid automatic repeat request
  • the terminal device may determine that the effective time of the target model is the first moment after the moment when the confirmation character ACK is sent plus the preset duration.
  • the preset duration may be predefined, or determined based on relevant information of the access network device, or determined based on the communication protocol, and the embodiment of the present disclosure does not impose specific limitations on this.
  • the method for determining the model used by the terminal device provided by the embodiment of the present disclosure also includes: determining the effective time of the target model; determining the effective time of the target model;
  • the effective time of the target model is determined based on the time when the DCI signaling is received and the effective time parameter; wherein the DCI signaling carries the effective time parameter.
  • the terminal device after receiving the model indication information sent by the access network device, the terminal device determines the target model to be used, and further, can determine the effective time of the target model.
  • the MAC CE signaling carries the validity time parameter.
  • the terminal device After the terminal device receives the MAC CE signaling including the model indication information sent by the access network device, it determines the target model based on the time when the MAC CE signaling is received and the validity time parameter. effective time.
  • the effective time parameter carried in MAC CE signaling is 1, and the time when the terminal device receives the MAC CE signaling is X, then it is determined that the effective time of the target model is X+1 time slots. Or, if the MAC CE signaling carries an effective time parameter of 3, and the time it takes for the terminal device to receive the MAC CE signaling is X, then the effective time of the target model is determined to be X+3 seconds.
  • the RRC signaling carries the validity time parameter.
  • the terminal device After the terminal device receives the RRC signaling including the model indication information sent by the access network device, it determines the validity time of the target model based on the time when the RRC signaling is received and the validity time parameter. .
  • the effective time parameter carried in the RRC signaling is 1, and the time when the terminal device receives the RRC signaling is X, then it is determined that the effective time of the target model is X+1 time slots.
  • the RRC signaling carries an effective time parameter of 2, and the time when the terminal device receives the RRC signaling is X, then it is determined that the effective time of the target model is X+2 milliseconds.
  • the DCI signaling carries the effective time parameter.
  • the terminal device After the terminal device receives the DCI signaling including the model indication information sent by the access network device, it determines the effective time of the target model based on the time when the DCI signaling is received and the effective time parameter. .
  • the effective time parameter carried in the DCI signaling is 2, and the time when the terminal device receives the DCI signaling is X, then the effective time of the target model is determined to be X+2 time slots.
  • the effective time parameter can also be other values.
  • the effective time for determining the target model can also be the time when the model indication information is received plus the effective time. Time parameters of frames, subframes, mini-slots, symbols, etc.
  • FIG. 3 is a flow chart of another method for determining a model used by a terminal device provided by an embodiment of the present disclosure.
  • this method is applied to terminal equipment.
  • This method may include but is not limited to the following steps:
  • S31 Receive model indication information sent by the access network device.
  • artificial intelligence AI is a method of teaching the same things to computers. Artificial intelligence is the concept of imitating human abilities. Artificial intelligence can include a variety of models, such as machine learning models, deep learning models, federated learning models, etc. ,
  • the terminal device receives the model indication information sent by the access network device, where the model indication information may indicate information related to the model used by the terminal device.
  • the model indication information instructs the first terminal device to use a deep learning model, etc.
  • the model indication information indicates relevant parameters of the model used by the first terminal device, etc.
  • S32 Determine the target model used by the terminal device according to the model indication information; in response to the terminal device having a first model currently in use, modify the first model according to the model indication information to generate the target model.
  • the terminal device receives the model indication information sent by the access network device and determines the target model used by the terminal device. If, at this time, the terminal device has a first model that is currently in use, the first model can be processed. Modify and generate the target model.
  • the first model currently used by the terminal device is inherent to the terminal device, or predefined, or generated according to the model indication information last sent by the access network device, or obtained by training by the terminal device. Or obtained by joint training of terminal equipment and access network equipment.
  • the model indication information includes model parameter information
  • the model parameter information includes at least one of the following:
  • the number of neuron nodes in each network layer is the number of neuron nodes in each network layer
  • the model indication information sent by the access network device to the terminal device includes model parameter information.
  • the model parameter information includes: model type parameters, the number of network layers, the number of neuron nodes in each network layer, and the number of neural nodes in each network layer.
  • the model type parameter is used to indicate the type of model used by the terminal device.
  • the terminal device can determine the target model to be used based on the model type parameter.
  • the number of network layers is used to indicate the number of network layers of the model used by the terminal device.
  • the terminal device can determine and select the corresponding number of network layers based on the number of network layers.
  • a combination of network layer structures is used as the target model.
  • the number of neuron nodes in each network layer is used to indicate the number of neuron nodes in each network layer of the model used by the terminal device; the calculation matrix parameters of the neuron nodes are used to indicate the model used by the terminal device.
  • the calculation parameter matrix of the neuron node; the deviation parameter of the neuron node is used to indicate the deviation of the neuron node of the model used by the terminal device;
  • the activation function parameter of the neuron node is used to indicate the activation of the neuron node of the model used by the terminal device function;
  • the sliding step size parameter is used to indicate the sliding step size of the model used by the terminal device;
  • the padding value parameter is used to indicate the padding value of the model used by the terminal device.
  • the model indication information sent by the access network device to the terminal device includes model parameter information.
  • the model parameter information includes: model type parameters and calculation matrix parameters of the neuron nodes.
  • the model can be configured according to the model type.
  • the parameters determine the type of the model, and further, determine the calculation matrix of the neuron node of the model.
  • the model type parameter indicates that the type of the model is a convolutional neural network model, and the calculation matrix parameter of the neuron node is the convolution kernel, then it can Determine the convolution kernel of the convolutional neural network model.
  • model parameter information may be different for different model types.
  • the above examples are only for illustration, and the embodiments of the present disclosure do not specifically limit this.
  • S31 Receive model indication information sent by the access network device, including:
  • the terminal device receives the model indication information sent by the access network device, and may receive the model indication information by receiving a broadcast message, a unicast message, or a multicast message from the access network device.
  • the access network device can send a unicast message to the terminal device which is the specific terminal.
  • the access network device can send a unicast message to the terminal device which belongs to the specific terminal group.
  • the terminal equipment sends the multicast message, so that the terminal equipment can receive the model indication information sent by the access network equipment.
  • receiving a broadcast message from an access network device includes: receiving a System Information Block (SIB) of the access network device; where the SIB includes model indication information.
  • SIB System Information Block
  • the system information block SIB of the access network device may be an existing SIB or a newly set SIB.
  • the newly set SIB is used to send model indication information.
  • the broadcast message of the access network device may be SIB, and the terminal device may obtain the model indication information by receiving the SIB.
  • receiving unicast messages or multicast messages from access network devices includes:
  • receive downlink control information DCI signaling of the access network device includes model indication information.
  • the unicast message of the access network device may be MAC CE (Mediaaccess Control Control Element, Media Access Control Element) signaling, RRC (Radio Resource Control, Radio Resource Control) signaling or DCI (Downlink ControlInformation, downlink control information) signaling
  • the terminal device can obtain the model indication information after receiving MAC CE signaling, RRC signaling or DCI signaling.
  • S31 and S32 can be implemented alone, or can be implemented in combination with any other steps in the embodiment of the present disclosure.
  • S21 and S22 in the embodiment of the present disclosure can be implemented together.
  • the embodiment of the present disclosure does not This is not limited. It should be noted that the information contained in S31 and S32 does not need to be completely consistent, that is, S32 may only modify some of the parameters determined in S31, S32 may include parameters not included in S31, etc.
  • FIG. 4 is a flow chart of yet another method for determining a model used by a terminal device provided by an embodiment of the present disclosure.
  • this method is applied to access network equipment.
  • This method may include but is not limited to the following steps:
  • S41 Send model indication information to the terminal device; where the model indication information is used to indicate the target model used by the terminal device.
  • artificial intelligence AI is a method of teaching the same things to computers. Artificial intelligence is the concept of imitating human abilities. Artificial intelligence can include a variety of models, such as machine learning models, deep learning models, federated learning models, etc. ,
  • the terminal device receives the model indication information sent by the access network device, where the model indication information may indicate information related to the model used by the terminal device.
  • the model indication information instructs the first terminal device to use a deep learning model, etc.
  • the model indication information indicates relevant parameters of the model used by the first terminal device, etc.
  • the terminal device receives the model indication information sent by the access network device and can determine the target model used by the terminal device, where the model indication information can indicate relevant information of the model used by the terminal device.
  • the terminal device can determine that the target model used is a deep learning model.
  • the model pre-stored in the terminal device may be inherent to the terminal device, or predefined, or generated based on the model indication information last sent by the access network device, or obtained by training on the terminal device, or Obtained by joint training of terminal equipment and access network equipment.
  • the model indication information sent by the access network device instructs the first terminal device to use the parameter information of the deep learning model.
  • the terminal device receives the model indication information sent by the access network device and can use the deep learning model according to the model indication information. Carry out the initial configuration of the model based on the parameter information to obtain the deep learning model and serve it as the target model.
  • the model indication information includes model parameter information
  • the model parameter information includes at least one of the following:
  • the number of neuron nodes in each network layer is the number of neuron nodes in each network layer
  • the model indication information sent by the access network device to the terminal device includes model parameter information.
  • the model parameter information includes: model type parameters, the number of network layers, the number of neuron nodes in each network layer, and the number of neural nodes in each network layer.
  • the model type parameter is used to indicate the type of model used by the terminal device.
  • the terminal device can determine the target model to be used based on the model type parameter.
  • the number of network layers is used to indicate the number of network layers of the model used by the terminal device.
  • the terminal device can determine and select the corresponding number of network layers based on the number of network layers.
  • a combination of network layer structures is used as the target model.
  • the number of neuron nodes in each network layer is used to indicate the number of neuron nodes in each network layer of the model used by the terminal device; the calculation matrix parameters of the neuron nodes are used to indicate the model used by the terminal device.
  • the calculation parameter matrix of the neuron node; the deviation parameter of the neuron node is used to indicate the deviation of the neuron node of the model used by the terminal device;
  • the activation function parameter of the neuron node is used to indicate the activation of the neuron node of the model used by the terminal device function;
  • the sliding step size parameter is used to indicate the sliding step size of the model used by the terminal device;
  • the padding value parameter is used to indicate the padding value of the model used by the terminal device.
  • the model indication information sent by the access network device to the terminal device includes model parameter information.
  • the model parameter information includes: model type parameters and calculation matrix parameters of the neuron nodes.
  • the model can be configured according to the model type.
  • the parameters determine the type of the model, and further, determine the calculation matrix of the neuron node of the model.
  • the model type parameter indicates that the type of the model is a convolutional neural network model, and the calculation matrix parameter of the neuron node is the convolution kernel, then it can Determine the convolution kernel of the convolutional neural network model.
  • model parameter information may be different for different model types.
  • the above examples are only for illustration, and the embodiments of the present disclosure do not specifically limit this.
  • S41 Send model indication information to the terminal device, including:
  • the terminal device receives the model indication information sent by the access network device, and may receive the model indication information by receiving a broadcast message, a unicast message, or a multicast message from the access network device.
  • the access network device can send a unicast message to the terminal device which is the specific terminal.
  • the access network device can send a unicast message to the terminal device which belongs to the specific terminal group.
  • the terminal equipment sends the multicast message, so that the terminal equipment can receive the model indication information sent by the access network equipment.
  • sending the broadcast message to the terminal device includes: sending a SIB to the terminal device; wherein the SIB includes model indication information.
  • the system information block SIB of the access network device can be an existing SIB or a newly set SIB.
  • the newly set SIB is used to send model indication information.
  • the broadcast message of the access network device may be SIB, and the terminal device may obtain the model indication information by receiving the SIB.
  • sending a unicast message or a multicast message to the terminal device includes:
  • MAC CE signaling includes model indication information
  • radio resource control RRC signaling to the terminal device;
  • the RRC signaling includes model indication information;
  • downlink control information DCI signaling is sent to the terminal device; the DCI signaling includes model indication information.
  • the unicast message of the access network device may be MAC CE (Mediaaccess Control Control Element, Media Access Control Element) signaling, RRC (Radio Resource Control, Radio Resource Control) signaling or DCI (Downlink ControlInformation, downlink control information) signaling
  • the terminal device can obtain the model indication information after receiving MAC CE signaling, RRC signaling or DCI signaling.
  • the terminal device after receiving the model indication information sent by the access network device, the terminal device determines the target model to be used, and further, can determine the effective time of the target model.
