WO2024094166A1 - 报告传输方法及通信装置 - Google Patents

报告传输方法及通信装置 Download PDF

Info

Publication number
WO2024094166A1
WO2024094166A1 PCT/CN2023/129573 CN2023129573W WO2024094166A1 WO 2024094166 A1 WO2024094166 A1 WO 2024094166A1 CN 2023129573 W CN2023129573 W CN 2023129573W WO 2024094166 A1 WO2024094166 A1 WO 2024094166A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
model
report
network
cell
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2023/129573
Other languages
English (en)
French (fr)
Inventor
陈晓宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Spreadtrum Communications Shanghai Co Ltd
Original Assignee
Spreadtrum Communications Shanghai Co Ltd
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 Spreadtrum Communications Shanghai Co Ltd filed Critical Spreadtrum Communications Shanghai Co Ltd
Publication of WO2024094166A1 publication Critical patent/WO2024094166A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports

Definitions

  • the present application relates to the field of communication technology, and in particular to a report transmission method and a communication device.
  • AI models are currently widely used in various fields.
  • AI models can be used to achieve prediction, classification, decision-making, etc.
  • AI models can be used in image processing, analysis, text processing and other fields to achieve various functions.
  • Integrating AI models into wireless communication networks can obviously significantly improve technical indicators such as throughput, processing delay, and enhance user capacity. This is an important task for future wireless communication networks.
  • how to integrate AI models into wireless communication networks is still a problem that needs to be solved urgently.
  • the embodiments of the present application provide a report transmission method and a communication device, whereby a terminal device can send updates of an AI model to a network device via a report, thereby allowing the terminal device and the network device to have a consistent understanding of the currently used model, thereby improving the success rate of data transmission between the terminal device and the network device.
  • an embodiment of the present application provides a report transmission method, the method comprising:
  • the terminal device can send the update status of the AI model to the network device via a report, so that the terminal device and the network device have a consistent understanding of the current usage model, thereby improving the success rate of data transmission between the terminal device and the network device.
  • the report includes at least one of the following information:
  • First indication information where the first indication information is used to indicate that the update of the first AI model is completed
  • Model information of a second AI model where the second AI model is a model obtained by updating the first AI model
  • the second indication information is used to indicate model information of a deactivated AI model
  • third indication information where the third indication information is used to indicate that the update of the first AI model is not completed
  • Preset information associated with the second AI model the preset information including at least one of network information, access network information, channel quality information, time information, or terminal device identification information, and the second AI model is a model obtained by updating the first AI model;
  • Model information of a third AI model where the third AI model is switched to when the first AI model is not updated to the second AI model;
  • Fourth indication information where the fourth indication information is used to indicate the use of a non-AI model
  • fifth indication information where the fifth indication information is used to indicate at least one attribute information of the second AI model, where the at least one attribute information is attribute information that is not supported by the terminal device when the first AI model is not updated to the second AI model;
  • first request information where the first request information is used to request the network to indicate a fourth AI model
  • the reference signal information measured when the first AI model is updated including at least one of the number of reference signal resources, the index of a reference signal resource set, the index of the reference signal resource, and a measurement result of the reference signal.
  • the terminal device can report one or more information of the model update to the network device, so that the network device can promptly know the model used by the terminal device side, thereby improving the success rate of data transmission.
  • the report type includes an AI model update report
  • the report type includes at least one of the following: a conventional measurement feedback report of a non-AI model, a prediction feedback report of an AI model, an enhanced measurement feedback report of an AI model, and an update report of an AI model.
  • the report type of the report can be notified to the network device side, thereby facilitating the network device to interpret the report.
  • the at least one attribute information includes at least one of the following: a model identifier of the second AI model, model structure information of the second AI model, and a model parameter of the second AI model.
  • the terminal device will inform the network device of at least one of the model identifier, model structure information or model parameters of the unsupported second AI model, so that the subsequent network device can avoid scheduling the second AI model when scheduling the terminal device. It can also avoid the deterioration of transmission performance caused by the inconsistency of the AI models used by the network device and the terminal device.
  • the report includes at least one part, and information carried by a part ranked first in the report is used to determine information carried by a part ranked later.
  • the information carried by the first part of the report can be used to determine the information carried by the second part, thereby facilitating the interpretation of the report by the network device and reducing the overhead of the report and the complexity of decoding the report by the network device.
  • the format of the report is determined by a triggering method for triggering the update of the first AI model; the triggering method includes: model update triggered by a detected event, or model update triggered by network signaling.
  • the sending a report includes:
  • the report is sent using uplink resources, where the uplink resources include periodic uplink channel resources preconfigured by the network, or the most recent uplink authorization resource that can be used to carry the report, or the uplink authorization resource that has been used the most times in a historical time period, or the uplink authorization resource that was used last, or the uplink authorization resource indicated by a network device triggered by a scheduling request SR.
  • the uplink resources include periodic uplink channel resources preconfigured by the network, or the most recent uplink authorization resource that can be used to carry the report, or the uplink authorization resource that has been used the most times in a historical time period, or the uplink authorization resource that was used last, or the uplink authorization resource indicated by a network device triggered by a scheduling request SR.
  • the resources used by the terminal device to send the report are defined, which facilitates the terminal device to send the report and reduces the delay in report transmission.
  • the sending a report includes:
  • the report is sent on a primary cell; or, the report is sent on a cell in the FR1 frequency band.
  • the sending a report includes:
  • the report is repeatedly sent using one or more uplink beams.
  • the repeatedly sending the report using one or more uplink beams includes:
  • the report is repeatedly sent using one or more uplink beams in a time division multiplexing manner; or, the report is sent simultaneously using multiple uplink beams.
  • This method can be implemented by repeatedly sending reports through time division multiplexing, or by using multiple uplink beams to send reports simultaneously, thereby improving the reliability of report transmission.
  • the simultaneously transmitted reports are transmitted on the multiple uplink beams using different layers or frequency domain resources or orthogonal code sequences respectively.
  • reports sent simultaneously are sent on multiple uplink beams using different layers or frequency domain resources or orthogonal code sequences to reduce mutual interference.
  • the sending a report includes:
  • the report is sent in one of the following ways:
  • the report and the information carried in the second uplink channel are multiplexed onto the channel resources of the third uplink channel for transmission; or, the first uplink channel is transmitted and the information carried in the second uplink channel is discarded; or, the transmission power of the first uplink channel and/or the transmission power of the second uplink channel is adjusted, and the power-adjusted first uplink channel and the second uplink channel are transmitted, wherein the sum of the power-adjusted transmission power of the first uplink channel and the transmission power of the second uplink channel is less than or equal to the maximum transmission power supported by the terminal device.
  • the adjusting the transmit power of the first uplink channel and/or the transmit power of the second uplink channel includes:
  • the transmission power of the first uplink channel carrying the report is increased, and/or the transmission power of the second uplink channel is decreased, thereby adjusting the transmission power of the channel while satisfying the total power supported by the terminal, increasing the report transmission success rate, and transmitting more information.
  • the increasing the transmit power of the first uplink channel; and/or the decreasing the transmit power of the second uplink channel includes:
  • the transmit power of the first uplink channel is increased; and/or the transmit power of the second uplink channel is decreased.
  • the priority comparison is used to determine which transmission power is increased or decreased, thereby ensuring the success rate of sending high-priority information.
  • the sending the first uplink channel and discarding information carried in the second uplink channel includes:
  • the priority of the report is greater than the priority of the information carried in the second uplink channel, the first uplink channel is sent and the information carried in the second uplink channel is discarded.
  • the report carried in the first uplink channel is sent first to ensure the sending of high priority information.
  • the order in which the report and the information carried in the second uplink channel are arranged in the third uplink channel is determined by the priority of the report and the priority of the information carried in the second uplink channel.
  • the method further includes:
  • the second uplink channel is sent, and the report carried in the first uplink channel is discarded.
  • the report will be discarded, thereby ensuring the transmission of high-priority information.
  • the report has the highest priority; or, when the report contains the first information, the report has the highest priority; or, when the updated second AI model is different from the first AI model, the report has the highest priority.
  • the first information includes at least one of the following: the first indication information, model information of the second AI model, the third indication information, model information of the third AI model, the fourth indication information, and a report type of the report.
  • the report has the highest priority, thereby dynamically determining the priority of the report and ensuring consistency in the understanding of the AI model between the AI network side and the terminal side.
  • the priority of the report is the lowest.
  • the priority of the report is set to the lowest to ensure the transmission of other high-priority information.
  • the effective time of the report is determined by at least one of the following:
  • the first period of time after the report is sent shall come into effect
  • the second time period after the network sends a target signaling becomes effective, where the target signaling is used to instruct to update the first AI model;
  • the third time period after sending the second request information becomes effective, wherein the second request information is used to request the network to send information for assisting in updating the first AI model;
  • the effectiveness time is indicated by the network or agreed upon by a protocol.
  • the effective time is determined by the subcarrier spacing corresponding to the preset information associated with the second AI model, or by the minimum subcarrier spacing among multiple subcarrier spacings corresponding to the preset information associated with the second AI model, and the preset information includes at least one of network information, access network information, channel quality information, time information or terminal device identification information.
  • the network information includes at least one of the following:
  • Public land mobile network PLMN information Public land mobile network PLMN information, operator identification information, network equipment vendor identification information, tracking area identification TAI information, roaming control SOR information, and routing selection strategy URSP information.
  • This method is implemented to associate network information with AI models, making it easier to determine the network information corresponding to various models.
  • the access network information includes at least one of the following:
  • Working frequency information cell group information, serving cell information, physical cell identifier, transmitting and receiving point TRP identifier information, bandwidth part BWP identifier information, and reference signal RS information associated with the cell.
  • the access network information is associated with the AI model, thereby facilitating the determination of the access network information corresponding to various models.
  • an embodiment of the present application provides a report transmission method, the method comprising:
  • the report includes at least one of the following information:
  • First indication information where the first indication information is used to indicate that the update of the first AI model is completed
  • Model information of a second AI model where the second AI model is a model obtained by updating the first AI model
  • the second indication information is used to indicate model information of a deactivated AI model
  • third indication information where the third indication information is used to indicate that the update of the first AI model is not completed
  • Preset information associated with the second AI model the preset information including at least one of network information, access network information, channel quality information, time information, or terminal device identification information, and the second AI model is a model obtained by updating the first AI model;
  • Model information of a third AI model where the third AI model is switched to when the first AI model is not updated to the second AI model;
  • Fourth indication information where the fourth indication information is used to indicate the use of a non-AI model
  • fifth indication information where the fifth indication information is used to indicate at least one attribute information of the second AI model, where the at least one attribute information is attribute information that is not supported by the terminal device when the first AI model is not updated to the second AI model;
  • first request information where the first request information is used to request the network to indicate a fourth AI model
  • the reference signal information measured when the first AI model is updated including at least one of the number of reference signal resources, the index of a reference signal resource set, the index of the reference signal resource, and a measurement result of the reference signal.
  • the network information includes at least one of the following:
  • Public land mobile network PLMN information Public land mobile network PLMN information, operator identification information, network equipment vendor identification information, tracking area identification TAI information, roaming control SOR information, and routing selection strategy URSP information.
  • the access network information includes at least one of the following:
  • Working frequency information cell group information, serving cell information, physical cell identifier, transmitting and receiving point TRP identifier information, bandwidth part BWP identifier information, and reference signal RS information associated with the cell.
  • the report type includes an AI model update report
  • the report type includes at least one of the following: a conventional measurement feedback report of a non-AI model, a prediction feedback report of an AI model, an enhanced measurement feedback report of an AI model, and an update report of an AI model.
  • the at least one attribute information includes at least one of the following: a model identifier of the second AI model, model structure information of the second AI model, and a model parameter of the second AI model.
  • the report includes at least one part, and information carried by a part ranked first in the report is used to determine information carried by a part ranked later.
  • the method further includes:
  • part or all of the information in the report can be sent to the target network, target site, or target cell, so that other networks, sites, or cells can obtain updated information related to the AI model.
  • the target network satisfies at least one of the following:
  • the target network is the same as the current network
  • the target network has the same operator identifier or the same PLMN information as the current network;
  • the target network and the current network have the same network equipment vendor identifier
  • the target network is the last network where the terminal device resides
  • the target network is a network adjacent to the current network
  • the current network is the network where the terminal device currently resides.
  • the target network can be determined, thereby facilitating sending part or all of the information in the report to the target network.
  • the target site satisfies at least one of the following:
  • the target site and the current site have the same operator identifier or PLMN or network equipment vendor;
  • the target site is a site corresponding to each neighboring area in a neighboring area list configured for the current site, where the neighboring area list includes one or more neighboring areas;
  • the cell of the target site and the cell of the current site are both in the neighboring cell list of the reference site;
  • the target site is a site corresponding to the first neighboring area in the neighboring area list configured for the current site, where the first neighboring area is a neighboring area associated with beam information configured, activated or indicated by the network;
  • the cell of the target site and the cell of the current site are both in the neighboring cell list of the reference site, and the cell of the target site and the cell of the current site are both cells associated with beam information configured, activated or indicated by the network;
  • the target site is a site corresponding to the last cell where the terminal device resides;
  • the target site is an adjacent site of the current site
  • the target site is an AI model information management server
  • the current site is the site corresponding to the cell where the terminal device is currently located.
  • the target site can be determined, thereby facilitating sending part or all of the information in the report to the target site.
  • the target cell satisfies at least one of the following:
  • the target cell and the current cell have the same operator identifier or PLMN or network equipment vendor;
  • the target cell is a cell in a neighbor cell list configured for the current cell, where the neighbor cell list includes one or more neighbor cells;
  • the target cell and the current cell are both in the neighboring cell list of the reference cell;
  • the target cell is a cell in a neighbor cell list configured for the current cell, and the target cell is a neighbor cell associated with beam information configured, activated or indicated by the network;
  • the target cell and the current cell are both in the neighbor cell list of the reference cell, and the target cell and the current cell are both cells associated with beam information configured, activated or indicated by the network;
  • the target cell is the last cell where the terminal device resides
  • the target cell is a neighboring cell of the current cell
  • the current cell is the cell where the terminal device currently resides.
  • the target cell can be determined, thereby facilitating sending part or all of the information in the report to the target cell.
  • an embodiment of the present application provides a communication device, which includes a unit for implementing a method in any possible implementation manner of the first aspect above, or includes a unit for implementing a method in any possible implementation manner of the second aspect above.
  • an embodiment of the present application provides a communication device, which includes a processor and a memory, the processor and the memory are connected to each other, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method as described in the first aspect or any optional embodiment of the first aspect, or to execute the method as described in the second aspect or any optional embodiment of the second aspect.
  • an embodiment of the present application provides a chip, comprising a processor and an interface, wherein the processor and the interface are coupled; the interface is used to receive or output signals, and the processor is used to execute code instructions to execute the method described in the first aspect or any optional embodiment of the first aspect, or to execute the method described in the second aspect or any optional embodiment of the second aspect.
  • an embodiment of the present application provides a module device, which includes a communication module, a power module, a storage module and a chip module, wherein: the power module is used to provide power to the module device; the storage module is used to store data and/or instructions; the communication module communicates with an external device; the chip module is used to call the data and/or instructions stored in the storage module, and in combination with the communication module, execute the method as described in the first aspect or any optional implementation method of the first aspect, or execute the method as described in the second aspect or any optional implementation method of the second aspect.
  • an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program includes program instructions.
  • the program instructions When an electronic device executes the program instructions, it implements the method described in the first aspect or any optional embodiment of the first aspect, or implements the method described in the second aspect or any optional embodiment of the second aspect.
  • FIG1 is a schematic diagram of the structure of a communication system provided in an embodiment of the present application.
  • FIG2 is a flow chart of a report transmission method provided in an embodiment of the present application.
  • FIG3a is a schematic diagram of a report provided in an embodiment of the present application.
  • FIG3b is a schematic diagram of resource conflict processing provided by an embodiment of the present application.
  • FIG3c is a schematic diagram of an effective time point provided in an embodiment of the present application.
  • FIG3d is a schematic diagram of a flow chart of another report transmission method provided in an embodiment of the present application.
  • FIG4 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application.
  • FIG5 is a schematic diagram of the structure of another communication device provided in an embodiment of the present application.
  • FIG6 is a schematic diagram of the structure of another communication device provided in an embodiment of the present application.
  • FIG. 7 is a schematic diagram of the structure of a module device provided in an embodiment of the present application.
  • the character "/" indicates that the objects before and after the association are in an or relationship.
  • A/B can represent A or B.
  • "And/or" describes the association relationship of the associated objects, indicating that three relationships can exist.
  • a and/or B can represent: A exists alone, A and B exist at the same time, and B exists alone.
  • At least one refers to one or more
  • plural refers to two or more
  • at least one of the following” or similar expressions refers to any combination of these items, which may include any combination of single items or plural items.
  • at least one of A, B, or C may represent: A, B, C, A and B, A and C, B and C, or A, B and C.
  • each of A, B, and C may be an element itself, or a set containing one or more elements.
  • transmission can include sending and/or receiving, which can be a noun or a verb.
  • the equal to involved in the embodiments of the present application can be used in conjunction with greater than, and is applicable to the technical solution adopted when greater than, and can also be used in conjunction with less than, and is applicable to the technical solution adopted when less than. It should be noted that when equal to is used in conjunction with greater than, it cannot be used in conjunction with less than; when equal to is used in conjunction with less than, it cannot be used in conjunction with greater than.
  • the terminal equipment is a device with wireless transceiver functions, which can be referred to as a terminal, user equipment (UE), mobile station (MS), mobile terminal (MT), access terminal equipment, vehicle-mounted terminal equipment, industrial control terminal equipment, UE unit, UE station, mobile station, remote station, remote terminal equipment, mobile device, UE terminal equipment, wireless communication equipment, UE agent or UE device, etc.
  • the terminal equipment can be fixed or mobile. It should be noted that the terminal equipment can support at least one wireless communication technology, such as long term evolution (LTE), new radio (NR), etc.
  • LTE long term evolution
  • NR new radio
  • the terminal device can be a mobile phone, a tablet computer, a desktop computer, a laptop computer, an all-in-one computer, a vehicle-mounted terminal, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, etc.
  • VR virtual reality
  • AR augmented reality
  • the terminal device may be a wireless terminal in a smart city, a wireless terminal in a smart home, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a wearable device, a terminal device in a future mobile communication network, or a terminal device in a future evolved public mobile land network (PLMN), etc.
  • the terminal device may also be a device with a transceiver function, such as a chip system.
  • the chip system may include a chip and may also include other discrete devices.
  • the network equipment is a device that provides wireless communication functions for terminal equipment, and may also be referred to as access network equipment, radio access network (RAN) equipment, etc.
  • the network equipment may support at least one wireless communication technology, such as LTE, NR, etc.
  • the network equipment includes but is not limited to: the next generation base station (generation nodeB, gNB) in the fifth generation mobile communication system (5th-generation, 5G), the sixth generation mobile communication system (6th-generation, 6G), the evolved node B (eNB), the radio network controller (RNC), the node B (NB), the base station controller (BSC), the base transceiver station (BTS), the home base station (for example, home evolved node B, or home node B, HNB), the baseband unit (BBU), the transmitting and receiving point (transmitting and receiving point,
  • the network device may also be a wireless controller, a centralized unit (CU), and/or a distributed unit (DU) in a cloud radio access network (CRAN) scenario, or the network device may be a relay station, an access point, a vehicle-mounted device, a terminal device, a wearable device, and a network device in future mobile communications or a network device in a future evolved PLMN.
  • the network device may also be a centralized
  • FIG 1 is a schematic diagram of the structure of a communication system provided in an embodiment of the present application.
  • the communication system may include but is not limited to one or more network devices, one or more terminal devices, as shown in Figure 1, taking a network device 101 and a terminal device 102 as an example, wherein the network device 101 in Figure 1 is a base station as an example, and the terminal device 102 is a mobile phone as an example, and the terminal device 102 can establish a wireless link with the network device 101 for communication.
  • the communication system shown in Figure 1 includes but is not limited to network devices and terminal devices, and may also include other communication devices. The number and form of the devices shown in Figure 1 are used for example and do not constitute a limitation on the embodiments of the present application.
  • AI models are currently widely used in various fields. Integrating AI models into wireless communication networks can significantly improve technical indicators such as throughput, processing latency, and user capacity, which is an important task for future wireless communication networks.
  • AI models can be implemented in many ways, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc.
  • neural network is composed of neurons, including: input parameters, multiplicative coefficients, additive coefficients, activation functions, etc.
  • Common activation functions include: Sigmoid, tanh, ReLU (Rectified Linear Unit, linear rectification function, rectified linear unit), etc.
  • the parameters of the neural network are optimized by the gradient optimization algorithm, which is a type of algorithm that minimizes or maximizes the objective function (also called the loss function), and the objective function is often a mathematical combination of model parameters and data.
  • the gradient optimization algorithm which is a type of algorithm that minimizes or maximizes the objective function (also called the loss function)
  • the objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we build a neural network model f. With the model, we can predict the output information based on the input, and calculate the difference between the predicted value and the true value, which is the loss function. Our goal is to find a suitable system to minimize the value of the loss function. The smaller the loss value, the closer the model is to the actual situation.
