WO2023134628A1 - 传输方法、装置和设备 - Google Patents

传输方法、装置和设备 Download PDF

Info

Publication number
WO2023134628A1
WO2023134628A1 PCT/CN2023/071321 CN2023071321W WO2023134628A1 WO 2023134628 A1 WO2023134628 A1 WO 2023134628A1 CN 2023071321 W CN2023071321 W CN 2023071321W WO 2023134628 A1 WO2023134628 A1 WO 2023134628A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
information
output result
feedback information
mode
Prior art date
Application number
PCT/CN2023/071321
Other languages
English (en)
French (fr)
Inventor
施源
Original Assignee
维沃移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2023134628A1 publication Critical patent/WO2023134628A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B17/00Monitoring; Testing
    • H04B17/30Monitoring; Testing of propagation channels
    • H04B17/391Modelling the propagation channel
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W72/00Local resource management
    • H04W72/04Wireless resource allocation

Definitions

  • the present application belongs to the technical field of communication, and specifically relates to a transmission method, device and equipment.
  • the training of analog beamforming vectors is usually carried out in a polling manner, that is, the array elements in each polarization direction of each antenna panel send training signals (that is, candidate forming vectors) at the agreed time in a time-division multiplexing manner.
  • the terminal feeds back the beam report after the measurement, so that the network-side device can use the shaping vector of the training signal to realize simulated beam transmission when transmitting services next time.
  • the content of the beam report usually includes several optimal transmit beam identities and measured beam qualities of several optimal transmit beams (such as Layer 1 Reference Signal Received Power (Layer 1 Reference Signal Received Power, L1-RSRP)).
  • the network side device can perform beam indication on the channel or reference signal of the downlink and uplink, which is used to establish a beam link between the network side device and the terminal to realize the transmission of the channel or reference signal.
  • the specific process of beam indication is, for example, as follows: the network side device sends beam indication information to the terminal, carrying beam information to be used, and the terminal returns a response.
  • the above process needs to be interacted through signaling. After the interaction is completed, the beam to be used can take effect, which leads to a high delay in beam switching. Especially in some high-speed scenarios, beams are frequently switched, and the signaling interaction delay may be Does not meet demand.
  • Embodiments of the present application provide a transmission method, a terminal, and a network side device, which can solve the problem of determining transmission parameters.
  • a transmission method which is applied to a first device, and the method includes:
  • the target model includes a first model of a first device and/or a second model of a second device; the first model is correlated with the second model;
  • the transmission parameters are determined according to the output result of the target model.
  • a transmission method which is applied to a second device, and the method includes:
  • the target model includes a first model of a first device and/or a second model of a second device; the first model is correlated with the second model;
  • the transmission parameters are determined according to the output result of the target model.
  • a transmission device including:
  • An acquiring device configured to acquire an output result of a target model, where the target model includes a first model of the first device and/or a second model of the second device; the first model has a correlation with the second model;
  • a processing device configured to determine transmission parameters according to the output result of the target model.
  • a transmission device including:
  • An acquiring device configured to acquire an output result of a target model, where the target model includes a first model of the first device and/or a second model of the second device; the first model has a correlation with the second model;
  • a processing device configured to determine transmission parameters according to the output result of the target model.
  • a first device including a processor and a memory, the memory stores programs or instructions that can run on the processor, and when the programs or instructions are executed by the processor, the The steps of the method in one aspect.
  • a first device including a processor and a communication interface, wherein the communication interface is used to obtain an output result of a target model, and the target model includes the first model of the first device and/or the first A second model of the device; the first model has a correlation with the second model; the processor is configured to determine transmission parameters according to an output result of the target model.
  • a second device including a processor and a memory, the memory stores programs or instructions that can run on the processor, and when the programs or instructions are executed by the processor, the following The steps of the method described in the two aspects.
  • a second device including a processor and a communication interface, wherein the communication interface is used to obtain an output result of a target model, and the target model includes the first model of the first device and/or the first A second model of the device; the first model has a correlation with the second model; the processor is configured to determine transmission parameters according to an output result of the target model.
  • a ninth aspect provides a communication system, including: a first device and a second device, the terminal can be used to perform the steps of the transmission method described in the first aspect, and the network side device can be used to perform the steps of the second The steps of the transmission method described in the aspect.
  • a readable storage medium is provided, and a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method as described in the first aspect are implemented, or the The steps of the method described in the second aspect.
  • a chip in an eleventh aspect, includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run a program or an instruction to implement the method described in the first aspect. method, or implement the method as described in the second aspect.
  • a twelfth aspect provides a computer program/program product, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the The steps of the transmission method described in the second aspect.
  • the first device obtains the output result of the target model, and determines the transmission parameters according to the output result of the target model; wherein, the target model includes a first model of the first device and/or a second model of the second device; Since the first model has a correlation with the second model, the first device may determine the transmission parameters based on the first model and/or the second model, and the second device may determine the transmission parameters based on the first model and/or the second model, so that the determination The consistency of the transmission parameters is high, and there is no need for further interaction of transmission parameters between devices, so that the signaling overhead is small, the transmission delay is reduced, and the transmission efficiency is improved.
  • FIG. 1 is a structural diagram of a wireless communication system applicable to an embodiment of the present application
  • FIG. 2 is one of the schematic flow diagrams of the transmission method provided by the embodiment of the present application.
  • FIG. 3 is the second schematic flow diagram of the transmission method provided by the embodiment of the present application.
  • Fig. 4 is one of the structural schematic diagrams of the transmission device provided by the embodiment of the present application.
  • Fig. 5 is the second structural schematic diagram of the transmission device provided by the embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • FIG. 7 is a schematic diagram of a hardware structure of a terminal provided by an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a network side device according to an embodiment of the present application.
  • first, second and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific sequence or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application are capable of operation in sequences other than those illustrated or described herein and that "first" and “second” distinguish objects. It is usually one category, and the number of objects is not limited. For example, there may be one or more first objects.
  • “and/or” in the description and claims means at least one of the connected objects, and the character “/” generally means that the related objects are an "or” relationship.
  • LTE Long Term Evolution
  • LTE-Advanced LTE-Advanced
  • LTE-A Long Term Evolution-Advanced
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency Division Multiple Access
  • system and “network” in the embodiments of the present application are often used interchangeably, and the described technology can be used for the above-mentioned system and radio technology, and can also be used for other systems and radio technologies.
  • the following description describes the New Radio (New Radio, NR) system for example purposes, and uses NR terminology in most of the following descriptions, but these techniques can also be applied to applications other than NR system applications, such as the 6th generation (6th Generation , 6G) communication system.
  • 6G 6th generation
  • Fig. 1 shows a block diagram of a wireless communication system to which the embodiment of the present application is applicable.
  • the wireless communication system includes a terminal 11 and a network side device 12 .
  • the terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer) or a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a palmtop computer, a netbook, a super mobile personal computer (ultra-mobile personal computer, UMPC), mobile Internet device (Mobile Internet Device, MID), augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) equipment, robot, wearable device (Wearable Device) , vehicle equipment (VUE), pedestrian terminal (PUE), smart home (home equipment with wireless communication functions, such as refrigerators, TVs, washing machines or furniture, etc.), game consoles, personal computers (personal computers, PCs), teller machines or self-service Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (
  • the network side device 12 may include an access network device or a core network device, where the access network device 12 may also be called a radio access network device, a radio access network (Radio Access Network, RAN), a radio access network function, or Wireless access network unit.
  • RAN Radio Access Network
  • RAN Radio Access Network
  • Wireless access network unit Wireless access network unit
  • the access network device 12 may include a base station, a WLAN access point, or a WiFi node, etc., and the base station may be called a Node B, an evolved Node B (eNB), an access point, a Base Transceiver Station (Base Transceiver Station, BTS), a radio Base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B, Home Evolved Node B, Transmitting Receiving Point (TRP) or all As long as the same technical effect is achieved, the base station is not limited to a specific technical vocabulary. It should be noted that in this embodiment of the application, only the base station in the NR system is used as an example for introduction, and The specific type of the base station is not limited.
  • the beam indication needs to be interacted through signaling. After the interaction is completed, the new beam can take effect, which leads to the delay of beam switching cannot be reduced, especially in some high-speed scenarios, the beam is often switched, and the signaling interaction delay Demand may not be met, reducing resource utilization.
  • each polarization direction element on the panel of each high-frequency antenna array can only transmit analog beams in a time-division multiplexed manner.
  • the shaping weight of the analog beam is realized by adjusting the parameters of the RF front-end phase shifter and other equipment.
  • the training of analog beamforming vectors is usually performed in a polling manner, that is, the array elements in each polarization direction of each antenna panel are sequentially sent training signals at an agreed time in a time-division multiplexing manner (i.e. shape vector), the terminal feeds back the beam report after the measurement, and the network side equipment uses the training signal to realize the simulated beam transmission in the next service transmission.
  • the content of the beam report usually includes the identifiers of several optimal transmit beams and the measured beam qualities of several optimal transmit beams.
  • the network side device When performing beam measurement, the network side device will configure a reference signal resource set (RS resource set), which includes at least one reference signal resource, such as SSB resource or CSI-RS resource.
  • the terminal measures the L1-RSRP/L1-SINR of each RS resource, and reports at least one optimal measurement result to the network side device, and the reported content includes SSB RI or CRI, and L1-RSRP/L1-SINR.
  • the content of the report reflects at least one optimal beam and its quality, and is used by the network to determine the beam used to send the channel or signal to the UE.
  • the network can perform beam indication on downlink and uplink channels or reference signals, which are used to establish a beam link between the network and the UE to realize channel or Transmission of reference signals.
  • the network uses RRC signaling to configure K transmission configuration indication (Transmission Configuration Indication, TCI) state states for each CORESET.
  • K Transmission Configuration Indication
  • MAC CE indicates or activates 1 TCI state.
  • the UE monitors the PDCCH it uses the same quasi-colocation (QCL) for all search spaces in the CORESET, that is, the same TCI state to monitor the PDCCH.
  • the referenceSignal in the TCI state (such as periodic CSI-RS resource, semi-persistent CSI-RS resource, SS block, etc.) and the UE-specific PDCCH DMRS port are spatially QCL. The UE can know which receiving beam to use to receive the PDCCH according to the TCI state.
  • the network configures M TCI states through RRC signaling, and then uses MAC CE commands to activate 2N TCI states, and then notifies the TCI state through the N-bitTCI field of DCI.
  • the referenceSignal in the TCI state is related to the scheduling
  • the DMRS port of the PDSCH is QCL.
  • the UE can know which receiving beam to use to receive the PDSCH according to the TCI state.
  • the network configures QCL information for the CSI-RS resource through RRC signaling.
  • the network indicates its QCL information when activating a CSI-RS resource from the CSI-RS resource set configured by RRC through the MAC CE command.
  • the network configures QCL for the CSI-RS resource through RRC signaling, and uses DCI to trigger CSI-RS.
  • the network uses RRC signaling to configure spatial relation information (spatial relation information) for each PUCCH resource through the parameter PUCCH-SpatialRelationInfo.
  • spatial relation information spatial relation information
  • the spatial relation information configured for PUCCH resource contains multiple, use MAC-CE indication Or activate one of the spatial relation information.
  • the spatial relation information configured for the PUCCH resource contains only one, no additional MAC CE command is required.
  • the spatial relation information of PUSCH is when the DCI carried by PDCCH schedules PUSCH, each SRI codepoint of the SRI field in DCI indicates an SRI, and the SRI is used to indicate the spatial relation information of PUSCH.
  • the network configures spatial relation information for the SRS resource through RRC signaling.
  • the SRS type is semi-persistent SRS
  • the network activates one from a set of spatial relation information configured by RRC through the MAC CE command.
  • the SRS type is aperiodic SRS
  • the network configures spatial relation information for the SRS resource through RRC signaling.
  • AI Artificial Intelligence
  • neural networks There are many ways to implement AI models, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc.
  • the embodiment of the present application uses a neural network as an example for illustration, but does not limit the specific type of the AI model.
  • the neural network is composed of neurons, where a1, a2,...aK are inputs, w is a weight (multiplicative coefficient), b is a bias (additive coefficient), and ⁇ (.) is an activation function.
  • Common activation functions include Sigmoid, tanh, Rectified LinearUnit (ReLU), etc.
  • the parameters of the neural network are optimized by an optimization algorithm.
  • An optimization algorithm is a class of algorithms that can help us minimize or maximize an objective function (sometimes called a loss function).
  • the objective function is often a mathematical combination of model parameters and data. For example, given the data X and its corresponding label Y, we construct a neural network model f(.), with the model, the predicted output f(x) can be obtained according to the input x, and the predicted value and the real value can be calculated The gap between (f(x)-Y), this is the loss function.
  • Our purpose is to find the appropriate w, b to minimize the value of the above loss function, the smaller the loss value, the closer our model is to the real situation.
  • the current common optimization algorithms are basically based on the BP (error Back Propagation, error back propagation) algorithm.
  • 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 samples are passed in from the input layer, processed layer by layer by each hidden layer, and passed to the output layer. If the actual output of the output layer does not match the expected output, it will enter the error backpropagation stage.
  • Error backpropagation is to transmit the output error layer by layer through the hidden layer to the input layer in some form, and distribute the error to all the units of each layer, so as to obtain the error signal of each layer unit, and this error signal is used as the correction unit Basis for weight.
  • This weight adjustment process of each layer of signal forward propagation and error back propagation is carried out repeatedly.
  • the process of continuously adjusting the weights is also the learning and training process of the network. This process has been carried out until the error of the network output is reduced to an acceptable level, or until the preset number of learning times.
  • optimization algorithms are based on the error/loss obtained by the loss function when the error is backpropagated, and the derivative/partial derivative of the current neuron is calculated, and the learning rate, the previous gradient/derivative/partial derivative, etc. are added to obtain the gradient. Pass the gradient to the previous layer.
  • Fig. 2 is a schematic flowchart of an embodiment of a transmission method provided by an embodiment of the present invention. As shown in Figure 2, the method provided in this embodiment includes:
  • Step 101 the first device acquires an output result of a target model, and the target model includes a first model of the first device and/or a second model of the second device; the first model has a correlation with the second model.
  • the first device can obtain the output result of the target model by itself, and/or interact with other devices to obtain the output result of the target model, and the target model includes the first model of the first device and/or the second model of the second device
  • the transmission parameter can be determined based on the output result of the target model; since the first model is correlated with the second model, the output result of the first model is correlated with the output result of the second model, so that the first device and the The transmission parameters determined by the second device are also relevant;
  • the first device is any of the following: a terminal, a network side device or an auxiliary network central unit
  • the second device is any of the following: a terminal, a network side device or an auxiliary network central unit; that is, the first device and the second device Terminal B can be various combinations of network-side devices (such as base stations), terminals and auxiliary network central units, for example, the first device is a terminal, and the second device is a network-side device; or, the first device is a network-side device, and the second The device is a terminal; or both the first device and the second device are network-side devices; or, both the first device and the second device are terminals, or the first device is an auxiliary network central unit, and the second device is a network-side device, etc.
  • the auxiliary network central unit is a unit for information interaction, which can communicate with terminals and network side devices.
  • the types of the first device and the second device are not limited, which improves the applicability of the transmission method.
  • Step 102 the first device determines transmission parameters according to the output result of the target model.
  • the first device determines the transmission parameter according to the output result of the target model; that is, the output result of the target model contains information for determining the transmission parameter, and the first device can determine the transmission parameter according to the information output by the target model for determining the transmission parameter Transfer parameters.
  • the transmission parameters include, for example: signal or channel beam related information, Channel Quality Indication (CQI) related information, modulation and coding strategy (Molation and Coding Scheme, MCS) related information, wideband precoding matrix indication (Transmitted Precoding Matrix Indicator, TPMI) related information, power control related information, model parameter information, model verification information, feedback information for model adjustment, etc.
  • CQI Channel Quality Indication
  • MCS modulation and Coding Scheme
  • TPMI Transmitted Precoding Matrix Indicator
  • the beam-related information includes, but is not limited to, at least one of the following:
  • Spatial related information Time related information; Beam quality information; Beam ID; Angle;
  • the space related information includes but not limited to at least one of the following: at least one optimal beam related information, at least one angle related information or at least one beam quality related information;
  • the time-related information includes but is not limited to at least one of the following: at least one future beam-related information, at least one future angle-related information, or at least one future beam quality-related information.
  • the future beam refers to a beam used or predicted at a time after the current time.
  • CQI-related information MCS-related information
  • TPMI-related information power control-related information
  • power control-related information are similar to beam-related information, and will not be repeated here.
  • the output result B of the first model includes information for determining the transmission parameter C, and the first device can determine the transmission parameter C according to the output result B of the first model.
  • the first device obtains the output result of the target model, and determines the transmission parameters according to the output result of the target model; wherein, the target model includes the first model of the first device and/or the second model of the second device; because The first model has a correlation with the second model, the first device may determine the transmission parameter based on the first model and/or the second model, and the second device may determine the transmission parameter based on the first model and/or the second model, so that the determined The consistency of transmission parameters is high, and there is no need for further interaction between devices to transmit parameters, so that the signaling overhead is small, the transmission delay is reduced, and the transmission efficiency is improved.