  • the effective time for the terminal device to determine the target model please refer to the relevant descriptions of other embodiments, which will not be described again here.
  • the access network device receives the feedback MAC CE signaling, or RRC signaling, or the acknowledgment character ACK of the DCI signaling sent by the terminal device.
  • the terminal device After the terminal device receives the MAC CE signaling including the model indication information sent by the access network device, it will feedback and send the confirmation character ACK to the access network device.
  • the terminal device After the terminal device receives the DCI signaling including the model indication information sent by the access network device, it will perform HARQ (Hybrid Automatic Repeat Request, hybrid automatic repeat request)-ACK feedback and send the confirmation character ACK to the access network device. HARQ (Hybrid Automatic Repeat Request, hybrid automatic repeat request)-ACK feedback and send the confirmation character ACK to the access network device. .
  • HARQ Hybrid Automatic Repeat Request, hybrid automatic repeat request
  • the validity time parameter is carried in MAC CE signaling, or RRC signaling, or DCI signaling.
  • the MAC CE signaling, or RRC signaling, or DCI signaling sent by the access network device carries the validity time parameter. Therefore, the terminal device receives the MAC CE signaling, or RRC signaling, or After DCI signaling, the effective time of the target model can be determined according to the effective time parameter.
  • the effective time of the target model can be determined according to the effective time parameter.
  • FIG. 5 is a flow chart of yet another method for determining a model used by a terminal device provided by an embodiment of the present disclosure.
  • this method is applied to access network equipment.
  • This method may include but is not limited to the following steps:
  • model parameter information sent by the core network device is received.
  • the access network device can receive the model parameter information sent by the core network device, and further determine the model parameter information. It can be understood that the artificial intelligence model can be trained on the core network equipment, and after the artificial intelligence model training is completed, the model parameter information can be sent to the access network equipment.
  • S52 Send model indication information to the terminal device; where the model indication information is used to indicate the target model used by the terminal device.
  • the method for the access network device to send the model indication information to the terminal device may refer to the relevant descriptions in the above embodiments and will not be described again here.
  • S51 and S52 can be implemented alone, or can be implemented in combination with any other steps in the embodiment of the present disclosure.
  • S41 and S42 in the embodiment of the present disclosure can be implemented together.
  • the embodiment of the present disclosure does not This is not limited.
  • network devices and terminal devices may include hardware structures and software modules to implement the above functions in the form of hardware structures, software modules, or hardware structures plus software modules.
  • a certain function among the above functions can be executed by a hardware structure, a software module, or a hardware structure plus a software module.
  • FIG. 6 is a schematic structural diagram of a communication device 1 provided by an embodiment of the present application.
  • the communication device 1 shown in Figure 6 may include a transceiver module 11 and a processing module.
  • the transceiver module 11 may include a sending module and/or a receiving module.
  • the sending module is used to implement the sending function
  • the receiving module is used to implement the receiving function.
  • the transceiving module 11 may implement the sending function and/or the receiving function.
  • the communication device 1 may be a terminal device, a device in the terminal device, or a device that can be used in conjunction with the terminal device.
  • the communication device 1 may be a network device, a device in a network device, or a device that can be used in conjunction with the network device.
  • the communication device 1 is a terminal device 1 and includes: a transceiver module 11 and a processing module 12 .
  • the transceiver module 11 is configured to receive model indication information sent by the access network device.
  • the processing module 12 is configured to determine the target model used by the terminal device according to the model indication information.
  • the processing module 12 is also configured to respond to the presence of a first model currently in use in the terminal device, modify the first model according to the model indication information, and generate a target model.
  • the first model is inherent to the terminal device, or is predefined, or is generated according to the model indication information last sent by the access network device, or is obtained through training by the terminal device, or is obtained by the terminal device and the access network device. Obtained by joint training with network equipment.
  • the model indication information includes model parameter information
  • the model parameter information includes at least one of the following:
  • the transceiver module 11 is specifically used for:
  • the transceiver module 11 is specifically configured to: receive the system information block SIB of the access network device; where the SIB includes model indication information.
  • the transceiver module 11 is specifically used for:
  • receive downlink control information DCI signaling of the access network device includes model indication information.
  • the processing module 12 is also used to determine the effective time of the target model; wherein the effective time is the time X when the model indication information of the access network device is received plus N time units; N is greater than or equal to 0 .
  • the processing module 12 is also used to determine the effective time of the target model; wherein the effective time is the time when the terminal device sends feedback MAC CE signaling, or RRC signaling, or the confirmation character ACK of the DCI signaling plus the time The first moment after the preset duration.
  • processing module 12 is also used to:
  • the effective time of the target model based on the time when the RRC signaling is received and the effective time parameter; the RRC signaling carries the effective time parameter;
  • the communication device 1 is access network equipment and includes: a transceiver module 11.
  • the transceiver module 11 is configured to send model indication information to the terminal device; wherein the model indication information is used to indicate the target model used by the terminal device.
  • the model indication information includes model parameter information
  • the model parameter information includes at least one of the following:
  • the transceiver module 11 is specifically used for:
  • the transceiver module 11 is specifically used for:
  • the transceiver module 11 is specifically used for:
  • radio resource control RRC signaling to the terminal device;
  • the RRC signaling includes the model indication information;
  • downlink control information DCI signaling is sent to the terminal device; the DCI signaling includes the model indication information.
  • the transceiver module 11 is also configured to receive an acknowledgment character ACK sent by the terminal device to feedback the MAC CE signaling, the RRC signaling, or the DCI signaling.
  • the MAC CE signaling, or RRC signaling, or DCI signaling carries a validity time parameter.
  • the communication device further includes a processing module 12 for determining the model parameter information.
  • the transceiver module 11 is also used to receive the model parameter information sent by the core network device.
  • the communication device 1 provided in the above embodiments of the present disclosure achieves the same or similar beneficial effects as the communication methods provided in some of the above embodiments, and will not be described again here.
  • FIG. 7 is a schematic structural diagram of another communication device 1000 provided by an embodiment of the present disclosure.
  • the communication device 1000 may be an access network device, a terminal device, a chip, a chip system, a processor, etc. that supports the access network device to implement the above method, or a chip, a chip system, or a processor that supports the terminal device to implement the above method.
  • Chip system, or processor, etc. The communication device 1000 can be used to implement the method described in the above method embodiment. For details, please refer to the description in the above method embodiment.
  • the communication device 1000 may be an access network device, a terminal device, a chip, a chip system, a processor, etc. that supports the access network device to implement the above method, or a chip, a chip system, or a processor that supports the terminal device to implement the above method.
  • Chip system, or processor, etc. The device can be used to implement the method described in the above method embodiment. For details, please refer to the description in the above method embodiment.
  • Communication device 1000 may include one or more processors 1001.
  • the processor 1001 may be a general-purpose processor or a special-purpose processor, or the like.
  • it can be a baseband processor or a central processing unit.
  • the baseband processor can be used to process communication protocols and communication data.
  • the central processor can be used to control communication devices (such as base stations, baseband chips, terminal equipment, terminal equipment chips, DU or CU, etc.) and execute computer programs. , processing data for computer programs.
  • the communication device 1000 may also include one or more memories 1002, on which a computer program 1004 may be stored.
  • the memory 1002 executes the computer program 1004, so that the communication device 1000 performs the method described in the above method embodiment.
  • the memory 1002 may also store data.
  • the communication device 1000 and the memory 1002 can be provided separately or integrated together.
  • the communication device 1000 may also include a transceiver 1005 and an antenna 1006.
  • the transceiver 1005 may be called a transceiver unit, a transceiver, a transceiver circuit, etc., and is used to implement transceiver functions.
  • the transceiver 1005 may include a receiver and a transmitter.
  • the receiver may be called a receiver or a receiving circuit, etc., used to implement the receiving function;
  • the transmitter may be called a transmitter, a transmitting circuit, etc., used to implement the transmitting function.
  • the communication device 1000 may also include one or more interface circuits 1007.
  • the interface circuit 1007 is used to receive code instructions and transmit them to the processor 1001 .
  • the processor 1001 executes the code instructions to cause the communication device 1000 to perform the method described in the above method embodiment.
  • the communication device 1000 is a terminal device: the transceiver 1005 is used to execute S21 in FIG. 2; S31 in FIG. 3; the processor 1001 is used to execute S22 in FIG. 2; and S32 in FIG. 3.
  • the communication device 1000 is an access network device: the transceiver 1005 is used to perform S41 in Figure 4; S52 in Figure 5; and the processor 1001 is used to perform S51 in Figure 5.
  • the processor 1001 may include a transceiver for implementing receiving and transmitting functions.
  • the transceiver may be a transceiver circuit, an interface, or an interface circuit.
  • the transceiver circuits, interfaces or interface circuits used to implement the receiving and transmitting functions can be separate or integrated together.
  • the above-mentioned transceiver circuit, interface or interface circuit can be used for reading and writing codes/data, or the above-mentioned transceiver circuit, interface or interface circuit can be used for signal transmission or transfer.
  • the processor 1001 may store a computer program 1003, and the computer program 1003 runs on the processor 1001, causing the communication device 1000 to perform the method described in the above method embodiment.
  • the computer program 1003 may be solidified in the processor 1001, in which case the processor 1001 may be implemented by hardware.
  • the communication device 1000 may include a circuit, and the circuit may implement the functions of sending or receiving or communicating in the foregoing method embodiments.
  • the processors and transceivers described in this disclosure may be implemented on integrated circuits (ICs), analog ICs, radio frequency integrated circuits (RFICs), mixed signal ICs, application specific integrated circuits (ASICs), printed circuit boards ( printed circuit board (PCB), electronic equipment, etc.
  • the processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), n-type metal oxide-semiconductor (NMOS), P-type Metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.
  • CMOS complementary metal oxide semiconductor
  • NMOS n-type metal oxide-semiconductor
  • PMOS P-type Metal oxide semiconductor
  • BJT bipolar junction transistor
  • BiCMOS bipolar CMOS
  • SiGe silicon germanium
  • GaAs gallium arsenide
  • the communication device described in the above embodiments may be a terminal device, but the scope of the communication device described in the present disclosure is not limited thereto, and the structure of the communication device may not be limited by FIG. 7 .
  • the communication device may be a stand-alone device or may be part of a larger device.
  • the communication device may be:
  • the IC collection may also include storage components for storing data and computer programs;
  • FIG. 8 is a structural diagram of a chip provided in an embodiment of the present disclosure.
  • Chip 1100 includes processor 1101 and interface 1103.
  • the number of processors 1101 may be one or more, and the number of interfaces 1103 may be multiple.
  • Interface 1103, used to receive code instructions and transmit them to the processor.
  • the processor 1101 is configured to run code instructions to perform the method for determining the model used by the terminal device as described in some of the above embodiments.
  • Interface 1103, used to receive code instructions and transmit them to the processor.
  • the processor 1101 is configured to run code instructions to perform the method for determining the model used by the terminal device as described in some of the above embodiments.
  • the chip 1100 also includes a memory 1102, which is used to store necessary computer programs and data.
  • Embodiments of the present disclosure also provide a communication system that includes a communication device as a terminal device in the aforementioned embodiment of FIG. 6 and a communication device as an access network device.
  • the system includes a communication device as a terminal device in the aforementioned embodiment of FIG. 7 communication devices and communication devices as access network equipment.
  • the present disclosure also provides a readable storage medium on which instructions are stored, and when the instructions are executed by a computer, the functions of any of the above method embodiments are implemented.
  • the present disclosure also provides a computer program product, which, when executed by a computer, implements the functions of any of the above method embodiments.
  • the above embodiments it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software it may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer programs.
  • the computer program When the computer program is loaded and executed on a computer, the processes or functions described in accordance with the embodiments of the present disclosure are generated in whole or in part.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
  • the computer program may be stored in or transferred from one computer-readable storage medium to another, for example, the computer program may be transferred from a website, computer, server, or data center Transmission to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more available media integrated.
  • the usable media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVD)), or semiconductor media (e.g., solid state disks, SSD)) etc.
  • magnetic media e.g., floppy disks, hard disks, magnetic tapes
  • optical media e.g., high-density digital video discs (DVD)
  • DVD digital video discs
  • semiconductor media e.g., solid state disks, SSD
  • At least one in the present disclosure can also be described as one or more, and the plurality can be two, three, four or more, and the present disclosure is not limited.
  • the technical feature is distinguished by “first”, “second”, “third”, “A”, “B”, “C” and “D” etc.
  • the technical features described in “first”, “second”, “third”, “A”, “B”, “C” and “D” are in no particular order or order.
  • each table in this disclosure can be configured or predefined.
  • the values of the information in each table are only examples and can be configured as other values, which is not limited by this disclosure.
  • it is not necessarily required to configure all the correspondences shown in each table.
  • the corresponding relationships shown in some rows may not be configured.
  • appropriate deformation adjustments can be made based on the above table, such as splitting, merging, etc.
  • the names of the parameters shown in the titles of the above tables may also be other names understandable by the communication device, and the values or expressions of the parameters may also be other values or expressions understandable by the communication device.
  • other data structures can also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables or hash tables. wait.
  • Predefinition in this disclosure may be understood as definition, pre-definition, storage, pre-storage, pre-negotiation, pre-configuration, solidification, or pre-burning.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请提供了一种终端设备使用的模型的确定方法和装置，该方法包括：接收接入网设备发送的模型指示信息（S21），根据模型指示信息确定终端设备使用的目标模型（S22）。从而，终端设备可以确定使用不同的人工智能AI模型，可以提高终端设备的性能。