  • the common optimization algorithms are basically based on the error back propagation (BP) algorithm.
  • BP error back propagation
  • the basic idea of the BP algorithm is that the learning process consists of two processes: the forward propagation of the signal and the back propagation of the error.
  • the input sample is transmitted from the input layer, processed by each hidden layer layer by layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, it will enter the error back propagation stage.
  • Error back propagation is to propagate the output error layer by layer through the hidden layer to the input layer in some form, and distribute the error to all units in each layer, so as to obtain the error signal of each layer unit, and this error signal is used as the basis for correcting the weights of each unit.
  • This process of adjusting the weights of each layer of the signal forward propagation and error back propagation is repeated.
  • the process of continuous adjustment of weights is the learning and training process of the AI network. This process continues until the error of the network output is reduced to an acceptable level, or until the pre-set number of learning times is reached.
  • the model information of the AI model may include at least one of the following:
  • Model ID model ID
  • model structure number of layers, number of neurons, etc.
  • model parameters model computing power, storage capacity, etc.
  • the AI model can be a fully connected network, a convolutional neural network, and so on.
  • the update of the AI model may include at least one of the following: activation, switching, training, updating, supervision, selection, verification, validation, fine-tuning, adjustment, and testing of AI model information.
  • FIG. 2 a flow chart of an embodiment of a report transmission method provided by the present application is shown. As shown in FIG. 2 , the method may include but is not limited to the following steps:
  • the terminal device sends a report based on the update status of the first AI model, where the report includes update information of the first AI model.
  • the triggering method for triggering the terminal device to update the first AI model is not limited in this application.
  • it can be based on an event detected by the terminal device to trigger the model update, or it can be that the network device triggers the terminal device to update the model through network signaling.
  • the network signaling indicates that the terminal device needs to update from the first AI model to the second AI model.
  • the network device receives a report sent by the terminal device.
  • the report may include at least one of the following information a to information m, and the information a to information m are described below respectively:
  • first indication information is used to indicate completion of updating the first AI model
  • the completion of updating the first AI model may be confirmed by an ACK.
  • model information of a second AI model where the second AI model is a model obtained by updating the first AI model
  • the model information of the second AI model may include but is not limited to at least one of the model ID, model structure or model parameters of the second AI model.
  • the terminal device updates from the first AI model to the second AI model, and the deactivated AI model indicated by the second indication information may include the first AI model before the update, and/or other models other than the first AI model and the second AI model, which is not limited in this application. It is understandable that after deactivating the AI model, the network device may not subsequently instruct the terminal device to switch to the deactivated AI model, or it may take a long time for the terminal device to switch to the deactivated AI model, or the terminal device may not be able to switch to the deactivated AI model.
  • third indication information where the third indication information is used to indicate that the update of the first AI model is not completed
  • the fact that the terminal device fails to complete the update of the first AI model can be understood as the terminal device not supporting the layer, model size, model computing power, etc. of the second AI model, and thus fails to complete the update of the first AI model to the second AI model. It can also be that the terminal device fails to update, resulting in the failure to complete the update of the first AI model.
  • the second AI model is a model obtained by updating the first AI model
  • the preset information associated with the second AI model can be understood as a corresponding relationship between the second AI model and the preset information, that is, when the preset information changes, other models may be associated, and different models may be associated through changes in the preset information.
  • the network information may include at least one of the following: Public Land Mobile Network (PLMN) information, operator identification information, network equipment vendor identification information, Tracking Area ID (TAI) information, roaming control (SOR) information, terminal route selection policy (UE Route Selection Policy, URSP) information, etc.
  • PLMN Public Land Mobile Network
  • TAI Tracking Area ID
  • SOR roaming control
  • UE Route Selection Policy URSP
  • the access network information may include at least one of the following: operating frequency information (frequency number, frequency band number, etc.), cell group information (cell group id), serving cell information (serving cell id), physical cell identifier (PCI), transmission and reception point (TRP) identification information, bandwidth part (Bandwidth Part, BWP) identification information, reference signal (RS) information associated with the cell, such as synchronization signal block (Synchronization Signal Block, SSB).
  • the TRP identification information may include but is not limited to at least one of the following: control-resource set (CORESET) identification, control resource set pool (CORESET Pool) identification, control resource set group identification, transmission configuration indication (TCI) state pool identification, TCI state identification, reference signal resource identification, reference signal resource set identification.
  • the channel quality information can be the reference signal receiving power (RSRP) of layer 1 or layer 3, signal to interference plus noise ratio (SINR), etc.
  • RSRP reference signal receiving power
  • SINR signal to interference plus noise ratio
  • the time information may be timestamp information, time period information, time point, etc.
  • the time information may also be associated with the model, for example, at a certain timestamp, the first AI model needs to be updated to the second AI model.
  • the terminal device identification information may be the device vendor identification information or other identification of the terminal device, and this application does not limit this.
  • the terminal device when the terminal device needs to update from the first AI model to the second model, but the terminal device has not completed the update to the second AI model, the reason for the failure to complete the update is not limited, for example, the model structure or parameters of the second AI model are not supported, or the update process fails due to other reasons.
  • the terminal device can switch to a third AI model, which can be a default model, which can be the same as or different from the first AI model, and the third AI model is different from the second AI model.
  • fourth indication information where the fourth indication information is used to indicate the use of a non-AI model
  • non-AI models can be understood as using conventional measurement and transmission methods, that is, not using AI models for prediction.
  • the terminal device may not support the model structure or parameters of the second AI model, or the update process fails due to other reasons.
  • the terminal device may instruct it to use a non-AI model through the fourth indication information.
  • fifth indication information is used to indicate at least one attribute information of the second AI model, where the at least one attribute information is attribute information that is not supported by the terminal device when the first AI model is not updated to the second AI model;
  • the terminal device may not support at least one attribute information of the second AI model, resulting in the terminal device not converting the first AI model into
  • the terminal device indicates, through fifth indication information, which attribute information of the second AI model is not supported.
  • the at least one attribute information may include at least one of the following: a model identifier of the second AI model, model structure information of the second AI model, and model parameters of the second AI model.
  • the terminal device does not support the layer, model size, or model computing power in the second AI model.
  • the report type may include an AI model update report, that is, the AI report is distinguished from other regular reports by the report type.
  • Other regular reports may include (Channel State Information, CSI) report, beam report, hybrid automatic repeat request (Hybrid Automatic Repeat reQuest, HARQ) report, etc.
  • the report type may include at least one of a conventional measurement feedback report of a non-AI model (such as the aforementioned CSI report, beam report, HARQ report, and other conventional reports), a prediction feedback report of an AI model, an enhanced measurement feedback report of an AI model, and an update report of an AI model. That is, the AI model update report is divided into multiple types.
  • different report types can be indicated by different values of a parameter
  • the parameter can be the report Quantity parameter indicated in the configuration signaling report configuration, that is, the report type is indicated by the value of the report Quantity parameter. It is understandable that it can also be other parameters, such as newly defined parameters, etc., which are not limited in this application.
  • the report includes a bit. If the value of the bit is 1, it indicates that the report is an AI model update report. If the value of the bit is 0, it indicates that the report is other regular reports. Optionally, which other regular report can be obtained by the value of the report Quantity parameter. It is understandable that the above-mentioned bit value of 1 indicating an AI model update report is only an example, and it can also be a value of 0 to indicate an AI model update report, which is not limited in this application.
  • the terminal device when the terminal device needs to update from the first AI model to the second model, but the terminal device has not completed the update to the second AI model, the reason for the incomplete update is not limited, for example, the model structure or parameters of the second AI model are not supported, or the update process fails due to other reasons.
  • the terminal device can request the network to instruct the fourth AI model to switch through the first request information.
  • the terminal device may indicate to the network device the recommended duration for updating from the first AI model to the second AI model, so as to avoid the problem of data transmission failure caused by the network device scheduling before the terminal device is updated.
  • the terminal device can indicate the effective period of the report to the network through a report.
  • the effective period can be understood as the updated AI model taking effect after the effective period.
  • reference signal information measured when the first AI model is updated including at least one of the number of reference signal resources, the index of a reference signal resource set, the index of the reference signal resource, and a measurement result of the reference signal.
  • the report may include reference signal information in which the measurement result of the reference signal is greater than or equal to a preset threshold when the AI model is updated, and the reference information includes at least one of the number of reference signal resources, the index of the reference signal resource set, the index of the reference signal resource, and the measurement result of the reference signal.
  • the report may include one or more of the above information a-m, and the report may also report other information in addition to the above information a-m, which is not limited in this application.
  • the report in the embodiment of the present application may include one or more parts.
  • the information carried in the partial part ordered first in the report can be used to determine the information carried in the partial part ordered later.
  • the information carried in the partial part ordered first in the report can determine whether the partial part ordered later carries information, and/or, the information carried in the partial part ordered first in the report can determine what information the partial part ordered later carries.
  • the information carried in the partial part ordered first (for example, part1) can determine the length, content or format of the partial part ordered later.
  • the report includes a first part (part1) and a second part (part2), and the first part (part1) is ordered before the second part (part2). Therefore, the information carried in the first part (part1) can determine the information carried in the second part (part2).
  • part1 includes the above information a, that is, part1 includes the first indication information for indicating that the update of the first AI model is completed
  • the report may not include other parts part, thereby saving signaling overhead.
  • Other parts part may also be included, for example, the other parts part includes at least one of the above information b, information c, information e and information m.
  • part 1 may include at least one of information f, information g, information h and information j.
  • part 2 may include at least one of an index of the reference signal resource and a measurement result of the reference signal.
  • the format of the report can be determined by the triggering method for triggering the update of the first AI model.
  • different triggering methods have different report formats, where the report format can be understood as the length of the report and/or the content included in the part.
  • the triggering method includes: model update triggered by an event detected by the terminal device, or model update triggered by network signaling.
  • part 1 may include at least one of information b, information c, information f, information g, information i, and information j, and part 2 may include at least one of information e and information h.
  • part 1 may include uplink information a or d
  • part 2 may include at least one of information b, information c, information f, information g, information i, and information j
  • part 3 may include at least one of information e and information h.
  • each information in the report is encoded independently, such as the information a-m above, each information is encoded independently.
  • the information of a part is encoded, for example, the information in part1 is encoded together, and the information in part2 is encoded together.
  • all the information in the report is jointly encoded.
  • multiple parts are jointly encoded together, such as the information in part1 and the information in part2 are jointly encoded together.
  • each signaling domain in the report can be differentially quantized.
  • the following example illustrates the differential quantization method of the information contained in each signaling domain in the report.
  • each signaling domain in the report can be differentially quantized independently, or multiple signaling domains can be differentially quantized together, which is not limited in this application.
  • the following example illustrates the differential quantization of the reference signal resource measurement result RSRP in a signaling domain. For example, if a signaling domain contains the measurement results of N reference signal resources, the maximum or minimum value of the N measurement results can be quantized using K1 bits, and then the difference between the other N-1 measurement results in the signaling domain and the measurement result is quantized. The bit length required for the quantized N-1 measurement results is less than K1.
  • the maximum or minimum value is selected from the multiple signaling domains, and the other measurement results are differentially quantized with the maximum or minimum value.
  • N is an integer greater than 1
  • K1 is an integer greater than or equal to 1. It can be understood that at least one signaling field in the above report may contain the measurement result RSRP of the reference signal resource reaching the preset threshold value, so as to save signaling overhead.
  • the terminal device may use the periodic uplink channel resources preconfigured by the network to send reports.
  • the terminal device uses the preconfigured periodic Physical Uplink Control Channel (PUCCH) resources to send reports.
  • PUCCH Physical Uplink Control Channel
  • the terminal device may send the report using the most recent uplink authorization resource available for carrying the report (next available), for example, the next uplink authorization resource available for carrying the report.
  • the uplink authorization resource may be a dynamic authorization resource or a configured authorization resource.
  • the terminal device sends a report using the uplink authorized resource that is used most times in a historical time period, and the historical time period may be a period of time before the report is generated.
  • the terminal device may use the last used uplink authorization resource to send a report, and the present application does not limit the content of the last used uplink authorization resource transmission.
  • the terminal device may send a scheduling request (SR) to the network device, trigger the network device to indicate uplink authorized resources through the SR, and the terminal device uses the uplink authorized resources indicated by the network device to send a report.
  • SR scheduling request
  • the terminal device may send a report on the primary cell Pcell.
  • the terminal device may send a report on a cell in the FR1 frequency band.
  • the terminal device may use one or more uplink beams to repeatedly send reports to improve the reliability of report transmission.
  • the terminal device may use one or more uplink beams to repeatedly send reports in a time division multiplexing manner, or the terminal device may use multiple uplink beams to send reports simultaneously, and the multiple uplink beams may be beams on multiple panels.
  • the reports sent simultaneously on multiple uplink beams may be completely identical, or different layers or frequency domain resources or orthogonal code sequences may be used respectively to reduce mutual interference.
  • the report containing the AI model update information in the embodiment of the present application may also be sent simultaneously with other reports (such as CSI reports, beam reports, HARQ reports, etc.).
  • reports such as CSI reports, beam reports, HARQ reports, etc.
  • multiple uplink beams are used to simultaneously send reports containing AI model update information and other reports, wherein each uplink beam sends a report.
  • the reports sent simultaneously use different layers or frequency domain resources or orthogonal code sequences on multiple uplink beams to reduce mutual interference.
  • the following describes a solution to the conflict between the information resources of the first uplink channel used to carry reports and the channel resources of the second uplink channel used to carry other information, wherein the conflict can be understood as the overlap in the time domain and/or frequency domain between the channel resources of the first uplink channel and the channel resources of the second uplink channel, and the information carried in the second uplink channel may include CSI reports, beam reports, HARQ reports, SRs, beam failure recovery requests, etc., which are not limited in this application.
  • the report and the information carried in the second uplink channel are multiplexed onto the channel resources of the third uplink channel for transmission.
  • the third uplink channel may be the first uplink channel, for example, the first uplink channel is sufficient to carry the information carried in the report and the second uplink channel, or the third uplink channel may be the second uplink channel, for example, the second uplink channel is sufficient to carry the information carried in the report and the second uplink channel, or may be an uplink channel other than the first uplink channel and the second uplink channel.
  • the order of arrangement of the information carried in the report and the second uplink channel in the third uplink channel can be determined by the priority of the report and the priority of the information carried in the second uplink channel.
  • the higher the priority of the information the higher the order of the information, which can ensure that the information with higher priority is carried first, so that the information with higher priority is parsed first.
  • the information carried in the report and/or the second uplink channel can be divided into multiple parts, at least one part of the information is discarded, and the remaining information is multiplexed to the channel resources of the third uplink channel.
  • the report for carrying AI model update information of the present application is divided into two parts, and the lower priority part is discarded, and the remaining part is multiplexed with the information carried in the second uplink channel to the channel resources of the third uplink channel for transmission.
  • the first uplink channel is sent, and the information carried in the second uplink channel is discarded.
  • the AI model update report of the present application is assumed to have the highest priority.
  • the report can be sent using the resources of the next uplink authorization 1, but the report conflicts with the resources of other uplink channels (i.e., the second uplink channel) or reference signals (RS).
  • the other uplink channels or reference signals can be discarded, and the first uplink channel for carrying the report can be sent on the above-mentioned authorization 1.
  • the transmit power of the first uplink channel and/or the transmit power of the second uplink channel may be adjusted, and the first uplink channel and the second uplink channel after the power adjustment are transmitted, wherein the sum of the transmit power of the first uplink channel and the transmit power of the second uplink channel after the power adjustment is less than or equal to the maximum transmit power supported by the terminal device.
  • the transmit power of the first uplink channel may be increased, and/or the transmit power of the second uplink channel may be decreased. For example, if the priority of the report carried in the first uplink channel is greater than the priority of the information carried in the second uplink channel, the transmit power in the first uplink channel may be increased; and/or the transmit power of the second uplink channel may be decreased. For another example, if the priority of the report carried in the first uplink channel is less than the priority of the information carried in the second uplink channel, the transmit power in the first uplink channel may be decreased; and/or the transmit power of the second uplink channel may be increased.
  • the priority of the report containing AI model update information can have the highest priority, that is, higher than the priority of various uplink control information (Uplink Control Information, UCI).
  • UCI Uplink Control Information
  • the priority of the report is the highest, wherein the first information may include at least one of the following items: the above information a (i.e., the first indication information), the above information b (i.e., the model information of the second AI model), the above information d (i.e., the third indication information), the above information f (i.e., the model information of the third AI model), the above information g (i.e., the fourth indication information), and the above information i (i.e., the report type of the report).
  • the above information a i.e., the first indication information
  • the above information b i.e., the model information of the second AI model
  • the above information d i.e., the third indication information
  • the above information f i.e., the model information of the third AI model
  • the above information g i.e., the fourth indication information
  • the above information i i.e., the report type of the report.
  • the report containing the AI model update information has the highest priority.
  • the report containing the AI model update information has the lowest priority.
  • the priority of the report is the lowest, and the second information may be the above-mentioned information d (ie, the third indication information).
  • the effective time of the report can be understood as the network
  • the time when the network device and the terminal device enable the content indicated in the report for example, if the report indicates an update to the second AI model, the effective time can be understood as the time when the second AI model is enabled.
  • the effective time of the report can be determined by at least one of the following:
  • the first duration after sending the report can be understood as the first duration after the end of the time domain resources of the uplink channel where the report is located.
  • the time offset can be understood as the first duration, and after sending the report, the start time of the first time slot after the time offset is the effective time point, that is, it takes effect from the effective time point.
  • the second time period after the network sends the target signaling is effective, and the target signaling is used to indicate that the first AI model is updated; for example, it can be effective in the first time slot after the second time period after the network sends the target signaling.
  • the second time period after the target signaling is sent can be understood as the second time period after the time domain resource of the downlink channel where the target signaling is located ends.
  • the third time period after sending the second request information takes effect, and the second request information is used to request the network to send information used to assist in updating the first AI model; for example, the second request information can be used to request the network to send a reference signal for the terminal device to measure in order to update the first AI model.
  • the effective time length of the second AI model that is, the second AI model is valid during the effective time length
  • the second AI model is a model obtained by updating the first AI model
  • the units of the above various durations may be frames, time slots, symbols, etc., without limitation.
  • the above effective time may be indicated by the network or agreed upon by a protocol.
  • the above-mentioned effective time needs to meet at least one of the following: the training time, inference time, update time, etc. of the AI model (for example, measuring the reference signal sent by the network and using the AI model for training, that is, the new model needs to be enabled after the training is completed), the compilation time of the AI model (when the AI model structure is updated, the AI model needs to be compiled, and the effective time needs to be enabled after the compilation time), and the parameter update time of the AI model (when the parameters of the AI model are updated, the parameter update time needs to be met).
  • the training time for example, measuring the reference signal sent by the network and using the AI model for training, that is, the new model needs to be enabled after the training is completed
  • the compilation time of the AI model when the AI model structure is updated, the AI model needs to be compiled, and the effective time needs to be enabled after the compilation time
  • the parameter update time of the AI model when the parameters of the AI model are updated, the parameter update time needs to be met.
  • the above-mentioned effective time (such as the number of symbols contained in the duration) can be determined by the subcarrier spacing corresponding to the preset information associated with the updated second AI model, or by the minimum subcarrier spacing among the multiple subcarrier spacings corresponding to the preset information associated with the updated second AI model.
  • the preset information includes at least one of network information, access network information, channel quality information, time information or terminal equipment identification information.
  • the network information includes at least one of the following: public land mobile network PLMN information, operator identification information, network equipment vendor identification information, tracking area identification TAI information, roaming control SOR information, routing selection strategy URSP information, etc.
  • the access network information includes at least one of the following: operating frequency information, cell group information, service cell information, physical cell identification, sending and receiving point TRP identification information, bandwidth part BWP identification information, reference signal RS information associated with the cell, etc.
  • operating frequency information cell group information
  • service cell information physical cell identification
  • sending and receiving point TRP identification information bandwidth part BWP identification information
  • reference signal RS information reference signal associated with the cell, etc.
  • each BWP of each cell in the cell group will correspond to a subcarrier spacing SCS, then the minimum SCS is used to determine the effective time, so as to ensure that the updated AI models corresponding to all cells in the cell group are effective at the same time.
  • the length of each symbol can be determined by the subcarrier spacing, and therefore, the number of symbols contained in the above time length is also determined by the subcarrier spacing.
  • FIG. 3d is a flow chart of another report transmission method provided in an embodiment of the present application. As shown in FIG. 3d, the method includes but is not limited to the following steps:
  • the terminal device sends a report based on the update status of the first AI model, where the report includes update information of the first AI model.
  • the network device receives a report sent by the terminal device.
  • step 201-step 202 can refer to step 101-step 102 in the embodiment of Figure 2, and will not be repeated here.
  • the network device sends part or all of the information in the report to the target network, target site or target cell.