  • the first model is correlated with the second model, and at least one of the following is satisfied:
  • the first model is identical to the second model
  • the first model is obtained by performing the first target processing based on the first model and/or the second model.
  • the first model has a correlation with the second model, that is, the output result of the first model is correlated with the output result of the second model, that is, the transmission parameter determined by the first device based on the output result and the second
  • the transmission parameters determined by the device based on the output results are dependent.
  • the first model and the second model satisfy the following conditions, for example:
  • the first model is the same as the second model; that is, the first model corresponding to the first terminal is the same as the second model corresponding to the second terminal;
  • the first model is obtained by performing the first target processing based on the first model and/or the second model; for example, the first model and/or the second model are processed according to the target rules, and the processed model is used as the first terminal corresponding first model of .
  • the degree of correlation between the first model and the second model can be adjusted according to actual application scenarios, so that the output results of the first terminal according to the target model and the transmission parameters determined by the second device are more consistent.
  • performing the first target processing based on the first model and/or the second model includes but is not limited to at least one of the following:
  • the first model is a student model or sub-model of the second model
  • the second target processing includes at least one of the following: pruning, deletion and increase;
  • the decomposition process includes at least one of: tensor decomposition and low-rank decomposition.
  • the initial first model is trained based on the output results of the second model, and the model obtained after training is used as the first model of the first device; or the second model is decomposed and/or decomposed, and trained The model obtained later is used as the first model of the first device.
  • the first model and/or the second model may be processed in different ways, and the processed model may be used as the first model, so that the correlation between the first model and the second model is higher.
  • the first model of the first device is obtained through at least one of the following methods:
  • the first device is obtained from the second device, and the first model is obtained by the second device from the third device, or generated by the second device;
  • the first model of the first device can be obtained in various ways, such as generated by the first device, or obtained by the second device and/or the third device.
  • the second model of the second device is obtained through at least one of the following methods:
  • the second device is obtained from the first device, and the second model is obtained by the first device from the third device, or generated by the first device;
  • the acquisition method of the second model is similar to the acquisition method of the first model.
  • the model can be interacted with the first device and the second device through an additional third device;
  • the model can be interacted with the first device or the second device through an additional third device, and then interacted with the other end through the first device or the second device that has obtained the model;
  • the model can be directly obtained by the first device or the second device, and then interacted with the other end through the first device or the second device that has obtained the model;
  • the first model may be obtained directly on the first device, and the second model may be obtained directly on the second device.
  • the first model of the first device and the second model of the second device can be obtained in various ways according to device capabilities and actual application scenarios, which is more flexible and easier to meet actual needs, improving the practicality.
  • the first target processing is performed based on the first model and/or the second model, including at least one of the following:
  • a first target treatment is performed by the first device based on the first model and/or the second model.
  • different devices can be selected to perform the first target processing based on the first model and/or the second model, that is, by
  • Different devices can be used for the first object processing, so the flexibility is relatively high, and the practicability is improved.
  • a part of the operation can be performed on one device, interacted with another device, and the other device can perform the same, different or partly the same part of different operations.
  • different devices can be used to perform the first target processing of the first model and/or the second model, which has greater flexibility and improves usability.
  • the first device and the second device may exchange related capability information, and the method further includes:
  • the first device sends capability information of the first model to the second device; and/or,
  • the first device sends a request message to the second device based on the capability information of the first model, where the request message is used to request first information related to transmission parameters; and/or,
  • the first device sends first indication information to the second device according to the output result of the first model, where the first indication information is used to indicate second information related to the transmission parameter.
  • the capabilities of the first model of the first device and the second model of the second device may be different, in order to make the output results of the first model and the second model and the transmission parameters determined by the first device and the second device more accurate Consistent, the first device and the second device need the capability information of the interaction model; that is, the capability information of the first model can be sent to the second device through the first device; and/or, the first device sends the capability information of the first model to the second device based on the capability information of the first model.
  • the second device sends a request message, the request message is used to request the first information related to the transmission parameter; and/or, the first device sends the first indication information to the second device according to the output result of the first model, and the first indication information is used to indicate The second information related to the transmission parameter; the capability information enabling the first device and the second device to interact with the model.
  • the first information and/or the second information related to the transmission parameters may include input parameter information and/or output parameter information of the model.
  • the second device may also send capability information of the second model to the first device, and the second device may also send request information and/or instruction information to the first device.
  • the first device and the second device can exchange model capability information, and the output results of the first model and the second model, and the transmission parameters determined by the first device and the second device are more consistent.
  • the first information and/or the second information includes but not limited to at least one of the following:
  • the sending beam information includes but is not limited to at least one of the following: the number of sending beams, the number of sending beam repetitions, increasing the difference in the number of sending beams, decreasing the difference in the number of sending beams, increasing the difference in sending beam repetitions, reducing
  • the difference of the number of transmission beam repetitions increases the number of transmission beams, decreases the number of transmission beams, increases the number of transmission beam repetitions, decreases the number of transmission beams, the minimum number of transmission beams to reach the target value, and the minimum number of transmission beams to reach the target accuracy value
  • Quantity the minimum number of beams sent to reach the target value or the minimum number of beams sent to reach the target accuracy value
  • the receiving beam information includes but is not limited to at least one of the following: the number of receiving beams, the number of repetitions of receiving beams, increasing the difference in the number of receiving beams, decreasing the difference in the number of receiving beams, increasing the difference in the number of receiving beams repeating, decreasing The difference in the number of repetitions of received beams, the indication of increasing the number of received beams, the indication of decreasing the number of received beams, the indication of increasing the number of repetitions of received beams or the indication of decreasing the number of received beams;
  • the sending and receiving beam pair information includes but not limited to at least one of the following: the number of sending and receiving beam pairs, the number of repetitions of sending and receiving beam pairs, increasing the difference in the number of sending and receiving beam pairs, reducing the difference in the number of sending and receiving beam pairs, Increase the difference in the number of repetitions of sending and receiving beam pairs, reduce the difference in the number of repetitions of sending and receiving beam pairs, increase the indication of the number of sending and receiving beam pairs, decrease the indication of the number of sending and receiving beam pairs, increase the indication of the number of repetitions of sending and receiving beam pairs, and reduce the Indication of the number of received beam pairs.
  • step 102 may be implemented in the following manner:
  • the first device determines the transmission parameters according to the output result of the target model and the target mode;
  • the target mode includes any of the following modes: the first mode, the second mode, the third mode and the fourth mode;
  • the first mode is that the first device outputs the first feedback information, and the first feedback information includes the output result of the first model;
  • the second mode is that the first device outputs the first feedback information, and the first feedback information includes the first The output result of the model, and the first feedback information is used to adjust the mode of the second model
  • the third mode is that the first device outputs the first feedback information, the first feedback information does not include the output result of the first model, and the second The mode in which the device outputs the output result of the second model obtained based on the first feedback information
  • the fourth mode is that the first device outputs the first feedback information, the first feedback information does not include the output result of the first model, and the second device outputs the output result based on the first A mode in which the output result of the second model is obtained from the feedback information, and the output result of the second model is used to adjust the first model.
  • the first device may determine the transmission parameters according to the output result of the target model and the target mode; the target mode includes any of the following modes: the first mode, the second mode, the third mode, and the fourth mode; wherein, in different modes , the content of the first feedback information output by the first device is different, and the function of the first feedback information is also different.
  • the first feedback information includes the output result of the first model
  • the third mode and the fourth mode the first feedback information does not include the output result of the first model.
  • the first feedback information is used to adjust the second model.
  • the first feedback information can be used as the first The input of the second model; that is, in different target modes, the feedback information output by the first device is different, and the functions of the feedback information are also different, which can meet the needs of different scenarios.
  • the first device outputs first feedback information
  • the first feedback information includes the output information of the first model
  • the second device receives the first device feedback information
  • the first device and/or the second device may directly use the output result of the first model of the first device to determine transmission parameters, that is, perform subsequent information transmission based on relevant information included in the output result of the first model.
  • the second device passes the first feedback information output by the first device through the first model of the first device to obtain an output result of the second model.
  • the first device outputs first feedback information, the first feedback information does not include the output result of the first model, or the first feedback information only includes measurement information,
  • the second device passes the first feedback information output by the first device through the second model of the second device to obtain the output result of the second model, and the first device and/or the second device can directly use the output result of the second model Determine transmission parameters for subsequent information transmission; or the second device uses the output result of the second model, and the first device uses the output result of the first model to determine transmission parameters for subsequent information transmission.
  • the first device outputs first feedback information, the first feedback information does not include the output result of the first model, or the first feedback information only includes measurement information
  • the second device passes the first feedback information output by the first device through the second model of the second device, obtains the output result of the second model, and feeds back the output result of the second model to the first device, and the first device passes
  • the output result of the second model adjusts and calibrates the parameters of the first model, and/or verifies and calibrates whether the output result of the first model is the same or similar to the output result of the second model or the error is within a certain range.
  • the first device may feed back the error result or confirm whether the results are consistent, or when the error result exceeds the error range, feed back the error result or notify the second device that the error result exceeds the error range.
  • the target mode takes effect periodically or is triggered by behavior.
  • the transmission parameters are determined through different target modes, and the determination of the transmission parameters is more flexible, which meets the requirements of different scenarios.
  • the method when the target mode is the first mode or the second mode, the method further includes:
  • the first device sends first feedback information to the second device, where the first feedback information includes an output result of the first model and at least one of the following: input information and measurement information of the first model;
  • the first feedback information is used by the second device to determine transmission parameters.
  • the first device and the second device can exchange feedback information, the first device sends the first feedback information to the second device, the first feedback information includes the output result of the first model and at least one of the following items: the input of the first model Information, measurement information; the first feedback information is used by the second device to determine the transmission parameters, for example, to obtain the output result of the second model or to adjust the second model; that is, the first feedback information sent by the first device to the second device, Including not only the output results of the first model, but also the input information and/or measurement information of the first model, which can make the determined transmission parameters more accurate, and the transmission parameters determined by the first device and the second device have a high consistency. The consistency of the output results of the first model and the second model is high.
  • the measurement information in the first feedback information may be measurement information fed back by the second device, measurement information obtained by the first device, and the like.
  • the measurement information may be beam measurement information or measurement information related to determining transmission parameters, etc.
  • the accuracy of the transmission parameters can be improved through the interactive feedback information between the first device and the second device, the transmission parameters determined by the first device and the second device are highly consistent, and the first model and the second model The consistency of the output results is high.
  • the method also includes:
  • the first device receives the first error feedback information sent by the second device, and the first error feedback information is used to feed back at least one of the following items: whether the output result of the first model is consistent with the output result of the second model, the output result of the first model The first error result between the output result of the second model and the indication information that the first error result exceeds the first error range.
  • the first device receives the first error feedback information sent by the second device, and the first device may adjust and optimize the first model according to the first error feedback information.
  • the second model in this embodiment may be an adjusted second model based on the first feedback information.
  • the method when the target mode is the third mode or the fourth mode, the method further includes:
  • the first device receives second feedback information sent by the second device, and the second feedback information includes at least one of the following: output results of the second model, input information of the second model, and measurement information;
  • the second feedback information is used by the first device to determine transmission parameters.
  • the measurement information in the second feedback information may be measurement information fed back by the first device, measurement information acquired by the first device, and the like.
  • the measurement information may be beam measurement information, measurement information related to determining transmission parameters, and the like.
  • the second feedback information is used by the first device to determine transmission parameters, for example, to obtain an output result of the first model, to adjust the first model, and so on.
  • the accuracy of the transmission parameters can be improved through the interactive feedback information between the first device and the second device, the transmission parameters determined by the first device and the second device are highly consistent, and the first model and the second model The consistency of the output results is high.
  • the first device determines the transmission parameters according to the output result of the target model and the target mode, including:
  • the first device adjusts the first model according to the second feedback information to obtain the adjusted first model; and/or,
  • the first device determines whether the output result of the first model is consistent with the output result of the second model, or whether a second error result between the output result of the first model and the output result of the second model is within a second error range.
  • the first device adjusts the first model according to the second feedback information; and/or, determines the error result between the output result of the first model and the output result of the second model, and then adjusts the first model based on the error result. Adjust and optimize.
  • the first device sends second error feedback information to the second device; the second error feedback information is used to feed back at least one of the following items: whether the output result of the first model is consistent with the output result of the second model, whether the output result of the first model is consistent with the output result of the second model, The second error result between the output result of the first model and the output result of the second model or the indication information that the second error result exceeds the second error range.
  • the method when the target mode is the third mode or the fourth mode, the method further includes:
  • the first device sends first feedback information to the second device, and the first feedback information includes at least one of the following: input information and measurement information of the first model;
  • the first device receives the output result of the second model sent by the second device; the output result of the second model is obtained based on the first feedback information.
  • the first feedback information does not include the output result of the first model, and the rest are similar, and will not be repeated here.
  • the method when the target mode is the first mode, the method further includes:
  • the first device sends first feedback information to the second device, where the first feedback information includes an output result of the first model and at least one of the following: input information and measurement information of the first model;
  • the first device receives the output result of the second model sent by the second device
  • the first device determines transmission parameters according to the output result of the target model and the target mode, including:
  • the first device uses the output result of the first model to determine the transmission parameter, satisfying at least one of the following:
  • the output result of the first model is consistent with the output result of the second model
  • the output of the first model and/or the second model takes effect
  • the function of the first model and/or the second model takes effect
  • the transmission parameters determined by the first device and the second device through signaling interaction are consistent.
  • the output result of the second model received by the first device may be obtained based on the first feedback information
  • the method when the target mode is the third mode, the method further includes:
  • the first device sends first feedback information to the second device, where the first feedback information includes at least one of the following: input information and measurement information of the first model;
  • the first device receives the output result of the second model sent by the second device
  • the first device determines transmission parameters according to the output result of the target model and the target mode, including:
  • the first device uses the output result of the first model to determine the transmission parameter, satisfying at least one of the following:
  • the output result of the first model is consistent with the output result of the second model
  • the output of the first model and/or the second model takes effect
  • the function of the first model and/or the second model takes effect
  • the transmission parameters determined by the first device and the second device through signaling interaction are consistent.
  • the output result of the second model received by the first device may be obtained based on the first feedback information
  • the first device uses the output result of the first model to determine the transmission parameter
  • the second device uses the output result of the first model and/or the second model to determine the transmission parameter, because the first model and the second model have a correlation , so that the consistency of the determined transmission parameters is high.
  • the method further includes:
  • the first device receives the second indication information sent by the second device, where the second indication information is used to instruct the first device to adjust the model parameters of the first model and/or adjust the target mode.
  • the first device receives the second instruction information sent by the second device, and the second instruction information is used to instruct the first device to adjust the model of the first model parameters, and/or adjust the target mode used by the first device; that is, if the transmission parameters determined by the first device and the second device are inconsistent, the correlation between the first model and the second model may be small and/or the target used The modes are different, so it is necessary to adjust the parameters of the model and/or the used target mode, so that the consistency of the transmission parameters determined by the first device and the second device is relatively high.
  • the target mode may be determined or updated through signaling interaction or information interaction to include at least one of the above modes, for example, the first mode is used in signaling interaction, or the first mode and the first mode are used in signaling interaction.
  • the above schema definition may only include model functions, excluding configuration of feedback information.
  • the method also includes:
  • the first device receives second feedback information sent by the second device, and the second feedback information includes at least one of the following: output results of the second model, input information of the second model, and measurement information;
  • the first device determines the transmission parameters according to the output result of the target model and the target mode, including:
  • the feedback information of the interaction between the first device and the second device includes at least one of the following:
  • At least some output parameters in the output results of the first model and/or the second model are At least some output parameters in the output results of the first model and/or the second model.
  • the output parameters reported in the output results of the first model and/or the second model are pre-configured, configured or predefined by the protocol;
  • the input parameters reported in the first model and/or the second model are pre-configured, configured or predefined in the protocol;
  • a reference signal ID associated with the feedback information of the first device and the second device
  • the input parameter and/or output parameter is a parameter of at least one of the following periods, and the following at least one period includes: a recent period, a current period, or a period associated with feedback information.
  • the information included in the feedback information of the interaction between the first device and the second device, the period of the input parameter and/or the output parameter can be selected and determined according to the actual scene, so that the content of the feedback information is more flexible.
  • the feedback information includes complete input and or output parameters, the quantity of input and/or output parameters may not be fed back.
  • the above modes can be activated periodically or triggered by aperiodic behavior, such as a reference signal with a period of 10ms, but the target mode usage is a period of 20ms, or triggered when needed.
  • aperiodic behavior such as a reference signal with a period of 10ms, but the target mode usage is a period of 20ms, or triggered when needed.
  • the information included in the feedback information of the interaction between the first device and the second device, the period of the input parameter and/or the output parameter can be selected and determined according to the actual scene, so that the content of the feedback information is more flexible. Increased flexibility and practicality of the transfer method.
  • the feedback information of the interaction between the first device and the second device when the feedback information of the interaction between the first device and the second device includes the output of the first model or the second model, it also includes but is not limited to at least one of the following: input information of the feedback end model and feedback end measurement information.
  • the feedback information sent by the first device to the second device includes: an output result of the first model, and further includes at least one of the following items: input information of the first model and measurement information of the first device.