Description

终端设备使用的模型的确定方法和装置 技术领域
本公开涉及通信技术领域，尤其涉及一种终端设备使用的模型的确定方法和装置。
背景技术
相关技术中，提出利用AI(Artificial Intelligence，人工智能)技术提高空口的性能，AI模型的种类多种多样，终端设备可以使用AI模型进行性能预测，例如：在AI模型和波束管理的应用中，终端设备可以利用AI模型预测在未来一段时间使用的最佳波束，而不需要终端设备不断的进行波束测量，可以降低终端设备测量的复杂度还可以减少信令开销。
发明内容
本公开实施例提供一种终端设备使用的模型的确定方法和装置，终端设备能够根据接入网设备的模型指示信息确定目标模型，实现终端设备使用不同的AI模型，可以提高终端设备的性能。
第一方面，本公开实施例提供一种终端设备使用的模型的确定方法，该方法由终端设备执行，该方法包括：接收接入网设备发送的模型指示信息；根据所述模型指示信息确定所述终端设备使用的目标模型。
在该技术方案中，接收接入网设备发送的模型指示信息，根据模型指示信息确定终端设备使用的目标模型。从而，终端设备可以确定使用不同的AI模型，可以提高终端设备的性能。
第二方面，本公开实施例提供另一种终端设备使用的模型的确定方法，该方法由接入网设备执行，该方法包括：向终端设备发送模型指示信息；其中，所述模型指示信息用于指示所述终端设备使用的目标模型。
第三方面，本公开实施例提供一种通信装置，该通信装置具有实现上述第一方面所述的方法中终端设备的部分或全部功能，比如通信装置的功能可具备本公开中的部分或全部实施例中的功能，也可以具备单独实施本公开中的任一个实施例的功能。所述功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。所述硬件或软件包括一个或多个与上述功能相对应的单元或模块。
在一种实现方式中，该通信装置的结构中可包括收发模块和处理模块，所述处理模块被配置为支持通信装置执行上述方法中相应的功能。所述收发模块用于支持通信装置与其他设备之间的通信。所述通信装置还可以包括存储模块，所述存储模块用于与收发模块和处理模块耦合，其保存通信装置必要的计算机程序和数据。
作为示例，处理模块可以为处理器，收发模块可以为收发器或通信接口，存储模块可以为存储器。
在一种实现方式中，所述通信装置包括：收发模块，用于接收接入网设备发送的模型指示信息；处理模块，用于根据所述模型指示信息确定所述终端设备使用的目标模型。
第四方面，本公开实施例提供另一种通信装置，该通信装置具有实现上述第二方面所述的方法示例中网络设备的部分或全部功能，比如通信装置的功能可具备本公开中的部分或全部实施例中的功能，也可以具备单独实施本公开中的任一个实施例的功能。所述功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。所述硬件或软件包括一个或多个与上述功能相对应的单元或模块。
在一种实现方式中，该通信装置的结构中可包括收发模块和处理模块，该处理模块被配置为支持通信装置执行上述方法中相应的功能。收发模块用于支持通信装置与其他设备之间的通信。所述通信装置还可以包括存储模块，所述存储模块用于与收发模块和处理模块耦合，其保存通信装置必要的计算机程序和数据。
在一种实现方式中，所述通信装置包括：收发模块，用于向终端设备发送模型指示信息；其中，所述模型指示信息用于指示所述终端设备使用的目标模型。
第五方面，本公开实施例提供一种通信装置，该通信装置包括处理器，当该处理器调用存储器中的计算机程序时，执行上述第一方面所述的方法。
第六方面，本公开实施例提供一种通信装置，该通信装置包括处理器，当该处理器调用存储器中的计算机程序时，执行上述第二方面所述的方法。
第七方面，本公开实施例提供一种通信装置，该通信装置包括处理器和存储器，该存储器中存储有计算机程序；所述处理器执行该存储器所存储的计算机程序，以使该通信装置执行上述第一方面所述的方法。
第八方面，本公开实施例提供一种通信装置，该通信装置包括处理器和存储器，该存储器中存储有计算机程序；所述处理器执行该存储器所存储的计算机程序，以使该通信装置执行上述第二方面所述的方法。
第九方面，本公开实施例提供一种通信装置，该装置包括处理器和接口电路，该接口电路用于接收代码指令并传输至该处理器，该处理器用于运行所述代码指令以使该装置执行上述第一方面所述的方法。
第十方面，本公开实施例提供一种通信装置，该装置包括处理器和接口电路，该接口电路用于接收代码指令并传输至该处理器，该处理器用于运行所述代码指令以使该装置执行上述第二方面所述的方法。
第十一方面，本公开实施例提供一种通信系统，该系统包括第三方面所述的通信装置以及第四方面所述的通信装置，或者，该系统包括第五方面所述的通信装置以及第六方面所述的通信装置，或者，该系统包括第七方面所述的通信装置以及第八方面所述的通信装置，或者，该系统包括第九方面所述的通信装置以及第十方面所述的通信装置。
第十二方面，本发明实施例提供一种计算机可读存储介质，用于储存为上述终端设备所用的指令，当所述指令被执行时，使所述终端设备执行上述第一方面所述的方法。
第十三方面，本发明实施例提供一种可读存储介质，用于储存为上述接入网设备所用的指令，当所述指令被执行时，使所述接入网设备执行上述第二方面所述的方法。
第十四方面，本公开还提供一种包括计算机程序的计算机程序产品，当其在计算机上运行时，使得计算机执行上述第一方面所述的方法。
第十五方面，本公开还提供一种包括计算机程序的计算机程序产品，当其在计算机上运行时，使得计算机执行上述第二方面所述的方法。
第十六方面，本公开提供一种芯片系统，该芯片系统包括至少一个处理器和接口，用于支持终端设备实现第一方面所涉及的功能，例如，确定或处理上述方法中所涉及的数据和信息中的至少一种。在一种可能的设计中，所述芯片系统还包括存储器，所述存储器，用于保存终端设备必要的计算机程序和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
第十七方面，本公开提供一种芯片系统，该芯片系统包括至少一个处理器和接口，用于支持接入网 设备实现第二方面所涉及的功能，例如，确定或处理上述方法中所涉及的数据和信息中的至少一种。在一种可能的设计中，所述芯片系统还包括存储器，所述存储器，用于保存接入网设备必要的计算机程序和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
第十八方面，本公开提供一种计算机程序，当其在计算机上运行时，使得计算机执行上述第一方面所述的方法。
第十九方面，本公开提供一种计算机程序，当其在计算机上运行时，使得计算机执行上述第二方面所述的方法。
附图说明
为了更清楚地说明本公开实施例或背景技术中的技术方案，下面将对本公开实施例或背景技术中所需要使用的附图进行说明。
图1是本公开实施例提供的一种通信系统的架构图；
图2是本公开实施例提供的一种终端设备使用的模型的确定方法的流程图；
图3是本公开实施例提供的另一种终端设备使用的模型的确定方法的流程图；
图4是本公开实施例提供的又一种终端设备使用的模型的确定方法的流程图；
图5是本公开实施例提供的又一种终端设备使用的模型的确定方法的流程图；
图6是本公开实施例提供的一种通信装置的结构图；
图7是本公开实施例提供的另一种通信装置的结构图；
图8是本公开实施例提供的一种芯片的结构示意图。
具体实施方式
为了更好的理解本公开实施例公开的一种终端设备使用的模型的确定方法和装置，下面首先对本公开实施例适用的通信系统进行描述。
请参见图1，图1是本公开实施例提供的一种通信系统的示意图，如图1所示，该通信系统可以包括接入网设备、多个终端设备，核心网设备。接入网设备与接入网设备之间通过有线或无线的方式进行通信，例如通过图1中的Xn接口相互通信。接入网设备可以覆盖一个或者多个小区，如：接入网设备1覆盖有小区1.1、小区1.2，接入网设备2覆盖有小区2.1。终端设备可以在其中一个小区中驻留接入网设备，处于连接态。进一步，终端设备可以经过RRC释放过程从连接态转换为非激活态，即转换为非连接态。处于非连接态的终端设备可以驻留在原小区，根据该终端设备在原小区的传输参数，与原小区中的接入网设备进行上行传输和/或下行传输。处于非连接态的终端设备也可以移动到新的小区，根据该终端设备在新的小区的传输参数，与新的小区的接入网设备进行上行传输和/或下行传输。
需要说明的是，图1仅为示例性框架图，图1中包括的节点的数量、小区数量以及终端所处状态不受限制。除图1所示功能节点外，还可以包括其他节点，如：核心网设备、网关设备、应用服务器等等，不予限制。接入网设备通过有线或无线的方式与核心网设备相互通信，如通过下一代(next generation，NG)接口相互通信。
其中，接入网设备主要用于实现终端设备的资源调度、无线资源管理、和无线资源控制中至少一项功能。具体的，接入网设备可以包括基站、无线接入点、发送接收点(transmission receptionpoint，TRP)、 发送点(transmission point，TP)以及某种其它接入节点中的任一节点。本公开实施例中，用于实现接入网设备的功能的装置可以是接入网设备；也可以是能够支持接入网设备实现该功能的装置，例如芯片系统，该装置可以被安装在接入网设备中或者和接入网设备匹配使用。在本公开实施例提供的技术方案中，以用于实现接入网设备的功能的装置是接入网设备为例，描述本公开实施例提供的技术方案。
其中，核心网设备可以是包括AMF和/或一种位置管理功能网元。可选地，位置管理功能网元包括位置服务器(location server)，位置服务器可以实现为以下任意一项：LMF(Location Management Function，位置管理网元)、E-SMLC(Enhanced Serving Mobile Location Centre，增强服务的流动定位中心)、SUPL(Secure User Plane Location，安全用户平面定位)、SUPL SLP(SUPL Location Platform，安全用户平面定位定位平台)。
终端设备是用户侧的一种用于接收或发射信号的实体，如手机。终端设备也可以称为终端设备(terminal)、用户设备(user equipment，UE)、移动台(mobile station，MS)、移动终端设备(mobile terminal，MT)等。终端设备可以是具备通信功能的汽车、智能汽车、手机(mobile phone)、穿戴式设备、平板电脑(Pad)、带无线收发功能的电脑、虚拟现实(virtual reality，VR)终端设备、增强现实(augmented reality，AR)终端设备、工业控制(industrial control)中的无线终端设备、无人驾驶(self-driving)中的无线终端设备、远程手术(remote medical surgery)中的无线终端设备、智能电网(smart grid)中的无线终端设备、运输安全(transportation safety)中的无线终端设备、智慧城市(smart city)中的无线终端设备、智慧家庭(smart home)中的无线终端设备等等。本公开的实施例对终端设备所采用的具体技术和具体设备形态不做限定。
AMF网元，主要负责终端设备的接入认证、移动性管理、各个功能网元间的信令交互等工作，如：对用户的注册状态、用户的连接状态、用户注册入网、跟踪区更新、小区切换用户认证和密钥安全等进行管理。
AIF网元，与核心网设备(AMF网元)通过有线或者无线接口连接，主要负责人工智能AI模型参数的训练。
需要说明的是，本公开实施例的技术方案可以应用于各种通信系统。例如：长期演进(long term evolution，LTE)系统、第五代(5th generation，5G)移动通信系统、5G新空口(new radio，NR)系统，或者其他未来的新型移动通信系统等。还需要说明的是，本公开实施例中的侧链路还可以称为侧行链路或直通链路。
可以理解的是，本公开实施例描述的通信系统是为了更加清楚的说明本公开实施例的技术方案，并不构成对于本公开实施例提供的技术方案的限定，本领域普通技术人员可知，随着系统架构的演变和新业务场景的出现，本公开实施例提供的技术方案对于类似的技术问题，同样适用。
需要说明的是，本公开实施例中时间单元可以是物理时间单元，也可以是逻辑时间单元，例如单位为秒、毫秒、微秒、帧、子帧、时隙(slot)、迷你时隙、正交频分复用(orthogonal frequencydivision multiplexing，OFDM)符号(symbol)等。
基于此，本公开实施例提供一种终端设备使用的模型的确定方法和装置，以至少解决相关技术中存在的问题。
请参见图2，图2是本公开实施例提供的一种终端设备使用的模型的确定方法的流程图。
如图2所示，该方法应用于终端设备，该方法可以包括但不限于如下步骤：
S21：接收接入网设备发送的模型指示信息。