  • the network device may send all the information in the report to the target network, target site or target cell, or may send part of the information therein to the target network, target site or target cell.
  • some general information may be sent to the target network, target site or target cell.
  • the general information includes but is not limited to at least one of the following: model information of the updated second AI model, the data set used for model updating, reference signal information used during training, location information of the terminal device, operator identification/PLMN/network equipment vendor information of the terminal device, current TAI/SOR/URSP information of the terminal device, current access network information of the terminal device, ID of the terminal device, equipment vendor information of the terminal device, etc.
  • the target network may satisfy at least one of the following:
  • the target network is the same as the current network
  • the target network has the same operator ID or the same PLMN information as the current network
  • the target network and the current network have the same network equipment vendor ID;
  • the target network is the previous network where the terminal device resides;
  • the target network is a network adjacent to the current network
  • the current network is the network where the terminal device currently resides.
  • the above network can be understood as a core network or an operator network, which is not limited in this application.
  • the target site satisfies at least one of the following:
  • the target site has the same operator ID or PLMN or network equipment vendor as the current site;
  • the target site is a site corresponding to each neighboring area in the neighboring area list configured for the current site, and the neighboring area list includes one or more neighboring areas;
  • the cell of the target site and the cell of the current site are both in the neighboring cell list of the reference site;
  • the target site is a site corresponding to the first neighboring cell in the neighboring cell list configured for the current site, where the first neighboring cell is a neighboring cell associated with beam information configured, activated or indicated by the network;
  • the cell of the target site and the cell of the current site are both in the neighboring cell list of the reference site, and the cell of the target site and the cell of the current site are both cells associated with beam information configured, activated or indicated by the network;
  • the target site is the site corresponding to the last cell where the terminal device resides;
  • the target site is the adjacent site of the current site
  • the target site is the AI model information management server, for example, LMF, AI model information processing node, and third-party OTT (over the top) server;
  • AI model information management server for example, LMF, AI model information processing node, and third-party OTT (over the top) server;
  • the current site is the site corresponding to the cell where the terminal device is currently located.
  • the above site can be understood as a base station or a TRP, and the current site can be the above network device.
  • the target cell satisfies at least one of the following:
  • the target cell has the same operator ID or PLMN or network equipment vendor as the current cell;
  • the target cell is a cell in a neighbor cell list configured for the current cell, where the neighbor cell list includes one or more neighbor cells;
  • the target cell and the current cell are both in the neighboring cell list of the reference cell;
  • the target cell is a cell in the neighbor cell list configured for the current cell, and the target cell is a neighbor cell associated with the beam information configured, activated or indicated by the network;
  • the target cell and the current cell are both in the neighbor cell list of the reference cell, and the target cell and the current cell are both cells associated with beam information configured, activated or indicated by the network;
  • the target cell is the last cell where the terminal device resides
  • the target cell is a neighboring cell of the current cell
  • the current cell is the cell where the terminal device currently resides.
  • the network device may send all or part of the information in the report to the target cell, target site, or target network, so that the target cell, target site, or target network can obtain the AI model update information of the terminal device in advance, and prepare the terminal device to switch to the target cell, target site, or target network in advance.
  • FIG 4 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application.
  • the device may be a terminal device, or a device in a terminal device, for example, a chip or chip module in the terminal device, or a device that can be used in conjunction with the terminal device.
  • the communication device 400 shown in Figure 4 may include a sending unit 401 and a processing unit 402. Among them:
  • the sending unit 401 is used to send a report according to the update status of the first artificial intelligence AI model; wherein the report includes the update information of the first AI model.
  • the report includes at least one of the following information:
  • First indication information where the first indication information is used to indicate that the update of the first AI model is completed
  • Model information of a second AI model where the second AI model is a model obtained by updating the first AI model
  • the second indication information is used to indicate model information of a deactivated AI model
  • third indication information where the third indication information is used to indicate that the update of the first AI model is not completed
  • Preset information associated with the second AI model the preset information including at least one of network information, access network information, channel quality information, time information, or terminal device identification information, and the second AI model is a model obtained by updating the first AI model;
  • Model information of a third AI model where the third AI model is switched to when the first AI model is not updated to the second AI model;
  • Fourth indication information where the fourth indication information is used to indicate the use of a non-AI model
  • the fifth indication information is used to indicate at least one attribute information of the second AI model, wherein the at least one attribute information
  • the information is attribute information that is not supported by the terminal device when the first AI model is not updated to the second AI model
  • first request information where the first request information is used to request the network to indicate a fourth AI model
  • the reference signal information measured when the first AI model is updated including at least one of the number of reference signal resources, the index of a reference signal resource set, the index of the reference signal resource, and a measurement result of the reference signal.
  • the report type includes an AI model update report
  • the report type includes at least one of a conventional measurement feedback report of a non-AI model, a prediction feedback report of an AI model, an enhanced measurement feedback report of an AI model, and an update report of an AI model.
  • the at least one attribute information includes at least one of the following: a model identifier of the second AI model, model structure information of the second AI model, and a model parameter of the second AI model.
  • the report includes at least one part, and information carried by a part ranked first in the report is used to determine information carried by a part ranked later.
  • the format of the report is determined by a triggering method for triggering the update of the first AI model; the triggering method includes: model update triggered by a detected event, or model update triggered by network signaling.
  • the sending a report includes:
  • the sending unit 401 is specifically used to send the report using uplink resources, where the uplink resources include periodic uplink channel resources pre-configured by the network, or the most recent uplink authorization resource that can be used to carry the report, or the uplink authorization resource that is used the most times in a historical time period, or the uplink authorization resource used last, or the uplink authorization resource indicated by the network device triggered by a scheduling request SR.
  • the uplink resources include periodic uplink channel resources pre-configured by the network, or the most recent uplink authorization resource that can be used to carry the report, or the uplink authorization resource that is used the most times in a historical time period, or the uplink authorization resource used last, or the uplink authorization resource indicated by the network device triggered by a scheduling request SR.
  • the sending unit 401 is specifically configured to send the report in a primary cell; or, send the report in a cell in the FR1 frequency band.
  • the sending unit 401 is specifically configured to repeatedly send the report using one or more uplink beams.
  • the sending unit 401 is specifically configured to use one or more uplink beams to repeatedly send the report in a time division multiplexing manner; or, use multiple uplink beams to simultaneously send the report.
  • the simultaneously transmitted reports are transmitted on the multiple uplink beams using different layers or frequency domain resources or orthogonal code sequences respectively.
  • the sending unit 401 is specifically configured to send the report in one of the following ways if a channel resource of the first uplink channel used to carry the report conflicts with a channel resource of the second uplink channel:
  • the report and the information carried in the second uplink channel are multiplexed onto the channel resources of the third uplink channel for transmission; or, the first uplink channel is transmitted and the information carried in the second uplink channel is discarded; or, the transmission power of the first uplink channel and/or the transmission power of the second uplink channel is adjusted by the processing unit 402, and the transmission unit 401 is instructed to transmit the first uplink channel and the second uplink channel after the power adjustment, wherein the sum of the transmission power of the first uplink channel and the transmission power of the second uplink channel after the power adjustment is less than or equal to the maximum transmission power supported by the terminal device.
  • the processing unit 402 is specifically used to increase the transmission power of the first uplink channel if the priority of the report is greater than the priority of the information carried in the second uplink channel; and/or, to reduce the transmission power of the second uplink channel.
  • the sending unit 401 is specifically configured to send the first uplink channel and discard the information carried in the second uplink channel if the priority of the report is greater than the priority of the information carried in the second uplink channel.
  • the order in which the report and the information carried in the second uplink channel are arranged in the third uplink channel is determined by the priority of the report and the priority of the information carried in the second uplink channel.
  • the sending unit 401 is specifically configured to send the second uplink channel and discard the report carried in the first uplink channel if the priority of the report is lower than the priority of the information carried in the second uplink channel.
  • the report has the highest priority; or, when the report contains the first information, the report has the highest priority; or, when the updated second AI model is different from the first AI model, the report has the highest priority.
  • the first information includes at least one of the following: the first indication information, model information of the second AI model, the third indication information, model information of the third AI model, the fourth indication information, and a report type of the report.
  • the priority of the report is the lowest.
  • the effective time of the report is determined by at least one of the following:
  • the first period of time after the report is sent shall come into effect
  • the second time period takes effect after the network sends a target signaling, where the target signaling is used to indicate that the first AI model is to be updated;
  • the third time period after sending the second request information becomes effective, wherein the second request information is used to request the network to send information for assisting in updating the first AI model;
  • the effectiveness time is indicated by the network or agreed upon by a protocol.
  • the effective time is determined by the subcarrier spacing corresponding to the preset information associated with the second AI model, or by the minimum subcarrier spacing among multiple subcarrier spacings corresponding to the preset information associated with the second AI model, and the preset information includes at least one of network information, access network information, channel quality information, time information or terminal device identification information.
  • the network information includes at least one of the following:
  • Public land mobile network PLMN information Public land mobile network PLMN information, operator identification information, network equipment vendor identification information, tracking area identification TAI information, roaming control SOR information, and routing selection strategy URSP information.
  • the access network information includes at least one of the following:
  • Working frequency information cell group information, serving cell information, physical cell identifier, transmitting and receiving point TRP identifier information, bandwidth part BWP identifier information, and reference signal RS information associated with the cell.
  • FIG. 5 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application.
  • the device may be a network device, or a device in a network device, for example, a chip or chip module in the network device, or a device that can be used in conjunction with a network device.
  • the communication device 500 shown in Figure 5 may include a receiving unit 501 and a sending unit 502. Among them:
  • the receiving unit 501 is used to receive a report sent by a terminal device, where the report includes update information of the terminal device to the first AI artificial intelligence model.
  • the report includes at least one of the following information:
  • First indication information where the first indication information is used to indicate that the update of the first AI model is completed
  • Model information of a second AI model where the second AI model is a model obtained by updating the first AI model
  • the second indication information is used to indicate model information of a deactivated AI model
  • third indication information where the third indication information is used to indicate that the update of the first AI model is not completed
  • Preset information associated with the second AI model the preset information including at least one of network information, access network information, channel quality information, time information, or terminal device identification information, and the second AI model is a model obtained by updating the first AI model;
  • Model information of a third AI model where the third AI model is switched to when the first AI model is not updated to the second AI model;
  • Fourth indication information where the fourth indication information is used to indicate the use of a non-AI model
  • fifth indication information where the fifth indication information is used to indicate at least one attribute information of the second AI model, where the at least one attribute information is attribute information that is not supported by the terminal device when the first AI model is not updated to the second AI model;
  • first request information where the first request information is used to request the network to indicate a fourth AI model
  • the reference signal information measured when the first AI model is updated including at least one of the number of reference signal resources, the index of a reference signal resource set, the index of the reference signal resource, and a measurement result of the reference signal.
  • the network information includes at least one of the following:
  • Public land mobile network PLMN information Public land mobile network PLMN information, operator identification information, network equipment vendor identification information, tracking area identification TAI information, roaming control SOR information, and routing selection strategy URSP information.
  • the access network information includes at least one of the following:
  • the report type includes an AI model update report
  • the report type includes at least one of a conventional measurement feedback report of a non-AI model, a prediction feedback report of an AI model, an enhanced measurement feedback report of an AI model, and an update report of an AI model.
  • the at least one attribute information includes at least one of the following: a model identifier of the second AI model, model structure information of the second AI model, and a model parameter of the second AI model.
  • the report includes at least one part, and information carried by a part ranked first in the report is used to determine information carried by a part ranked later.
  • the sending unit 502 is configured to send part or all of the information in the report to a target network, a target site, or a target cell.
  • the target network satisfies at least one of the following:
  • the target network is the same as the current network
  • the target network has the same operator identifier or the same PLMN information as the current network;
  • the target network and the current network have the same network equipment vendor identifier
  • the target network is the last network where the terminal device resides
  • the target network is a network adjacent to the current network
  • the current network is the network where the terminal device currently resides.
  • the target site satisfies at least one of the following:
  • the target site and the current site have the same operator identifier or PLMN or network equipment vendor;
  • the target site is a site corresponding to each neighboring area in a neighboring area list configured for the current site, where the neighboring area list includes one or more neighboring areas;
  • the cell of the target site and the cell of the current site are both in the neighboring cell list of the reference site;
  • the target site is a site corresponding to the first neighboring area in the neighboring area list configured for the current site, where the first neighboring area is a neighboring area associated with beam information configured, activated or indicated by the network;
  • the cell of the target site and the cell of the current site are both in the neighboring cell list of the reference site, and the cell of the target site and the cell of the current site are both cells associated with beam information configured, activated or indicated by the network;
  • the target site is a site corresponding to the last cell where the terminal device resides;
  • the target site is an adjacent site of the current site
  • the target site is an AI model information management server
  • the current site is the site corresponding to the cell where the terminal device is currently located.
  • the target cell satisfies at least one of the following:
  • the target cell and the current cell have the same operator identifier or PLMN or network equipment vendor;
  • the target cell is a cell in a neighbor cell list configured for the current cell, where the neighbor cell list includes one or more neighbor cells;
  • the target cell and the current cell are both in the neighboring cell list of the reference cell;
  • the target cell is a cell in a neighbor cell list configured for the current cell, and the target cell is a neighbor cell associated with beam information configured, activated or indicated by the network;
  • the target cell and the current cell are both in the neighbor cell list of the reference cell, and the target cell and the current cell are both cells associated with beam information configured, activated or indicated by the network;
  • the target cell is the last cell where the terminal device resides
  • the target cell is a neighboring cell of the current cell
  • the current cell is the cell where the terminal device currently resides.
  • the communication device 600 can be a terminal device or a device for a terminal device.
  • the device for a terminal device can be a chip system or a chip in the terminal device.
  • the chip system can be composed of a chip, or it can include a chip and other discrete devices.
  • the communication device can also be used to implement the functions of the network device in Figure 2 or Figure 3d above.
  • the communication device 600 can be a network device or a device for a network device.
  • the device for a network device can be a chip system or a chip in the network device. Among them, the chip system can be composed of a chip, or it can include a chip and other discrete devices.
  • the communication device 600 includes at least one processor 620, which is used to implement the data processing function of the terminal device or network device in the method provided in the embodiment of the present application.
  • the communication device 600 may also include a communication interface 610, which is used to implement the transceiver operation of the terminal device or network device in the method provided in the embodiment of the present application.
  • the processor 620 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
  • the communication interface 610 may be a transceiver, circuit, bus, module or other type of communication interface, which is used to communicate with other devices through a transmission medium.
  • the communication interface 610 is used for the device in the communication device 600 to communicate with other devices.
  • the processor 620 uses the communication interface 610 to send and receive data, and is used to implement the method described in FIG. 2 or FIG. 3 d of the above method embodiment.
  • the communication device 600 may also include at least one memory 630 for storing program instructions and/or data.
  • the memory 630 is coupled to the processor 620.
  • the coupling in the embodiment of the present application is an indirect coupling or communication connection between devices, units or modules, which may be electrical, mechanical or other forms, and is used for information exchange between devices, units or modules.
  • the processor 620 may operate in conjunction with the memory 630.
  • the processor 620 may execute program instructions stored in the memory 630. At least one of the at least one memory may be included in the processor.
  • the processor 620 can read the software program in the memory 630, interpret and execute the instructions of the software program, and process the data of the software program.
  • the processor 620 performs baseband processing on the data to be sent, and outputs the baseband signal to the radio frequency circuit (not shown in Figure 6).
  • the radio frequency circuit performs radio frequency processing on the baseband signal and then sends the radio frequency signal outward in the form of electromagnetic waves through the antenna.
  • the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency signal into a baseband signal, and outputs the baseband signal to the processor 620.
  • the processor 620 converts the baseband signal into data and processes the data.
  • the RF circuit and antenna may be arranged independently from the processor 620 that performs baseband processing.
  • the RF circuit and antenna may be arranged remotely from the communication device.
  • connection medium between the communication interface 610, the processor 620 and the memory 630 is not limited in the embodiment of the present application.
  • the memory 630, the processor 620 and the communication interface 610 are connected via a bus 640.
  • the bus is represented by a bold line in FIG6 .
  • the connection mode between other components is only for schematic illustration and is not limited thereto.
  • the bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one bold line is used in FIG6 , but it does not mean that there is only one bus or one type of bus.
  • the communication interface 610 may output or receive a baseband signal.
  • the communication interface 610 may output or receive a radio frequency signal.
  • the communication device can execute the relevant steps of the terminal device or network device in the aforementioned method embodiment. For details, please refer to the implementation methods provided in the above steps, which will not be repeated here.
  • each module contained therein may be implemented in the form of hardware such as circuits, and different modules may be located in the same component (for example, a chip, a circuit module, etc.) or in different components within the terminal, or at least some of the modules may be implemented in the form of a software program that runs on a processor integrated within the terminal, and the remaining (if any) modules may be implemented in the form of hardware such as circuits.
  • the above-mentioned memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories.
  • the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory.
  • the volatile memory may be a random access memory (RAM), which is used as an external cache.
  • RAM random access memory
  • SRAM static ram
  • DRAM dynamic random access memory
  • SDRAM synchronous DRAM
  • DDR SDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous link dynamic random access memory
  • DR RAM direct rambus RAM
  • the embodiment of the present application provides a chip.
  • the chip includes: a processor and a memory.
  • the number of the processors may be one or more, and the number of the memories may be one or more.
  • the processor may execute the report transmission method shown in FIG. 2 or FIG. 3d and the steps executed in the related implementation modes by reading instructions and data stored in the memory.
  • FIG 7 is a schematic diagram of the structure of a module device provided in an embodiment of the present application.
  • the module device 700 can execute the relevant steps of the terminal device or network device in the aforementioned method embodiment, and the module device 700 includes: a communication module 701, a power module 702, a storage module 703 and a chip module 704.
  • the power module 702 is used to provide power to the module device;
  • the storage module 703 is used to store data and/or instructions;
  • the communication module 701 is used to communicate with an external device;
  • the chip module 704 is used to call the data and/or instructions stored in the storage module 703, and in combination with the communication module 701, the above-mentioned report transmission method shown in Figure 2 or Figure 3d, and the steps performed by the relevant implementation method can be executed.
  • a computer-readable storage medium stores a computer program, and the computer program includes program instructions.
  • the steps performed by the terminal device or the steps performed by the network device in the report transmission method shown in FIG. 2 or FIG. 3d are implemented.
  • the computer-readable storage medium may be an internal storage unit of the terminal device or network device described in any of the aforementioned embodiments, such as a hard disk or memory of the device.
  • the computer-readable storage medium may also be an external storage device of the terminal device or network device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the device.
  • the computer-readable storage medium may also include both an internal storage unit of the terminal device or network device and an external storage device.
  • the computer-readable storage medium is used to store the computer program and other programs and data required by the terminal device or network device.
  • the computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media sets.
  • the available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a high-density digital video disc (DVD)), or a semiconductor medium.
  • the semiconductor medium may be a solid-state hard disk.
  • the various modules/units included in the various devices and products described in the above embodiments can be software modules/units, or hardware modules/units, or they can be partially software modules/units and partially hardware modules/units.
  • the various modules/units included therein can all be implemented in the form of hardware such as circuits, or at least some of the modules/units can be implemented in the form of software programs, which run on a processor integrated inside the chip, and the remaining (if any) modules/units can be implemented in the form of hardware such as circuits;
  • the various modules/units included therein can all be implemented in the form of hardware such as circuits, and different modules/units can be located in the same component of the chip module (such as a chip, circuit module, etc.) or in different components, or at least some of the modules/units can be implemented in the form of software programs.
  • each module/unit contained therein can be implemented in the form of hardware such as circuits, and different modules/units can be located in the same component (for example, chip, circuit module, etc.) or in different components in the terminal, or, at least some modules/units can be implemented in the form of a software program, which runs on a processor integrated inside the data acquisition node, and the remaining (if any) modules/units can be implemented in the form of hardware such as circuits.
  • the above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof.
  • the above embodiments 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 instructions or computer programs.
  • the processes or functions described in the embodiments of the present application 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 devices.
  • the computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means.
  • the size of the serial numbers of the above-mentioned processes does not mean the order of execution.
  • the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
  • the disclosed methods, devices and systems can be implemented in other ways.
  • the device embodiments described above are merely schematic; for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
  • Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically separate. Including, two or more units can also be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium.
  • the above-mentioned software functional unit is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a gateway node, etc.) to perform some steps of the method described in each embodiment of the present invention.
  • the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