  • the feedback information sent by the second device to the first device includes: an output result of the second model, and further includes at least one of the following: input information of the second model and measurement information of the second device.
  • the feedback information of the interaction between the first device and the second device may include but not limited to at least one of the following: input information of the feedback end model and feedback end measurement information .
  • the order of parameters included in the feedback information of the interaction between the first device and the second device is determined according to pre-configuration, configuration or protocol pre-definition.
  • the order of parameters of different types and/or parameters of the same type in the feedback information exchanged between the first device and the second device may be determined according to pre-configuration, configuration or protocol pre-definition.
  • the order is to output parameters first and then input parameters;
  • the agreed rules can also be from large to small or from small to large based on beam quality.
  • the first device is a terminal, configured with a first model
  • the second device is a network side device configured with a second model
  • the network-side device and/or the terminal obtains the output result of the target model, and determines the transmission parameters.
  • Step 1 The network side device configures the first model and the second model to the first device and/or the second device;
  • the terminal may perform pruning on the model, etc.
  • model parameters of the terminal and the network side device may be inconsistent.
  • Step 2 The network side device sends beams, and the terminal obtains multiple beam information after measurement;
  • the number of beams included in the output of the first model of the terminal may be different from the number of beams included in the output of the second model, and the terminal may feed back to the network-side device The ability to transmit the minimum number of beams.
  • the terminal may request feedback of parameters related to the number of beams;
  • the method also includes:
  • Step 3a The terminal inputs the historical beam measurement result and the current beam measurement result into the first model, or inputs the current beam measurement result into the first model, and obtains the output result of the first model; optionally, the output result of the first model includes at least one Beam ID and/or beam quality information;
  • Step 4a The terminal feeds back the output result and/or measurement information of the first model to the network-side device. After the network-side device receives the fed-back information, the network-side device can adjust the second model so that the first model of the terminal and the network-side The output of the second model of the device is consistent;
  • the output result of the second model of the network-side device is consistent with the output result of the first model of the terminal, and/or the deviation of the output result is within a target range, and the second model of the network-side device may not be adjusted.
  • the method further includes:
  • Step 3b The terminal outputs feedback information, wherein the feedback information may include measurement information, but does not include the output result of the first model.
  • the network side device After receiving the feedback information, the network side device obtains the output result of the second model based on the feedback information;
  • optional Ground, output result can comprise at least one beam ID and/or beam quality information;
  • Step 4b The network-side device sends the output result of the second model, or information about beam scheduling to the terminal. After receiving the output result of the second model, the terminal can adjust the first model parameters of the terminal according to the output result of the second model, so that The output result of the first model of the terminal is consistent with that of the second model of the network side device.
  • the method also includes:
  • Step 3c The terminal inputs the historical beam measurement result and the current beam measurement result into the first model, or inputs the current beam measurement result into the first model, and obtains the output result of the first model; optionally, the output result of the first model includes at least one Beam ID and/or beam quality information;
  • Step 4c The terminal feeds back the output result of the first model to the network-side device. After the network-side device receives the feedback information, if the output result of the second model of the network-side device is inconsistent with the received output result of the first model, the network-side device sending an output result of the second model to the terminal, and/or instructing the terminal to adjust parameters of the first model;
  • Step 5 The terminal adjusts the parameters of the first model according to the output result of the second model sent by the network side device.
  • Fig. 3 is a schematic flowchart of an embodiment of a transmission method provided by an embodiment of the present invention. As shown in Figure 3, the method provided in this embodiment includes:
  • Step 201 the second device acquires an output result of the target model, and the target model includes the first model of the first device and/or the second model of the second device; the first model has a correlation with the second model;
  • Step 202 the second device determines transmission parameters according to the output result of the target model.
  • the first model is correlated with the second model, and at least one of the following is satisfied:
  • the first model is the same as the second model
  • the first model is obtained by performing first target processing based on the first model and/or the second model.
  • the first target processing based on the first model and/or the second model includes at least one of the following:
  • the first model being a student model or a sub-model of the second model
  • the second target processing includes at least one of the following: pruning, pruning and adding;
  • the decomposition process includes at least one of the following: tensor decomposition and low-rank decomposition.
  • the second model of the second device is acquired in at least one of the following ways:
  • the second device is obtained from the first device, and the second model is obtained by the first device from the third device, or generated by the first device;
  • the first target processing based on the first model and/or the second model includes at least one of the following:
  • a first object processing is performed by the first device based on the first model and/or the second model.
  • the method also includes:
  • the second device receives the capability information of the first model sent by the first device; and/or,
  • the second device sends a response message to the first device, the response message is sent based on the request message sent by the first device, and the response message is used to carry first information related to the transmission parameter; and / or,
  • the second device receives first indication information sent by the first device, where the first indication information is used to indicate second information related to the transmission parameter.
  • the first information and/or second information includes at least one of the following:
  • the sending beam information includes at least one of the following: the number of sending beams, the number of repetitions of sending beams, the difference in the number of sending beams, the difference in the number of sending beams, the difference in the number of sending beams, and the reduction in the number of sending beams.
  • the difference of the number of beam repetitions increases the number of transmitted beams, decreases the number of transmitted beams, increases the number of transmitted beam repetitions, decreases the number of transmitted beams, the minimum number of transmitted beams to reach the target value, and the minimum number of transmitted beams to reach the target accuracy value , the minimum number of beams sent to reach the target value or the minimum number of beams sent to reach the target accuracy value;
  • the receiving beam information includes at least one of the following: the number of receiving beams, the number of repetitions of receiving beams, the difference in the number of receiving beams, the difference in the number of receiving beams, the difference in the number of repetitions of receiving beams, and the difference in the number of repetitions of receiving beams. value, increase the indication of the number of received beams, decrease the indication of the number of received beams, increase the indication of the number of repetitions of received beams or decrease the indication of the number of received beams;
  • the sending and receiving beam pair information includes at least one of the following: the number of sending and receiving beam pairs, the number of repetitions of sending and receiving beam pairs, increasing the difference in the number of sending and receiving beam pairs, reducing the difference in the number of sending and receiving beam pairs, and increasing the number of sending and receiving beam pairs Repeat times difference, reduce sending and receiving beam pair repetition times difference, increase sending and receiving beam pair number indication, reduce sending and receiving beam pair number indication, increase sending and receiving beam pair repetition number indication, reduce sending and receiving beam pair number indication .
  • the second device determines transmission parameters according to an output result of the target model, including:
  • the second device determines transmission parameters according to an output result of the target model and a target mode;
  • the target mode includes any of the following modes: a first mode, a second mode, a third mode, and a fourth mode;
  • the first mode is that the first device outputs first feedback information, and the first feedback information includes the mode of the output result of the first model;
  • the second mode is that the first device outputs First feedback information, the first feedback information includes the output result of the first model, and the first feedback information is used to adjust the mode of the second model, and the third mode is the first mode a device outputs first feedback information, the first feedback information does not include the output result of the first model, and the second device outputs a mode of the output result of the second model obtained based on the first feedback information
  • the first device outputs first feedback information, the first feedback information does not include the output result of the first model, and the second device outputs the first feedback information obtained based on the first feedback information.
  • the output results of the two models, and the output results of the second model are used to adjust the first model.
  • the method further includes:
  • the second device receives first feedback information sent by the first device, where the first feedback information includes an output result of the first model and at least one of the following: input information and measurement information of the first model ;
  • the first feedback information is used by the second device to determine transmission parameters.
  • the method also includes:
  • the second device sends first error feedback information to the first device, and the first error feedback information is used to feed back at least one of the following: an output result of the first model and an output result of the second model Whether they are consistent, a first error result between the output result of the first model and the output result of the second model, or indication information that the first error result exceeds a first error range.
  • the first device determines transmission parameters according to an output result of the target model and a target mode, including:
  • the second device adjusts the second model according to the first feedback information to obtain an adjusted second model; and/or,
  • the second device determines whether the output of the first model is consistent with the output of the second model, or a first error between the output of the first model and the output of the second model Whether the result is within the first margin of error.
  • the method further includes:
  • the second device sends second feedback information to the first device, where the second feedback information includes at least one of the following: output results of the second model, input information of the second model, and measurement information;
  • the second feedback information is used by the first device to determine transmission parameters.
  • the method also includes:
  • the second device receives second error feedback information sent by the first device; the second error feedback information is used to feed back at least one of the following: the output result of the first model and the output of the second model Whether the results are consistent, a first error result between the output result of the first model and the output result of the second model, or indication information that the first error result exceeds a first error range.
  • the method further includes:
  • the second device receives the first feedback information sent by the first device, and the first feedback information includes at least one of the following: input information and measurement information of the first model;
  • the second device sends the output result of the second model to the first device; the output result of the second model is obtained based on the first feedback information.
  • the method further includes:
  • the second device receives the first feedback information sent by the first device, where the first feedback information includes an output result of the first model and at least one of the following: input information of the first model, measurement information;
  • the second device sends an output of the second model to the first device
  • the second device determines transmission parameters according to the output result of the target model and the target mode, including:
  • the second device uses the output result of the first model or the output result of the second model to determine the transmission parameter, satisfying at least one of the following:
  • the output result of the first model is consistent with the output result of the second model
  • the output of the first model and/or the second model takes effect
  • the transmission parameters determined by the first device and the second device through signaling interaction are consistent.
  • the method further includes:
  • the second device receives the first feedback information sent by the first device, and the first feedback information includes at least one of the following: input information and measurement information of the first model;
  • the second device sends an output of the second model to the first device
  • the second device determines transmission parameters according to the output result of the target model and the target mode, including:
  • the second device uses the output result of the first model or the output result of the second model to determine the transmission parameter, satisfying at least one of the following:
  • the output result of the first model is consistent with the output result of the second model
  • the output of the first model and/or the second model takes effect
  • the transmission parameters determined by the first device and the second device through signaling interaction are consistent.
  • the method further includes:
  • the second device sends second indication information to the first device, where the second indication information is used to instruct the first device to adjust a model parameter of the first model and/or adjust the target mode.
  • the method also includes:
  • the second device sends second feedback information to the first device, where the second feedback information includes at least one of the following: output results of the second model, input information of the second model, and measurement information;
  • the second feedback information is used by the first device to adjust the first model.
  • the target mode takes effect periodically or is triggered by behavior.
  • the transmission method provided in the embodiment of the present application may be executed by a transmission device.
  • the transmission device provided in the embodiment of the present application is described by taking the transmission device executing the transmission method as an example.
  • Fig. 4 is one of the structural schematic diagrams of the transmission device provided by the present application. As shown in Figure 4, the transmission device provided in this embodiment includes:
  • An acquisition module 410 configured to acquire an output result of a target model, where the target model includes a first model of the transmission device and/or a second model of the second device; the first model has a correlation with the second model;
  • the processing module 420 is configured to determine transmission parameters according to the output result of the target model.
  • the first model is correlated with the second model, and at least one of the following is satisfied:
  • the first model is identical to the second model
  • the first model is obtained by performing the first target processing based on the first model and/or the second model.
  • performing the first target processing based on the first model and/or the second model includes at least one of the following:
  • the first model is a student model or sub-model of the second model
  • the second target processing includes at least one of the following: pruning, deletion and increase;
  • the decomposition process includes at least one of: tensor decomposition and low-rank decomposition.
  • the first model is obtained through at least one of the following methods:
  • the first model is obtained from the second device, and the first model is obtained by the second device from the third device, or generated by the second device;
  • the first target processing is performed based on the first model and/or the second model, including at least one of the following:
  • the first object processing is carried out by means of the transmission device based on the first model and/or the second model.
  • a sending module configured to send the capability information of the first model to the second device; and/or,
  • the first information and/or the second information includes at least one of the following:
  • the sending beam information includes at least one of the following: the number of sending beams, the number of sending beam repetitions, increasing the difference in the number of sending beams, reducing the difference in the number of sending beams, increasing the difference in the number of sending beam repetitions, and reducing the sending beam repetition
  • the number of times difference increases the indication of the number of transmitted beams, decreases the indication of the number of transmitted beams, increases the indication of the number of transmitted beam repetitions, decreases the indication of the number of transmitted beams, the minimum number of transmitted beams to reach the target value, the minimum number of transmitted beams to reach the target accuracy value, and The minimum number of beams sent for the target value or the minimum number of beams sent to reach the target accuracy value;
  • the receiving beam information includes at least one of the following: the number of receiving beams, the number of repetitions of receiving beams, the difference in the number of receiving beams, the difference in the number of receiving beams, the difference in the number of repetitions of receiving beams, the difference in the number of repetitions of receiving beams, Increase the indication of the number of received beams, decrease the indication of the number of received beams, increase the indication of the number of repetitions of received beams, or decrease the indication of the number of received beams;
  • the sending and receiving beam pair information includes at least one of the following: the number of sending and receiving beam pairs, the number of sending and receiving beam pairs repetitions, the increase in the difference in the number of sending and receiving beam pairs, the reduction in the difference in the number of sending and receiving beam pairs, and the increase in the number of sending and receiving beam pair repetitions Difference, reduce the difference in the number of repetitions of sending and receiving beam pairs, increase the indication of the number of sending and receiving beam pairs, decrease the indication of the number of sending and receiving beam pairs, increase the indication of the number of repetitions of sending and receiving beam pairs, and decrease the indication of the number of sending and receiving beam pairs.
  • the processing module 420 is specifically configured to determine the transmission parameters according to the output result of the target model and the target mode;
  • the target mode includes any of the following modes: the first mode, the second mode, the third mode and the fourth mode;
  • the first mode is that the transmission device outputs the first feedback information, and the first feedback information includes the output result of the first model
  • the second mode is that the transmission device outputs the first feedback information, and the first feedback information includes the output result of the first model.
  • Output results, and the first feedback information is used to adjust the mode of the second model
  • the third mode is that the transmission device outputs the first feedback information, the first feedback information does not include the output result of the first model, and the second device outputs based on The mode of the output result of the second model obtained from the first feedback information
  • the fourth mode is that the transmission device outputs the first feedback information, the first feedback information does not include the output result of the first model, and the output of the second device is obtained based on the first feedback information
  • the output of the second model of , and the output of the second model is used to adjust the model of the first model.
  • the sending module is configured to send first feedback information to the second device when the target mode is the first mode or the second mode, where the first feedback information includes an output result of the first model and at least one of the following: Input information and measurement information of the first model;
  • the first feedback information is used by the second device to determine transmission parameters.
  • the obtaining module 410 is specifically configured to receive first error feedback information sent by the second device, and the first error feedback information is used to feed back at least one of the following: whether the output result of the first model and the output result of the second model Consistency, a first error result between the output result of the first model and the output result of the second model, or indication information that the first error result exceeds the first error range.
  • the obtaining module 410 is specifically configured to receive second feedback information sent by the second device, where the second feedback information includes at least one of the following: output results of the second model, input information of the second model, and measurement information;
  • the second feedback information is used to determine transmission parameters.
  • the processing module 420 is specifically configured to adjust the first model according to the second feedback information to obtain the adjusted first model; and/or,
  • the sending module is configured to send second error feedback information to the second device; the second error feedback information is used to feed back at least one of the following items: whether the output result of the first model is consistent with the output result of the second model, the first The first error result between the output result of the model and the output result of the second model or the indication information that the first error result exceeds the first error range.
  • the sending module is configured to send first feedback information to the second device when the target mode is the third mode or the fourth mode, where the first feedback information includes at least one of the following: input information of the first model, measurement information;
  • An output result of the second model sent by the second device is received; the output result of the second model is obtained based on the first feedback information.
  • the sending module is configured to send first feedback information to the second device when the target mode is the first mode, where the first feedback information includes an output result of the first model and at least one of the following: input information, measurement information;
  • the obtaining module 410 is configured to receive the output result of the second model sent by the second device;
  • the processing module 420 is specifically used for:
  • the output result of the first model is consistent with the output result of the second model
  • the output of the first model and/or the second model takes effect
  • the function of the first model and/or the second model takes effect
  • the transmission parameters determined by the first device and the second device through signaling interaction are consistent.
  • the sending module is also used for:
  • first feedback information includes at least one of the following: input information and measurement information of the first model;
  • the processing module 420 is specifically used for:
  • the output result of the first model is consistent with the output result of the second model
  • the output of the first model and/or the second model takes effect
  • the function of the first model and/or the second model takes effect
  • the transmission parameters determined by the first device and the second device through signaling interaction are consistent.
  • the obtaining module 410 is specifically configured to further include: when the transmission parameters determined by the transmission device and the second device are inconsistent:
  • the second instruction information sent by the second device is received, where the second instruction information is used to instruct the transmission device to adjust the model parameter and/or adjust the target mode of the first model.
  • the obtaining module 410 is specifically configured to receive second feedback information sent by the second device, where the second feedback information includes at least one of the following: output results of the second model, input information of the second model, and measurement information.
  • the target mode takes effect periodically or is triggered by behavior.
  • the feedback information of the interaction between the transmission device and the second device includes at least one of the following:
  • At least some output parameters in the output results of the first model and/or the second model are At least some output parameters in the output results of the first model and/or the second model.