可以理解的是，人工智能AI是一种向计算机传授相同事物的方法，人工智能是模仿人类能力的概念，人工智能可以包括多种模型，例如，机器学习模型、深度学习模型、联邦学习模型等，每种模型下还包含各种子模型类型，比如深度学习模型中又包括卷积神经网络，递归神经网络等，这里的模型类型不区分模型或者子模型。
本公开实施例中，终端设备接收接入网设备发送的模型指示信息，其中，模型指示信息可以指示终端设备使用的模型的相关信息，例如，模型指示信息指示第一终端设备使用深度学习模型等、或者模型指示信息指示第一终端设备使用的模型的相关参数等。
S22：根据模型指示信息确定终端设备使用的目标模型。
本公开实施例中，终端设备接收接入网设备发送的模型指示信息，可以确定终端设备使用的目标模型，其中，模型指示信息可以指示终端设备使用的模型的相关信息。
在一示例性实施例中，在终端设备中预先存储有一个或多个模型(包括深度学习模型)的情况下，接入网设备发送的模型指示信息指示第一终端设备使用深度学习模型，则终端设备可以确定使用的目标模型为深度学习模型。
本公开实施例中，终端设备中预先存储的模型可以为终端设备固有的，或者预定义的、或者根据接入网设备上一次发送的模型指示信息生成的、或者终端设备进行训练得到的、或者终端设备和接入网设备联合训练得到的。
在另一示例性实施例中，接入网设备发送的模型指示信息指示第一终端设备使用深度学习模型的参数信息，终端设备接收到接入网设备发送的模型指示信息，可以根据深度学习模型的参数信息的进行模型的初始配置，得到深度学习模型，并作为目标模型。
在一些实施例中，模型指示信息包括模型参数信息，模型参数信息包括以下至少一个：
模型类型参数；
网络层数；
每层网络层数中的神经元节点个数；
神经元节点的计算矩阵参数；
神经元节点的偏差参数；
神经元节点的激活函数参数；
滑动步长参数；
填充值参数。
本公开实施例中，接入网设备发送至终端设备的模型指示信息包括模型参数信息，模型参数信息包括：模型类型参数、网络层数、每层网络层数中的神经元节点个数、神经元节点的计算参数矩阵参数、神经元节点的偏差参数、神经元节点的激活函数参数、滑动步长参数和填充值参数中的一个或多个。
其中，模型类型参数用于指示终端设备使用的模型的类型，在终端设备中预先存储有一个或多个模型的情况下，终端设备可以根据模型类型参数，确定使用的目标模型。网络层数用于指示终端设备使用的模型的网络层数，在终端设备中预先存储有模型的一个或多个网络层结构的情况下，终端设备可以根据网络层数，确定选择对应网络层数的网络层结构的组合为使用的目标模型。每层网络层数中的神经元节点个数用于指示终端设备使用的模型的每层网络层数中的神经元节点个数；神经元节点的计算矩阵参 数用于指示终端设备使用的模型的神经元节点的计算参数矩阵；神经元节点的偏差参数用于指示终端设备使用的模型的神经元节点的偏差；神经元节点的激活函数参数用于指示终端设备使用的模型的神经元节点的激活函数；滑动步长参数用于指示终端设备使用的模型的滑动步长；填充值参数用于指示终端设备使用的模型的填充(padding)值。
示例性实施例中，接入网设备发送至终端设备的模型指示信息包括模型参数信息，模型参数信息包括：模型类型参数和神经元节点的计算矩阵参数，本公开实施例中，可以根据模型类型参数确定模型的类型，并进一步的，确定模型的神经元节点的计算矩阵，例如：模型类型参数指示模型的类型为卷积神经网络模型，神经元节点的计算矩阵参数为卷积核，则可以确定卷积神经网络模型的卷积核。
需要说明的是，针对不同的模型类型，所需要的模型参数信息可以不同，上述示例仅作为示意，本公开实施例对此不作具体限制。
在一些实施例中，S21：接收接入网设备发送的模型指示信息，包括：
接收接入网设备的广播消息，其中，广播消息包括模型指示信息；
或者，接收接入网设备的单播消息；其中，单播消息包括模型指示信息；
或者，接收接入网设备的组播消息；其中，组播消息包括模型指示信息。
本公开实施例中，终端设备接收接入网设备发送的模型指示信息，可以通过接收接入网设备的广播消息，或单播消息，或组播消息接收模型指示信息。
其中，在终端设备为特定终端的情况下，接入网设备可以向为特定终端的终端设备发送单播消息，在终端设备属于特定终端组的情况下，接入网设备可以向属于特定终端组的终端设备发送组播消息，从而，终端设备可以接收到接入网设备发送的模型指示信息。
在一些实施例中，接收接入网设备的广播消息，包括：接收接入网设备的系统信息块SIB(System Information Block，系统信息块)；其中，SIB包括模型指示信息。
其中，接入网设备的系统信息块SIB可以为现有的SIB，也可以为新设置的SIB，新设置的SIB用于发送模型指示信息。
本公开实施例中，接入网设备的广播消息可以为SIB，终端设备接收SIB可以获取模型指示信息。
在一些实施例中，接收接入网设备的单播消息或者组播消息，包括：
接收接入网设备的媒体接入控制控制单元MAC CE信令；MAC CE信令包括模型指示信息；
或者，接收接入网设备的无线资源控制RRC信令；RRC信令包括模型指示信息；
或者，接收接入网设备的下行控制信息DCI信令；DCI信令包括模型指示信息。
本公开实施例中，接入网设备的单播消息可以为MAC CE(Mediaaccess Control Control Element，媒体接入控制控制元素)信令、RRC(Radio Resource Control，无线资源控制)信令或DCI(Downlink ControlInformation，下行控制信息)信令，终端设备接收到MAC CE信令、RRC信令或DCI信令，可以获取模型指示信息。
在一些实施例中，本公开实施例提供的终端设备使用的模型的确定方法，还包括：确定目标模型的生效时间；其中，生效时间为接收到接入网设备的模型指示信息的时间X加上N个时间单元；N大于或等于0。
本公开实施例中，终端设备接收到接入网设备发送的模型指示信息之后，确定使用的目标模型，并且，进一步的，可以确定目标模型的生效时间。
在一示例性实施例中，终端设备接收接入网设备发送的模型指示信息，确定使用的目标模型，并且确定目标模型立即生效，终端设备确定目标模型的生效时间为接收到接入网设备发送的模型指示信息的时间。
在另一示例性实施例中，终端设备接收接入网设备发送的模型指示信息，确定使用的目标模型，并且确定目标模型在N个时间单元后立即生效，例如N个时间单元为2个时隙，终端设备确定目标模型的生效时间为接收到接入网设备发送的模型指示信息的时间X加上2个时隙。
本公开实施例中，终端设备接收到接入网设备发送的包括模型指示信息的单播消息、组播消息或广播消息，确定使用的目标模型，并且确定目标模型立即生效，终端设备确定目标模型的生效时间为接收到接入网设备发送的单播消息、组播消息或广播消息的时间X加上N个时间单元。
本公开实施例中，N个时间单元可以预定义，或者根据接入网设备的相关信息确定，或者根据通信协议确定，本公开实施例对此不作具体限制。
其中，广播消息可以为SIB，单播消息和组播消息可以为MAC CE信令、RRC信令或DCI信令。
示例性的，终端设备接收到接入网设备发送的包括模型指示信息的SIB，确定使用的目标模型，并且确定目标模型立即生效，终端设备确定目标模型的生效时间为接收到接入网设备发送的SIB的时间X加上N个时间单元。
示例性的，终端设备接收到接入网设备发送的包括模型指示信息的MAC CE信令，确定使用的目标模型，并且确定目标模型立即生效，终端设备确定目标模型的生效时间为接收到接入网设备发送的MAC CE信令的时间X加上N个时间单元。
在一些实施例中，本公开实施例提供的终端设备使用的模型的确定方法，还包括：确定目标模型的生效时间；确定目标模型的生效时间；其中，生效时间为终端设备发送反馈MAC CE信令、或RRC信令，或DCI信令的确认字符ACK的时刻加上预设时长之后的第一时刻。
本公开实施例中，终端设备接收到接入网设备发送的模型指示信息之后，确定使用的目标模型，并且，进一步的，可以确定目标模型的生效时间。
其中，终端设备接收到接入网设备发送的包括模型指示信息的MAC CE信令之后，会进行反馈，发送确认字符ACK至接入网设备，本公开实施例中，终端设备可以确定目标模型的生效时间为发送确认字符ACK的时刻加上预设时长之后的第一时刻。
其中，终端设备接收到接入网设备发送的包括模型指示信息的DCI信令之后，会进行HARQ(Hybrid Automatic Repeat Request，混合自动重传请求)-ACK反馈，发送确认字符ACK至接入网设备，本公开实施例中，终端设备可以确定目标模型的生效时间为发送确认字符ACK的时刻加上预设时长之后的第一时刻。
本公开实施例中，预设时长可以预定义，或者根据接入网设备的相关信息确定，或者根据通信协议确定，本公开实施例对此不作具体限制。
在一些实施例中，本公开实施例提供的终端设备使用的模型的确定方法，还包括：确定目标模型的生效时间；确定目标模型的生效时间；
根据接收到MAC CE信令的时间和生效时间参数，确定目标模型的生效时间；其中，MAC CE信令中携带生效时间参数；
或者，根据接收到RRC信令的时间和生效时间参数，确定目标模型的生效时间；其中，RRC信令 中携带生效时间参数；
或者，根据接收到DCI信令的时间和生效时间参数，确定目标模型的生效时间；其中，DCI信令中携带生效时间参数。
本公开实施例中，终端设备接收到接入网设备发送的模型指示信息之后，确定使用的目标模型，并且，进一步的，可以确定目标模型的生效时间。
其中，MAC CE信令中携带生效时间参数，终端设备接收到接入网设备发送的包括模型指示信息的MAC CE信令之后，根据接收到MAC CE信令的时间和生效时间参数，确定目标模型的生效时间。
示例性的，MAC CE信令中携带生效时间参数为1，终端设备接收到MAC CE信令的时间为X，则确定目标模型的生效时间为X+1个时隙。或者，MAC CE信令中携带生效时间参数为3，终端设备接收到MAC CE信令的时间为X，则确定目标模型的生效时间为X+3秒。
其中，RRC信令中携带生效时间参数，终端设备接收到接入网设备发送的包括模型指示信息的RRC信令之后，根据接收到RRC信令的时间和生效时间参数，确定目标模型的生效时间。
示例性的，RRC信令中携带生效时间参数为1，终端设备接收到RRC信令的时间为X，则确定目标模型的生效时间为X+1个时隙。或者，RRC信令中携带生效时间参数为2，终端设备接收到RRC信令的时间为X，则确定目标模型的生效时间为X+2豪秒。
其中，DCI信令中携带生效时间参数，终端设备接收到接入网设备发送的包括模型指示信息的DCI信令之后，根据接收到DCI信令的时间和生效时间参数，确定目标模型的生效时间。
示例性的，DCI信令中携带生效时间参数为2，终端设备接收到DCI信令的时间为X，则确定目标模型的生效时间为X+2个时隙。
需要说明的是，上述示例仅作为示意，并不作为对本公开实施例的具体限制，生效时间参数还可以为其他值，确定目标模型的生效时间还可以为接收到模型指示信息的时间加上生效时间参数的帧、子帧、迷你时隙、符号等。
请参见图3，图3是本公开实施例提供的另一种终端设备使用的模型的确定方法的流程图。
如图3所示，该方法应用于终端设备，该方法可以包括但不限于如下步骤：
S31：接收接入网设备发送的模型指示信息。
可以理解的是，人工智能AI是一种向计算机传授相同事物的方法，人工智能是模仿人类能力的概念，人工智能可以包括多种模型，例如，机器学习模型、深度学习模型、联邦学习模型等，
本公开实施例中，终端设备接收接入网设备发送的模型指示信息，其中，模型指示信息可以指示终端设备使用的模型的相关信息，例如，模型指示信息指示第一终端设备使用深度学习模型等、或者模型指示信息指示第一终端设备使用的模型的相关参数等。
S32：根据模型指示信息确定终端设备使用的目标模型；响应于终端设备存在当前使用中的第一模型，根据模型指示信息对第一模型进行修改，生成目标模型。
本公开实施例中，终端设备接收到接入网设备发送的模型指示信息，确定终端设备使用的目标模型，如果，此时终端设备存在当前正在使用中的第一模型，可以对第一模型进行修改，生成目标模型。
在一些实施例中，终端设备当前使用中的第一模型为终端设备固有的，或者预定义的、或者根据接入网设备上一次发送的模型指示信息生成的、或者终端设备进行训练得到的、或者终端设备和接入网设备联合训练得到的。
在一些实施例中，模型指示信息包括模型参数信息，模型参数信息包括以下至少一个：
模型类型参数；
网络层数；
每层网络层数中的神经元节点个数；
神经元节点的计算矩阵参数；
神经元节点的偏差参数；
神经元节点的激活函数参数；
滑动步长参数；
填充值参数。
本公开实施例中，接入网设备发送至终端设备的模型指示信息包括模型参数信息，模型参数信息包括：模型类型参数、网络层数、每层网络层数中的神经元节点个数、神经元节点的计算参数矩阵参数、神经元节点的偏差参数、神经元节点的激活函数参数、滑动步长参数和填充值参数中的一个或多个。