Landscapes

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

Abstract

本申请提供一种报告传输方法及通信装置，其中，报告传输方法包括：根据对第一人工智能AI模型的更新情况，发送报告；其中，所述报告包括对所述第一AI模型的更新信息。采用本申请终端设备可将对AI模型的更新情况通过报告发送给网络设备，从而让终端设备与网络设备对当前使用模型的理解一致，提高终端设备和网络设备之间数据传输的成功率。

Description

报告传输方法及通信装置 技术领域
本申请涉及通信技术领域，尤其涉及一种报告传输方法及通信装置。
背景技术
人工智能(Artificial Intelligence，AI)模型目前在各个领域获得了广泛的应用，AI模型有多种实现方式，例如：神经网络、决策树、支持向量机、贝叶斯分类器等。使用AI模型可以实现预测、分类、决策等等。目前将AI模型可以使用到图像处理、分析，文本处理等等领域，从而实现各种功能。未来将AI模型融入无线通信网络也将成为一个趋势，将AI模型融入无线通信网络显然能显著提升吞吐量、处理时延，以及增强用户容量等技术指标，这是未来无线通信网络的重要任务。而如何实现将AI模型融入无线通信网络还是一个亟待解决的问题。
发明内容
本申请实施例提供一种报告传输方法及通信装置，终端设备可将对AI模型的更新情况通过报告发送给网络设备，从而让终端设备与网络设备对当前使用模型的理解一致，提高终端设备和网络设备之间数据传输的成功率。
第一方面，本申请实施例提供了一种报告传输方法，该方法包括：
根据对第一人工智能AI模型的更新情况，发送报告；其中，所述报告包括对所述第一AI模型的更新信息。
基于第一方面的描述，终端设备可将对AI模型的更新情况通过报告发送给网络设备，从而让终端设备与网络设备对当前使用模型的理解一致，提高终端设备和网络设备之间数据传输的成功率。
在一种可能的实现方式中，所述报告包括以下至少一项信息：
第一指示信息，所述第一指示信息用于指示完成对所述第一AI模型的更新；
第二AI模型的模型信息，所述第二AI模型为将所述第一AI模型更新后得到的模型；
第二指示信息，所述第二指示信息用于指示去激活的AI模型的模型信息；
第三指示信息，所述第三指示信息用于指示未完成对所述第一AI模型的更新；
第二AI模型所关联的预设信息，所述预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项，所述第二AI模型为将所述第一AI模型更新后得到的模型；
第三AI模型的模型信息，所述第三AI模型是在未将所述第一AI模型更新到第二AI模型的情况下所切换到的模型；
第四指示信息，所述第四指示信息用于指示使用非AI模型；
第五指示信息，所述第五指示信息用于指示第二AI模型的至少一个属性信息，所述至少一个属性信息为未将所述第一AI模型更新到所述第二AI模型的情况下终端设备不支持的属性信息；
所述报告的报告类型；
第一请求信息，所述第一请求信息用于请求网络指示第四AI模型；
从所述第一AI模型更新至第二AI模型的建议时长，所述第二AI模型为将所述第一AI模型更新后得到的模型；
在完成对所述第一AI模型的更新之后的生效时长；
在对所述第一AI模型更新时所测量的参考信号信息，所述参考信号信息包括参考信号资源的数量、参考信号资源集合的索引、参考信号资源的索引、参考信号的测量结果中的至少一项。
实施该方式，终端设备可将模型更新的一种或多种信息上报给网络设备，从而让网络设备及时获知终端设备侧所使用的模型，从而提高数据传输成功率。
在一种可能的实现方式中，所述报告类型包括AI模型更新报告；或者，
所述报告类型包括以下至少一项：非AI模型的常规测量反馈报告、AI模型的预测反馈报告、AI模型的增强测量反馈报告以及AI模型的更新报告中至少一项。
实施该方式，可以将报告的报告类型告知网络设备侧，从而便于网络设备解读该报告。
在一种可能的实现方式中，所述至少一个属性信息包括以下至少一项：所述第二AI模型的模型标识、所述第二AI模型的模型结构信息以及所述第二AI模型的模型参数。
实施该方式，终端设备将不支持的第二AI模型的模型标识、模型结构信息或模型参数中至少一项告知给网络设备，从而便于后续网络设备调度该终端设备时避免调度到该第二AI模型，还可以避免网络设备与终端设备使用的AI模型不一致导致的传输性能恶化。
在一种可能的实现方式中，所述报告包括至少一个部分，所述报告中排序在前的部分所携带的信息用于确定排序在后的部分所携带的信息。
实施该方式，报告中排序在前的部分所携带的信息可以用确定排序在后的部分所携带的信息，从而便于对网络设备对报告的解读，可降低报告的开销和网络设备解码报告的复杂度。
在一种可能的实现方式中，所述报告的格式由触发对所述第一AI模型进行更新的触发方式确定；所述触发方式包括：基于检测的事件触发的模型更新，或者基于网络信令触发的模型更新。
实施该方式，不同触发方式对应的报告格式不同，从而便于网络设备正确检测不同格式的报告。
在一种可能的实现方式中，所述发送报告，包括：
使用上行资源发送所述报告，所述上行资源包括网络预配置的周期性的上行信道资源，或者最近的可用于承载所述报告的上行授权资源，或者在历史时间段内使用次数最多的上行授权资源，或者上一次使用的上行授权资源，或者通过调度请求SR触发网络设备指示的上行授权资源。
实施该方式，对终端设备发送报告所使用的资源进行定义，便于终端设备发送报告，降低报告传输的时延。
在一种可能的实现方式中，所述发送报告，包括：
在主小区上发送所述报告；或者，在FR1频段的小区上发送所述报告。
实施该方式，可以提高报告传输的鲁棒性。
在一种可能的实现方式中，所述发送报告，包括：
使用一个或多个上行波束重复发送所述报告。
实施该方式，使用一个或多个上行波束重复发送报告，可以提高报告发送的可靠性。
在一种可能的实现方式中，所述使用一个或多个上行波束重复发送所述报告，包括：
使用一个或多个上行波束以时分复用的方式重复发送所述报告；或者，使用多个上行波束同时发送所述报告。
实施该方式，可以是通过时分复用的方式重复发送报告，或者也可以使用多个上行波束同时发送报告，从而提高报告传输的可靠性。
在一种可能的实现方式中，所述同时发送的报告在所述多个上行波束上分别采用不同的层或者频域资源或者正交码序列发送。
实施该方式，同时发送的报告在多个上行波束上分别采用不同的层或频域资源或正交码序列发送，减小彼此的干扰。
在一种可能的实现方式中，所述发送报告，包括：
若用于承载所述报告的第一上行信道的信道资源与第二上行信道的信道资源存在冲突时，采用以下一种方式发送报告：
将所述报告和所述第二上行信道中承载的信息复用到第三上行信道的信道资源上发送；或者，发送所述第一上行信道，且丢弃所述第二上行信道中承载的信息；或者，调整所述第一上行信道的发送功率和/或所述第二上行信道的发送功率，并发送功率调整后的第一上行信道和第二上行信道，其中，功率调整后的第一上行信道的发送功率和第二上行信道的发送功率之和小于或等于终端设备支持的最大发送功率。
实施该方式，提供了在报告所在的信道资源和其他信息所在信道资源存在冲突时的处理方式。
在一种可能的实现方式中，所述调整所述第一上行信道的发送功率和/或所述第二上行信道的发送功率，包括：
将所述第一上行信道的发送功率调高；和/或，将所述第二上行信道的发送功率调低。
实施该方式，将承载报告的第一上行信道的发送功率调高，和/或将第二上行信道的发送功率调低，从而在满足终端支持的总功率和的前提下，调整信道的发送功率，提供报告的发送成功率，又能传输更多的信息。
在一种可能的实现方式中，所述将所述第一上行信道的发送功率调高；和/或，将所述第二上行信道的发送功率调低，包括：
若所述报告的优先级大于所述第二上行信道中承载的信息的优先级，则将所述第一上行信道的发送功率调高；和/或，将所述第二上行信道的发送功率调低。
实施该方式，在报告的优先级大于第二上行信道中承载的信息的优先级时，将第一上行信道的发送功率调高，和/或，将第二上行信道的发送功率调低，即通过优先级比较确定将哪个的发送功率调高或调低，从而保证高优先信息的发送成功率。
在一种可能的实现方式中，所述发送所述第一上行信道，且丢弃所述第二上行信道中承载的信息，包括：
若所述报告的优先级大于所述第二上行信道中承载的信息的优先级，发送所述第一上行信道，且丢弃所述第二上行信道中承载的信息。
实施该方式，在报告的优先级大于第二上行信道中承载的信息的优先级的情况下，优先发送第一上行信道中承载的报告，保证高优先级信息的发送。
在一种可能的实现方式中，在将所述报告和所述第二上行信道中承载的信息复用到第三上行信道的信道资源上发送的情况下，所述报告和所述第二上行信道中承载的信息在所述第三上行信道中的排列顺序由所述报告的优先级和所述第二上行信道中承载的信息的优先级确定。
实施该方式，将越高优先级信息排序在越前面，从而保证高优先级信息的优先解读。
在一种可能的实现方式中，所述方法还包括：
若所述报告的优先级低于所述第二上行信道中承载的信息的优先级，发送所述第二上行信道，且丢弃所述第一上行信道中承载的所述报告。
实施该方式，若报告的优先级低于第二上行信道中承载的信息的优先级，则会将报告丢弃，从而保证高优先级的信息传输。
在一种可能的实现方式中，所述报告的优先级最高；或者，在所述报告中包含第一信息的情况下，所述报告的优先级最高；或者，更新后的第二AI模型与所述第一AI模型不同时，所述报告的优先级最高。
实施该方式，提供了报告的优先级确定方式，从而便于在传输报告时，通过优先级比较进行传输。
在一种可能的实现方式中，所述第一信息包括以下至少一项：所述第一指示信息、所述第二AI模型的模型信息、所述第三指示信息、所述第三AI模型的模型信息、所述第四指示信息、所述报告的报告类型。
实施该方式，在报告中包括以下至少一项信息时，该报告的优先级最高，从而动态的确定报告的优先级，保证AI网络侧和终端侧对AI模型的理解一致性。
在一种可能的实现方式中，在未对所述第一AI模型进行更新的情况下，所述报告的优先级最低。
实施该方式，在未对第一AI模型进行更新时，将报告的优先级设置为最低，保证其他高优先级信息的传输。
在一种可能的实现方式中，所述报告的生效时间由以下至少一项确定：
发送所述报告之后的第一时长开始生效；
网络发送目标信令后的第二时长开始生效，所述目标信令用于指示对所述第一AI模型进行更新；
发送第二请求信息后的第三时长开始生效，所述第二请求信息用于请求网络发送用于辅助对所述第一AI模型进行更新的信息；
所述报告或第二请求信息中携带的生效时间；
第二AI模型的有效时间长度，所述第二AI模型为将所述第一AI模型更新后得到的模型。
实施该方式，让网络侧和终端侧对模型的生效时间理解一致，从而提高数据传输成功率。
在一种可能的实现方式中，所述生效时间由网络指示或协议约定。
在一种可能的实现方式中，所述生效时间由所述第二AI模型所关联的预设信息对应的子载波间隔确定，或者由所述第二AI模型所关联的预设信息对应的多个子载波间隔中最小子载波间隔确定，所述预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项。
实施该方式，可以保证网络侧和终端侧对模型的生效时间理解一致，从而提高数据传输成功率。
在一种可能的实现方式中，所述网络信息包括以下至少一项：
公共陆地移动网络PLMN信息、运营商标识信息、网络设备商标识信息、跟踪区标识TAI信息、漫游控制SOR信息、路由选择策略URSP信息。
实施该方式，将网络信息与AI模型进行关联，从而便于确定各种模型对应的网络信息。
在一种可能的实现方式中，所述接入网信息包括以下至少一项：
工作频率信息、小区组信息、服务小区信息、物理小区标识、发送接收点TRP标识信息、带宽部分BWP标识信息、与小区关联的参考信号RS信息。
实施该方式，将接入网信息与AI模型进行关联，从而便于确定各种模型对应的接入网信息。
第二方面，本申请实施例提供了一种报告传输方法，该方法包括：
接收终端设备发送的报告，所述报告包括所述终端设备对第一AI人工智能模型的更新信息。
在一种可能的实现方式中，所述报告包括以下至少一项信息：
第一指示信息，所述第一指示信息用于指示完成对所述第一AI模型的更新；
第二AI模型的模型信息，所述第二AI模型为将所述第一AI模型更新后得到的模型；
第二指示信息，所述第二指示信息用于指示去激活的AI模型的模型信息；
第三指示信息，所述第三指示信息用于指示未完成对所述第一AI模型的更新；
第二AI模型所关联的预设信息，所述预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项，所述第二AI模型为将所述第一AI模型更新后得到的模型；
第三AI模型的模型信息，所述第三AI模型是在未将所述第一AI模型更新到第二AI模型的情况下所切换到的模型；
第四指示信息，所述第四指示信息用于指示使用非AI模型；
第五指示信息，所述第五指示信息用于指示第二AI模型的至少一个属性信息，所述至少一个属性信息为未将所述第一AI模型更新到所述第二AI模型的情况下终端设备不支持的属性信息；
所述报告的报告类型；
第一请求信息，所述第一请求信息用于请求网络指示第四AI模型；
从所述第一AI模型更新至第二AI模型的建议时长，所述第二AI模型为将所述第一AI模型更新后得到的模型；
在完成对所述第一AI模型的更新之后的生效时长；
在对所述第一AI模型更新时所测量的参考信号信息，所述参考信号信息包括参考信号资源的数量、参考信号资源集合的索引、参考信号资源的索引、参考信号的测量结果中至少一项。
在一种可能的实现方式中，所述网络信息包括以下至少一项：
公共陆地移动网络PLMN信息、运营商标识信息、网络设备商标识信息、跟踪区标识TAI信息、漫游控制SOR信息、路由选择策略URSP信息。
在一种可能的实现方式中，所述接入网信息包括以下至少一项：
工作频率信息、小区组信息、服务小区信息、物理小区标识、发送接收点TRP标识信息、带宽部分BWP标识信息、与小区关联的参考信号RS信息。
在一种可能的实现方式中，所述报告类型包括AI模型更新报告；或者，
所述报告类型包括以下至少一项：非AI模型的常规测量反馈报告、AI模型的预测反馈报告、AI模型的增强测量反馈报告以及AI模型的更新报告中至少一项。
在一种可能的实现方式中，所述至少一个属性信息包括以下至少一项：所述第二AI模型的模型标识、所述第二AI模型的模型结构信息以及所述第二AI模型的模型参数。
在一种可能的实现方式中，所述报告包括至少一个部分，所述报告中排序在前的部分所携带的信息用于确定排序在后的部分所携带的信息。
第二方面的上述可能的实现方式的有益效果请参照终端侧的描述，在此不再赘述。
在一种可能的实现方式中，所述方法还包括：
向目标网络或目标站点或目标小区发送所述报告中的部分信息或全部信息。
实施该方式，可以向目标网络或目标站点或目标小区发送报告中的部分信息或全部信息，以便于其他网络或站点或小区获取AI模型相关的更新信息。
在一种可能的实现方式中，所述目标网络满足以下至少一项：
所述目标网络与当前网络相同；
所述目标网络与当前网络具有相同的运营商标识或具有相同的PLMN信息；
所述目标网络与当前网络具有相同的网络设备商标识；
所述目标网络为所述终端设备驻留的上一个网络；
所述目标网络为当前网络相邻的网络；
其中，所述当前网络为所述终端设备当前驻留的网络。
实施该方式，可以确定目标网络，从而便于向目标网络发送报告中的部分信息或全部信息。
在一种可能的实现方式中，所述目标站点满足以下至少一项：
所述目标站点与当前站点具有相同的运营商标识或者PLMN或网络设备商；
所述目标站点为当前站点配置的邻区列表中各个邻区所对应的站点，所述邻区列表包括一个或多个邻区；
所述目标站点的小区与当前站点的小区均在参考站点的邻区列表中；
所述目标站点为当前站点配置的邻区列表中第一邻区所对应的站点，所述第一邻区是网络配置或激活或指示的波束信息所关联的邻区；
所述目标站点的小区与当前站点的小区均在参考站点的邻区列表中，且所述目标站点的小区与所述当前站点的小区均为网络配置或激活或指示的波束信息关联的小区；
所述目标站点为所述终端设备驻留的上一个小区对应的站点；
所述目标站点为当前站点的相邻站点；
所述目标站点为AI模型信息管理服务器；
其中，所述当前站点为所述终端设备当前所在小区对应的站点。
实施该方式，可以确定目标站点，从而便于向目标站点发送报告中的部分信息或全部信息。
在一种可能的实现方式中，所述目标小区满足以下至少一项：
所述目标小区与当前小区具有相同的运营商标识或者PLMN或网络设备商；
所述目标小区为当前小区配置的邻区列表中的小区，所述邻区列表包括一个或多个邻区；
所述目标小区与当前小区均在参考小区的邻区列表中；
所述目标小区为当前小区配置的邻区列表中的小区，且所述目标小区是网络配置或激活或指示的波束信息所关联的邻区；
所述目标小区与当前小区均在参考小区的邻区列表中，且所述目标小区与所述当前小区均为网络配置或激活或指示的波束信息关联的小区；
所述目标小区为所述终端设备驻留的上一个小区；
所述目标小区为当前小区的邻区；
其中，所述当前小区为所述终端设备当前驻留的小区。
实施该方式，可以确定目标小区，从而便于向目标小区发送报告中的部分信息或全部信息。
第三方面，本申请实施例提供了一种通信装置，该通信装置包括用于实现上述第一方面中任一种可能的实现方式中的方法的单元，或者，包括用于实现上述第二方面中任一种可能的实现方式中的方法的单元。
第四方面，本申请实施例提供了一种通信装置，该通信装置包括处理器和存储器，处理器和存储器相互连接，存储器用于存储计算机程序，计算机程序包括程序指令，处理器被配置用于调用该程序指令，以执行如第一方面或第一方面任一可选的实施方式所述的方法，或者以执行如第二方面或第二方面任一可选的实施方式所述的方法。
第五方面，本申请实施例提供一种芯片，该芯片包括处理器与接口，处理器和接口耦合；接口用于接收或输出信号，处理器用于执行代码指令，以执行如第一方面或第一方面任一可选的实施方式所述的方法，或者以执行如第二方面或第二方面任一可选的实施方式所述的方法。
第六方面，本申请实施例提供一种模组设备，该模组设备包括通信模组、电源模组、存储模组以及芯片模组，其中：该电源模组用于为该模组设备提供电能；该存储模组用于存储数据和/或指令；该通信模组与外部设备通信；该芯片模组用于调用存储模组存储的数据和/或指令，结合通信模组，执行如第一方面或第一方面任一可选的实施方式所述的方法，或者执行如第二方面或第二方面任一可选的实施方式所述的方法。
第七方面，本申请实施例提供了一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，当电子设备执行所述程序指令时，以实现如第一方面或第一方面任一可选的实施方式所述的方法，或者，以实现如第二方面或第二方面任一可选的实施方式所述的方法。
附图说明
图1是本申请实施例提供的一种通信系统的结构示意图；
图2是本申请实施例提供的一种报告传输方法的流程示意图；
图3a是本申请实施例提供的一种报告的示意图；
图3b是本申请实施例提供的一种资源冲突处理示意图；
图3c是本申请实施例提供的一种生效时间点示意图；