  • the output parameters reported in the output results of the first model and/or the second model are pre-configured, configured or predefined by the protocol;
  • the input parameters reported in the first model and/or the second model are pre-configured, configured or predefined in the protocol;
  • the input parameter and/or output parameter is a parameter of at least one of the following periods, and the following at least one period includes: a recent period, a current period, or a period associated with a feedback report.
  • the feedback information of the interaction between the transmission device and the second device includes the output result of the first model or the second model, it also includes at least one of the following: input information of the feedback end model and feedback end measurement information.
  • the order of the parameters included in the feedback information of the interaction between the transmission apparatus and the second device is determined according to pre-configuration, configuration or protocol pre-definition.
  • the output result includes at least one of the following:
  • Space-related information is Space-related information; time-related information; beam quality information.
  • the transmission device is any of the following: a terminal, a network side device, or an auxiliary network central unit
  • the second device is any of the following: a terminal, a network side device, or an auxiliary network central unit.
  • the device of this embodiment can be used to execute the method of any one of the aforementioned first device method embodiments, and its specific implementation process and technical effect are similar to those in the first device method embodiment.
  • the implementation of the first device method please refer to the implementation of the first device method The detailed introduction in the example will not be repeated here.
  • FIG. 5 is the second structural schematic diagram of the transmission device provided by the present application. As shown in Figure 5, the transmission device provided in this embodiment includes:
  • An acquisition module 510 configured to acquire an output result of a target model, where the target model includes a first model of the first device and/or a second model of the transmission device; the first model has a correlation with the second model;
  • the processing module 520 is configured to determine transmission parameters according to the output result of the target model.
  • the first model is correlated with the second model, and at least one of the following is satisfied:
  • the first model is identical to the second model
  • the first model is obtained by performing the first target processing based on the first model and/or the second model.
  • performing the first target processing based on the first model and/or the second model includes at least one of the following:
  • the first model is a student model or sub-model of the second model
  • the second target processing includes at least one of the following: pruning, deletion and increase;
  • the decomposition process includes at least one of: tensor decomposition and low-rank decomposition.
  • the second model is obtained through at least one of the following methods:
  • the second model is obtained from the first device, and the second model is obtained by the first device from the third device, or generated by the first device;
  • the acquisition module 510 specifically configured to perform the first target processing based on the first model and/or the second model, includes at least one of the following:
  • a first target treatment is performed by the first device based on the first model and/or the second model.
  • the acquiring module 510 is specifically configured to receive capability information of the first model sent by the first device; and/or,
  • a sending module configured to send a response message to the first device, where the response message is sent based on the request message sent by the first device, and the response message is used to carry first information related to transmission parameters; and/or,
  • the obtaining module 510 is specifically configured to receive first indication information sent by the first device, where the first indication information is used to indicate second information related to the transmission parameter.
  • the first information and/or the second information includes at least one of the following:
  • the sending beam information includes at least one of the following: the number of sending beams, the number of sending beam repetitions, increasing the difference in the number of sending beams, reducing the difference in the number of sending beams, increasing the difference in the number of sending beam repetitions, and reducing the sending beam repetition
  • the number of times difference increases the indication of the number of transmitted beams, decreases the indication of the number of transmitted beams, increases the indication of the number of transmitted beam repetitions, decreases the indication of the number of transmitted beams, the minimum number of transmitted beams to reach the target value, the minimum number of transmitted beams to reach the target accuracy value, and The minimum number of beams sent for the target value or the minimum number of beams sent to reach the target accuracy value;
  • the receiving beam information includes at least one of the following: the number of receiving beams, the number of repetitions of receiving beams, the difference in the number of receiving beams, the difference in the number of receiving beams, the difference in the number of repetitions of receiving beams, the difference in the number of repetitions of receiving beams, Increase the indication of the number of received beams, decrease the indication of the number of received beams, increase the indication of the number of repetitions of received beams, or decrease the indication of the number of received beams;
  • the sending and receiving beam pair information includes at least one of the following: the number of sending and receiving beam pairs, the number of sending and receiving beam pairs repetitions, the increase in the difference in the number of sending and receiving beam pairs, the reduction in the difference in the number of sending and receiving beam pairs, and the increase in the number of sending and receiving beam pair repetitions Difference, reduce the difference in the number of repetitions of sending and receiving beam pairs, increase the indication of the number of sending and receiving beam pairs, decrease the indication of the number of sending and receiving beam pairs, increase the indication of the number of repetitions of sending and receiving beam pairs, and decrease the indication of the number of sending and receiving beam pairs.
  • processing module 520 is specifically configured to:
  • the transmission parameters are determined according to the output result of the target model and the target mode;
  • the target mode includes any of the following modes: a first mode, a second mode, a third mode and a fourth mode;
  • the first mode is that the first device outputs the first feedback information, and the first feedback information includes the output result of the first model;
  • the second mode is that the first device outputs the first feedback information, and the first feedback information includes the first The output result of the model, and the mode in which the first feedback information is used to adjust the second model,
  • the third mode is that the first device outputs the first feedback information, the first feedback information does not include the output result of the first model, and the transmission means A mode for outputting the output result of the second model obtained based on the first feedback information
  • the fourth mode is for the first device to output the first feedback information, the first feedback information does not include the output result of the first model, and the output of the transmission device is based on the first feedback
  • the output result of the second model is obtained from the information, and the output result of the second model is used to adjust the mode of the first model.
  • the obtaining module 510 is specifically configured to:
  • the first feedback information is used by the transmission device to determine transmission parameters.
  • the sending module is configured to send first error feedback information to the first device, and the first error feedback information is used to feed back at least one of the following items: whether the output result of the first model is consistent with the output result of the second model, the first The first error result between the output result of the model and the output result of the second model or the indication information that the first error result exceeds the first error range.
  • processing module 520 is specifically configured to:
  • the sending module is also used for:
  • the second feedback information includes at least one of the following: output results of the second model, input information of the second model, and measurement information;
  • the second feedback information is used by the first device to determine transmission parameters.
  • the obtaining module 510 is specifically configured to receive second error feedback information sent by the first device; the second error feedback information is used to feed back at least one of the following: whether the output result of the first model and the output result of the second model Consistency, a first error result between the output result of the first model and the output result of the second model, or indication information that the first error result exceeds the first error range.
  • the obtaining module 510 is specifically used for:
  • the sending module is configured to send the output result of the second model to the first device; the output result of the second model is obtained based on the first feedback information.
  • the obtaining module 510 is specifically used to:
  • a sending module configured to send the output result of the second model to the first device
  • the processing module 520 is specifically used for:
  • the output result of the first model is consistent with the output result of the second model
  • the output of the first model and/or the second model takes effect
  • the function of the first model and/or the second model takes effect
  • the transmission parameters determined by the first device and the transmission apparatus through signaling interaction are consistent.
  • the acquiring module 510 is specifically used for:
  • a sending module configured to send the output result of the second model to the first device
  • the processing module 520 is specifically used for:
  • the output result of the first model is consistent with the output result of the second model
  • the output of the first model and/or the second model takes effect
  • the function of the first model and/or the second model takes effect
  • the transmission parameters determined by the first device and the transmission apparatus through signaling interaction are consistent.
  • the sending module is further configured to:
  • the sending module is further configured to send second feedback information to the first device, where the second feedback information includes at least one of the following: output results of the second model, input information of the second model, measurement information; second feedback information Adjust the first model for the first device.
  • the target mode takes effect periodically or is triggered by behavior.
  • the device of this embodiment can be used to execute the method of any one of the aforementioned second device method embodiments, and its specific implementation process and technical effect are similar to those in the second device method embodiment.
  • the second device method please refer to the implementation of the second device method The detailed introduction in the example will not be repeated here.
  • the transmission device in this embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or a component in the electronic device, such as an integrated circuit or a chip.
  • the electronic device may be a terminal, or other devices other than the terminal.
  • the terminal may include, but not limited to, the types of terminal 11 listed above, and other devices may be servers, Network Attached Storage (NAS), etc., which are not specifically limited in this embodiment of the present application.
  • NAS Network Attached Storage
  • the transmission device provided in the embodiment of the present application can realize various processes realized by the method embodiments in FIG. 1 to FIG. 8 , and achieve the same technical effect. To avoid repetition, details are not repeated here.
  • this embodiment of the present application also provides a communication device 600, including a processor 601 and a memory 602, and the memory 602 stores programs or instructions that can run on the processor 601, such as
  • the communication device 600 is the first device, when the program or instruction is executed by the processor 601, each step of the above transmission method embodiment can be implemented, and the same technical effect can be achieved.
  • the communication device 600 is the second device, when the program or instruction is executed by the processor 601, each step of the above transmission method embodiment can be achieved, and the same technical effect can be achieved. To avoid repetition, details are not repeated here.
  • the embodiment of the present application also provides a first device, including a processor and a communication interface, the processor is used to obtain the output result of the target model, and the target model includes the first model of the terminal and/or the second model of the second device; the first The model has a correlation with the second model, and the communication interface is used to determine the transmission parameters according to the output result of the target model.
  • This terminal embodiment corresponds to the above-mentioned first device and/or second device-side method embodiments, and the various implementation processes and implementation methods of the above-mentioned method embodiments can be applied to this first device embodiment, and can achieve the same technology Effect.
  • FIG. 7 is a schematic diagram of a hardware structure of a terminal implementing an embodiment of the present application.
  • the terminal 1000 includes but not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010, etc. at least some of the components.
  • the terminal 1000 can also include a power supply (such as a battery) for supplying power to various components, and the power supply can be logically connected to the processor 1010 through the power management system, so as to manage charging, discharging, and power consumption through the power management system. Management and other functions.
  • a power supply such as a battery
  • the terminal structure shown in FIG. 7 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown in the figure, or combine some components, or arrange different components, which will not be repeated here.
  • the input unit 1004 may include a graphics processing unit (Graphics Processing Unit, GPU) 10041 and a microphone 10042, and the graphics processor 10041 can be used by the image capture device (such as the image data of the still picture or video obtained by the camera) for processing.
  • the display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 1007 includes at least one of a touch panel 10071 and other input devices 10072 .
  • the touch panel 10071 is also called a touch screen.
  • the touch panel 10071 may include two parts, a touch detection device and a touch controller.
  • Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, and joysticks, which will not be repeated here.
  • the radio frequency unit 1001 after the radio frequency unit 1001 obtains the output result of the target model, it can transmit it to the processor 1010 for processing; in addition, the radio frequency unit 1001 can send the uplink data to the network side device.
  • the radio frequency unit 1001 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.
  • the memory 1009 can be used to store software programs or instructions as well as various data.
  • the memory 1009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage program or instruction area may store an operating system, an application program or instructions required by at least one function (such as a voice playback function, image playback function, etc.), etc.
  • memory 1009 may include volatile memory or nonvolatile memory, or, memory 1009 may include both volatile and nonvolatile memory.
  • Non-volatile memory can also include non-volatile memory, wherein, the non-volatile memory can be read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), programmable Erasable programmable read-only memory (Erasable PROM, EPROM), electrically erasable programmable read-only memory (Electrically EPROM, EEPROM) or flash memory.
  • ROM Read-Only Memory
  • PROM programmable read-only memory
  • Erasable PROM Erasable PROM
  • EPROM programmable Erasable programmable read-only memory
  • Electrically erasable programmable read-only memory Electrically erasable programmable read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • Volatile memory can be random access memory (Random Access Memory, RAM), static random access memory (Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), synchronous dynamic random access memory (Synchronous DRAM) , SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDRSDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous connection dynamic random access memory (Synch link DRAM, SLDRAM) and Direct Memory Bus Random Access Memory (Direct Rambus RAM, DRRAM).
  • RAM Random Access Memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • synchronous dynamic random access memory Synchronous DRAM
  • SDRAM double data rate synchronous dynamic random access memory
  • Double Data Rate SDRAM, DDRSDRAM double data rate synchronous dynamic random access memory
  • Enhanced SDRAM, ESDRAM enhanced synchronous dynamic random access memory
  • Synch link DRAM, SLDRAM synchronous connection dynamic random access memory
  • the processor 1010 may include one or more processing units; optionally, the processor 1010 may integrate an application processor and a modem processor, where the application processor mainly processes the operating system, user interface, application programs or instructions, etc.
  • modem processors mainly process wireless communication signals, such as baseband processors. It can be understood that the foregoing modem processor may not be integrated into the processor 1010 .
  • the radio frequency unit 1001 is configured to obtain an output result of a target model, where the target model includes a first model of the first device and/or a second model of the second device; the first model has a correlation with the second model;
  • Processor 1010 configured to determine transmission parameters according to output results of the target model.
  • the first model is correlated with the second model, and at least one of the following is satisfied:
  • the first model is identical to the second model
  • the first model is obtained by performing the first target processing based on the first model and/or the second model.
  • the processor 1010 performing the first target processing based on the first model and/or the second model includes at least one of the following:
  • the first model is a student model or sub-model of the second model
  • the second target processing includes at least one of the following: pruning, deletion and increase;
  • the decomposition process includes at least one of: tensor decomposition and low-rank decomposition.
  • the first model is obtained through at least one of the following methods:
  • the first model is obtained from the second device, and the first model is obtained by the second device from the third device, or generated by the second device;
  • the processor 1010 performs the first target processing based on the first model and/or the second model, including at least one of the following:
  • the first target processing is performed by the terminal based on the first model and/or the second model.
  • the radio frequency unit 1001 is specifically configured to send capability information of the first model to the second device; and/or,
  • the first information and/or the second information includes at least one of the following:
  • the sending beam information includes at least one of the following: the number of sending beams, the number of sending beam repetitions, increasing the difference in the number of sending beams, reducing the difference in the number of sending beams, increasing the difference in the number of sending beam repetitions, and reducing the sending beam repetition
  • the number of times difference increases the indication of the number of transmitted beams, decreases the indication of the number of transmitted beams, increases the indication of the number of transmitted beam repetitions, decreases the indication of the number of transmitted beams, the minimum number of transmitted beams to reach the target value, the minimum number of transmitted beams to reach the target accuracy value, and The minimum number of beams sent for the target value or the minimum number of beams sent to reach the target accuracy value;
  • the receiving beam information includes at least one of the following: the number of receiving beams, the number of repetitions of receiving beams, the difference in the number of receiving beams, the difference in the number of receiving beams, the difference in the number of repetitions of receiving beams, the difference in the number of repetitions of receiving beams, Increase the indication of the number of received beams, decrease the indication of the number of received beams, increase the indication of the number of repetitions of received beams, or decrease the indication of the number of received beams;
  • the sending and receiving beam pair information includes at least one of the following: the number of sending and receiving beam pairs, the number of sending and receiving beam pairs repetitions, the increase in the difference in the number of sending and receiving beam pairs, the reduction in the difference in the number of sending and receiving beam pairs, and the increase in the number of sending and receiving beam pair repetitions Difference, reduce the difference in the number of repetitions of sending and receiving beam pairs, increase the indication of the number of sending and receiving beam pairs, decrease the indication of the number of sending and receiving beam pairs, increase the indication of the number of repetitions of sending and receiving beam pairs, and decrease the indication of the number of sending and receiving beam pairs.
  • processor 1010 is specifically configured to:
  • the transmission parameters are determined according to the output result of the target model and the target mode;
  • the target mode includes any of the following modes: a first mode, a second mode, a third mode and a fourth mode;
  • the first mode is that the terminal outputs the first feedback information, and the first feedback information includes the output result of the first model
  • the second mode is that the terminal outputs the first feedback information, and the first feedback information includes the output result of the first model , and the first feedback information is used to adjust the mode of the second model
  • the third mode is that the terminal outputs the first feedback information, the first feedback information does not include the output result of the first model, and the second device outputs based on the first feedback
  • the fourth mode is that the terminal outputs the first feedback information, the first feedback information does not include the output result of the first model, and the second device outputs the second model obtained based on the first feedback information
  • the output of , and the output of the second model is used to adjust the model of the first model.
  • the radio frequency unit 1001 is specifically used for:
  • the first feedback information includes the output result of the first model and at least one of the following: input information of the first model, measurement information;
  • the first feedback information is used by the second device to determine transmission parameters.
  • the radio frequency unit 1001 is specifically used for:
  • the first error feedback information is used to feed back at least one of the following: whether the output result of the first model is consistent with the output result of the second model, whether the output result of the first model is consistent with the output result of the second model
  • the radio frequency unit 1001 is specifically used for:
  • Receive second feedback information sent by the second device where the second feedback information includes at least one of the following: output results of the second model, input information of the second model, and measurement information;
  • the second feedback information is used to determine transmission parameters.
  • processor 1010 is specifically configured to:
  • the radio frequency unit 1001 is specifically used for:
  • the second error feedback information is used to feed back at least one of the following: whether the output result of the first model is consistent with the output result of the second model, whether the output result of the first model is consistent with the output result of the second model The first error result between the output results or the indication information that the first error result exceeds the first error range.
  • the radio frequency unit 1001 is specifically used for:
  • the target mode is the third mode or the fourth mode
  • sending first feedback information to the second device where the first feedback information includes at least one of the following: input information and measurement information of the first model;
  • An output result of the second model sent by the second device is received; the output result of the second model is obtained based on the first feedback information.