其中，模型类型参数用于指示终端设备使用的模型的类型，在终端设备中预先存储有一个或多个模型的情况下，终端设备可以根据模型类型参数，确定使用的目标模型。网络层数用于指示终端设备使用的模型的网络层数，在终端设备中预先存储有模型的一个或多个网络层结构的情况下，终端设备可以根据网络层数，确定选择对应网络层数的网络层结构的组合为使用的目标模型。每层网络层数中的神经元节点个数用于指示终端设备使用的模型的每层网络层数中的神经元节点个数；神经元节点的计算矩阵参数用于指示终端设备使用的模型的神经元节点的计算参数矩阵；神经元节点的偏差参数用于指示终端设备使用的模型的神经元节点的偏差；神经元节点的激活函数参数用于指示终端设备使用的模型的神经元节点的激活函数；滑动步长参数用于指示终端设备使用的模型的滑动步长；填充值参数用于指示终端设备使用的模型的填充(padding)值。
示例性实施例中，接入网设备发送至终端设备的模型指示信息包括模型参数信息，模型参数信息包括：模型类型参数和神经元节点的计算矩阵参数，本公开实施例中，可以根据模型类型参数确定模型的类型，并进一步的，确定模型的神经元节点的计算矩阵，例如：模型类型参数指示模型的类型为卷积神经网络模型，神经元节点的计算矩阵参数为卷积核，则可以确定卷积神经网络模型的卷积核。
需要说明的是，针对不同的模型类型，所需要的模型参数信息可以不同，上述示例仅作为示意，本公开实施例对此不作具体限制。
在一些实施例中，S31：接收接入网设备发送的模型指示信息，包括：
接收接入网设备的广播消息，其中，广播消息包括模型指示信息；
或者，接收接入网设备的单播消息；其中，单播消息包括模型指示信息；
或者，接收接入网设备的组播消息；其中，组播消息包括模型指示信息。
本公开实施例中，终端设备接收接入网设备发送的模型指示信息，可以通过接收接入网设备的广播消息，或单播消息，或组播消息接收模型指示信息。
其中，在终端设备为特定终端的情况下，接入网设备可以向为特定终端的终端设备发送单播消息，在终端设备属于特定终端组的情况下，接入网设备可以向属于特定终端组的终端设备发送组播消息，从而，终端设备可以接收到接入网设备发送的模型指示信息。
在一些实施例中，接收接入网设备的广播消息，包括：接收接入网设备的系统信息块SIB(System  Information Block，系统信息块)；其中，SIB包括模型指示信息。
其中，接入网设备的系统信息块SIB可以为现有的SIB，也可以为新设置的SIB，新设置的SIB用于发送模型指示信息。
本公开实施例中，接入网设备的广播消息可以为SIB，终端设备接收SIB可以获取模型指示信息。
在一些实施例中，接收接入网设备的单播消息或者组播消息，包括：
接收接入网设备的媒体接入控制控制单元MAC CE信令；MAC CE信令包括模型指示信息；
或者，接收接入网设备的无线资源控制RRC信令；RRC信令包括模型指示信息；
或者，接收接入网设备的下行控制信息DCI信令；DCI信令包括模型指示信息。
本公开实施例中，接入网设备的单播消息可以为MAC CE(Mediaaccess Control Control Element，媒体接入控制控制元素)信令、RRC(Radio Resource Control，无线资源控制)信令或DCI(Downlink ControlInformation，下行控制信息)信令，终端设备接收到MAC CE信令、RRC信令或DCI信令，可以获取模型指示信息。
需要说明的是，S31与S32可以单独被实施，也可以结合本公开实施例中的任何一个其他步骤一起被实施，例如结合本公开实施例中的S21与S22一起被实施，本公开实施例并不对此做出限定。需要说明的是，S31和S32中包含信息不需要完全一致，即S32可以只修改部分S31中确定的参数、S32可以包括S31中未包含的参数等。
请参见图4，图4是本公开实施例提供的又一种终端设备使用的模型的确定方法的流程图。
如图4所示，该方法应用于接入网设备，该方法可以包括但不限于如下步骤：
S41：向终端设备发送模型指示信息；其中，模型指示信息用于指示终端设备使用的目标模型。
可以理解的是，人工智能AI是一种向计算机传授相同事物的方法，人工智能是模仿人类能力的概念，人工智能可以包括多种模型，例如，机器学习模型、深度学习模型、联邦学习模型等，
本公开实施例中，终端设备接收接入网设备发送的模型指示信息，其中，模型指示信息可以指示终端设备使用的模型的相关信息，例如，模型指示信息指示第一终端设备使用深度学习模型等、或者模型指示信息指示第一终端设备使用的模型的相关参数等。
本公开实施例中，终端设备接收接入网设备发送的模型指示信息，可以确定终端设备使用的目标模型，其中，模型指示信息可以指示终端设备使用的模型的相关信息。
在一示例性实施例中，在终端设备中预先存储有一个或多个模型(包括深度学习模型)的情况下，接入网设备发送的模型指示信息指示第一终端设备使用深度学习模型，则终端设备可以确定使用的目标模型为深度学习模型。
本公开实施例中，终端设备中预先存储的模型可以为终端设备固有的，或者预定义的、或者根据接入网设备上一次发送的模型指示信息生成的、或者终端设备进行训练得到的、或者终端设备和接入网设备联合训练得到的。
在另一示例性实施例中，接入网设备发送的模型指示信息指示第一终端设备使用深度学习模型的参数信息，终端设备接收到接入网设备发送的模型指示信息，可以根据深度学习模型的参数信息的进行模型的初始配置，得到深度学习模型，并作为目标模型。
在一些实施例中，模型指示信息包括模型参数信息，模型参数信息包括以下至少一个：
模型类型参数；
网络层数；
每层网络层数中的神经元节点个数；
神经元节点的计算矩阵参数；
神经元节点的偏差参数；
神经元节点的激活函数参数；
滑动步长参数；
填充值参数。
本公开实施例中，接入网设备发送至终端设备的模型指示信息包括模型参数信息，模型参数信息包括：模型类型参数、网络层数、每层网络层数中的神经元节点个数、神经元节点的计算参数矩阵参数、神经元节点的偏差参数、神经元节点的激活函数参数、滑动步长参数和填充值参数中的一个或多个。
其中，模型类型参数用于指示终端设备使用的模型的类型，在终端设备中预先存储有一个或多个模型的情况下，终端设备可以根据模型类型参数，确定使用的目标模型。网络层数用于指示终端设备使用的模型的网络层数，在终端设备中预先存储有模型的一个或多个网络层结构的情况下，终端设备可以根据网络层数，确定选择对应网络层数的网络层结构的组合为使用的目标模型。每层网络层数中的神经元节点个数用于指示终端设备使用的模型的每层网络层数中的神经元节点个数；神经元节点的计算矩阵参数用于指示终端设备使用的模型的神经元节点的计算参数矩阵；神经元节点的偏差参数用于指示终端设备使用的模型的神经元节点的偏差；神经元节点的激活函数参数用于指示终端设备使用的模型的神经元节点的激活函数；滑动步长参数用于指示终端设备使用的模型的滑动步长；填充值参数用于指示终端设备使用的模型的填充(padding)值。
示例性实施例中，接入网设备发送至终端设备的模型指示信息包括模型参数信息，模型参数信息包括：模型类型参数和神经元节点的计算矩阵参数，本公开实施例中，可以根据模型类型参数确定模型的类型，并进一步的，确定模型的神经元节点的计算矩阵，例如：模型类型参数指示模型的类型为卷积神经网络模型，神经元节点的计算矩阵参数为卷积核，则可以确定卷积神经网络模型的卷积核。
需要说明的是，针对不同的模型类型，所需要的模型参数信息可以不同，上述示例仅作为示意，本公开实施例对此不作具体限制。
在一些实施例中，S41：向终端设备发送模型指示信息，包括：
向终端设备发送广播消息，其中，广播消息包括模型指示信息；
或者，向终端设备发送单播消息；其中，单播消息包括模型指示信息；
或者，向终端设备发送组播消息；其中，组播消息包括模型指示信息。
本公开实施例中，终端设备接收接入网设备发送的模型指示信息，可以通过接收接入网设备的广播消息，或单播消息，或组播消息接收模型指示信息。
其中，在终端设备为特定终端的情况下，接入网设备可以向为特定终端的终端设备发送单播消息，在终端设备属于特定终端组的情况下，接入网设备可以向属于特定终端组的终端设备发送组播消息，从而，终端设备可以接收到接入网设备发送的模型指示信息。
在一些实施例中，向终端设备发送广播消息，包括：向终端设备发送SIB；其中，SIB包括模型指示信息。
其中，接入网设备的系统信息块SIB可以为现有的SIB，也可以为新设置的SIB，新设置的SIB用 于发送模型指示信息。
本公开实施例中，接入网设备的广播消息可以为SIB，终端设备接收SIB可以获取模型指示信息。
在一些实施例中，向终端设备发送单播消息或者组播消息，包括：
向终端设备发送媒体接入控制控制单元MAC CE信令；MAC CE信令包括模型指示信息；
或者，向终端设备发送无线资源控制RRC信令；RRC信令包括模型指示信息；
或者，向终端设备发送下行控制信息DCI信令；DCI信令包括模型指示信息。
本公开实施例中，接入网设备的单播消息可以为MAC CE(Mediaaccess Control Control Element，媒体接入控制控制元素)信令、RRC(Radio Resource Control，无线资源控制)信令或DCI(Downlink ControlInformation，下行控制信息)信令，终端设备接收到MAC CE信令、RRC信令或DCI信令，可以获取模型指示信息。
本公开实施例中，终端设备接收到接入网设备发送的模型指示信息之后，确定使用的目标模型，并且，进一步的，可以确定目标模型的生效时间。其中，终端设备确定目标模型的生效时间可以参见其他实施例的相关描述，此处不再赘述。
在一些实施例中，接入网设备接收终端设备发送的反馈MAC CE信令、或RRC信令，或DCI信令的确认字符ACK。
其中，终端设备接收到接入网设备发送的包括模型指示信息的MAC CE信令之后，会进行反馈，发送确认字符ACK至接入网设备。
其中，终端设备接收到接入网设备发送的包括模型指示信息的DCI信令之后，会进行HARQ(Hybrid Automatic Repeat Request，混合自动重传请求)-ACK反馈，发送确认字符ACK至接入网设备。
在一些实施例中，MAC CE信令，或RRC信令，或DCI信令中携带生效时间参数。
本公开实施例中，接入网设备发送的MAC CE信令，或RRC信令，或DCI信令中携带生效时间参数，从而，终端设备在接收到MAC CE信令，或RRC信令，或DCI信令后，可以根据生效时间参数确定目标模型的生效时间，具体实现方式可以参见上述实施例的相关描述，此处不再赘述。
请参见图5，图5是本公开实施例提供的又一种终端设备使用的模型的确定方法的流程图。
如图5所示，该方法应用于接入网设备，该方法可以包括但不限于如下步骤：
S51：确定模型参数信息。
在一些实施例中，接收核心网设备发送的模型参数信息。
本公开实施例中，接入网设备可以接收核心网设备发送的模型参数信息，进一步的确定模型参数信息。可以理解的是，人工智能模型可以在核心网设备上进行训练，在人工智能模型训练完成后，可以发送模型参数信息给接入网设备。
S52：向终端设备发送模型指示信息；其中，模型指示信息用于指示终端设备使用的目标模型。
需要说明的是，接入网设备向终端设备发送模型指示信息的方法可以参见上述实施例中的相关描述，此处不再赘述。
需要说明的是，S51与S52可以单独被实施，也可以结合本公开实施例中的任何一个其他步骤一起被实施，例如结合本公开实施例中的S41与S42一起被实施，本公开实施例并不对此做出限定。
上述本公开提供的实施例中，分别从终端设备、接入网设备的角度对本公开实施例提供的方法进行了介绍。为了实现上述本公开实施例提供的方法中的各功能，网络设备和终端设备可以包括硬件结构、 软件模块，以硬件结构、软件模块、或硬件结构加软件模块的形式来实现上述各功能。上述各功能中的某个功能可以以硬件结构、软件模块、或者硬件结构加软件模块的方式来执行。
请参见图6，为本申请实施例提供的一种通信装置1的结构示意图。图6所示的通信装置1可包括收发模块11和处理模块。收发模块11可包括发送模块和/或接收模块，发送模块用于实现发送功能，接收模块用于实现接收功能，收发模块11可以实现发送功能和/或接收功能。
通信装置1可以是终端设备，也可以是终端设备中的装置，还可以是能够与终端设备匹配使用的装置。或者，通信装置1可以是网络设备，也可以是网络设备中的装置，还可以是能够与网络设备匹配使用的装置。
通信装置1为终端设备1：包括：收发模块11和处理模块12。
收发模块11，用于接收接入网设备发送的模型指示信息。
处理模块12，用于根据模型指示信息确定终端设备使用的目标模型。
在一些实施例中，处理模块12，还用于响应于终端设备存在当前使用中的第一模型，根据模型指示信息对第一模型进行修改，生成目标模型。
在一些实施例中，第一模型为终端设备固有的，或者预定义的、或者根据接入网设备上一次发送的模型指示信息生成的、或者终端设备进行训练得到的、或者终端设备和接入网设备联合训练得到的。