图3d是本申请实施例提供的另一种报告传输方法的流程示意图；
图4是本申请实施例提供的一种通信装置的结构示意图；
图5是本申请实施例提供的另一种通信装置的结构示意图；
图6是本申请实施例提供的又一种通信装置的结构示意图；
图7是本申请实施例提供的一种模组设备的结构示意图。
具体实施方式
本申请实施例中，除非另有说明，字符“/”表示前后关联对象是一种或的关系。例如，A/B可以表示A或B。“和/或”描述关联对象的关联关系，表示可以存在三种关系。例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。
需要指出的是，本申请实施例中涉及的“第一”、“第二”等词汇，仅用于区分描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量，也不能理解为指示或暗示顺序。
本申请实施例中，“至少一个”是指一个或者多个，“多个”是指两个或两个以上。此外，“以下至少一项(个)”或者其类似表达，是指的这些项中的任意组合，可以包括单项(个)或复数项(个)的任意组合。例如，A、B或C中的至少一项(个)，可以表示：A，B，C，A和B，A和C，B和C，或A、B和C。其中，A、B、C中的每个本身可以是元素，也可以是包含一个或多个元素的集合。
本申请实施例中，“示例的”、“在一些实施例中”、“在另一实施例中”等用于表示作例子、例证或说明。本申请中被描述为“示例”的任何实施例或设计方案不应被解释为比其它实施例或设计方案更优选或更具优势。确切而言，使用示例的一词旨在以具体方式呈现概念。
本申请实施例中的“的(of)”、“相应的(corresponding，relevant)”和“对应的(corresponding)”有时可以混用，应当指出的是，在不强调其区别时，所要表达的含义是一致的。本申请实施例中，通信、传输有时可以混用，应当指出的是，在不强调其区别时，其所表达的含义是一致的。例如，传输可以包括发送和/或接收，可以为名词，也可以是动词。
本申请实施例中涉及的等于可以与大于连用，适用于大于时所采用的技术方案，也可以与小于连用，适用于小于时所采用的技术方案。需要说明的是，当等于与大于连用时，不能与小于连用；当等于与小于连用时，不与大于连用。
以下对本申请实施例涉及的部分术语进行解释说明，以便于本领域技术人员理解。
1、终端设备。本申请实施例中终端设备是一种具有无线收发功能的设备，可以称之为终端(terminal)、用户设备(user equipment，UE)、移动台(mobile station，MS)、移动终端(mobile terminal，MT)、接入终端设备、车载终端设备、工业控制终端设备、UE单元、UE站、移动站、远方站、远程终端设备、移动设备、UE终端设备、无线通信设备、UE代理或UE装置等。终端设备可以是固定的或者移动的。需要说明的是，终端设备可以支持至少一种无线通信技术，例如长期演进(long term evolution，LTE)、新空口(new radio，NR)等。例如，终端设备可以是手机(mobile phone)、平板电脑(pad)、台式机、笔记本电脑、一体机、车载终端、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、无人驾驶(self driving)中的无线终端、远程手术(remote medical surgery)中的无线终端、智能电网(smart grid)中的无线终端、运输安全(transportation safety)中的无线终端、智慧城市(smart city)中的无线终端、智慧家庭(smart home)中的无线终端、蜂窝电话、无绳电话、会话启动协议(session initiation protocol，SIP)电话、无线本地环路(wireless local loop，WLL)站、个人数字助理(personal digital assistant，PDA)、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、可穿戴设备、未来移动通信网络中的终端设备或者未来演进的公共移动陆地网络(public land mobile network，PLMN)中的终端设备等。在本申请的一些实施例中，终端设备还可以是具有收发功能的装置，例如芯片系统。其中，芯片系统可以包括芯片，还可以包括其它分立器件。
2、网络设备。本申请实施例中网络设备是一种为终端设备提供无线通信功能的设备，也可称之为接入网设备、无线接入网(radio access network，RAN)设备等。其中，网络设备可以支持至少一种无线通信技术，例如LTE、NR等。示例的，网络设备包括但不限于：第五代移动通信系统(5th-generation，5G)中的下一代基站(generation nodeB，gNB)、第六代移动通信系统(6th-generation，6G)、演进型节点B(evolved node B，eNB)、无线网络控制器(radio network controller，RNC)、节点B(node B，NB)、基站控制器(base station controller，BSC)、基站收发台(base transceiver station，BTS)、家庭基站(例如，home evolved node B、或home node B，HNB)、基带单元(baseband unit，BBU)、收发点(transmitting and receiving point， TRP)、发射点(transmitting point，TP)、移动交换中心等。网络设备还可以是云无线接入网络(cloud radio access network，CRAN)场景下的无线控制器、集中单元(centralized unit，CU)、和/或分布单元(distributed unit，DU)，或者网络设备可以为中继站、接入点、车载设备、终端设备、可穿戴设备以及未来移动通信中的网络设备或者未来演进的PLMN中的网络设备等。在一些实施例中，网络设备还可以为具有为终端设备提供无线通信功能的装置，例如芯片系统。示例的，芯片系统可以包括芯片，还可以包括其它分立器件。
请参阅图1，图1是本申请实施例提供的一种通信系统的结构示意图。该通信系统可以包括但不限于一个或多个网络设备、一个或多个终端设备，如图1以一个网络设备101和一个终端设备102为例，其中，图1中的网络设备101以基站为例，终端设备102以手机为例，终端设备102可以和网络设备101建立无线链路进行通信。图1所示的通信系统包括但不限于网络设备和终端设备，还可以包括其他的通信设备，图1所示的设备数量和形态用于举例并不构成对本申请实施例的限定。
在描述本申请的通信方法之前，先对本申请所涉及的概念进行阐述：
1、AI模型
AI模型目前在各个领域获得了广泛的应用，将AI模型融入无线通信网络，能显著提升吞吐量、处理时延，以及增强用户容量等技术指标，这是未来无线通信网络的重要任务。AI模型有多种实现方式，例如：神经网络、决策树、支持向量机、贝叶斯分类器等。
以神经网络为例，神经网络由神经元组成，其中包括：输入参数、乘性系数、加性系数、激活函数等。常见的激活函数包括：Sigmoid、tanh、ReLU(Rectified Linear Unit，线性整流函数，修正线性单元)等等。
神经网络的参数通过梯度优化算法进行优化，梯度优化算法是一类最小化或者最大化目标函数(也可称为损失函数)的算法，而目标函数往往是模型参数和数据的数学组合。例如给定数据X和其对应的标签Y，我们构建一个神经网络模型f，有了模型后，根据输入就可以预测出输出信息，并且可以计算出预测值和真实值之间的差距，这就是损失函数。我们的目的是找到合适的系统使损失函数的值达到最小。损失值越小，则说明模型越接近于真实情况。
目前常见的优化算法，基本都是基于误差反向传播(error Back Propagation，BP)算法。BP算法的基本思想是，学习过程由信号的正向传播与误差的反向传播两个过程组成。正向传播时，输入样本从输入层传入，经各隐层逐层处理后传向输出层。若输出层的实际输出与期望的输出不符，则转入误差的反向传播阶段。误差反传是将输出误差以某种形式通过隐层向输入层逐层反传，并将误差分摊给各层的所有单元，从而获得各层单元的误差信号，此误差信号即作为修正各单元权值的依据。这种信号正向传播与误差反传的各层权值调整过程，是周而复始的进行着。权值不断调整的过程，也就是AI网络的学习训练过程。此过程一直进行到网络输出的误差减少到可接受的程度，或进行到预先设定的学习次数为止。
常见的优化算法有梯度下降(Gradient Descent)、随机梯度下降(Stochatic Gradient Descent，SGD)、小批量梯度下降(mini-batch Gradient Descent)、动量法(Momentum)、Nesteroy(带动量的随机梯度下降)、自适应梯度下降(ADAptive GRADient Descent，Adagrad)、均方根误差降速(Root Mean Square Prop)、自适应动量估计(Adaptive Moment Estimation，Adam)等。
这些优化算法在误差反向传播时，都是根据损失函数得到的误差，对当前神经元求导数/偏导，加上学习速率、之前的梯度/导数/偏导等影响，得到梯度，将梯度传给上一层。
2、AI模型的模型信息可以包括以下至少一项：
模型ID，模型的结构(层数、神经元数量等)，模型的参数，模型的算力，存储能力等。示例性的，AI模型可以是全连接网络、卷积神经网络，等等。
3、AI模型的更新可以包括以下至少一项：AI模型信息的激活、切换、训练、更新、监督、选择、校验、验证、微调、调整、测试等。
如图2所示，为本申请提供的报告传输方法一个实施例的流程示意图，如图2所示，该方法可以包括但不限于以下步骤：
101，终端设备根据对第一AI模型的更新情况，发送报告，该报告包括对第一AI模型的更新信息。
示例性的，触发终端设备对第一AI模型进行更新的触发方式本申请不作限定，例如，可以是基于终端设备检测的事件触发模型更新，或者，也可以是网络设备通过网络信令触发终端设备进行模型更新。比如，基于终端设备检测的事件确定终端设备需要从第一AI模型更新到第二AI模型。又比如，网络信令指示终端设备需要从第一AI模型更新到第二AI模型。
102，网络设备接收终端设备发送的报告。
本申请实施例中，报告可以包括以下信息a至信息m中至少一项，下面对该信息a至信息m分别进行阐述：
a，第一指示信息，所述第一指示信息用于指示完成对所述第一AI模型的更新；
在一些实现方式中，可以通过ACK确认完成对第一AI模型的更新。
b，第二AI模型的模型信息，所述第二AI模型为将所述第一AI模型更新后得到的模型；
其中，第二AI模型的模型信息可以包括但不限于第二AI模型的模型ID、模型结构或模型参数中至少一项。
c，第二指示信息，所述第二指示信息用于指示去激活的AI模型的模型信息；
示例性的，终端设备从第一AI模型更新为第二AI模型，该第二指示信息指示的去激活的AI模型可以包括更新前的第一AI模型，和/或，除第一AI模型和第二AI模型之外的其他模型，本申请不作限定。可理解，在将AI模型去激活之后，网络设备后续可不指示终端设备切换到去激活的AI模型，或者，终端设备切换到去激活的AI模型会耗时比较长，或者，终端设备不能切换到去激活的AI模型。
d，第三指示信息，所述第三指示信息用于指示未完成对所述第一AI模型的更新；
其中，终端设备未完成对第一AI模型的更新，可理解为，终端设备不支持第二AI模型的层、模型大小、模型算力等，而未完成对第一AI模型更新到第二AI模型。也可以是终端设备更新失败而导致未完成对第一AI模型的更新。
e，第二AI模型所关联的预设信息，所述预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项，所述第二AI模型为将所述第一AI模型更新后得到的模型；
第二AI模型所关联的预设信息可理解为该第二AI模型与该预设信息之间存在对应关系，即该预设信息变化时，则可能关联其他模型，通过预设信息的变化，从而关联不同的模型。
其中，网络信息可以包括以下至少一项：公共陆地移动网络(Public Land Mobile Network，PLMN)信息、运营商标识信息、网络设备商标识信息、跟踪区标识(Tracking Area ID，TAI)信息、漫游控制(Steering of Roaming，SOR)信息、终端路由选择策略(UE Route Selection Policy，URSP)信息等。
接入网信息可以包括以下至少一项：工作频率信息(频率编号、频段编号等)、小区组信息(cell group id)、服务小区信息(serving cell id)、物理小区标识(Physical cell Identifier，PCI)、发送接收点(Transmission and reception point，TRP)标识信息、带宽部分(Bandwidth Part，BWP)标识信息、与小区关联的参考信号(RS)信息，例如同步信号块(Synchronization Signal Block，SSB)。TRP标识信息可以包括但不限于如下至少一项：控制资源集(control-resource set，CORESET)标识、控制资源集池(CORESET Pool)标识、控制资源集的组标识、传输配置指示(transmission configuration indication，TCI)状态池标识、TCI状态标识、参考信号资源标识、参考信号资源集合标识。
信道质量信息可以是层1或层3的参考信号接收功率(Reference Signal Receiving Power，RSRP)、信号与干扰加噪声比(Signal to Interference plus Noise Ratio，SINR)等。
时间信息可以是时间戳信息，或时间段信息，或时间点等等。时间信息也可以与模型相关联，例如，在某个时间戳需要将第一AI模型更新到第二AI模型。
终端设备标识信息可以是终端设备的设备商标识信息或其他标识，本申请不作限定。
f，第三AI模型的模型信息，所述第三AI模型是在未将所述第一AI模型更新到第二AI模型的情况下所切换到的模型；
示例性的，在终端设备需要从第一AI模型更新至第二模型的情况下，而终端设备未完成更新到第二AI模型，未完成更新的原因不限定，例如，不支持第二AI模型的模型结构或参数等，或者更新过程由于其他原因导致更新失败，此时终端设备可切换到第三AI模型，该第三AI模型可以是一个默认模型，该第三AI模型可以与第一AI模型相同或不同，该第三AI模型不同于第二AI模型。
g，第四指示信息，所述第四指示信息用于指示使用非AI模型；
其中，使用非AI模型可理解为使用常规测量和传输方式，即不使用AI模型进行预测。
示例性的，可以是终端设备不支持第二AI模型的模型结构或参数等，或者更新过程由于其他原因导致更新失败，则终端设备可以通过第四指示信息指示其使用非AI模型。
h，第五指示信息，所述第五指示信息用于指示第二AI模型的至少一个属性信息，所述至少一个属性信息为未将所述第一AI模型更新到所述第二AI模型的情况下终端设备不支持的属性信息；
示例性的，可以是终端设备不支持第二AI模型的至少一个属性信息，导致终端设备未将第一AI模型 更新到第二AI模型，终端设备通过第五指示信息指示不支持第二AI模型的哪些属性信息。该至少一个属性信息可以包括以下至少一项：第二AI模型的模型标识、第二AI模型的模型结构信息以及第二AI模型的模型参数等。例如，终端设备不支持第二AI模型中的层、模型大小或模型算力等。
i，所述报告的报告类型；
示例性的，该报告类型可以包括AI模型更新报告，即通过报告类型将AI报告与其他常规报告进行区分，其他常规报告可以包括(Channel State Information，CSI)报告，波束(beam)报告，混合自动重传请求(Hybrid Automatic Repeat reQuest，HARQ)报告等。
示例性的，该报告类型可以包括非AI模型的常规测量反馈报告(如前述的CSI报告，波束报告，HARQ报告等常规报告)、AI模型的预测反馈报告、AI模型的增强测量反馈报告以及AI模型的更新报告中至少一项。即将AI模型更新报告分为多种类型。
在一些实现方式中，可以通过参数的不同取值指示不同的报告类型，该参数可为配置信令report configuration中指示的report Quantity参数，即通过report Quantity参数的取值指示报告类型。可理解，也可以是其他参数，比如新定义的参数等，本申请不作限定。一种实现方式中，报告中包括一个比特，如果该比特取值为1，则指示该报告为AI模型更新报告。如果该比特取值为0，则指示该报告为其他常规报告，可选的，具体为其他哪种常规报告可通过report Quantity参数的取值获得。可理解，上述比特取值为1指示AI模型更新报告仅为举例，也可以是取值为0指示AI模型更新报告，本申请不作限定。
j，第一请求信息，所述第一请求信息用于请求网络指示第四AI模型；
示例性的，在终端设备需要从第一AI模型更新至第二模型的情况下，而终端设备未完成更新到第二AI模型，未完成更新的原因不限定，例如，不支持第二AI模型的模型结构或参数等，或者更新过程由于其他原因导致更新失败，此时终端设备可通过第一请求信息请求网络指示第四AI模型进行切换。
k，从所述第一AI模型更新至第二AI模型的建议时长，所述第二AI模型为将所述第一AI模型更新后得到的模型；
示例性的，在终端设备需要从第一AI模型更新到第二AI模型时，终端设备可向网络设备指示从第一AI模型更新至第二AI模型的建议时长，以避免网络设备在终端设备更新完之前就进行调度导致数据传输失败的问题。
l，在完成对所述第一AI模型的更新之后的生效时长；
终端设备可通过报告向网络指示该报告的生效时长，该生效时长可理解为在该生效时长之后更新后的AI模型开始生效。
m，在对所述第一AI模型更新时所测量的参考信号信息，所述参考信号信息包括参考信号资源的数量、参考信号资源集合的索引、参考信号资源的索引、参考信号的测量结果中的至少一项。
示例性的，报告中可以包括AI模型更新时参考信号的测量结果大于或等于预设门限的参考信号信息，该参考信息包括参考信号资源的数量、参考信号资源集合的索引、参考信号资源的索引、参考信号的测量结果中的至少一项。
可理解，报告可包括以上信息a-m中一项或多项，该报告也可以报告除上述信息a-m之外的其他信息，本申请不作限定。
本申请实施例中的报告可以包括一个或多个部分part。
一种可能的设计中，报告中排序在前的部分part中携带的信息可以用于确定排序在后的部分part所携带的信息。一种实现方式中，报告中排序在前的部分part中携带的信息可以确定排序在后的部分part是否携带信息，和/或，报告中排序在前的部分part中携带的信息可以确定排序在后的部分part携带哪些信息。换言之，排序在前的部分part(例如part1)中携带的信息可以确定排序在后的部分part的长度、内容或格式。例如，如图3a所示，报告中包括第一部分(part1)和第二部分(part2)，第一部分(part1)排序在第二部分(part2)之前，因此，第一部分(part1)中携带的信息可以确定第二部分(part2)中携带的信息。下面进行举例说明：