  • the radio frequency unit 1001 is specifically used for:
  • the target mode is the first mode
  • sending first feedback information to the second device the first feedback information includes an output result of the first model and at least one of the following: input information and measurement information of the first model;
  • Processor 1010 specifically for:
  • the output result of the first model is consistent with the output result of the second model
  • the output of the first model and/or the second model takes effect
  • the function of the first model and/or the second model takes effect
  • the radio frequency unit 1001 is specifically configured to:
  • first feedback information includes at least one of the following: input information and measurement information of the first model;
  • Processor 1010 specifically for:
  • the output result of the first model is consistent with the output result of the second model
  • the output of the first model and/or the second model takes effect
  • the function of the first model and/or the second model takes effect
  • the transmission parameters determined by the terminal and the second device through signaling interaction are consistent.
  • the radio frequency unit 1001 is specifically configured to:
  • the second indication information sent by the second device is received, where the second indication information is used to instruct the terminal to adjust the model parameters of the first model and/or adjust the target mode.
  • the radio frequency unit 1001 is specifically used for:
  • Receive second feedback information sent by the second device where the second feedback information includes at least one of the following: output results of the second model, input information of the second model, and measurement information.
  • the target mode takes effect periodically or is triggered by behavior.
  • the feedback information for interaction between the terminal and the second device includes at least one of the following:
  • At least some output parameters in the output results of the first model and/or the second model are At least some output parameters in the output results of the first model and/or the second model.
  • the output parameters reported in the output results of the first model and/or the second model are pre-configured, configured or predefined by the protocol;
  • the input parameters reported in the first model and/or the second model are pre-configured, configured or predefined in the protocol;
  • Beam related information corresponding to the reference signal associated with the feedback information of the terminal and the second device
  • the input parameter and/or output parameter is a parameter of at least one of the following periods, and the following at least one period includes: a recent period, a current period, or a period associated with a feedback report.
  • the feedback information for interaction between the terminal and the second device includes an output result of the first model or the second model, it further includes at least one of the following: input information of the feedback end model and feedback end measurement information.
  • the order of parameters included in the feedback information for interaction between the terminal and the second device is determined according to pre-configuration, configuration, or protocol pre-definition.
  • the output result includes at least one of the following:
  • Spatial related information Time related information; Beam quality information; Beam ID; Angle information.
  • the first device may also be a network side device.
  • the embodiment of the present application also provides a network side device.
  • the network side device 700 includes: an antenna 71 , a radio frequency device 72 , a baseband device 73 , a processor 75 and a memory 75 .
  • the antenna 71 is connected to a radio frequency device 72 .
  • the radio frequency device 72 receives information through the antenna 71, and sends the received information to the baseband device 73 for processing.
  • the baseband device 73 processes the information to be sent and sends it to the radio frequency device 72
  • the radio frequency device 72 processes the received information and sends it out through the antenna 71 .
  • the above frequency band processing device may be located in the baseband device 73 , and the method performed by the network side device in the above embodiment may be implemented in the baseband device 73 , and the baseband device 73 includes a baseband processor 75 and a memory 75 .
  • the baseband device 73 can include at least one baseband board, for example, a plurality of chips are arranged on the baseband board, as shown in FIG.
  • the program executes the network device operations shown in the above method embodiments.
  • the network side equipment of the baseband device 73 may also include a network interface 76 for exchanging information with the radio frequency device 72, and the interface is, for example, a common public radio interface (CPRI for short).
  • CPRI common public radio interface
  • the network side device 700 in this embodiment of the present invention further includes: instructions or programs stored in the memory 75 and operable on the processor 75, and the processor 75 invokes the instructions or programs in the memory 75 to execute FIG. 4 or FIG. 5
  • the methods executed by each module shown in the figure achieve the same technical effect, so in order to avoid repetition, they are not repeated here.
  • the second device is similar to the first device and will not be repeated here.
  • the embodiment of the present application also provides a readable storage medium.
  • the readable storage medium stores programs or instructions.
  • the program or instructions are executed by the processor, the various processes of the above-mentioned transmission method embodiments can be achieved, and the same Technical effects, in order to avoid repetition, will not be repeated here.
  • the processor is the processor in the terminal described in the foregoing embodiments.
  • the readable storage medium includes a computer-readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk, and the like.
  • the embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement each of the above transmission method embodiments process, and can achieve the same technical effect, in order to avoid repetition, it will not be repeated here.
  • the chip mentioned in the embodiment of the present application may also be called a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip.
  • An embodiment of the present application further provides a computer program/program product, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the above transmission method embodiment
  • Each process can achieve the same technical effect, so in order to avoid repetition, it will not be repeated here.
  • the embodiment of the present application also provides a communication system, including: a terminal and a network-side device, the terminal can be used to perform the steps of the above-mentioned transmission method, and the network-side device can be used to perform the steps of the above-mentioned transmission method step.
  • the term “comprising”, “comprising” or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase “comprising a " does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.
  • the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. Functions are performed, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
  • the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation.
  • the technical solution of the present application can be embodied in the form of computer software products, which are stored in a storage medium (such as ROM/RAM, magnetic disk, etc.) , CD-ROM), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present application.

Landscapes

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

Abstract

本申请公开了一种传输方法、装置和设备,属于通信技术领域,本申请实施例的传输方法包括:第一设备获取目标模型的输出结果,目标模型包括第一设备的第一模型和/或第二设备的第二模型;第一模型与第二模型具有相关性;第一设备根据目标模型的输出结果确定传输参数。

Description

传输方法、装置和设备
相关申请的交叉引用
本申请要求于2022年1月14日提交的申请号为202210045072.2,发明名称为“传输方法、装置和设备”的中国专利申请的优先权,其通过引用方式全部并入本申请。
技术领域
本申请属于通信技术领域,具体涉及一种传输方法、装置和设备。
背景技术
目前通常是使用轮询的方式进行模拟波束赋形向量的训练,即每个天线面板每个极化方向的阵元以时分复用方式依次在约定时间发送训练信号(即候选的赋形向量),终端经过测量后反馈波束报告,供网络侧设备在下一次传输业务时采用该训练信号的赋形向量实现模拟波束发射。波束报告的内容通常包括最优的若干个发射波束标识以及测量出的最优的若干个发射波束的波束质量(如层1参考信号接收功率(Layer 1 Reference Signal Received Power,L1-RSRP))。
在经过波束测量和波束报告后,网络侧设备可以对下行与上行链路的信道或参考信号做波束指示,用于网络侧设备与终端之间建立波束链路,实现信道或参考信号的传输,波束指示的具体过程例如为:网络侧设备向终端发送波束指示信息,携带待使用的波束信息,终端返回响应。上述过程需要通过信令进行交互,交互完成后,才能让待使用的波束生效,这就导致了波束切换的时延较高,特别是在一些高速场景,波束经常切换,信令交互时延可能不满足需求。
发明内容
本申请实施例提供一种传输方法、终端及网络侧设备,能够解决确定传输参数的问题。
第一方面,提供了一种传输方法,应用于第一设备,该方法包括:
获取目标模型的输出结果,所述目标模型包括第一设备的第一模型和/或第二设备的第二模型;所述第一模型与所述第二模型具有相关性;
根据所述目标模型的输出结果确定传输参数。