在一些实施例中，模型指示信息包括模型参数信息，模型参数信息包括以下至少一个：
模型类型参数；
神经元节点的计算矩阵参数；
神经元节点的偏差参数；
神经元节点的激活函数参数；
滑动步长参数；
填充值参数。
在一些实施例中，收发模块11，具体用于：
接收接入网设备的广播消息，其中，广播消息包括模型指示信息；
或者，接收接入网设备的单播消息；其中，单播消息包括模型指示信息；
或者，接收接入网设备的组播消息；其中，组播消息包括模型指示信息。
在一些实施例中，收发模块11，具体用于：接收接入网设备的系统信息块SIB；其中，SIB包括模型指示信息。
在一些实施例中，收发模块11，具体用于：
接收接入网设备的媒体接入控制控制单元MAC CE信令；MAC CE信令包括模型指示信息；
或者，接收接入网设备的无线资源控制RRC信令；RRC信令包括模型指示信息；
或者，接收接入网设备的下行控制信息DCI信令；DCI信令包括模型指示信息。
在一些实施例中，处理模块12，还用于确定目标模型的生效时间；其中，生效时间为接收到接入网设备的模型指示信息的时间X加上N个时间单元；N大于或等于0。
在一些实施例中，处理模块12，还用于确定目标模型的生效时间；其中，生效时间为终端设备发送反馈MAC CE信令、或RRC信令，或DCI信令的确认字符ACK的时刻加上预设时长之后的第一时刻。
在一些实施例中，处理模块12，还用于：
根据接收到MAC CE信令的时间和生效时间参数，确定目标模型的生效时间；MAC CE信令中携带生效时间参数；
或者，根据接收到RRC信令的时间和生效时间参数，确定目标模型的生效时间；RRC信令中携带生效时间参数；
或者，根据接收到DCI信令的时间和生效时间参数，确定目标模型的生效时间；DCI信令中携带生效时间参数。
通信装置1为接入网设备：包括：收发模块11。
收发模块11，用于向终端设备发送模型指示信息；其中，模型指示信息用于指示终端设备使用的目标模型。
在一些实施例中，模型指示信息包括模型参数信息，模型参数信息包括以下至少一个：
模型类型参数；
神经元节点的计算参数矩阵参数；
神经元节点的偏差参数；
神经元节点的激活函数参数；
滑动步长参数；
填充值参数。
在一些实施例中，收发模块11，具体用于：
向终端设备发送广播消息，其中，广播消息包括模型指示信息；
或者，向终端设备发送单播消息；其中，单播消息包括模型指示信息；
或者，向终端设备发送组播消息；其中，组播消息包括模型指示信息。
在一些实施例中，收发模块11，具体用于：
向终端设备发送SIB；其中，SIB包括模型指示信息。
在一些实施例中，收发模块11，具体用于：
向所述终端设备发送媒体接入控制控制单元MAC CE信令；所述MAC CE信令包括所述模型指示信息；
或者，向所述终端设备发送无线资源控制RRC信令；所述RRC信令包括所述模型指示信息；
或者，向所述终端设备发送下行控制信息DCI信令；所述DCI信令包括所述模型指示信息。
在一些实施例中，收发模块11，还用于接收所述终端设备发送的反馈所述MAC CE信令、或所述RRC信令，或所述DCI信令的确认字符ACK。
在一些实施例中，所述MAC CE信令，或RRC信令，或DCI信令中携带生效时间参数。
在一些实施例中，所述通信装置还包括处理模块12，用于确定所述模型参数信息。
在一些实施例中，收发模块11，还用于接收核心网设备发送的所述模型参数信息。
关于上述实施例中的通信装置1，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
本公开上述实施例中提供的通信装置1，与上面一些实施例中提供的通信方法取得相同或相似的有益效果，此处不再赘述。
请参见图7，图7是本公开实施例提供的另一种通信装置1000的结构示意图。通信装置1000可以是接入网设备，也可以是终端设备，也可以是支持接入网设备实现上述方法的芯片、芯片系统、或处理器等，还可以是支持终端设备实现上述方法的芯片、芯片系统、或处理器等。该通信装置1000可用于实现上述方法实施例中描述的方法，具体可以参见上述方法实施例中的说明。
通信装置1000可以是接入网设备，也可以是终端设备，也可以是支持接入网设备实现上述方法的芯片、芯片系统、或处理器等，还可以是支持终端设备实现上述方法的芯片、芯片系统、或处理器等。该装置可用于实现上述方法实施例中描述的方法，具体可以参见上述方法实施例中的说明。
通信装置1000可以包括一个或多个处理器1001。处理器1001可以是通用处理器或者专用处理器等。例如可以是基带处理器或中央处理器。基带处理器可以用于对通信协议以及通信数据进行处理，中央处理器可以用于对通信装置(如，基站、基带芯片，终端设备、终端设备芯片，DU或CU等)进行控制，执行计算机程序，处理计算机程序的数据。
可选的，通信装置1000中还可以包括一个或多个存储器1002，其上可以存有计算机程序1004，存储器1002执行所述计算机程序1004，以使得通信装置1000执行上述方法实施例中描述的方法。可选的，所述存储器1002中还可以存储有数据。通信装置1000和存储器1002可以单独设置，也可以集成在一起。
可选的，通信装置1000还可以包括收发器1005、天线1006。收发器1005可以称为收发单元、收发机、或收发电路等，用于实现收发功能。收发器1005可以包括接收器和发送器，接收器可以称为接收机或接收电路等，用于实现接收功能；发送器可以称为发送机或发送电路等，用于实现发送功能。
可选的，通信装置1000中还可以包括一个或多个接口电路1007。接口电路1007用于接收代码指令并传输至处理器1001。处理器1001运行所述代码指令以使通信装置1000执行上述方法实施例中描述的方法。
通信装置1000为终端设备：收发器1005用于执行图2中的S21；图3中的S31；处理器1001用于执行图2中的S22；图3中的S32。
通信装置1000为接入网设备：收发器1005用于执行图4中的S41；图5中的S52；处理器1001用于执行图5中的S51。
在一种实现方式中，处理器1001中可以包括用于实现接收和发送功能的收发器。例如该收发器可以是收发电路，或者是接口，或者是接口电路。用于实现接收和发送功能的收发电路、接口或接口电路可以是分开的，也可以集成在一起。上述收发电路、接口或接口电路可以用于代码/数据的读写，或者，上述收发电路、接口或接口电路可以用于信号的传输或传递。
在一种实现方式中，处理器1001可以存有计算机程序1003，计算机程序1003在处理器1001上运行，可使得通信装置1000执行上述方法实施例中描述的方法。计算机程序1003可能固化在处理器1001中，该种情况下，处理器1001可能由硬件实现。
在一种实现方式中，通信装置1000可以包括电路，所述电路可以实现前述方法实施例中发送或接收或者通信的功能。本公开中描述的处理器和收发器可实现在集成电路(integrated circuit，IC)、模拟IC、射频集成电路RFIC、混合信号IC、专用集成电路(application specific integrated circuit，ASIC)、印刷电路板(printed circuit board，PCB)、电子设备等上。该处理器和收发器也可以用各种IC工艺技术来制造，例如互补金属氧化物半导体(complementary metal oxide semiconductor，CMOS)、N型金 属氧化物半导体(nMetal-oxide-semiconductor，NMOS)、P型金属氧化物半导体(positive channel metal oxide semiconductor，PMOS)、双极结型晶体管(bipolar junction transistor，BJT)、双极CMOS(BiCMOS)、硅锗(SiGe)、砷化镓(GaAs)等。
以上实施例描述中的通信装置可以是终端设备，但本公开中描述的通信装置的范围并不限于此，而且通信装置的结构可以不受图7的限制。通信装置可以是独立的设备或者可以是较大设备的一部分。例如所述通信装置可以是：
(1)独立的集成电路IC，或芯片，或，芯片系统或子系统；
(2)具有一个或多个IC的集合，可选的，该IC集合也可以包括用于存储数据，计算机程序的存储部件；
(3)ASIC，例如调制解调器(Modem)；
(4)可嵌入在其他设备内的模块；
(5)接收机、终端设备、智能终端设备、蜂窝电话、无线设备、手持机、移动单元、车载设备、网络设备、云设备、人工智能设备等等；
(6)其他等等。
对于通信装置可以是芯片或芯片系统的情况，请参见图8，为本公开实施例中提供的一种芯片的结构图。
芯片1100包括处理器1101和接口1103。其中，处理器1101的数量可以是一个或多个，接口1103的数量可以是多个。
对于芯片用于实现本公开实施例中终端设备的功能的情况：
接口1103，用于接收代码指令并传输至所述处理器。
处理器1101，用于运行代码指令以执行如上面一些实施例所述的终端设备使用的模型的确定方法。
对于芯片用于实现本公开实施例中接入网设备的功能的情况：
接口1103，用于接收代码指令并传输至所述处理器。
处理器1101，用于运行代码指令以执行如上面一些实施例所述的终端设备使用的模型的确定方法。
可选的，芯片1100还包括存储器1102，存储器1102用于存储必要的计算机程序和数据。
本领域技术人员还可以了解到本公开实施例列出的各种说明性逻辑块(illustrative logical block)和步骤(step)可以通过电子硬件、电脑软件，或两者的结合进行实现。这样的功能是通过硬件还是软件来实现取决于特定的应用和整个系统的设计要求。本领域技术人员可以对于每种特定的应用，可以使用各种方法实现所述的功能，但这种实现不应被理解为超出本公开实施例保护的范围。
本公开实施例还提供一种通信系统，该系统包括前述图6实施例中作为终端设备的通信装置和作为接入网设备的通信装置，或者，该系统包括前述图7实施例中作为终端设备的通信装置和作为接入网设备的通信装置。
本公开还提供一种可读存储介质，其上存储有指令，该指令被计算机执行时实现上述任一方法实施例的功能。
本公开还提供一种计算机程序产品，该计算机程序产品被计算机执行时实现上述任一方法实施例的功能。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实 现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机程序。在计算机上加载和执行所述计算机程序时，全部或部分地产生按照本公开实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机程序可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机程序可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，高密度数字视频光盘(digital video disc，DVD))、或者半导体介质(例如，固态硬盘(solid state disk，SSD))等。
本领域普通技术人员可以理解：本公开中涉及的第一、第二等各种数字编号仅为描述方便进行的区分，并不用来限制本公开实施例的范围，也表示先后顺序。
本公开中的至少一个还可以描述为一个或多个，多个可以是两个、三个、四个或者更多个，本公开不做限制。在本公开实施例中，对于一种技术特征，通过“第一”、“第二”、“第三”、“A”、“B”、“C”和“D”等区分该种技术特征中的技术特征，该“第一”、“第二”、“第三”、“A”、“B”、“C”和“D”描述的技术特征间无先后顺序或者大小顺序。
本公开中各表所示的对应关系可以被配置，也可以是预定义的。各表中的信息的取值仅仅是举例，可以配置为其他值，本公开并不限定。在配置信息与各参数的对应关系时，并不一定要求必须配置各表中示意出的所有对应关系。例如，本公开中的表格中，某些行示出的对应关系也可以不配置。又例如，可以基于上述表格做适当的变形调整，例如，拆分，合并等等。上述各表中标题示出参数的名称也可以采用通信装置可理解的其他名称，其参数的取值或表示方式也可以通信装置可理解的其他取值或表示方式。上述各表在实现时，也可以采用其他的数据结构，例如可以采用数组、队列、容器、栈、线性表、指针、链表、树、图、结构体、类、堆、散列表或哈希表等。
本公开中的预定义可以理解为定义、预先定义、存储、预存储、预协商、预配置、固化、或预烧制。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本公开的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
以上所述，仅为本公开的具体实施方式，但本公开的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本公开的保护范围之内。因此，本公开的保护范围应以所述权利要求的保护范围为准。