例如，如果part1包括上述信息a，即part1包括用于指示完成对第一AI模型的更新的第一指示信息，则报告可以不包括其他部分part，从而节省信令开销。也可以包括其他部分part，比如该其他部分part包括上述信息b、信息c、信息e和m中至少一项。
又例如，如果part1包括上述信息d，即part1包括用于指示未完成对所述第一AI模型的更新的第三指示信息，则part2可以包括信息f、信息g、信息h以及信息j中至少一项。
又例如，如果part1包括上述信息m中参考信号资源的数量，则part2可以包括参考信号资源的索引、参考信号的测量结果中的至少一项。
一种可能的设计中，报告的格式可以由触发对第一AI模型进行更新的触发方式确定，换言之，不同的触发方式，报告的格式不同，其中，报告的格式可理解为报告的长度和/或part中包含的内容不同。触发方式包括：基于终端设备检测的事件触发的模型更新，或者基于网络信令触发的模型更新。
示例性的，如果是基于终端设备检测的事件触发的模型更新，part1可以包含信息b、信息c、信息f、信息g、信息i以及信息j中至少一项，part2可以包含信息e、信息h中至少一项。如果是基于网络信令触发的模型更新，part1可以包含上行信息a或d，part2可以包含信息b、信息c、信息f、信息g、信息i、信息j中至少一项，part3可以包含信息e、信息h中至少一项。
下面对报告中的编码方式进行举例说明，一种可能的设计中，报告中的各个信息独立编码，比如上述信息a-m中，各个信息独立进行编码。另一种可能的设计中，一个part的信息进行编码，例如，part1中信息一起进行编码，part2中信息一起进行编码。又一种可能的设计中，报告中所有的信息联合编码。在又一种可能的设计中，多个part一起联合编码，比如part1中信息和part2中信息一起联合编码。
可选的，对于报告中各个信令域中包含的信息可以进行差分量化，下面对报告中各个信令域中包含的信息的差分量化方式进行举例说明，在一种实现方式中，报告中各信令域可以各自独立进行差分量化，或多个信令域共同进行差分量化，本申请不作限定。下面以一个信令域中的参考信号资源的测量结果RSRP的差分量化进行举例说明，比如，一个信令域包含了N个参考信号资源的测量结果，则可将该N个测量结果中的最大值或最小值使用K1个比特进行量化，再将该信令域中其他N-1个测量结果与该测量结果的差值进行量化，量化后的N-1个测量结果所需的比特长度都小于K1。从而节省比特开销。可理解，如果将多个信令域共同进行差分量化，则从该多个信令域中选择最大值或最小值，并将其他测量结果与该最大值或最小值进行差分量化。上述N为大于1的整数，K1为大于或者等于1的整数。可理解，上述报告中的至少一个信令域中包含的可以是达到预设门限值的参考信号资源的测量结果RSRP，以节省信令开销。
下面对报告的发送方式进行举例说明：
一种实现方式中，终端设备可使用网络预配置的周期性的上行信道资源发送报告，例如，终端设备使用预配置的周期性的物理上行链路控制信道(Physical Uplink Control Channel，PUCCH)资源发送报告。
在另一种实现方式中，终端设备可使用最近的可用于承载该报告(next available)的上行授权资源发送该报告，例如，下一个可以用于承载该报告的上行授权资源。可理解，上行授权资源可以是动态授权资源或配置授权资源。
在又一种实现方式中，终端设备使用历史时间段内使用次数最多的上行授权资源发送报告，该历史时间段可以是在报告生成之前的一段时间。
在又一种实现方式中，终端设备可使用上一次使用的上行授权资源发送报告，本申请对上一次使用的上行授权资源传输的内容不作限定。
在又一种实现方式中，终端设备可向网络设备发送调度请求(Scheduling Request，SR)，通过SR触发网络设备指示上行授权资源，终端设备使用网络设备所指示的上行授权资源发送报告。
在又一种实现方式中，终端设备可在主小区Pcell上发送报告。
在又一种实现方式中，终端设备可在FR1频段的小区上发送报告。
在又一种实现方式中，终端设备可使用一个或多个上行波束重复发送报告，以提高报告传输的可靠性。
示例性的，终端设备可使用一个或多个上行波束以时分复用的方式重复发送报告，或者终端设备也可使用多个上行波束同时发送报告，该多个上行波束可以是多个面板上的波束。其中，同时发送的报告在多个上行波束上可以完全相同，或者分别采用不同的层layer或者频域资源或者正交码序列，以降低相互之间的干扰。
在一些实现方式中，本申请实施例中的包含AI模型更新信息的报告也可以与其他报告(例如CSI报告、波束报告、HARQ报告等)同时发送。示例性的，使用多个上行波束同时发送包含AI模型更新信息的报告与其他报告，其中每个上行波束发送一个报告，同理，同时发送的报告在多个上行波束上分别采用不同的层layer或者频域资源或者正交码序列，以降低相互之间的干扰。
可理解，上述对报告发送的各种实现方式可以单独实施，也可以结合实施，本申请不作限定。
下面阐述在用于承载报告的第一上行信道的信息资源与用于承载其他信息的第二上行信道的信道资源存在冲突时的解决方式，其中，冲突可理解为第一上行信道的信道资源与第二上行信道的信道资源时域和/或频域存在重叠，第二上行信道中承载的信息可以包括CSI报告、波束报告、HARQ报告、SR、波束失败恢复请求等，本申请不作限定。
一种实现方式中，将报告和第二上行信道中承载的信息复用到第三上行信道的信道资源上发送。示例性的，该第三上行信道可以为上述第一上行信道，例如，第一上行信道足以承载上述报告和第二上行信道中承载的信息，或者，该第三上行信道可以为上述第二上行信道，例如，第二上行信道足以承载上述报告和第二上行信道中承载的信息，或者可以为除第一上行信道和第二上行信道之外的其他上行信道。
示例性的，在将报告和第二上行信道中承载的信息复用到第三上行信道的信道资源上发送时，该报告和第二上行信道中承载的信息在第三上行信道中的排列顺序可以是由报告的优先级和第二上行信道中承载的信息的优先级确定，优先级越高的信息排序在越前面，可以保证优先承载优先级高的信息，让优先级越高的信息优先被解析。在一些实现方式中，如果第三上行信道的信道资源能够承载的数据量小于报告和第二上行信道中承载的信息的总数据量，则可以将报告和/或第二上行信道中承载的信息划分为多个部分，丢弃至少一个部分的信息，而将剩余信息复用到第三上行信道的信道资源上。例如，将本申请的用于承载AI模型更新信息的报告划分为两个部分，而丢弃其中优先级更低的部分，而将剩余部分与第二上行信道中承载的信息复用到第三上行信道的信道资源上发送。
在另一种实现方式中，发送第一上行信道，且丢弃第二上行信道中承载的信息。例如，默认本申请的AI模型更新报告的优先级最高。例如，如图3b所示，可以使用下一个上行授权1的资源发送报告，但是该报告与其他上行信道(即第二上行信道)或参考信号(Reference Signal，RS)所在资源存在冲突，则可以丢弃其他上行信道或参考信号，并在上述授权1上发送用于承载报告的第一上行信道。
在一些实施例中，可以是根据第一上行信道中承载的报告和第二上行信道中承载的信息的优先级比较结果，确定发送第一上行信道或第二上行信道。例如，若第一上行信道中承载的报告的优先级大于第二上行信道中承载的信息的优先级，则发送第一上行信道，且丢弃第二上行信道中承载的信息。又例如，若第一上行信道中承载的报告的优先级小于第二上行信道中承载的信息的优先级，则发送第二上行信道，且丢弃第一上行信道承载的报告。
在又一种实现方式中，可以调整第一上行信道的发送功率和/或调整第二上行信道的发送功率，并发送功率调整后的第一上行信道和第二上行信道，其中，功率调整后的第一上行信道的发送功率和第二上行信道的发送功率之和小于或等于终端设备支持的最大发送功率。在一些实施例中，可以是将第一上行信道的发送功率调高，和/或，将第二上行信道的发送功率调低。例如，若第一上行信道中承载的报告的优先级大于第二上行信道中承载的信息的优先级，则将第一上行信道中的发送功率调高；和/或，将所述第二上行信道的发送功率调低。又例如，若第一上行信道中承载的报告的优先级小于第二上行信道中承载的信息的优先级，则将第一上行信道中的发送功率调低；和/或，将所述第二上行信道的发送功率调高。
可理解，以上各种解决资源冲突的实现方式可单独实施也可结合实施，本申请不作限定。
下面对报告的优先级的确定方式进行举例说明：
一种实现方式中，包含AI模型更新信息的报告的优先级可以具有最高优先级，即高于各种上行控制信息(Uplink Control Information，UCI)的优先级。
另一种实现方式中，包含AI模型更新信息的报告在包含第一信息的情况下，该报告的优先级最高，其中，第一信息可以包括以下至少一项：上述信息a(即第一指示信息)、上述信息b(即第二AI模型的模型信息)、上述信息d(即第三指示信息)、上述信息f(即第三AI模型的模型信息)、上述信息g(即第四指示信息)、上述信息i(即报告的报告类型)。
又一种实现方式中，终端设备更新后的AI模型与更新前的AI模型不同时，则包含AI模型更新信息的报告的优先级最高。
在又一种实现方式中，如果未对第一AI模型进行更新的情况下，包含AI模型更新信息的报告的优先级最低。
在又一种实现方式中，包含AI模型更新信息的报告在包含第二信息的情况下，该报告的优先级最低，该第二信息可以为上述信息d(即第三指示信息)。
在终端设备将报告发送给网络设备之后，还需要确定该报告的生效时间，报告的生效时间可理解为网 络设备和终端设备启用报告中指示内容的时间，例如，报告中指示更新到第二AI模型，则生效时间可理解为启用第二AI模型的时间。该报告的生效时间可以由以下至少一项确定：
1、终端设备发送报告之后的第一时长开始生效；例如，可以是终端设备发送报告之后的第一时长之后的第一个时隙开始生效。其中，发送报告之后的第一时长之后可理解为，报告所在上行信道的时域资源结束之后的第一时长之后。如图3c所示，时间偏移即可理解为第一时长，在发送报告之后，该时间偏移后的第一个时隙开始时间为生效时间点，即该生效时间点起开始生效。
2、网络发送目标信令后的第二时长开始生效，该目标信令用于指示对第一AI模型进行更新；例如，可以是网络发送目标信令后的第二时长之后的第一个时隙开始生效。发送目标信令后的第二时长之后可理解为，目标信令所在下行信道的时域资源结束之后的第二时长之后。
3、发送第二请求信息后的第三时长开始生效，该第二请求信息用于请求网络发送用于辅助对第一AI模型进行更新的信息；例如，第二请求信息可以用于请求网络发送参考信号让终端设备测量，以对第一AI模型进行更新。
4、报告或第二请求信息中携带的生效时间；
5、第二AI模型的有效时间长度，即在该有效时间长度内第二AI模型有效，所述第二AI模型为将所述第一AI模型更新后得到的模型。
可理解，上述各种时长的单位可以是帧frame、时隙slot、符号symbol等，不作限定。上述生效时间可以由网络指示或协议约定。
上述生效时间需要满足以下至少一项：AI模型的训练时长、推理时长、更新时长等(比如测量网络发送的参考信号，并使用AI模型进行训练，即需要在训练完成之后才启用新的模型)、AI模型的编译时长(当更新AI模型结构时需要对AI模型进行编译，生效时间需要在编译时长之后启用)、AI模型的参数更新时长(当更新AI模型的参数时，需要满足参数更新时长)。
在一些实施例中，上述生效时间(比如时长中包含的符号数)可以是由更新后第二AI模型所关联的预设信息对应的子载波间隔确定的，或者，由更新后的第二AI模型所关联的预设信息对应的多个子载波间隔中的最小子载波间隔确定的。其中，预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项。网络信息包括以下至少一项：公共陆地移动网络PLMN信息、运营商标识信息、网络设备商标识信息、跟踪区标识TAI信息、漫游控制SOR信息、路由选择策略URSP信息等。接入网信息包括以下至少一项：工作频率信息、小区组信息、服务小区信息、物理小区标识、发送接收点TRP标识信息、带宽部分BWP标识信息、与小区关联的参考信号RS信息等。以预设信息为小区组作为举例，该小区组中每个小区的每个BWP都会对应一个子载波间隔SCS，那么就使用其中的最小SCS来确定生效时间，从而保证该小区组内的所有小区对应的更新后的AI模型同时生效。
可理解，每个符号的长度可以是由子载波间隔确定，因此，上述时长内包含的符号数也是由子载波间隔确定。
请参照图3d，为本申请实施例提供的另一种报告传输方法的流程示意图，如图3d所示，该方法包括但不限于以下步骤：
201，终端设备根据对第一AI模型的更新情况，发送报告，该报告包括对第一AI模型的更新信息。
202，网络设备接收终端设备发送的报告。
其中，步骤201-步骤202可参照图2实施例中的步骤101-步骤102，在此不再赘述。
203，网络设备向目标网络或目标站点或目标小区发送报告中的部分信息或全部信息。
网络设备可将报告中的全部信息发送给目标网络或目标站点或目标小区，也可以是将其中部分信息发送给目标网络或目标站点或目标小区，例如，可以是将一些通用的信息发送给目标网络或目标站点或目标小区，通用信息包括但不限于以下至少一项：更新后的第二AI模型的模型信息、模型更新所使用的数据集、训练时使用的参考信号信息、终端设备的位置信息、终端设备当前所在的运营商标识/PLMN/网络设备商信息、终端设备当前的TAI/SOR/URSP信息、终端设备当前的接入网信息、终端设备的ID、终端设备的设备商信息等等。
在一种实现方式，目标网络可以满足以下至少一项：
目标网络与当前网络相同；
目标网络与当前网络具有相同的运营商标识或具有相同的PLMN信息；
目标网络与当前网络具有相同的网络设备商标识；
目标网络为终端设备驻留的上一个网络；
目标网络为当前网络相邻的网络；
其中，当前网络为终端设备当前驻留的网络。上述网络可理解为核心网，或者运营商网络，本申请不作限定。
在另一种实现方式中，目标站点满足以下至少一项：
目标站点与当前站点具有相同的运营商标识或者PLMN或网络设备商；
目标站点为当前站点配置的邻区列表中各个邻区所对应的站点，邻区列表包括一个或多个邻区；
目标站点的小区与当前站点的小区均在参考站点的邻区列表中；
目标站点为当前站点配置的邻区列表中第一邻区所对应的站点，第一邻区是网络配置或激活或指示的波束信息所关联的邻区；
目标站点的小区与当前站点的小区均在参考站点的邻区列表中，且目标站点的小区与当前站点的小区均为网络配置或激活或指示的波束信息关联的小区；
目标站点为终端设备驻留的上一个小区对应的站点；
目标站点为当前站点的相邻站点；
目标站点为AI模型信息管理服务器，例如，LMF，AI模型信息处理节点，第三方的OTT(over the top)服务器；
其中，当前站点为终端设备当前所在小区对应的站点。上述站点可理解为基站或TRP，当前站点可以为上述网络设备。
在又一种实现方式中，目标小区满足以下至少一项：
目标小区与当前小区具有相同的运营商标识或者PLMN或网络设备商；
目标小区为当前小区配置的邻区列表中的小区，邻区列表包括一个或多个邻区；
目标小区与当前小区均在参考小区的邻区列表中；
目标小区为当前小区配置的邻区列表中的小区，且目标小区是网络配置或激活或指示的波束信息所关联的邻区；
目标小区与当前小区均在参考小区的邻区列表中，且目标小区与当前小区均为网络配置或激活或指示的波束信息关联的小区；
目标小区为终端设备驻留的上一个小区；
目标小区为当前小区的邻区；
其中，当前小区为终端设备当前驻留的小区。
该实施例中，网络设备可将报告中的全部或部分信息发送给目标小区或目标站点或目标网络，从而便于目标小区或目标站点或目标网络提前获取终端设备的AI模型更新信息，能够提前准备好终端设备切换到目标小区或目标站点或目标网络。
请参见图4，图4是本申请实施例提供的一种通信装置的结构示意图。该装置可以是终端设备，也可以是终端设备中的装置，比如，可以是该终端设备中的芯片或芯片模组，或者是能够和终端设备匹配使用的装置。图4所示的通信装置400可以包括发送单元401和处理单元402。其中：
发送单元401，用于根据对第一人工智能AI模型的更新情况，发送报告；其中，所述报告包括对所述第一AI模型的更新信息。
在一种可能的实现方式中，所述报告包括以下至少一项信息：
第一指示信息，所述第一指示信息用于指示完成对所述第一AI模型的更新；
第二AI模型的模型信息，所述第二AI模型为将所述第一AI模型更新后得到的模型；
第二指示信息，所述第二指示信息用于指示去激活的AI模型的模型信息；
第三指示信息，所述第三指示信息用于指示未完成对所述第一AI模型的更新；
第二AI模型所关联的预设信息，所述预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项，所述第二AI模型为将所述第一AI模型更新后得到的模型；
第三AI模型的模型信息，所述第三AI模型是在未将所述第一AI模型更新到第二AI模型的情况下所切换到的模型；
第四指示信息，所述第四指示信息用于指示使用非AI模型；
第五指示信息，所述第五指示信息用于指示第二AI模型的至少一个属性信息，所述至少一个属性信 息为未将所述第一AI模型更新到所述第二AI模型的情况下终端设备不支持的属性信息；
所述报告的报告类型；
第一请求信息，所述第一请求信息用于请求网络指示第四AI模型；
从所述第一AI模型更新至第二AI模型的建议时长，所述第二AI模型为将所述第一AI模型更新后得到的模型；
在完成对所述第一AI模型的更新之后的生效时长；
在对所述第一AI模型更新时所测量的参考信号信息，所述参考信号信息包括参考信号资源的数量、参考信号资源集合的索引、参考信号资源的索引、参考信号的测量结果中的至少一项。
在一种可能的实现方式中，所述报告类型包括AI模型更新报告；或者，
所述报告类型包括非AI模型的常规测量反馈报告、AI模型的预测反馈报告、AI模型的增强测量反馈报告以及AI模型的更新报告中至少一项。
在一种可能的实现方式中，所述至少一个属性信息包括以下至少一项：所述第二AI模型的模型标识、所述第二AI模型的模型结构信息以及所述第二AI模型的模型参数。
在一种可能的实现方式中，所述报告包括至少一个部分，所述报告中排序在前的部分所携带的信息用于确定排序在后的部分所携带的信息。
在一种可能的实现方式中，所述报告的格式由触发对所述第一AI模型进行更新的触发方式确定；所述触发方式包括：基于检测的事件触发的模型更新，或者基于网络信令触发的模型更新。
在一种可能的实现方式中，所述发送报告，包括：
所述发送单元401，具体用于使用上行资源发送所述报告，所述上行资源包括网络预配置的周期性的上行信道资源，或者最近的可用于承载所述报告的上行授权资源，或者在历史时间段内使用次数最多的上行授权资源，或者上一次使用的上行授权资源，或者通过调度请求SR触发网络设备指示的上行授权资源。
在一种可能的实现方式中，所述发送单元401，具体用于在主小区上发送所述报告；或者，在FR1频段的小区上发送所述报告。
在一种可能的实现方式中，所述发送单元401，具体用于使用一个或多个上行波束重复发送所述报告。