第二方面,提供了一种传输方法,应用于第二设备,该方法包括:
获取目标模型的输出结果,所述目标模型包括第一设备的第一模型和/或第二设备的第二模型;所述第一模型与所述第二模型具有相关性;
根据所述目标模型的输出结果确定传输参数。
第三方面,提供了一种传输装置,包括:
获取装置,用于获取目标模型的输出结果,所述目标模型包括第一设备的第一模型和/或第二设备的第二模型;所述第一模型与所述第二模型具有相关性;
处理装置,用于根据所述目标模型的输出结果确定传输参数。
第四方面,提供了一种传输装置,包括:
获取装置,用于获取目标模型的输出结果,所述目标模型包括第一设备的第一模型和/或第二设备的第二模型;所述第一模型与所述第二模型具有相关性;
处理装置,用于根据所述目标模型的输出结果确定传输参数。
第五方面,提供了一种第一设备,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤。
第六方面,提供了一种第一设备,包括处理器及通信接口,其中,所述通信接口用于获取目标模型的输出结果,所述目标模型包括第一设备的第一模型和/或第二设备的第二模型;所述第一模型与所述第二模型具有相关性;所述处理器用于根据所述目标模型的输出结果确定传输参数。
第七方面,提供了一种第二设备,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第二方面所述的方法的步骤。
第八方面,提供了一种第二设备,包括处理器及通信接口,其中,所述通信接口用于获取目标模型的输出结果,所述目标模型包括第一设备的第一模型和/或第二设备的第二模型;所述第一模型与所述第二模型具有相关性;所述处理器用于根据所述目标模型的输出结果确定传输参数。
第九方面,提供了一种通信系统,包括:第一设备及第二设备,所述终端可用于执行如第一方面所述的传输方法的步骤,所述网络侧设备可用于执行如第二方面所述的传输方法的步骤。
第十方面,提供了一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如第一方面所述的方法的步骤,或者实现如第二方面所述的方法的步骤。
第十一方面,提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现如第一方面所述的方法,或实现如第二方面所述的方法。
第十二方面,提供了一种计算机程序/程序产品,所述计算机程序/程序产品被存储在存储介质中,所述计算机程序/程序产品被至少一个处理器执行以实现如第一方面或第二方面所述的传输方法的步骤。
在本申请实施例中,第一设备获取目标模型的输出结果,根据目标模型的输出结果确定传输参数;其中,目标模型包括第一设备的第一模型和/或第二设备的第二模型;由于第一模型与第二模型具有相关性,第一设备可以基于第一模型和/或第二模型确定传输参数,第二设备可以基于第一模型和/或第二模型确定传输参数,使得确定的传输参数的一致性较高,无需设备之间进一步交互传输参数,使得信令开销较小,而且降低了传输时延,提高了传输效率。
附图说明
图1是本申请实施例可应用的无线通信系统的结构图;
图2是本申请实施例提供的传输方法的流程示意图之一;
图3是本申请实施例提供的传输方法的流程示意图之二;
图4是本申请实施例提供的传输装置的结构示意图之一;
图5是本申请实施例提供的传输装置的结构示意图之二;
图6是本申请实施例提供的通信设备的结构示意图;
图7是本申请实施例提供的终端的硬件结构示意图;
图8是本申请实施例的网络侧设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员所获得的所有其他实施例,都属于本申请保护的范围。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象,而不用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换,以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施,且“第一”、“第二”所区别的对象通常为一类,并不限定对象的个数,例如第一对象可以是一个,也可以是多个。此外,说明书以及权利要求中“和/或”表示所连接对象的至少其中之一,字符“/”一般表示前后关联对象是一种“或”的关系。
值得指出的是,本申请实施例所描述的技术不限于长期演进型(Long Term Evolution,LTE)/LTE的演进(LTE-Advanced,LTE-A)系统,还可用于其他无线通信系统,诸如码分多址(Code Division Multiple Access,CDMA)、时分多址(Time Division Multiple Access,TDMA)、频分多址(Frequency Division Multiple Access,FDMA)、正交频分多址(Orthogonal Frequency  Division Multiple Access,OFDMA)、单载波频分多址(Single-carrier Frequency Division Multiple Access,SC-FDMA)和其他系统。本申请实施例中的术语“系统”和“网络”常被可互换地使用,所描述的技术既可用于以上提及的系统和无线电技术,也可用于其他系统和无线电技术。以下描述出于示例目的描述了新空口(New Radio,NR)系统,并且在以下大部分描述中使用NR术语,但是这些技术也可应用于NR系统应用以外的应用,如第6代(6th Generation,6G)通信系统。
图1示出本申请实施例可应用的一种无线通信系统的框图。无线通信系统包括终端11和网络侧设备12。其中,终端11可以是手机、平板电脑(Tablet Personal Computer)、膝上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant,PDA)、掌上电脑、上网本、超级移动个人计算机(ultra-mobile personal computer,UMPC)、移动上网装置(Mobile Internet Device,MID)、增强现实(augmented reality,AR)/虚拟现实(virtual reality,VR)设备、机器人、可穿戴式设备(Wearable Device)、车载设备(VUE)、行人终端(PUE)、智能家居(具有无线通信功能的家居设备,如冰箱、电视、洗衣机或者家具等)、游戏机、个人计算机(personal computer,PC)、柜员机或者自助机等终端侧设备,可穿戴式设备包括:智能手表、智能手环、智能耳机、智能眼镜、智能首饰(智能手镯、智能手链、智能戒指、智能项链、智能脚镯、智能脚链等)、智能腕带、智能服装等。需要说明的是,在本申请实施例并不限定终端11的具体类型。网络侧设备12可以包括接入网设备或核心网设备,其中,接入网设备12也可以称为无线接入网设备、无线接入网(Radio Access Network,RAN)、无线接入网功能或无线接入网单元。接入网设备12可以包括基站、WLAN接入点或WiFi节点等,基站可被称为节点B、演进节点B(eNB)、接入点、基收发机站(Base Transceiver Station,BTS)、无线电基站、无线电收发机、基本服务集(Basic Service Set,BSS)、扩展服务集(Extended Service Set,ESS)、家用B节点、家用演进型B节点、发送接收点(Transmitting Receiving Point,TRP)或所述领域中其他某个合适的术 语,只要达到相同的技术效果,所述基站不限于特定技术词汇,需要说明的是,在本申请实施例中仅以NR系统中的基站为例进行介绍,并不限定基站的具体类型。
目前,波束指示需要通过信令进行交互,交互完成后,才能让新的波束生效,这就导致了波束切换的时延无法降低,特别是在一些高速场景,波束经常切换,信令交互时延可能不满足需求,降低了资源利用率。
关于波束测量和报告:目前模拟波束赋形是全带宽发射的,并且每个高频天线阵列的面板上每个极化方向阵元仅能以时分复用的方式发送模拟波束。模拟波束的赋形权值是通过调整射频前端移相器等设备的参数来实现。相关技术中,通常是使用轮询的方式进行模拟波束赋形向量的训练,即每个天线面板每个极化方向的阵元以时分复用方式依次在约定时间发送训练信号(即候选的赋形向量),终端经过测量后反馈波束报告,供网络侧设备在下一次传输业务时采用该训练信号来实现模拟波束发射。波束报告的内容通常包括最优的若干个发射波束标识以及测量出的最优的若干发射波束的波束质量。在做波束测量时,网络侧设备会配置参考信号资源集合(RS resource set),其中包括至少一个参考信号资源,例如SSB resource或CSI-RS resource。终端测量每个RS resource的L1-RSRP/L1-SINR,并将最优的至少一个测量结果上报给网络侧设备,上报内容包括SSB RI或CRI、及L1-RSRP/L1-SINR。该报告内容反映了至少一个最优的波束及其质量,供网络确定用来向UE发送信道或信号的波束。
关于波束指示机制,相关技术中,在经过波束测量和波束报告后,网络可以对下行与上行链路的信道或参考信号做波束指示,用于网络与UE之间建立波束链路,实现信道或参考信号的传输。
对于PDCCH的波束指示,网络使用RRC信令为每个CORESET配置K个传输配置指示(Transmission Configuration Indication,TCI)状态state,当K>1时,由MAC CE指示或激活1个TCI state,当K=1时,不需要额外的MAC CE命令。UE在监听PDCCH时,对CORESET内全部search space使 用相同准共址(Quasi-colocation,QCL),即相同的TCI state来监听PDCCH。该TCI状态中的referenceSignal(例如周期CSI-RS resource、半持续CSI-RS resource、SS block等)与UE-specific PDCCH DMRS端口是空间QCL的。UE根据该TCI状态即可获知使用哪个接收波束来接收PDCCH。
对于PDSCH的波束指示,网络通过RRC信令配置M个TCI state,再使用MAC CE命令激活2N个TCI state,然后通过DCI的N-bitTCI field来通知TCI状态,该TCI状态中的referenceSignal与要调度的PDSCH的DMRS端口是QCL的。UE根据该TCI状态即可获知使用哪个接收波束来接收PDSCH。
对于CSI-RS的波束指示,当CSI-RS类型为周期CSI-RS时,网络通过RRC信令为CSI-RS resource配置QCL信息。当CSI-RS类型为半持续CSI-RS时,网络通过MAC CE命令来从RRC配置的CSI-RS resource set中激活一个CSI-RS resource时指示其QCL信息。当CSI-RS类型为非周期CSI-RS时,网络通过RRC信令为CSI-RS resource配置QCL,并使用DCI来触发CSI-RS。
对于PUCCH的波束指示,网络使用RRC信令通过参数PUCCH-SpatialRelationInfo为每个PUCCH resource配置空间相关信息(spatial relation information),当为PUCCH resource配置的spatial relation information包含多个时,使用MAC-CE指示或激活其中一个spatial relation information。当为PUCCH resource配置的spatial relation information只包含1个时,不需要额外的MAC CE命令。
对于PUSCH的波束指示,PUSCH的spatial relation信息是当PDCCH承载的DCI调度PUSCH时,DCI中的SRI field的每个SRI codepoint指示一个SRI,该SRI用于指示PUSCH的spatial relation information。
对于SRS的波束指示,当SRS类型为周期SRS时,网络通过RRC信令为SRS resource配置spatial relation information。当SRS类型为半持续SRS时,网络通过MAC CE命令来从RRC配置的一组spatial relation information中激活一个。当SRS类型为非周期SRS时,网络通过RRC信令为SRS resource配置spatial relation information。
人工智能(Artificial Intelligence,AI)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。本申请实施例以神经网络为例进行说明,但是并不限定AI模型的具体类型。神经网络由神经元组成,其中a1,a2,…aK为输入,w为权值(乘性系数),b为偏置(加性系数),σ(.)为激活函数。常见的激活函数包括Sigmoid、tanh、修正线性单元(Rectified LinearUnit,ReLU)等等。神经网络的参数通过优化算法进行优化。优化算法就是一种能够帮我们最小化或者最大化目标函数(有时候也叫损失函数)的一类算法。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x就可以得到预测输出f(x),并且可以计算出预测值和真实值之间的差距(f(x)-Y),这个就是损失函数。我们的目的是找到合适的w,b使上述的损失函数的值达到最小,损失值越小,则说明我们的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BP(error Back Propagation,误差反向传播)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向传播的各层权值调整过程,是周而复始地进行的。权值不断调整的过程,也就是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(Stochastic Gradient Descent,SGD)、mini-batch gradient descent(小批量梯度下降)、动量法(Momentum)、Nesterov(发明者的名字,具体为带动量的随机梯度下降)、自适应梯度下降(ADAptive GRADient descent,Adagrad)、Adadelta、均方根 误差降速(root mean square prop,RMSprop)、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/损失,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。
下面结合附图,通过一些实施例及其应用场景对本申请实施例提供的传输方法进行详细地说明。
图2是本发明实施例提供的传输方法一实施例的流程示意图。如图2所示,本实施例提供的方法,包括:
步骤101、第一设备获取目标模型的输出结果,目标模型包括第一设备的第一模型和/或第二设备的第二模型;第一模型与第二模型具有相关性。
具体地,第一设备可以通过自身获取目标模型的输出结果,和/或与其他设备交互获取目标模型的输出结果,目标模型包括第一设备的第一模型和/或第二设备的第二模型;基于目标模型的输出结果可以确定传输参数;由于第一模型与第二模型具有相关性,也就使得第一模型的输出结果与第二模型的输出结果具有相关性,进而使得第一设备和第二设备确定的传输参数也具有相关性;
可选地,第一设备为以下任一:终端、网络侧设备或辅助网络中心单元,第二设备为以下任一:终端、网络侧设备或辅助网络中心单元;即第一设备和第二设备B端可以是网络侧设备(例如基站),终端以及辅助网络中心单元的各种组合,例如第一设备为终端,第二设备为网络侧设备;或,第一设备为网络侧设备,第二设备为终端;或第一设备和第二设备均为网络侧设备;或,第一设备和第二设备均为终端,或第一设备是辅助网络中心单元,第二设备是网络侧设备等。其中辅助网络中心单元是用于信息交互的单元,可以与终端和网络侧设备通信。
本申请实施例中对第一设备和第二设备类型不作限定,提高了传输方法的适用性。
步骤102、第一设备根据目标模型的输出结果确定传输参数。
具体地,第一设备根据目标模型的输出结果确定传输参数;即目标模型输出结果中包含用于确定传输参数的信息,第一设备根据目标模型输出的用于确定传输参数的信息,就可以确定传输参数。
其中,传输参数例如包括:信号或信道的波束相关信息,信道质量指示(Channel Quality Indication,CQI)相关信息,调制与编码策略(Molation and Coding Scheme,MCS)相关信息,宽带预编码矩阵指示(Transmitted Precoding Matrix Indicator,TPMI)相关信息,功控相关信息,模型的参数信息,模型的验证信息,用于模型调整的反馈信息等。
可选地,波束相关信息例如包括但不限于以下至少一项:
空间相关信息;时间相关信息;波束质量信息;波束ID;角度;
其中,空间相关信息包括但不限于以下至少一项:至少一个最优波束相关信息、至少一个角度相关信息或至少一个波束质量相关信息;
时间相关信息包括但不限于以下至少一项:至少一个未来波束相关信息、至少一个未来角度相关信息或至少一个未来波束质量相关信息。
其中,未来波束是指当前时刻之后的时刻使用或预测的波束。
其他例如CQI相关信息、MCS相关信息,TPMI相关信息和功控相关信息与波束相关信息类似,此处不再赘述。
例如,第一模型的输出结果B中包含用于确定传输参数C的信息,第一设备根据第一模型的输出结果B,就可以确定传输参数C。
上述实施例的方法,第一设备获取目标模型的输出结果,根据目标模型的输出结果确定传输参数;其中,目标模型包括第一设备的第一模型和/或第二设备的第二模型;由于第一模型与第二模型具有相关性,第一设备可以基于第一模型和/或第二模型确定传输参数,第二设备可以基于第一模型和/或第二模型确定传输参数,使得确定的传输参数的一致性较高,无需设备之间进一步交互传输参数,使得信令开销较小,而且降低了传输时延,提高了传输效率。
在一实施例中,第一模型与第二模型具有相关性,满足以下至少一项:
第一模型与第二模型相同;
第一模型为基于第一模型和/或第二模型进行第一目标处理得到的。
具体地,第一模型与第二模型具有相关性,也就使得第一模型的输出结果与第二模型的输出结果具有相关性,也就使得第一设备基于输出结果确定的传输参数和第二设备基于输出结果确定的传输参数具有相关性。第一模型和第二模型例如满足以下情况:
第一模型与第二模型相同;即第一终端对应的第一模型与第二终端对应的第二模型相同;
第一模型为基于第一模型和/或第二模型进行第一目标处理得到的;例如,将第一模型和/或第二模型按照目标规则进行处理,将处理后的模型作为第一终端对应的第一模型。
上述实施方式中,第一模型和第二模型的相关程度可以根据实际应用场景进行针对性调整,使得第一终端根据目标模型的输出结果以及第二设备确定的传输参数的一致性更高。
在一实施例中,基于第一模型和/或第二模型进行第一目标处理包括但不限于以下至少一项:
基于第二模型的输出结果进行对第一模型进行训练;
对第二模型的网络结构进行第二目标处理;
对第二模型的参数进行量化;
对第二模型进行分解处理;
对第二模型进行教师学生方式的模型生成处理,第一模型为第二模型的学生模型或子模型;
其中,第二目标处理包括以下至少一项:剪枝、删减和增加;
分解处理包括以下至少一项:张量分解和低秩分解。
例如,基于第二模型的输出结果对初始的第一模型进行训练,将训练后得到的模型作为第一设备的第一模型;或者将第二模型进行分解处理和/或分 解处理,并经训练后得到的模型作为第一设备的第一模型。
上述实施方式中,可以将第一模型和/或第二模型进行不同方式的处理,并将处理后的模型作为第一模型,使得第一模型和第二模型的相关性更高。
在一实施例中,第一设备的第一模型是通过以下至少一种方式获取到的:
第一设备从第三设备获取到的;
第一设备从第二设备获取到的,第一模型为第二设备从第三设备获取到的,或第二设备生成的;
第一设备生成的。
具体地,根据设备能力和实际场景需求,第一设备的第一模型可以通过多种方式获得,如第一设备生成的,也可以通过第二设备和/或第三设备获得。
可选地,第二设备的第二模型是通过以下至少一种方式获取到的:
第二设备从第三设备获取到的;
第二设备从第一设备获取到的,第二模型为第一设备从第三设备获取到的,或第一设备生成的;
第二设备生成的。
第二模型的获取方式与第一模型的获取方式类似。
总之,模型可以是通过额外的第三设备交互到第一设备和第二设备;
模型可以是通过额外的第三设备交互到第一设备或第二设备后,再通过已获得模型的第一设备或第二设备交互到另一端;