Claims (24)

  1. 一种终端设备使用的模型的确定方法，其特征在于，所述方法由终端设备执行，所述方法包括：
    接收接入网设备发送的模型指示信息；
    根据所述模型指示信息确定所述终端设备使用的目标模型。
  2. 如权利要求1所述的方法，其特征在于，所述方法，还包括：
    响应于所述终端设备存在当前使用中的第一模型，根据所述模型指示信息对所述第一模型进行修改，生成所述目标模型。
  3. 如权利要求2所述的方法，其特征在于，所述第一模型为所述终端设备固有的，或者预定义的、或者根据所述接入网设备上一次发送的所述模型指示信息生成的、或者所述终端设备进行训练得到的、或者所述终端设备和所述接入网设备联合训练得到的。
  4. 如权利要求1至3中任一项所述的方法，其特征在于，所述模型指示信息包括模型参数信息，所述模型参数信息包括以下至少一个：
    模型类型参数；
    神经元节点的计算矩阵参数；
    所述神经元节点的偏差参数；
    所述神经元节点的激活函数参数；
    滑动步长参数；
    填充值参数。
  5. 如权利要求1至4中任一项所述的方法，其特征在于，所述接收接入网设备发送的模型指示信息，包括：
    接收所述接入网设备的广播消息，其中，所述广播消息包括所述模型指示信息；
    或者，接收所述接入网设备的单播消息；其中，所述单播消息包括所述模型指示信息；
    或者，接收所述接入网设备的组播消息；其中，所述组播消息包括所述模型指示信息。
  6. 如权利要求5所述的方法，其特征在于，所述接收所述接入网设备的广播消息，包括：
    接收所述接入网设备的系统信息块SIB；其中，所述SIB包括所述模型指示信息。
  7. 如权利要求5所述的方法，其特征在于，所述接收所述接入网设备的单播消息或者组播消息，包括：
    接收所述接入网设备的媒体接入控制控制单元MAC CE信令；所述MAC CE信令包括所述模型指示信息；
    或者，接收所述接入网设备的无线资源控制RRC信令；所述RRC信令包括所述模型指示信息；
    或者，接收所述接入网设备的下行控制信息DCI信令；所述DCI信令包括所述模型指示信息。
  8. 如权利要求1至7中任一项所述的方法，其特征在于，所述方法，还包括：
    确定所述目标模型的生效时间；其中，所述生效时间为接收到所述接入网设备的所述模型指示信息的时间X加上N个时间单元；N大于或等于0；所述时间单元为秒、毫秒、微秒、帧、子帧、时隙、迷你时隙和符号中的一个。
  9. 如权利要求7所述的方法，其特征在于，所述方法，还包括：
    确定所述目标模型的生效时间；其中，所述生效时间为所述终端设备发送反馈所述MAC CE信令、或所述RRC信令或所述DCI信令的确认字符ACK的时刻加上预设时长之后的第一时刻。
  10. 如权利要求7所述的方法，其特征在于，所述MAC CE信令、或所述RRC信令，或所述DCI信令中携带生效时间参数，所述方法，还包括：
    根据接收到所述MAC CE信令的时间和所述生效时间参数，确定所述目标模型的生效时间；
    或者，根据接收到所述RRC信令的时间和所述生效时间参数，确定所述目标模型的生效时间；
    或者，根据接收到所述DCI信令的时间和所述生效时间参数，确定所述目标模型的生效时间。
  11. 一种终端设备使用的模型的确定方法，其特征在于，所述方法由接入网设备执行，所述方法包括：
    向终端设备发送模型指示信息；其中，所述模型指示信息用于指示所述终端设备使用的目标模型。
  12. 如权利要求11所述的方法，其特征在于，所述模型指示信息包括模型参数信息，所述模型参数信息包括以下至少一个：
    模型类型参数；
    神经元节点的计算参数矩阵参数；
    所述神经元节点的偏差参数；
    所述神经元节点的激活函数参数；
    滑动步长参数；
    填充值参数。
  13. 如权利要求11或12所述的方法，其特征在于，所述向终端设备发送模型指示信息，包括：
    向所述终端设备发送广播消息，其中，所述广播消息包括所述模型指示信息；
    或者，向所述终端设备发送单播消息；其中，所述单播消息包括所述模型指示信息；
    或者，向所述终端设备发送组播消息；其中，所述组播消息包括所述模型指示信息。
  14. 如权利要求13所述的方法，其特征在于，所述向所述终端设备发送广播消息，包括：
    向所述终端设备发送SIB；其中，所述SIB包括所述模型指示信息。
  15. 如权利要求13所述的方法，其特征在于，所述向所述终端设备发送单播消息或者组播消息，包括：
    向所述终端设备发送媒体接入控制控制单元MAC CE信令；所述MAC CE信令包括所述模型指示信息；
    或者，向所述终端设备发送无线资源控制RRC信令；所述RRC信令包括所述模型指示信息；
    或者，向所述终端设备发送下行控制信息DCI信令；所述DCI信令包括所述模型指示信息。
  16. 如权利要求15所述的方法，其特征在于，所述方法，还包括：
    接收所述终端设备发送的反馈所述MAC CE信令、或所述RRC信令，或所述DCI信令的确认字符ACK。
  17. 如权利要求15所述的方法，其特征在于，所述MAC CE信令，或RRC信令，或DCI信令中携带生效时间参数。
  18. 如权利要求11至17中任一项所述的方法，其特征在于，所述方法，还包括：
    确定所述模型参数信息。
  19. 如权利要求18所述的方法，其特征在于，所述方法，还包括：
    接收核心网设备发送的所述模型参数信息。
  20. 一种通信装置，其特征在于，包括：
    收发模块，用于接收接入网设备发送的模型指示信息；
    处理模块，用于根据所述模型指示信息确定所述终端设备使用的目标模型。
  21. 一种通信装置，其特征在于，包括：
    收发模块，用于向终端设备发送模型指示信息；其中，所述模型指示信息用于指示所述终端设备使用的目标模型。
  22. 一种通信装置，其特征在于，所述装置包括处理器和存储器，所述存储器中存储有计算机程序，所述处理器执行所述存储器中存储的计算机程序，以使所述装置执行如权利要求1至10中任一项所述的方法，或所述处理器执行所述存储器中存储的计算机程序，以使所述装置执行如权利要求11至19中任一项所述的方法。
  23. 一种通信装置，其特征在于，包括：处理器和接口电路；
    所述接口电路，用于接收代码指令并传输至所述处理器；
    所述处理器，用于运行所述代码指令以执行如权利要求1至10中任一项所述的方法，或用于运行 所述代码指令以执行如权利要求11至19中任一项所述的方法。
  24. 一种计算机可读存储介质，用于存储有指令，当所述指令被执行时，使如权利要求1至10中任一项所述的方法被实现，或当所述指令被执行时，使如权利要求11至19中任一项所述的方法被实现。
PCT/CN2022/084687 2022-03-31 2022-03-31 终端设备使用的模型的确定方法和装置 WO2023184452A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202280000814.8A CN117178579A (zh) 2022-03-31 2022-03-31 终端设备使用的模型的确定方法和装置
PCT/CN2022/084687 WO2023184452A1 (zh) 2022-03-31 2022-03-31 终端设备使用的模型的确定方法和装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/084687 WO2023184452A1 (zh) 2022-03-31 2022-03-31 终端设备使用的模型的确定方法和装置