在一种可能的实现方式中，所述发送单元401，具体用于使用一个或多个上行波束以时分复用的方式重复发送所述报告；或者，使用多个上行波束同时发送所述报告。
在一种可能的实现方式中，所述同时发送的报告在所述多个上行波束上分别采用不同的层或者频域资源或者正交码序列发送。
在一种可能的实现方式中，所述发送单元401，具体用于若用于承载所述报告的第一上行信道的信道资源与第二上行信道的信道资源存在冲突时，采用以下一种方式发送报告：
将所述报告和所述第二上行信道中承载的信息复用到第三上行信道的信道资源上发送；或者，发送所述第一上行信道，且丢弃所述第二上行信道中承载的信息；或者，通过处理单元402调整所述第一上行信道的发送功率和/或所述第二上行信道的发送功率，并指示发送单元401发送功率调整后的第一上行信道和第二上行信道，其中，功率调整后的第一上行信道的发送功率和第二上行信道的发送功率之和小于或等于终端设备支持的最大发送功率。
在一种可能的实现方式中，处理单元402具体用于若所述报告的优先级大于所述第二上行信道中承载的信息的优先级，则将所述第一上行信道的发送功率调高；和/或，将所述第二上行信道的发送功率调低。
在一种可能的实现方式中，发送单元401具体用于若所述报告的优先级大于所述第二上行信道中承载的信息的优先级，发送所述第一上行信道，且丢弃所述第二上行信道中承载的信息。
在一种可能的实现方式中，在将所述报告和所述第二上行信道中承载的信息复用到第三上行信道的信道资源上发送的情况下，所述报告和所述第二上行信道中承载的信息在所述第三上行信道中的排列顺序由所述报告的优先级和所述第二上行信道中承载的信息的优先级确定。
在一种可能的实现方式中，发送单元401具体用于若所述报告的优先级低于所述第二上行信道中承载的信息的优先级，发送所述第二上行信道，且丢弃所述第一上行信道中承载的所述报告。
在一种可能的实现方式中，所述报告的优先级最高；或者，在所述报告中包含第一信息的情况下，所述报告的优先级最高；或者，更新后的第二AI模型与所述第一AI模型不同时，所述报告的优先级最高。
在一种可能的实现方式中，所述第一信息包括以下至少一项：所述第一指示信息、所述第二AI模型的模型信息、所述第三指示信息、所述第三AI模型的模型信息、所述第四指示信息、所述报告的报告类型。
在一种可能的实现方式中，在未对所述第一AI模型进行更新的情况下，所述报告的优先级最低。
在一种可能的实现方式中，所述报告的生效时间由以下至少一项确定：
发送所述报告之后的第一时长开始生效；
网络发送目标信令后的第二时长开始生效，所述目标信令用于指示对所述第一AI模型进行更新；
发送第二请求信息后的第三时长开始生效，所述第二请求信息用于请求网络发送用于辅助对所述第一AI模型进行更新的信息；
所述报告或第二请求信息中携带的生效时间；
第二AI模型的有效时间长度，所述第二AI模型为将所述第一AI模型更新后得到的模型。
在一种可能的实现方式中，所述生效时间由网络指示或协议约定。
在一种可能的实现方式中，所述生效时间由所述第二AI模型所关联的预设信息对应的子载波间隔确定，或者由所述第二AI模型所关联的预设信息对应的多个子载波间隔中的最小子载波间隔确定，所述预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项。
在一种可能的实现方式中，所述网络信息包括以下至少一项：
公共陆地移动网络PLMN信息、运营商标识信息、网络设备商标识信息、跟踪区标识TAI信息、漫游控制SOR信息、路由选择策略URSP信息。
在一种可能的实现方式中，所述接入网信息包括以下至少一项：
工作频率信息、小区组信息、服务小区信息、物理小区标识、发送接收点TRP标识信息、带宽部分BWP标识信息、与小区关联的参考信号RS信息。
其中，该实施方式的相关内容可参见上述方法实施例的相关内容。此处不再详述。
请参见图5，图5是本申请实施例提供的一种通信装置的结构示意图。该装置可以是网络设备，也可以是网络设备中的装置，比如，可以是该网络设备中的芯片或芯片模组，或者是能够和网络设备匹配使用的装置。图5所示的通信装置500可以包括接收单元501和发送单元502。其中：
接收单元501，用于接收终端设备发送的报告，所述报告包括所述终端设备对第一AI人工智能模型的更新信息。
在一种可能的实现方式中，所述报告包括以下至少一项信息：
第一指示信息，所述第一指示信息用于指示完成对所述第一AI模型的更新；
第二AI模型的模型信息，所述第二AI模型为将所述第一AI模型更新后得到的模型；
第二指示信息，所述第二指示信息用于指示去激活的AI模型的模型信息；
第三指示信息，所述第三指示信息用于指示未完成对所述第一AI模型的更新；
第二AI模型所关联的预设信息，所述预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项，所述第二AI模型为将所述第一AI模型更新后得到的模型；
第三AI模型的模型信息，所述第三AI模型是在未将所述第一AI模型更新到第二AI模型的情况下所切换到的模型；
第四指示信息，所述第四指示信息用于指示使用非AI模型；
第五指示信息，所述第五指示信息用于指示第二AI模型的至少一个属性信息，所述至少一个属性信息为未将所述第一AI模型更新到所述第二AI模型的情况下终端设备不支持的属性信息；
所述报告的报告类型；
第一请求信息，所述第一请求信息用于请求网络指示第四AI模型；
从所述第一AI模型更新至第二AI模型的建议时长，所述第二AI模型为将所述第一AI模型更新后得到的模型；
在完成对所述第一AI模型的更新之后的生效时长；
在对所述第一AI模型更新时所测量的参考信号信息，所述参考信号信息包括参考信号资源的数量、参考信号资源集合的索引、参考信号资源的索引、参考信号的测量结果中至少一项。
在一种可能的实现方式中，所述网络信息包括以下至少一项：
公共陆地移动网络PLMN信息、运营商标识信息、网络设备商标识信息、跟踪区标识TAI信息、漫游控制SOR信息、路由选择策略URSP信息。
在一种可能的实现方式中，所述接入网信息包括以下至少一项：
工作频率信息、小区组信息、服务小区信息、物理小区标识、发送接收点TRP标识信息、带宽部分 BWP标识信息、与小区关联的参考信号RS信息。
在一种可能的实现方式中，所述报告类型包括AI模型更新报告；或者，
所述报告类型包括非AI模型的常规测量反馈报告、AI模型的预测反馈报告、AI模型的增强测量反馈报告以及AI模型的更新报告中至少一项。
在一种可能的实现方式中，所述至少一个属性信息包括以下至少一项：所述第二AI模型的模型标识、所述第二AI模型的模型结构信息以及所述第二AI模型的模型参数。
在一种可能的实现方式中，所述报告包括至少一个部分，所述报告中排序在前的部分所携带的信息用于确定排序在后的部分所携带的信息。
在一种可能的实现方式中，所述发送单元502，用于向目标网络或目标站点或目标小区发送所述报告中的部分信息或全部信息。
在一种可能的实现方式中，所述目标网络满足以下至少一项：
所述目标网络与当前网络相同；
所述目标网络与当前网络具有相同的运营商标识或具有相同的PLMN信息；
所述目标网络与当前网络具有相同的网络设备商标识；
所述目标网络为所述终端设备驻留的上一个网络；
所述目标网络为当前网络相邻的网络；
其中，所述当前网络为所述终端设备当前驻留的网络。
在一种可能的实现方式中，所述目标站点满足以下至少一项：
所述目标站点与当前站点具有相同的运营商标识或者PLMN或网络设备商；
所述目标站点为当前站点配置的邻区列表中各个邻区所对应的站点，所述邻区列表包括一个或多个邻区；
所述目标站点的小区与当前站点的小区均在参考站点的邻区列表中；
所述目标站点为当前站点配置的邻区列表中第一邻区所对应的站点，所述第一邻区是网络配置或激活或指示的波束信息所关联的邻区；
所述目标站点的小区与当前站点的小区均在参考站点的邻区列表中，且所述目标站点的小区与所述当前站点的小区均为网络配置或激活或指示的波束信息关联的小区；
所述目标站点为所述终端设备驻留的上一个小区对应的站点；
所述目标站点为当前站点的相邻站点；
所述目标站点为AI模型信息管理服务器；
其中，所述当前站点为所述终端设备当前所在小区对应的站点。
在一种可能的实现方式中，所述目标小区满足以下至少一项：
所述目标小区与当前小区具有相同的运营商标识或者PLMN或网络设备商；
所述目标小区为当前小区配置的邻区列表中的小区，所述邻区列表包括一个或多个邻区；
所述目标小区与当前小区均在参考小区的邻区列表中；
所述目标小区为当前小区配置的邻区列表中的小区，且所述目标小区是网络配置或激活或指示的波束信息所关联的邻区；
所述目标小区与当前小区均在参考小区的邻区列表中，且所述目标小区与所述当前小区均为网络配置或激活或指示的波束信息关联的小区；
所述目标小区为所述终端设备驻留的上一个小区；
所述目标小区为当前小区的邻区；
其中，所述当前小区为所述终端设备当前驻留的小区。
其中，该实施方式的相关内容可参见上述方法实施例的相关内容。此处不再详述。
请参见图6，图6是本申请实施例提供的又一种通信装置的结构示意图，用于实现上述图2或图3d中终端设备的功能。该通信装置600可以是终端设备或用于终端设备的装置。用于终端设备的装置可以为终端设备内的芯片系统或芯片。其中，芯片系统可以由芯片构成，也可以包含芯片和其他分立器件。
该通信装置也可以用于实现上述图2或图3d中网络设备的功能。该通信装置600可以是网络设备或用于网络设备的装置。用于网络设备的装置可以为网络设备内的芯片系统或芯片。其中，芯片系统可以由芯片构成，也可以包含芯片和其他分立器件。
通信装置600包括至少一个处理器620，用于实现本申请实施例提供的方法中终端设备或网络设备的数据处理功能。通信装置600还可以包括通信接口610，用于实现本申请实施例提供的方法中终端设备或网络设备的收发操作。在本申请实施例中，处理器620可以是中央处理单元(Central Processing Unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。在本申请实施例中，通信接口610可以是收发器、电路、总线、模块或其它类型的通信接口，用于通过传输介质和其它设备进行通信。例如，通信接口610用于通信装置600中的装置可以和其它设备进行通信。处理器620利用通信接口610收发数据，并用于实现上述方法实施例图2或图3d所述的方法。
通信装置600还可以包括至少一个存储器630，用于存储程序指令和/或数据。存储器630和处理器620耦合。本申请实施例中的耦合是装置、单元或模块之间的间接耦合或通信连接，可以是电性，机械或其它的形式，用于装置、单元或模块之间的信息交互。处理器620可能和存储器630协同操作。处理器620可能执行存储器630中存储的程序指令。所述至少一个存储器中的至少一个可以包括于处理器中。
当通信装置600开机后，处理器620可以读取存储器630中的软件程序，解释并执行软件程序的指令，处理软件程序的数据。当需要通过无线发送数据时，处理器620对待发送的数据进行基带处理后，输出基带信号至射频电路(图6未示意)，射频电路将基带信号进行射频处理后将射频信号通过天线以电磁波的形式向外发送。当有数据发送到通信装置600时，射频电路通过天线接收到射频信号，将射频信号转换为基带信号，并将基带信号输出至处理器620，处理器620将基带信号转换为数据并对该数据进行处理。
在另一种实现中，所述的射频电路和天线可以独立于进行基带处理的处理器620而设置，例如在分布式场景中，射频电路和天线可以与独立于通信装置，呈拉远式的布置。
本申请实施例中不限定上述通信接口610、处理器620以及存储器630之间的具体连接介质。本申请实施例在图6中以存储器630、处理器620以及通信接口610之间通过总线640连接，总线在图6中以粗线表示，其它部件之间的连接方式，仅是进行示意性说明，并不引以为限。所述总线可以分为地址总线、数据总线、控制总线等。为便于表示，图6中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
通信装置600具体是用于终端设备时，例如通信装置600具体是芯片或者芯片系统时，通信接口610所输出或接收的可以是基带信号。通信装置600具体是终端设备时，通信接口610所输出或接收的可以是射频信号。
需要说明的是，该通信装置可以执行前述方法实施例中终端设备或网络设备的相关步骤，具体可参见上述各个步骤所提供的实现方式，在此不再赘述。
对于应用于或集成于通信装置的各个装置、产品，其包含的各个模块可以都采用电路等硬件的方式实现，不同的模块可以位于终端内同一组件(例如，芯片、电路模块等)或者不同组件中，或者，至少部分模块可以采用软件程序的方式实现，该软件程序运行于终端内部集成的处理器，剩余的(如果有)部分模块可以采用电路等硬件方式实现。
上述存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable rom，PROM)、可擦除可编程只读存储器(erasable prom，EPROM)、电可擦除可编程只读存储器(electrically eprom，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的随机存取存储器(random access memory，RAM)可用，例如静态随机存取存储器(static ram，SRAM)、动态随机存取存储器(dynamic random access memory，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。
本申请实施例提供一种芯片。该芯片包括：处理器和存储器。其中，处理器的数量可以是一个或多个，存储器的数量可以是一个或多个。处理器通过读取存储器上存储的指令和数据，可执行上述图2或图3d中所示的报告传输方法，以及相关实施方式所执行的步骤。
如图7所示，图7是本申请实施例提供的一种模组设备的结构示意图。该模组设备700可以执行前述方法实施例中终端设备或网络设备的相关步骤，该模组设备700包括：通信模组701、电源模组702、存储模组703以及芯片模组704。其中，电源模组702用于为模组设备提供电能；存储模组703用于存储数据和/或指令；通信模组701用于与外部设备进行通信；芯片模组704用于调用存储模组703存储的数据和/或指令，结合通信模组701，可执行上述如图2或图3d所示的报告传输方法，以及相关实施方式所执行的步骤。
本申请实施例中还提供一种计算机可读存储介质。所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，当电子设备执行所述程序指令时，实现上述图2或图3d所示的报告传输方法中终端设备所执行的步骤或者网络设备所执行的步骤。
所述计算机可读存储介质可以是前述任一实施例所述的终端设备或网络设备的内部存储单元，例如设备的硬盘或内存。所述计算机可读存储介质也可以是所述终端设备或网络设备的外部存储设备，例如所述设备上配备的插接式硬盘，智能存储卡(smart media card，SMC)，安全数字(secure digital，SD)卡，闪存卡(flash card)等。进一步地，所述计算机可读存储介质还可以既包括所述终端设备或网络设备的内部存储单元也包括外部存储设备。所述计算机可读存储介质用于存储所述计算机程序以及所述终端设备或网络设备所需的其他程序和数据。所述计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的数据。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合的服务器、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。半导体介质可以是固态硬盘。
关于上述实施例中描述的各个装置、产品包含的各个模块/单元，其可以是软件模块/单元，也可以是硬件模块/单元，或者也可以部分是软件模块/单元，部分是硬件模块/单元。例如，对于应用于或集成于芯片的各个装置、产品，其包含的各个模块/单元可以都采用电路等硬件的方式实现，或者，至少部分模块/单元可以采用软件程序的方式实现，该软件程序运行于芯片内部集成的处理器，剩余的(如果有)部分模块/单元可以采用电路等硬件方式实现；对于应用于或集成于芯片模组的各个装置、产品，其包含的各个模块/单元可以都采用电路等硬件的方式实现，不同的模块/单元可以位于芯片模组的同一组件(例如芯片、电路模块等)或者不同组件中，或者，至少部分模块/单元可以采用软件程序的方式实现，该软件程序运行于芯片模组内部集成的处理器，剩余的(如果有)部分模块/单元可以采用电路等硬件方式实现；对于应用于或集成于数据采集节点的各个装置、产品，其包含的各个模块/单元可以都采用电路等硬件的方式实现，不同的模块/单元可以位于终端内同一组件(例如，芯片、电路模块等)或者不同组件中，或者，至少部分模块/单元可以采用软件程序的方式实现，该软件程序运行于数据采集节点内部集成的处理器，剩余的(如果有)部分模块/单元可以采用电路等硬件方式实现。
上述实施例，可以全部或部分地通过软件、硬件、固件或其他任意组合来实现。当使用软件实现时，上述实施例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指令或计算机程序。在计算机上加载或执行所述计算机指令或计算机程序时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以为通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令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，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线或无线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。
应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
在本申请所提供的几个实施例中，应该理解到，所揭露的方法、装置和系统，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的；例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式；例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理 包括，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网关节点等)执行本发明各个实施例所述方法的部分步骤。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等。
以上所揭露的仅为本申请一种较佳实施例而已，当然不能以此来限定本申请之权利范围，本领域普通技术人员可以理解实现上述实施例的全部或部分流程，并依本申请权利要求所作的等同变化，仍属于申请所涵盖的范围。