Publications (1)

Publication Number Publication Date
WO2023184452A1 true WO2023184452A1 (zh) 2023-10-05

Family

ID=88198788

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/084687 WO2023184452A1 (zh) 2022-03-31 2022-03-31 终端设备使用的模型的确定方法和装置

Country Status (2)

Country Link
CN (1) CN117178579A (zh)
WO (1) WO2023184452A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200413316A1 (en) * 2018-03-08 2020-12-31 Telefonaktiebolaget Lm Ericsson (Publ) Managing communication in a wireless communications network
CN113570062A (zh) * 2020-04-28 2021-10-29 大唐移动通信设备有限公司 机器学习模型参数传递方法及装置
US20210352575A1 (en) * 2018-10-19 2021-11-11 Lg Electronics Inc. Method supporting separate data transmission for independent network slices in wireless communication system
WO2022013104A1 (en) * 2020-07-13 2022-01-20 Telefonaktiebolaget Lm Ericsson (Publ) Managing a wireless device that is operable to connect to a communication network
CN114095969A (zh) * 2020-08-24 2022-02-25 华为技术有限公司 一种智能的无线接入网络
CN114091679A (zh) * 2020-08-24 2022-02-25 华为技术有限公司 一种更新机器学习模型的方法及通信装置
CN114143799A (zh) * 2020-09-03 2022-03-04 华为技术有限公司 通信方法及装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200413316A1 (en) * 2018-03-08 2020-12-31 Telefonaktiebolaget Lm Ericsson (Publ) Managing communication in a wireless communications network
US20210352575A1 (en) * 2018-10-19 2021-11-11 Lg Electronics Inc. Method supporting separate data transmission for independent network slices in wireless communication system
CN113570062A (zh) * 2020-04-28 2021-10-29 大唐移动通信设备有限公司 机器学习模型参数传递方法及装置
WO2022013104A1 (en) * 2020-07-13 2022-01-20 Telefonaktiebolaget Lm Ericsson (Publ) Managing a wireless device that is operable to connect to a communication network
CN114095969A (zh) * 2020-08-24 2022-02-25 华为技术有限公司 一种智能的无线接入网络
CN114091679A (zh) * 2020-08-24 2022-02-25 华为技术有限公司 一种更新机器学习模型的方法及通信装置
CN114143799A (zh) * 2020-09-03 2022-03-04 华为技术有限公司 通信方法及装置

Also Published As

Publication number Publication date
CN117178579A (zh) 2023-12-05

Similar Documents

Publication Publication Date Title
WO2023010471A1 (zh) 一种传输配置指示tci状态配置的方法及其装置
WO2023184457A1 (zh) 生效时间确定方法及装置
WO2024050776A1 (zh) 一种信息确定方法/装置/设备及存储介质
WO2023201756A1 (zh) 一种用于基于条件的移动性的信息的处理方法及装置
WO2023184452A1 (zh) 终端设备使用的模型的确定方法和装置
WO2023245499A1 (zh) 一种发送接收点trp的配置方法、装置、设备及存储介质
WO2024031274A1 (zh) 成功切换报告shr的记录上报方法和装置
WO2024020747A1 (zh) 一种模型的生成方法及装置
WO2024060234A1 (zh) 信息上报方法和装置
WO2023044621A1 (zh) 一种波束测量和上报的方法及其装置
WO2023206572A1 (zh) 小区状态配置方法及其装置
WO2024026885A1 (zh) 一种路径切换的方法及装置
WO2023197187A1 (zh) 一种信道状态信息的处理方法及装置
US20240179754A1 (en) Method and apparatus for configuring physical random access channel (prach)
WO2023184456A1 (zh) 测量时间的确定方法和装置
WO2023201755A1 (zh) 一种移动性管理的配置方法及装置
WO2023206179A1 (zh) 一种确定传输配置指示状态的方法及装置
WO2024086979A1 (zh) 一种传输配置指示tci状态的确定方法及装置
WO2024130518A1 (zh) 模型管理方法和装置
WO2024060143A1 (zh) 一种上报方法/装置/设备及存储介质
EP4362564A1 (en) Timing relationship adjustment method and apparatus
WO2024026886A1 (zh) 信息上报方法和装置
WO2024031272A1 (zh) 一种上报方法、装置、设备及存储介质
WO2023206180A1 (zh) 一种确定传输配置指示状态的方法及装置
WO2024026801A1 (zh) 一种侧行链路sl波束配置方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22934289

Country of ref document: EP

Kind code of ref document: A1