Claims (42)

  1. 一种报告传输方法，其特征在于，包括：
    根据对第一人工智能AI模型的更新情况，发送报告；其中，所述报告包括对所述第一AI模型的更新信息。
  2. 如权利要求1所述的方法，其特征在于，所述报告包括以下至少一项信息：
    第一指示信息，所述第一指示信息用于指示完成对所述第一AI模型的更新；
    第二AI模型的模型信息，所述第二AI模型为将所述第一AI模型更新后得到的模型；
    第二指示信息，所述第二指示信息用于指示去激活的AI模型的模型信息；
    第三指示信息，所述第三指示信息用于指示未完成对所述第一AI模型的更新；
    第二AI模型所关联的预设信息，所述预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项，所述第二AI模型为将所述第一AI模型更新后得到的模型；
    第三AI模型的模型信息，所述第三AI模型是在未将所述第一AI模型更新到第二AI模型的情况下所切换到的模型；
    第四指示信息，所述第四指示信息用于指示使用非AI模型；
    第五指示信息，所述第五指示信息用于指示第二AI模型的至少一个属性信息，所述至少一个属性信息为未将所述第一AI模型更新到所述第二AI模型的情况下终端设备不支持的属性信息；
    所述报告的报告类型；
    第一请求信息，所述第一请求信息用于请求网络指示第四AI模型；
    从所述第一AI模型更新至第二AI模型的建议时长，所述第二AI模型为将所述第一AI模型更新后得到的模型；
    在完成对所述第一AI模型的更新之后的生效时长；
    在对所述第一AI模型更新时所测量的参考信号信息，所述参考信号信息包括参考信号资源的数量、参考信号资源集合的索引、参考信号资源的索引、参考信号的测量结果中的至少一项。
  3. 如权利要求2所述的方法，其特征在于，所述报告类型包括AI模型更新报告；或者，
    所述报告类型包括非AI模型的常规测量反馈报告、AI模型的预测反馈报告、AI模型的增强测量反馈报告以及AI模型的更新报告中至少一项。
  4. 如权利要求2所述的方法，其特征在于，所述至少一个属性信息包括以下至少一项：所述第二AI模型的模型标识、所述第二AI模型的模型结构信息以及所述第二AI模型的模型参数。
  5. 如权利要求1-4任一项所述的方法，其特征在于，所述报告包括至少一个部分，所述报告中排序在前的部分所携带的信息用于确定排序在后的部分所携带的信息。
  6. 如权利要求1-5任一项所述的方法，其特征在于，所述报告的格式由触发对所述第一AI模型进行更新的触发方式确定；所述触发方式包括：基于检测的事件触发的模型更新，或者基于网络信令触发的模型更新。
  7. 如权利要求1-6任一项所述的方法，其特征在于，所述发送报告，包括：
    使用上行资源发送所述报告，所述上行资源包括网络预配置的周期性的上行信道资源，或者最近的可用于承载所述报告的上行授权资源，或者在历史时间段内使用次数最多的上行授权资源，或者上一次使用的上行授权资源，或者通过调度请求SR触发网络设备指示的上行授权资源。
  8. 如权利要求1-7任一项所述的方法，其特征在于，所述发送报告，包括：
    在主小区上发送所述报告；或者，在FR1频段的小区上发送所述报告。
  9. 如权利要求1-8任一项所述的方法，其特征在于，所述发送报告，包括：
    使用一个或多个上行波束重复发送所述报告。
  10. 如权利要求9所述的方法，其特征在于，所述使用一个或多个上行波束重复发送所述报告，包括：
    使用一个或多个上行波束以时分复用的方式重复发送所述报告；或者，使用多个上行波束同时发送所述报告。
  11. 如权利要求10所述的方法，其特征在于，所述同时发送的报告在所述多个上行波束上分别采用不同的层或者频域资源或者正交码序列发送。
  12. 如权利要求1-11任一项所述的方法，其特征在于，所述发送报告，包括：
    若用于承载所述报告的第一上行信道的信道资源与第二上行信道的信道资源存在冲突时，采用以下一种方式发送报告：
    将所述报告和所述第二上行信道中承载的信息复用到第三上行信道的信道资源上发送；或者，发送所述第一上行信道，且丢弃所述第二上行信道中承载的信息；或者，调整所述第一上行信道的发送功率和/或所述第二上行信道的发送功率，并发送功率调整后的第一上行信道和第二上行信道，其中，功率调整后的第一上行信道的发送功率和第二上行信道的发送功率之和小于或等于终端设备支持的最大发送功率。
  13. 如权利要求12所述的方法，其特征在于，所述调整所述第一上行信道的发送功率和/或所述上行第二信道的发送功率，包括：
    将所述第一上行信道的发送功率调高；和/或，将所述第二上行信道的发送功率调低。
  14. 如权利要求13所述的方法，其特征在于，所述将所述第一上行信道的发送功率调高；和/或，将所述第二上行信道的发送功率调低，包括：
    若所述报告的优先级大于所述第二上行信道中承载的信息的优先级，则将所述第一上行信道的发送功率调高；和/或，将所述第二上行信道的发送功率调低。
  15. 如权利要求12所述的方法，其特征在于，所述发送所述第一上行信道，且丢弃所述第二上行信道中承载的信息，包括：
    若所述报告的优先级大于所述第二上行信道中承载的信息的优先级，发送所述第一上行信道，且丢弃所述第二上行信道中承载的信息。
  16. 如权利要求12所述的方法，其特征在于，在将所述报告和所述第二上行信道中承载的信息复用到第三上行信道的信道资源上发送的情况下，所述报告和所述第二上行信道中承载的信息在所述第三上行信道中的排列顺序由所述报告的优先级和所述第二上行信道中承载的信息的优先级确定。
  17. 如权利要求15所述的方法，其特征在于，所述方法还包括：
    若所述报告的优先级低于所述第二上行信道中承载的信息的优先级，发送所述第二上行信道，且丢弃所述第一上行信道中承载的所述报告。
  18. 如权利要求14-16任一项所述的方法，其特征在于，所述报告的优先级最高；或者，在所述报告中包含第一信息的情况下，所述报告的优先级最高；或者，更新后的第二AI模型与所述第一AI模型不同时，所述报告的优先级最高。
  19. 如权利要求18所述的方法，其特征在于，所述第一信息包括以下至少一项：所述第一指示信息、所述第二AI模型的模型信息、所述第三指示信息、所述第三AI模型的模型信息、所述第四指示信息、所述报告的报告类型。
  20. 如权利要求17所述的方法，在未对所述第一AI模型进行更新的情况下，所述报告的优先级最低。
  21. 如权利要求1-20任一项所述的方法，其特征在于，所述报告的生效时间由以下至少一项确定：
    发送所述报告之后的第一时长开始生效；
    网络发送目标信令后的第二时长开始生效，所述目标信令用于指示对所述第一AI模型进行更新；
    发送第二请求信息后的第三时长开始生效，所述第二请求信息用于请求网络发送用于辅助对所述第一AI模型进行更新的信息；
    所述报告或第二请求信息中携带的生效时间；
    第二AI模型的有效时间长度，所述第二AI模型为将所述第一AI模型更新后得到的模型。
  22. 如权利要求21所述的方法，其特征在于，所述生效时间由网络指示或协议约定。
  23. 如权利要求21或22所述的方法，其特征在于，所述生效时间由所述第二AI模型所关联的预设信息对应的子载波间隔确定，或者由所述第二AI模型所关联的预设信息对应的多个子载波间隔中最小子载波间隔确定，所述预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项。
  24. 如权利要求2或23所述的方法，其特征在于，所述网络信息包括以下至少一项：
    公共陆地移动网络PLMN信息、运营商标识信息、网络设备商标识信息、跟踪区标识TAI信息、漫游控制SOR信息、路由选择策略URSP信息。
  25. 如权利要求2或23所述的方法，其特征在于，所述接入网信息包括以下至少一项：
    工作频率信息、小区组信息、服务小区信息、物理小区标识、发送接收点TRP标识信息、带宽部分BWP标识信息、与小区关联的参考信号RS信息。
  26. 一种报告传输方法，其特征在于，包括：
    接收终端设备发送的报告，所述报告包括所述终端设备对第一AI人工智能模型的更新信息。
  27. 如权利要求26所述的方法，其特征在于，所述报告包括以下至少一项信息：
    第一指示信息，所述第一指示信息用于指示完成对所述第一AI模型的更新；
    第二AI模型的模型信息，所述第二AI模型为将所述第一AI模型更新后得到的模型；
    第二指示信息，所述第二指示信息用于指示去激活的AI模型的模型信息；
    第三指示信息，所述第三指示信息用于指示未完成对所述第一AI模型的更新；
    第二AI模型所关联的预设信息，所述预设信息包括网络信息、接入网信息、信道质量信息、时间信息或终端设备标识信息中至少一项，所述第二AI模型为将所述第一AI模型更新后得到的模型；
    第三AI模型的模型信息，所述第三AI模型是在未将所述第一AI模型更新到第二AI模型的情况下所切换到的模型；
    第四指示信息，所述第四指示信息用于指示使用非AI模型；
    第五指示信息，所述第五指示信息用于指示第二AI模型的至少一个属性信息，所述至少一个属性信息为未将所述第一AI模型更新到所述第二AI模型的情况下终端设备不支持的属性信息；
    所述报告的报告类型；
    第一请求信息，所述第一请求信息用于请求网络指示第四AI模型；
    从所述第一AI模型更新至第二AI模型的建议时长，所述第二AI模型为将所述第一AI模型更新后得到的模型；
    在完成对所述第一AI模型的更新之后的生效时长；
    在对所述第一AI模型更新时所测量的参考信号信息，所述参考信号信息包括参考信号资源的数量、参考信号资源集合的索引、参考信号资源的索引、参考信号的测量结果中至少一项。
  28. 如权利要求27所述的方法，其特征在于，所述网络信息包括以下至少一项：
    公共陆地移动网络PLMN信息、运营商标识信息、网络设备商标识信息、跟踪区标识TAI信息、漫游控制SOR信息、路由选择策略URSP信息。
  29. 如权利要求27所述的方法，其特征在于，所述接入网信息包括以下至少一项：
    工作频率信息、小区组信息、服务小区信息、物理小区标识、发送接收点TRP标识信息、带宽部分BWP标识信息、与小区关联的参考信号RS信息。
  30. 如权利要求27所述的方法，其特征在于，所述报告类型包括AI模型更新报告；或者，
    所述报告类型包括非AI模型的常规测量反馈报告、AI模型的预测反馈报告、AI模型的增强测量反馈报告以及AI模型的更新报告中至少一项。
  31. 如权利要求27所述的方法，其特征在于，所述至少一个属性信息包括以下至少一项：所述第二AI模型的模型标识、所述第二AI模型的模型结构信息以及所述第二AI模型的模型参数。
  32. 如权利要求26-31任一项所述的方法，其特征在于，所述报告包括至少一个部分，所述报告中排序在前的部分所携带的信息用于确定排序在后的部分所携带的信息。
  33. 如权利要求26-32任一项所述的方法，其特征在于，所述方法还包括：
    向目标网络或目标站点或目标小区发送所述报告中的部分信息或全部信息。
  34. 如权利要求33所述的方法，其特征在于，所述目标网络满足以下至少一项：
    所述目标网络与当前网络相同；
    所述目标网络与当前网络具有相同的运营商标识或具有相同的PLMN信息；
    所述目标网络与当前网络具有相同的网络设备商标识；
    所述目标网络为所述终端设备驻留的上一个网络；
    所述目标网络为当前网络相邻的网络；
    其中，所述当前网络为所述终端设备当前驻留的网络。
  35. 如权利要求33所述的方法，其特征在于，所述目标站点满足以下至少一项：
    所述目标站点与当前站点具有相同的运营商标识或者PLMN信息或网络设备商；
    所述目标站点为当前站点配置的邻区列表中各个邻区所对应的站点，所述邻区列表包括一个或多个邻区；
    所述目标站点的小区与当前站点的小区均在参考站点的邻区列表中；
    所述目标站点为当前站点配置的邻区列表中第一邻区所对应的站点，所述第一邻区是网络配置或激活或指示的波束信息所关联的邻区；
    所述目标站点的小区与当前站点的小区均在参考站点的邻区列表中，且所述目标站点的小区与所述当前站点的小区均为网络配置或激活或指示的波束信息关联的小区；
    所述目标站点为所述终端设备驻留的上一个小区对应的站点；
    所述目标站点为当前站点的相邻站点；
    所述目标站点为AI模型信息管理服务器；
    其中，所述当前站点为所述终端设备当前所在小区对应的站点。
  36. 如权利要求33所述的方法，其特征在于，所述目标小区满足以下至少一项：
    所述目标小区与当前小区具有相同的运营商标识或者PLMN信息或网络设备商；
    所述目标小区为当前小区配置的邻区列表中的小区，所述邻区列表包括一个或多个邻区；
    所述目标小区与当前小区均在参考小区的邻区列表中；
    所述目标小区为当前小区配置的邻区列表中的小区，且所述目标小区是网络配置或激活或指示的波束信息所关联的邻区；
    所述目标小区与当前小区均在参考小区的邻区列表中，且所述目标小区与所述当前小区均为网络配置或激活或指示的波束信息关联的小区；
    所述目标小区为所述终端设备驻留的上一个小区；
    所述目标小区为当前小区的邻区；
    其中，所述当前小区为所述终端设备当前驻留的小区。
  37. 一种通信装置，其特征在于，包括：
    发送单元，用于根据对第一人工智能AI模型的更新情况，发送报告；其中，所述报告包括对所述第一AI模型的更新信息。
  38. 一种通信装置，其特征在于，包括：
    接收单元，用于接收终端设备发送的报告，所述报告包括所述终端设备对第一AI人工智能模型的更新信息。
  39. 一种通信装置，其特征在于，所述通信装置包括处理器和存储器，所述处理器和所述存储器相互连接，其中，所述存储器用于存储计算机程序，所述计算机程序包括程序指令，所述处理器调用所述程序指令，执行如权利要求1至25任一项所述的方法，或者执行如权利要求26-36任一项所述的方法。
  40. 一种芯片，其特征在于，所述芯片包括处理器与接口，所述处理器和所述接口耦合；所述接口用于接收或输出信号，所述处理器用于执行代码指令，以执行如权利要求1至25任一项所述的方法，或者以执行如权利要求26-36任一项所述的方法。
  41. 一种模组设备，其特征在于，所述模组设备包括通信模组、电源模组、存储模组以及芯片模组，其中：
    所述电源模组用于为所述模组设备提供电能；
    所述存储模组用于存储数据和/或指令；
    所述通信模组用于与外部设备通信；
    所述芯片模组用于调用所述存储模组存储的数据和/或指令，结合所述通信模组，执行如权利要求1至25任一项所述的方法，或者执行如权利要求26-36任一项所述的方法。
  42. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，当电子设备执行所述程序指令时，实现如权利要求1至25任一项所述的方法，或者实现如权利要求26-36任一项所述的方法。
PCT/CN2023/129573 2022-11-03 2023-11-03 报告传输方法及通信装置 Ceased WO2024094166A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211372491.3 2022-11-03
CN202211372491.3A CN117998443A (zh) 2022-11-03 2022-11-03 报告传输方法及通信装置

Publications (1)

Publication Number Publication Date
WO2024094166A1 true WO2024094166A1 (zh) 2024-05-10

Family

ID=90887563

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/129573 Ceased WO2024094166A1 (zh) 2022-11-03 2023-11-03 报告传输方法及通信装置

Country Status (2)

Country Link
CN (1) CN117998443A (zh)
WO (1) WO2024094166A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025236963A1 (zh) * 2024-05-11 2025-11-20 华为技术有限公司 通信方法、通信装置和系统
WO2025241568A1 (zh) * 2024-05-24 2025-11-27 华为技术有限公司 通信方法及装置
WO2026016102A1 (zh) * 2024-07-17 2026-01-22 Oppo广东移动通信有限公司 无线通信方法、终端设备以及网络设备
WO2026021295A1 (zh) * 2024-07-22 2026-01-29 维沃移动通信有限公司 模型参数传输方法、装置及通信设备
WO2026031182A1 (zh) * 2024-08-09 2026-02-12 Oppo广东移动通信有限公司 无线通信的方法、终端设备和网络设备
CN121645302A (zh) * 2026-02-04 2026-03-10 荣耀终端股份有限公司 通信方法及相关装置
WO2026060610A1 (zh) * 2024-09-19 2026-03-26 北京小米移动软件有限公司 通信方法、终端、网络设备及存储介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025255752A1 (zh) * 2024-06-12 2025-12-18 Oppo广东移动通信有限公司 基于ai模型的通信方法、装置、设备、介质和程序产品
CN120091398A (zh) * 2024-07-23 2025-06-03 中兴通讯股份有限公司 模型管理方法、通信节点及存储介质
WO2026031038A1 (zh) * 2024-08-08 2026-02-12 Oppo广东移动通信有限公司 无线通信的方法、终端设备和网络设备
CN121510038A (zh) * 2024-08-08 2026-02-10 维沃移动通信有限公司 Ai模型传输的指示方法、装置、通信设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021163895A1 (zh) * 2020-02-18 2021-08-26 Oppo广东移动通信有限公司 网络模型的管理方法及建立或修改会话的方法、装置
WO2022148226A1 (zh) * 2021-01-08 2022-07-14 展讯通信（上海）有限公司 模型更新方法及装置、存储介质、终端、网络侧设备
US20220225126A1 (en) * 2021-01-13 2022-07-14 Samsung Electronics Co., Ltd. Data processing method and device in wireless communication network
WO2022222089A1 (en) * 2021-04-22 2022-10-27 Qualcomm Incorporated Machine learning model reporting, fallback, and updating for wireless communications

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021163895A1 (zh) * 2020-02-18 2021-08-26 Oppo广东移动通信有限公司 网络模型的管理方法及建立或修改会话的方法、装置
WO2022148226A1 (zh) * 2021-01-08 2022-07-14 展讯通信（上海）有限公司 模型更新方法及装置、存储介质、终端、网络侧设备
US20220225126A1 (en) * 2021-01-13 2022-07-14 Samsung Electronics Co., Ltd. Data processing method and device in wireless communication network
WO2022222089A1 (en) * 2021-04-22 2022-10-27 Qualcomm Incorporated Machine learning model reporting, fallback, and updating for wireless communications

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
INTEL CORPORATION: "AI/ML enabled RAN and NR Air Interface", 3GPP DRAFT; RWS-210373, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. TSG RAN, no. 20210628 - 20210702, 7 June 2021 (2021-06-07), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , XP052025926 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025236963A1 (zh) * 2024-05-11 2025-11-20 华为技术有限公司 通信方法、通信装置和系统
WO2025241568A1 (zh) * 2024-05-24 2025-11-27 华为技术有限公司 通信方法及装置
WO2026016102A1 (zh) * 2024-07-17 2026-01-22 Oppo广东移动通信有限公司 无线通信方法、终端设备以及网络设备
WO2026021295A1 (zh) * 2024-07-22 2026-01-29 维沃移动通信有限公司 模型参数传输方法、装置及通信设备
WO2026031182A1 (zh) * 2024-08-09 2026-02-12 Oppo广东移动通信有限公司 无线通信的方法、终端设备和网络设备
WO2026060610A1 (zh) * 2024-09-19 2026-03-26 北京小米移动软件有限公司 通信方法、终端、网络设备及存储介质
CN121645302A (zh) * 2026-02-04 2026-03-10 荣耀终端股份有限公司 通信方法及相关装置

Also Published As

Publication number Publication date
CN117998443A (zh) 2024-05-07

Similar Documents

Publication Publication Date Title
WO2024094166A1 (zh) 报告传输方法及通信装置
CN112492698B (zh) 多链路低时延通信方法、装置、存储介质和电子装置
CN110417565B (zh) 一种模型更新方法、装置及系统
EP3619934B1 (en) Enabling exchange of information on radio frame configuration in neighbor cells
EP3295737A1 (en) Methods and devices for beam selection
CN117915481B (zh) 超密集工业物联网的资源分配方法及系统
KR101813822B1 (ko) D2d 발견 신호의 송신 방법과 송신 장치
WO2016119839A1 (en) Transmission power control
CN116488689A (zh) 波束信息交互方法、装置、设备及存储介质
JP2022516899A (ja) 無線通信方法及び装置
WO2024062879A1 (en) Artificial intelligence (ai)/machine learning (ml) for beam management
EP4068838B1 (en) Communication method and communication apparatus
US20210021534A1 (en) Measuring transmission delay
WO2024067143A1 (zh) 一种信息传输方法、装置和系统
EP3228136B1 (en) Methods and modules for handling channels in a radio spectrum
WO2024062878A1 (en) Artificial intelligence (ai)/machine learning (ml) for csi feedback enhancement
WO2024164962A1 (zh) 通信处理方法、装置、设备及可读存储介质
US20230062005A1 (en) Method and device for transmitting control information
WO2024062880A1 (en) Artificial intelligence (ai)/machine learning (ml) for positioning accuracy enhancements
CN115396072B (zh) 物理上行控制信道pucch资源的分配方法、装置及存储介质
WO2025077772A1 (en) Method and apparatus for determining ulplink transmission in mobile communications
WO2025015510A1 (zh) 用于测量的处理方法、装置、设备及存储介质
WO2025024999A1 (zh) 处理时延要求的确定方法及装置、终端设备、网络设备
WO2024067199A1 (zh) 资源协调方法、装置及存储介质
GB2638217A (en) Enhancement of beam reporting for beam prediction on the network side

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: 23885091

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 23885091

Country of ref document: EP

Kind code of ref document: A1