模型可以是直接在第一设备或第二设备获得后,再通过已获得模型的第一设备或第二设备交互到另一端;
第一模型可以是直接在第一设备获得,第二模型可以是直接在第二设备获得。
上述实施方式中,可以根据设备能力和实际应用场景,通过多种方式获得第一设备的第一模型,以及第二设备的第二模型,灵活性较大,更加容易满足实际的需求,提高了实用性。
在一实施例中,基于第一模型和/或第二模型进行第一目标处理,包括以 下至少一项:
通过第二设备基于第一模型和/或第二模型进行第一目标处理;
通过第三设备基于第一模型和/或第二模型进行第一目标处理;
通过第一设备基于第一模型和/或第二模型进行第一目标处理。
具体地,可以选取不同的设备基于第一模型和/或第二模型进行第一目标处理,即通过
不同的设备都可以进行第一目标处理,灵活性较大,提高了实用性。
若通过至少两个设备进行第一目标处理时,可在一个设备进行部分操作,交互到另一个设备,另一个设备再进行相同、不同或部分相同部分不同的操作。
上述实施方式中,通过不同的设备均可以进行第一模型和/或第二模型的第一目标处理,灵活性较大,提高了可用性。
在一实施例中,第一设备和第二设备可以进行相关能力信息的交互,该方法还包括:
第一设备向第二设备发送第一模型的能力信息;和/或,
第一设备基于第一模型的能力信息向第二设备发送请求消息,请求消息用于请求传输参数相关的第一信息;和/或,
第一设备根据第一模型的输出结果向第二设备发送第一指示信息,第一指示信息用于指示传输参数相关的第二信息。
具体地,第一设备的第一模型和第二设备的第二模型的能力可能会不相同,为使得第一模型和第二模型的输出结果、第一设备和第二设备确定的传输参数更加一致,第一设备和第二设备需要交互模型的能力信息;即可以通过第一设备向第二设备发送第一模型的能力信息;和/或,第一设备基于第一模型的能力信息向第二设备发送请求消息,请求消息用于请求传输参数相关的第一信息;和/或,第一设备根据第一模型的输出结果向第二设备发送第一指示信息,第一指示信息用于指示传输参数相关的第二信息;使得第一设备和第二设备可以交互模型的能力信息。
其中,传输参数相关的第一信息和/或第二信息,可以包括模型的输入参数信息和/或输出参数信息。
可选地,第二设备也可以向第一设备发送第二模型的能力信息,第二设备也可以向第一设备发送请求信息和/或指示信息。
上述实施方式中,第一设备和第二设备可以交互模型的能力信息,第一模型和第二模型的输出结果、第一设备和第二设备确定的传输参数更加一致。
在一实施例中,第一信息和/或第二信息包括但不限于以下至少一项:
发送波束信息、接收波束信息和发送接收波束对信息。
可选地,发送波束信息包括但不限于以下至少一项:发送波束数量、发送波束重复次数、增加发送波束数量差值、减小发送波束数量差值、增加发送波束重复次数差值、减小发送波束重复次数差值增加发送波束数量指示、减小发送波束数量指示、增加发送波束重复次数指示、减小发送波束数量指示、达到目标值的最少发送波束数量、达到目标精度值的最少发送波束数量、达到目标值的最少发送波束次数或达到目标精度值的最少发送波束次数;
可选地,接收波束信息包括但不限于以下至少一项:接收波束数量、接收波束重复次数、增加接收波束数量差值、减小接收波束数量差值、增加接收波束重复次数差值、减小接收波束重复次数差值、增加接收波束数量指示、减小接收波束数量指示、增加接收波束重复次数指示或减小接收波束数量指示;
可选地,发送接收波束对信息包括但不限于以下至少一项:发送接收波束对数量、发送接收波束对重复次数、增加发送接收波束对数量差值、减小发送接收波束对数量差值、增加发送接收波束对重复次数差值、减小发送接收波束对重复次数差值、增加发送接收波束对数量指示、减小发送接收波束对数量指示、增加发送接收波束对重复次数指示、减小发送接收波束对数量指示。
在一实施例中,步骤102可以通过如下方式实现:
第一设备根据目标模型的输出结果以及目标模式确定传输参数;目标模 式包括以下任一模式:第一模式、第二模式、第三模式和第四模式;
其中,第一模式为第一设备输出第一反馈信息,且第一反馈信息包括第一模型的输出结果的模式;第二模式为第一设备输出第一反馈信息,第一反馈信息包括第一模型的输出结果,且第一反馈信息用于对第二模型进行调整的模式,第三模式为第一设备输出第一反馈信息,第一反馈信息不包括第一模型的输出结果,且第二设备输出基于第一反馈信息得到的第二模型的输出结果的模式,第四模式为第一设备输出第一反馈信息,第一反馈信息不包括第一模型的输出结果,第二设备输出基于第一反馈信息得到的第二模型的输出结果,且第二模型的输出结果用于对第一模型进行调整的模式。
具体地,第一设备可以根据目标模型的输出结果以及目标模式确定传输参数;目标模式包括以下任一模式:第一模式、第二模式、第三模式和第四模式;其中,不同的模式下,第一设备输出的第一反馈信息包括的内容不同,第一反馈信息的作用也不同,如第一模式和第二模式下,第一反馈信息包括第一模型的输出结果,第三模式和第四模式下,第一反馈信息不包括第一模型的输出结果,第二模式下第一反馈信息用于对第二模型进行调整,第三模式和第四模式下第一反馈信息可以作为第二模型的输入;即在不同的目标模式下,第一设备输出的反馈信息不同,反馈信息的作用也不同,可以满足不同场景的需求。
例如,若第一设备和第二设备当前的目标模式为第一模式,第一设备输出第一反馈信息,第一反馈信息包括第一模型的输出信息,第二设备接收到第一设备反馈信息后,第一设备和/或第二设备可直接使用第一设备的第一模型的输出结果确定传输参数,即基于第一模型的输出结果中包括的相关信息进行后续信息传输。可选地,第二设备将第一设备输出的第一反馈信息,通过第一设备的第一模型后,获得第二模型的输出结果。
若第一设备和第二设备当前的目标模式为第二模式,第一设备输出第一反馈信息,第一反馈信息包括第一模型的输出信息,第二设备接收到第一反馈信息,并使用该第一反馈信息调整、校准第二设备的第二模型参数,和/或 验证、校准第二模型的输出结果是否与第一设备的第一模型的输出结果相同或相似或误差在一定范围内。可选地,此时第二设备可以反馈误差结果或确认结果是否一致,或当误差结果超过预设误差范围时,反馈误差结果或通知第一设备误差结果超出误差范围。
若第一设备和第二设备当前的目标模式为第三模式,第一设备输出第一反馈信息,第一反馈信息不包括第一模型的输出结果,或者第一反馈信息中仅包括测量信息,第二设备将第一设备输出的第一反馈信息,通过第二设备的第二模型后,获得第二模型的输出结果,第一设备和/或第二设备可直接使用第二模型的输出结果确定传输参数,用于后续信息传输;或第二设备使用第二模型的输出结果,第一设备使用第一模型的输出结果确定传输参数,用于后续信息传输。
若第一设备和第二设备当前的目标模式为第四模式,第一设备输出第一反馈信息,第一反馈信息不包括第一模型的输出结果,或者第一反馈信息中仅包括测量信息,第二设备将第一设备输出的第一反馈信息,通过第二设备的第二模型后,获得第二模型的输出结果,并将第二模型的输出结果反馈到第一设备,第一设备通过第二模型的输出结果调整、校准第一模型的参数,和/或验证、校准第一模型的输出结果是否与第二模型的输出结果相同或相似或误差在一定范围内。可选地,此时第一设备可以反馈误差结果或确认结果是否一致,或当误差结果超过误差范围时,反馈误差结果或通知第二设备误差结果超出误差范围。
可选地,目标模式为周期性生效或行为触发生效的。
上述实施方式中,通过不同的目标模式确定传输参数,传输参数确定的灵活性较大的,满足了不同场景的需求。
在一实施例中,在目标模式为第一模式或第二模式的情况下,该方法还包括:
第一设备向第二设备发送第一反馈信息,第一反馈信息包括第一模型的输出结果以及以下至少一项:第一模型的输入信息、测量信息;
第一反馈信息用于第二设备确定传输参数。
具体地,第一设备和第二设备可以交互反馈信息,第一设备向第二设备发送第一反馈信息,第一反馈信息包括第一模型的输出结果以及以下至少一项:第一模型的输入信息、测量信息;第一反馈信息用于第二设备确定传输参数,例如获取第二模型的输出结果或对第二模型进行调整等;即第一设备向第二设备发送的第一反馈信息,不仅包括第一模型的输出结果,还可以包括第一模型的输入信息和/或测量信息,可以使得确定的传输参数更加准确,第一设备和第二设备确定的传输参数一致性较高,第一模型和第二模型的输出结果的一致性较高。
可选地,第一反馈信息中的测量信息可以是第二设备反馈的测量信息,第一设备获取的测量信息等。测量信息可以是波束测量信息或与确定传输参数相关的测量信息等。
上述实施方式中,通过第一设备和第二设备交互反馈信息,能够提升传输参数的准确性,第一设备和第二设备确定的传输参数一致性较高,以及第一模型和第二模型的输出结果的一致性较高。
可选地,该方法还包括:
第一设备接收第二设备发送的第一误差反馈信息,第一误差反馈信息用于反馈以下至少一项:第一模型的输出结果与第二模型的输出结果是否一致、第一模型的输出结果与第二模型的输出结果之间的第一误差结果或第一误差结果超出第一误差范围的指示信息。
具体地,第一设备接收第二设备发送的第一误差反馈信息,第一设备可以根据第一误差反馈信息,对第一模型进行调整和优化。
可选地,该实施例中的第二模型可以是基于第一反馈信息进行调整之后的第二模型。
在一实施例中,在目标模式为第三模式或第四模式的情况下,该方法还包括:
第一设备接收第二设备发送的第二反馈信息,第二反馈信息包括以下至 少一项:第二模型的输出结果、第二模型的输入信息、测量信息;
第二反馈信息用于第一设备确定传输参数。
可选地,第二反馈信息中的测量信息可以是第一设备反馈的测量信息,第一设备获取的测量信息等。测量信息可以是波束测量信息,与确定传输参数相关的测量信息等。
第二反馈信息用于第一设备确定传输参数,例如获取第一模型的输出结果,对第一模型进行调整等。
上述实施方式中,通过第一设备和第二设备交互反馈信息,能够提升传输参数的准确性,第一设备和第二设备确定的传输参数一致性较高,以及第一模型和第二模型的输出结果的一致性较高。
在一实施例中,第一设备根据目标模型的输出结果以及目标模式确定传输参数,包括:
第一设备根据第二反馈信息对第一模型进行调整,得到调整后的第一模型;和/或,
第一设备确定第一模型的输出结果与第二模型的输出结果是否一致,或第一模型的输出结果与第二模型的输出结果之间的第二误差结果是否处于第二误差范围内。
具体地,第一设备根据第二反馈信息进行第一模型的调整;和/或,确定第一模型的输出结果与第二模型的输出结果的误差结果,进而可以基于误差结果对第一模型进行调整和优化。
在一实施例中,第一设备向第二设备发送第二误差反馈信息;第二误差反馈信息用于反馈以下至少一项:第一模型的输出结果与第二模型的输出结果是否一致、第一模型的输出结果与第二模型的输出结果之间的第二误差结果或第二误差结果超出第二误差范围的指示信息。
在一实施例中,在目标模式为第三模式或第四模式的情况下,该方法还包括:
第一设备向第二设备发送第一反馈信息,第一反馈信息包括以下至少一 项:第一模型的输入信息、测量信息;
第一设备接收第二设备发送的第二模型的输出结果;第二模型的输出结果为基于第一反馈信息得到的。
具体地,该实施例中,与前述第一模式或第二模式的情况下不同的是,第一反馈信息不包括第一模型的输出结果,其余类似,此次不再赘述。
在一实施例中,在目标模式为第一模式的情况下,方法还包括:
第一设备向第二设备发送第一反馈信息,第一反馈信息包括第一模型的输出结果以及以下至少一项:第一模型的输入信息、测量信息;
第一设备接收第二设备发送的第二模型的输出结果;
第一设备根据目标模型的输出结果以及目标模式确定传输参数,包括:
第一设备使用第一模型的输出结果确定传输参数,满足以下至少一项:
第一模型的输出结果和第二模型的输出结果一致;
第一模型和/或第二模型的输出结果生效;
第一模型和/或第二模型的功能生效;
第一设备和第二设备通过信令交互确定的传输参数一致。
可选地,第一设备接收到的第二模型的输出结果可以是基于第一反馈信息得到的;
在另一实施例中,在目标模式为第三模式的情况下,该方法还包括:
第一设备向第二设备发送第一反馈信息,第一反馈信息包括以下至少一项:第一模型的输入信息、测量信息;
第一设备接收第二设备发送的第二模型的输出结果;
第一设备根据目标模型的输出结果以及目标模式确定传输参数,包括:
第一设备使用第一模型的输出结果确定传输参数,满足以下至少一项:
第一模型的输出结果和第二模型的输出结果一致;
第一模型和/或第二模型的输出结果生效;
第一模型和/或第二模型的功能生效;
第一设备和第二设备通过信令交互确定的传输参数一致。
可选地,第一设备接收到的第二模型的输出结果可以是基于第一反馈信息得到的;
上述实施方式中,第一设备使用第一模型的输出结果确定传输参数,第二设备使用第一模型和/或第二模型的输出结果确定传输参数,由于第一模型和第二模型具有相关性,使得确定的传输参数的一致性较高。
在一实施例中,在第一设备和第二设备确定的传输参数不一致的情况下,该方法还包括:
第一设备接收第二设备发送的第二指示信息,第二指示信息用于指示第一设备调整第一模型的模型参数和/或调整目标模式。
具体地,在第一设备和第二设备确定的传输参数不一致的情况下,第一设备接收第二设备发送的第二指示信息,第二指示信息用于指示第一设备调整第一模型的模型参数,和/或调整第一设备使用的目标模式;即在第一设备和第二设备确定的传输参数不一致的情况下,可能第一模型和第二模型相关性较小和/或使用的目标模式不同,因此需要调整模型的参数,和/或使用的目标模式,使得第一设备和第二设备确定的传输参数的一致性较高。
例如,可以通过信令交互或信息交互确定或更新目标模式包含以上模式中至少之一,例如信令交互使用第一模式,或信令交互使用第一模式和第一模式等。可选地,以上模式定义中,可仅包含模型功能,不包括反馈信息的配置。
可选地,该方法还包括:
第一设备接收第二设备发送的第二反馈信息,第二反馈信息包括以下至少一项:第二模型的输出结果、第二模型的输入信息、测量信息;
可选地,第一设备根据目标模型的输出结果以及目标模式确定传输参数,包括:
第一设备基于第二反馈信息对第一模型进行调整,得到调整后的第一模型。
在一实施例中,第一设备和第二设备交互的反馈信息中包括以下至少一 项:
第一模型和/或第二模型的输出结果中全部输出参数;
第一模型和/或第二模型的输出结果中至少部分输出参数;
第一模型和/或第二模型的输出结果中预配置、配置或协议预定义的上报的输出参数;
第一模型和/或第二模型中输入参数数量;
第一模型和/或第二模型中输出参数数量;
第一模型和/或第二模型中所有输入参数;
第一模型和/或第二模型中至少部分输入参数;
第一模型和/或第二模型中预配置、配置或协议预定义的上报的输入参数;
第一设备和第二设备的反馈信息关联的输入参数;
第一设备和第二设备的反馈信息关联的参考信号ID;
第一设备和第二设备的反馈信息关联的参考信号对应的波束相关信息;
第一设备和第二设备的反馈信息关联的参考信号对应的角度相关信息;
波束相关信息;
角度相关信息;
波束确认信息;
指定波束信息;
网络侧设备标识ID;
速度;
地理位置信息。
可选地,输入参数和/或输出参数为以下至少一个周期的参数,以下至少一个周期包括:最近周期、当前周期或反馈信息关联的周期。
具体地,第一设备和第二设备交互的反馈信息中包括的信息,输入参数和/或输出参数的周期,都可以根据实际场景进行选择和确定,使得反馈信息的内容更加的灵活。可选地,当反馈信息中包含完整的输入和或输出参数时,可以不反馈输入和/或输出参数的数量。
例如,以上模式可以周期性生效或非周期行为被触发,例如参考信号10ms一个周期,但目标模式使用是20ms一个周期,或在需要时被触发。
上述实施方式中,第一设备和第二设备交互的反馈信息中包括的信息,输入参数和/或输出参数的周期,都可以根据实际场景进行选择和确定,使得反馈信息的内容更加的灵活,提高了传输方法的灵活性和实用性。
在一实施例中,第一设备和第二设备交互的反馈信息包括第一模型或第二模型的输出结果时,还包括但不限于以下至少一项:反馈端模型的输入信息和反馈端测量信息。
例如,第一设备向第二设备发送的反馈信息包括:第一模型的输出结果,还包括以下至少一项:第一模型的输入信息和第一设备的测量信息。
例如,第二设备向第一设备发送的反馈信息包括:第二模型的输出结果,还包括以下至少一项:第二模型的输入信息和第二设备的测量信息。
可选地,第一设备和第二设备交互的反馈信息不包括第一模型或第二模型的输出结果时,可以包括但不限于以下至少一项:反馈端模型的输入信息和反馈端测量信息。
在一实施例中,第一设备和第二设备交互的反馈信息中包括的参数的顺序为按照预配置、配置或协议预定义确定的。
具体地,第一设备和第二设备交互的反馈信息中不同类型的参数和/或相同类型的参数的顺序可以为按照预配置、配置或协议预定义确定的。
例如,顺序为先输出参数后输入参数;约定规则也可以是基于波束质量的从大到小或从小到大。
示例性地,第一设备为终端,配置第一模型;
第二设备为网络侧设备,配置第二模型;
网络侧设备和/或终端获取目标模型的输出结果,确定传输参数。
步骤1:网络侧设备配置第一模型和第二模型到第一设备和/或第二设备;
可选地,由于终端和网络侧设备的处理能力不同,终端可以对模型进行删减处理等;
可选地,终端和网络侧设备的模型参数可以不一致。
步骤2:网络侧设备发送波束,终端测量后获得多个波束信息;
可选地,由于终端的能力和网络侧设备能力不同,终端的第一模型的输出结果中包括的波束数量可能与第二模型的输出结果中包括的波束数量不同,终端可以向网络侧设备反馈最小发送波束数量的能力。
可选地,即使终端的计算能力足够,但由于第一模型训练造成达不到目标准确度,终端可以请求反馈波束数量相关参数;
在第二模式下,该方法还包括:
步骤3a:终端将历史波束测量结果和当前波束测量结果输入第一模型,或将当前波束测量结果输入第一模型,获取第一模型输出结果;可选地,第一模型的输出结果包括至少一个波束ID和/或波束质量信息;
步骤4a:终端向网络侧设备反馈第一模型的输出结果和/或测量信息,网络侧设备接收反馈的信息后,网络侧设备可以对第二模型进行调整,使得终端地第一模型和网络侧设备的第二模型的输出结果一致;
可选地,网络侧设备的第二模型的输出结果与终端的第一模型的输出结果一致,和/或输出结果偏差在目标范围内,网络侧设备的第二模型可以不进行调整。
在第四模式下,该方法还包括:
步骤3b:终端输出反馈信息,其中,反馈信息可以包括测量信息,但不包括第一模型的输出结果,网络侧设备接收反馈信息后,基于该反馈信息,获取第二模型的输出结果;可选地,输出结果可以包括至少一个波束ID和/或波束质量信息;
步骤4b:网络侧设备发送第二模型的输出结果,或调度波束的信息给终端,终端接收到第二模型的输出结果后,可以根据第二模型的输出结果调整终端的第一模型参数,使得终端的第一模型和网络侧设备的第二模型输出结果一致。
在第一模式的基础上,该方法还包括:
步骤3c:终端将历史波束测量结果和当前波束测量结果输入第一模型,或将当前波束测量结果输入第一模型,获取第一模型输出结果;可选地,第一模型的输出结果包括至少一个波束ID和/或波束质量信息;
步骤4c:终端向网络侧设备反馈第一模型的输出结果,网络侧设备接收反馈的信息后,若网络侧设备的第二模型的输出结果与接收的第一模型的输出结果不一致,网络侧设备向终端发送第二模型的输出结果,和/或,指示终端调整第一模型的参数;
步骤5:终端根据网络侧设备发送的第二模型的输出结果,调整第一模型的参数。
图3是本发明实施例提供的传输方法一实施例的流程示意图。如图3所示,本实施例提供的方法,包括:
步骤201、第二设备获取目标模型的输出结果,目标模型包括第一设备的第一模型和/或第二设备的第二模型;第一模型与所述第二模型具有相关性;
步骤202、第二设备根据所述目标模型的输出结果确定传输参数。
可选地,所述第一模型与所述第二模型具有相关性,满足以下至少一项:
所述第一模型与所述第二模型相同;
所述第一模型为基于所述第一模型和/或第二模型进行第一目标处理得到的。
可选地,所述基于所述第一模型和/或第二模型进行第一目标处理包括以下至少一项:
基于所述第二模型的输出结果进行对所述第一模型进行训练;
对所述第二模型的网络结构进行第二目标处理;
对所述第二模型的参数进行量化;
对所述第二模型进行分解处理;
对所述第二模型进行教师学生方式的模型生成处理,所述第一模型为所述第二模型的学生模型或子模型;
其中,所述第二目标处理包括以下至少一项:剪枝、删减和增加;
所述分解处理包括以下至少一项:张量分解和低秩分解。
可选地,所述第二设备的第二模型是通过以下至少一种方式获取到的:
所述第二设备从第三设备获取到的;
所述第二设备从所述第一设备获取到的,所述第二模型为所述第一设备从所述第三设备获取到的,或所述第一设备生成的;
所述第二设备生成的。
可选地,所述基于所述第一模型和/或第二模型进行第一目标处理,包括以下至少一项:
通过所述第二设备基于所述第一模型和/或第二模型进行第一目标处理;
通过第三设备基于所述第一模型和/或第二模型进行第一目标处理;
通过所述第一设备基于所述第一模型和/或第二模型进行第一目标处理。
可选地,所述方法还包括:
所述第二设备接收所述第一设备发送的所述第一模型的能力信息;和/或,
所述第二设备向所述第一设备发送响应消息,所述响应消息为基于所述第一设备发送的请求消息发送的,所述响应消息用于携带所述传输参数相关的第一信息;和/或,
所述第二设备接收所述第一设备发送的第一指示信息,所述第一指示信息用于指示所述传输参数相关的第二信息。
可选地,所述第一信息和/或第二信息包括以下至少一项:
发送波束信息、接收波束信息和发送接收波束对信息。
可选地,所述发送波束信息包括以下至少一项:发送波束数量、发送波束重复次数、增加发送波束数量差值、减小发送波束数量差值、增加发送波束重复次数差值、减小发送波束重复次数差值增加发送波束数量指示、减小发送波束数量指示、增加发送波束重复次数指示、减小发送波束数量指示、达到目标值的最少发送波束数量、达到目标精度值的最少发送波束数量、达到目标值的最少发送波束次数或达到目标精度值的最少发送波束次数;
所述接收波束信息包括以下至少一项:接收波束数量、接收波束重复次数、增加接收波束数量差值、减小接收波束数量差值、增加接收波束重复次数差值、减小接收波束重复次数差值、增加接收波束数量指示、减小接收波束数量指示、增加接收波束重复次数指示或减小接收波束数量指示;
所述发送接收波束对信息包括以下至少一项:发送接收波束对数量、发送接收波束对重复次数、增加发送接收波束对数量差值、减小发送接收波束对数量差值、增加发送接收波束对重复次数差值、减小发送接收波束对重复次数差值、增加发送接收波束对数量指示、减小发送接收波束对数量指示、增加发送接收波束对重复次数指示、减小发送接收波束对数量指示。
可选地,所述第二设备根据所述目标模型的输出结果确定传输参数,包括:
所述第二设备根据所述目标模型的输出结果以及目标模式确定传输参数;所述目标模式包括以下任一模式:第一模式、第二模式、第三模式和第四模式;
其中,所述第一模式为所述第一设备输出第一反馈信息,且所述第一反馈信息包括所述第一模型的输出结果的模式;所述第二模式为所述第一设备输出第一反馈信息,所述第一反馈信息包括所述第一模型的输出结果,且所述第一反馈信息用于对所述第二模型进行调整的模式,所述第三模式为所述第一设备输出第一反馈信息,所述第一反馈信息不包括所述第一模型的输出结果,且所述第二设备输出基于所述第一反馈信息得到的第二模型的输出结果的模式,所述第四模式为所述第一设备输出第一反馈信息,所述第一反馈信息不包括所述第一模型的输出结果,所述第二设备输出基于所述第一反馈信息得到的第二模型的输出结果,且所述第二模型的输出结果用于对所述第一模型进行调整的模式。
可选地,在所述目标模式为所述第一模式或所述第二模式的情况下,所述方法还包括:
所述第二设备接收所述第一设备发送的第一反馈信息,所述第一反馈信 息包括所述第一模型的输出结果以及以下至少一项:所述第一模型的输入信息、测量信息;
所述第一反馈信息用于所述第二设备确定传输参数。
可选地,所述方法还包括:
所述第二设备向所述第一设备发送第一误差反馈信息,所述第一误差反馈信息用于反馈以下至少一项:所述第一模型的输出结果与所述第二模型的输出结果是否一致、所述第一模型的输出结果与所述第二模型的输出结果之间的第一误差结果或所述第一误差结果超出第一误差范围的指示信息。
可选地,所述第一设备根据所述目标模型的输出结果以及目标模式确定传输参数,包括:
所述第二设备根据所述第一反馈信息对所述第二模型进行调整,得到调整后的第二模型;和/或,
所述第二设备确定所述第一模型的输出结果与所述第二模型的输出结果是否一致,或所述第一模型的输出结果与所述第二模型的输出结果之间的第一误差结果是否处于第一误差范围内。
可选地,在所述目标模式为所述第三模式或所述第四模式的情况下,所述方法还包括:
所述第二设备向所述第一设备发送第二反馈信息,所述第二反馈信息包括以下至少一项:所述第二模型的输出结果、所述第二模型的输入信息、测量信息;
所述第二反馈信息用于所述第一设备确定传输参数。
可选地,所述方法还包括:
所述第二设备接收所述第一设备发送的第二误差反馈信息;所述第二误差反馈信息用于反馈以下至少一项:所述第一模型的输出结果与所述第二模型的输出结果是否一致、所述第一模型的输出结果与所述第二模型的输出结果之间的第一误差结果或所述第一误差结果超出第一误差范围的指示信息。
可选地,在所述目标模式为第三模式或第四模式的情况下,所述方法还 包括:
所述第二设备接收所述第一设备发送的所述第一反馈信息,所述第一反馈信息包括以下至少一项:所述第一模型的输入信息、测量信息;
所述第二设备向所述第一设备发送所述第二模型的输出结果;所述第二模型的输出结果为基于所述第一反馈信息得到的。
可选地,在所述目标模式为第一模式的情况下,所述方法还包括:
所述第二设备接收所述第一设备发送的所述第一反馈信息,所述第一反馈信息包括所述第一模型的输出结果以及以下至少一项:所述第一模型的输入信息、测量信息;
所述第二设备向所述第一设备发送所述第二模型的输出结果;
所述第二设备根据所述目标模型的输出结果以及目标模式确定传输参数,包括:
所述第二设备使用所述第一模型的输出结果或所述第二模型的输出结果确定传输参数,满足以下至少一项:
所述第一模型的输出结果和所述第二模型的输出结果一致;
所述第一模型和/或所述第二模型的输出结果生效;
所述第一模型和/或所述第二模型的功能生效;
所述第一设备和所述第二设备通过信令交互确定的传输参数一致。
可选地,在所述目标模式为第三模式的情况下,所述方法还包括:
所述第二设备接收所述第一设备发送的所述第一反馈信息,所述第一反馈信息包括以下至少一项:所述第一模型的输入信息、测量信息;
所述第二设备向所述第一设备发送所述第二模型的输出结果;
所述第二设备根据所述目标模型的输出结果以及目标模式确定传输参数,包括:
所述第二设备使用所述第一模型的输出结果或所述第二模型的输出结果确定传输参数,满足以下至少一项:
所述第一模型的输出结果和所述第二模型的输出结果一致;
所述第一模型和/或所述第二模型的输出结果生效;
所述第一模型和/或所述第二模型的功能生效;
所述第一设备和所述第二设备通过信令交互确定的传输参数一致。
可选地,在所述第一设备和所述第二设备确定的传输参数不一致的情况下,所述方法还包括:
所述第二设备向所述第一设备发送第二指示信息,所述第二指示信息用于指示所述第一设备调整所述第一模型的模型参数和/或调整所述目标模式。
可选地,所述方法还包括:
所述第二设备向所述第一设备发送第二反馈信息,所述第二反馈信息包括以下至少一项:所述第二模型的输出结果、所述第二模型的输入信息、测量信息;所述第二反馈信息用于所述第一设备调整所述第一模型。
可选地,所述目标模式为周期性生效或行为触发生效的。
本实施例的方法,其具体实现过程与技术效果与第一设备方法实施例中类似,具体可以参见第一设备方法实施例中的详细介绍,此处不再赘述。
本申请实施例提供的传输方法,执行主体可以为传输装置。本申请实施例中以传输装置执行传输方法为例,说明本申请实施例提供的传输装置。
图4是本申请提供的传输装置的结构示意图之一。如图4所示,本实施例提供的传输装置,包括:
获取模块410,用于获取目标模型的输出结果,目标模型包括传输装置的第一模型和/或第二设备的第二模型;第一模型与第二模型具有相关性;
处理模块420,用于根据目标模型的输出结果确定传输参数。
可选地,第一模型与第二模型具有相关性,满足以下至少一项:
第一模型与第二模型相同;
第一模型为基于第一模型和/或第二模型进行第一目标处理得到的。
可选地,基于第一模型和/或第二模型进行第一目标处理包括以下至少一项:
基于第二模型的输出结果进行对第一模型进行训练;
对第二模型的网络结构进行第二目标处理;
对第二模型的参数进行量化;
对第二模型进行分解处理;
对第二模型进行教师学生方式的模型生成处理,第一模型为第二模型的学生模型或子模型;
其中,第二目标处理包括以下至少一项:剪枝、删减和增加;
分解处理包括以下至少一项:张量分解和低秩分解。
可选地,第一模型是通过以下至少一种方式获取到的:
从第三设备获取到的;
从第二设备获取到的,第一模型为第二设备从第三设备获取到的,或第二设备生成的;
传输装置生成的。
可选地,基于第一模型和/或第二模型进行第一目标处理,包括以下至少一项:
通过第二设备基于第一模型和/或第二模型进行第一目标处理;
通过第三设备基于第一模型和/或第二模型进行第一目标处理;
通过传输装置基于第一模型和/或第二模型进行第一目标处理。
可选地,还包括:
发送模块,用于向第二设备发送第一模型的能力信息;和/或,
基于第一模型的能力信息向第二设备发送请求消息,请求消息用于请求传输参数相关的第一信息;和/或,
根据第一模型的输出结果向第二设备发送第一指示信息,第一指示信息用于指示传输参数相关的第二信息。
可选地,第一信息和/或第二信息包括以下至少一项:
发送波束信息、接收波束信息和发送接收波束对信息。
可选地,发送波束信息包括以下至少一项:发送波束数量、发送波束重 复次数、增加发送波束数量差值、减小发送波束数量差值、增加发送波束重复次数差值、减小发送波束重复次数差值增加发送波束数量指示、减小发送波束数量指示、增加发送波束重复次数指示、减小发送波束数量指示、达到目标值的最少发送波束数量、达到目标精度值的最少发送波束数量、达到目标值的最少发送波束次数或达到目标精度值的最少发送波束次数;
接收波束信息包括以下至少一项:接收波束数量、接收波束重复次数、增加接收波束数量差值、减小接收波束数量差值、增加接收波束重复次数差值、减小接收波束重复次数差值、增加接收波束数量指示、减小接收波束数量指示、增加接收波束重复次数指示或减小接收波束数量指示;
发送接收波束对信息包括以下至少一项:发送接收波束对数量、发送接收波束对重复次数、增加发送接收波束对数量差值、减小发送接收波束对数量差值、增加发送接收波束对重复次数差值、减小发送接收波束对重复次数差值、增加发送接收波束对数量指示、减小发送接收波束对数量指示、增加发送接收波束对重复次数指示、减小发送接收波束对数量指示。
可选地,处理模块420,具体用于根据目标模型的输出结果以及目标模式确定传输参数;目标模式包括以下任一模式:第一模式、第二模式、第三模式和第四模式;
其中,第一模式为传输装置输出第一反馈信息,且第一反馈信息包括第一模型的输出结果的模式;第二模式为传输装置输出第一反馈信息,第一反馈信息包括第一模型的输出结果,且第一反馈信息用于对第二模型进行调整的模式,第三模式为传输装置输出第一反馈信息,第一反馈信息不包括第一模型的输出结果,且第二设备输出基于第一反馈信息得到的第二模型的输出结果的模式,第四模式为传输装置输出第一反馈信息,第一反馈信息不包括第一模型的输出结果,第二设备输出基于第一反馈信息得到的第二模型的输出结果,且第二模型的输出结果用于对第一模型进行调整的模式。
可选地,发送模块用于在目标模式为第一模式或第二模式的情况下,向第二设备发送第一反馈信息,第一反馈信息包括第一模型的输出结果以及以 下至少一项:第一模型的输入信息、测量信息;
第一反馈信息用于第二设备确定传输参数。
可选地,获取模块410,具体用于接收第二设备发送的第一误差反馈信息,第一误差反馈信息用于反馈以下至少一项:第一模型的输出结果与第二模型的输出结果是否一致、第一模型的输出结果与第二模型的输出结果之间的第一误差结果或第一误差结果超出第一误差范围的指示信息。
可选地,获取模块410,具体用于接收第二设备发送的第二反馈信息,第二反馈信息包括以下至少一项:第二模型的输出结果、第二模型的输入信息、测量信息;
第二反馈信息用于确定传输参数。
可选地,处理模块420,具体用于根据第二反馈信息对第一模型进行调整,得到调整后的第一模型;和/或,
确定第一模型的输出结果与第二模型的输出结果是否一致,或第一模型的输出结果与第二模型的输出结果之间的第二误差结果是否处于第二误差范围内。
可选地,发送模块用于向第二设备发送第二误差反馈信息;第二误差反馈信息用于反馈以下至少一项:第一模型的输出结果与第二模型的输出结果是否一致、第一模型的输出结果与第二模型的输出结果之间的第一误差结果或第一误差结果超出第一误差范围的指示信息。
可选地,发送模块用于在目标模式为第三模式或第四模式的情况下,向第二设备发送第一反馈信息,第一反馈信息包括以下至少一项:第一模型的输入信息、测量信息;
接收第二设备发送的第二模型的输出结果;第二模型的输出结果为基于第一反馈信息得到的。
可选地,发送模块用于在目标模式为第一模式的情况下,向第二设备发送第一反馈信息,第一反馈信息包括第一模型的输出结果以及以下至少一项:第一模型的输入信息、测量信息;
获取模块410用于接收第二设备发送的第二模型的输出结果;
处理模块420具体用于:
使用第一模型的输出结果确定传输参数,满足以下至少一项:
第一模型的输出结果和第二模型的输出结果一致;
第一模型和/或第二模型的输出结果生效;
第一模型和/或第二模型的功能生效;
第一设备和第二设备通过信令交互确定的传输参数一致。
可选地,在目标模式为第三模式的情况下,发送模块还用于:
向第二设备发送第一反馈信息,第一反馈信息包括以下至少一项:第一模型的输入信息、测量信息;
接收第二设备发送的第二模型的输出结果;
处理模块420具体用于:
使用第一模型的输出结果确定传输参数,满足以下至少一项:
第一模型的输出结果和第二模型的输出结果一致;
第一模型和/或第二模型的输出结果生效;
第一模型和/或第二模型的功能生效;
第一设备和第二设备通过信令交互确定的传输参数一致。
可选地,获取模块410,具体用于在传输装置和第二设备确定的传输参数不一致的情况下,还包括:
接收第二设备发送的第二指示信息,第二指示信息用于指示传输装置调整第一模型的模型参数和/或调整目标模式。
可选地,获取模块410,具体用于接收第二设备发送的第二反馈信息,第二反馈信息包括以下至少一项:第二模型的输出结果、第二模型的输入信息、测量信息。
可选地,目标模式为周期性生效或行为触发生效的。
可选地,传输装置和第二设备交互的反馈信息中包括以下至少一项:
第一模型和/或第二模型的输出结果中全部输出参数;
第一模型和/或第二模型的输出结果中至少部分输出参数;
第一模型和/或第二模型的输出结果中预配置、配置或协议预定义的上报的输出参数;
第一模型和/或第二模型中输入参数数量;
第一模型和/或第二模型中输出参数数量;
第一模型和/或第二模型中所有输入参数;
第一模型和/或第二模型中至少部分输入参数;
第一模型和/或第二模型中预配置、配置或协议预定义的上报的输入参数;
传输装置和第二设备的反馈信息关联的输入参数;
传输装置和第二设备的反馈信息关联的参考信号ID;
传输装置和第二设备的反馈信息关联的参考信号对应的波束相关信息;
传输装置和第二设备的反馈信息关联的参考信号对应的角度相关信息;
波束相关信息;
角度相关信息;
波束确认信息;
指定波束信息。
可选地,输入参数和/或输出参数为以下至少一个周期的参数,以下至少一个周期包括:最近周期、当前周期或反馈报告关联的周期。
可选地,传输装置和第二设备交互的反馈信息包括第一模型或第二模型的输出结果时,还包括以下至少一项:反馈端模型的输入信息和反馈端测量信息。
可选地,传输装置和第二设备交互的反馈信息中包括的参数的顺序为按照预配置、配置或协议预定义确定的。
可选地,在传输参数包括波束信息的情况下,输出结果包括以下至少一项:
空间相关信息;时间相关信息;波束质量信息。
可选地,传输装置为以下任一:终端、网络侧设备或辅助网络中心单元, 第二设备为以下任一:终端、网络侧设备或辅助网络中心单元。
本实施例的装置,可以用于执行前述第一设备方法实施例中任一实施例的方法,其具体实现过程与技术效果与第一设备方法实施例中类似,具体可以参见第一设备方法实施例中的详细介绍,此处不再赘述。
图5是本申请提供的传输装置的结构示意图之二。如图5所示,本实施例提供的传输装置,包括:
获取模块510,用于获取目标模型的输出结果,目标模型包括第一设备的第一模型和/或传输装置的第二模型;第一模型与第二模型具有相关性;
处理模块520,用于根据目标模型的输出结果确定传输参数。
可选地,第一模型与第二模型具有相关性,满足以下至少一项:
第一模型与第二模型相同;
第一模型为基于第一模型和/或第二模型进行第一目标处理得到的。
可选地,基于第一模型和/或第二模型进行第一目标处理包括以下至少一项:
基于第二模型的输出结果进行对第一模型进行训练;
对第二模型的网络结构进行第二目标处理;
对第二模型的参数进行量化;
对第二模型进行分解处理;
对第二模型进行教师学生方式的模型生成处理,第一模型为第二模型的学生模型或子模型;
其中,第二目标处理包括以下至少一项:剪枝、删减和增加;
分解处理包括以下至少一项:张量分解和低秩分解。
可选地,第二模型是通过以下至少一种方式获取到的:
从第三设备获取到的;
从第一设备获取到的,第二模型为第一设备从第三设备获取到的,或第一设备生成的;
传输装置生成的。
可选地,获取模块510,具体用于基于第一模型和/或第二模型进行第一目标处理,包括以下至少一项:
通过传输设备基于第一模型和/或第二模型进行第一目标处理;
通过第三设备基于第一模型和/或第二模型进行第一目标处理;
通过第一设备基于第一模型和/或第二模型进行第一目标处理。
可选地,获取模块510,具体用于接收第一设备发送的第一模型的能力信息;和/或,
发送模块,用于向第一设备发送响应消息,响应消息为基于第一设备发送的请求消息发送的,响应消息用于携带传输参数相关的第一信息;和/或,
获取模块510,具体用于接收第一设备发送的第一指示信息,第一指示信息用于指示传输参数相关的第二信息。
可选地,第一信息和/或第二信息包括以下至少一项:
发送波束信息、接收波束信息和发送接收波束对信息。
可选地,发送波束信息包括以下至少一项:发送波束数量、发送波束重复次数、增加发送波束数量差值、减小发送波束数量差值、增加发送波束重复次数差值、减小发送波束重复次数差值增加发送波束数量指示、减小发送波束数量指示、增加发送波束重复次数指示、减小发送波束数量指示、达到目标值的最少发送波束数量、达到目标精度值的最少发送波束数量、达到目标值的最少发送波束次数或达到目标精度值的最少发送波束次数;
接收波束信息包括以下至少一项:接收波束数量、接收波束重复次数、增加接收波束数量差值、减小接收波束数量差值、增加接收波束重复次数差值、减小接收波束重复次数差值、增加接收波束数量指示、减小接收波束数量指示、增加接收波束重复次数指示或减小接收波束数量指示;
发送接收波束对信息包括以下至少一项:发送接收波束对数量、发送接收波束对重复次数、增加发送接收波束对数量差值、减小发送接收波束对数量差值、增加发送接收波束对重复次数差值、减小发送接收波束对重复次数差值、增加发送接收波束对数量指示、减小发送接收波束对数量指示、增加 发送接收波束对重复次数指示、减小发送接收波束对数量指示。
可选地,处理模块520,具体用于:
根据目标模型的输出结果以及目标模式确定传输参数;目标模式包括以下任一模式:第一模式、第二模式、第三模式和第四模式;
其中,第一模式为第一设备输出第一反馈信息,且第一反馈信息包括第一模型的输出结果的模式;第二模式为第一设备输出第一反馈信息,第一反馈信息包括第一模型的输出结果,且第一反馈信息用于对第二模型进行调整的模式,第三模式为第一设备输出第一反馈信息,第一反馈信息不包括第一模型的输出结果,且传输装置输出基于第一反馈信息得到的第二模型的输出结果的模式,第四模式为第一设备输出第一反馈信息,第一反馈信息不包括第一模型的输出结果,传输设备输出基于第一反馈信息得到的第二模型的输出结果,且第二模型的输出结果用于对第一模型进行调整的模式。
可选地,在目标模式为第一模式或第二模式的情况下,获取模块510,具体用于:
接收第一设备发送的第一反馈信息,第一反馈信息包括第一模型的输出结果以及以下至少一项:第一模型的输入信息、测量信息;
第一反馈信息用于传输装置确定传输参数。
可选地,发送模块用于向第一设备发送第一误差反馈信息,第一误差反馈信息用于反馈以下至少一项:第一模型的输出结果与第二模型的输出结果是否一致、第一模型的输出结果与第二模型的输出结果之间的第一误差结果或第一误差结果超出第一误差范围的指示信息。
可选地,处理模块520具体用于:
根据第一反馈信息对第二模型进行调整,得到调整后的第二模型;和/或,
确定第一模型的输出结果与第二模型的输出结果是否一致,或第一模型的输出结果与第二模型的输出结果之间的第一误差结果是否处于第一误差范围内。
可选地,在目标模式为第三模式或第四模式的情况下,发送模块还用于:
向第一设备发送第二反馈信息,第二反馈信息包括以下至少一项:第二模型的输出结果、第二模型的输入信息、测量信息;
第二反馈信息用于第一设备确定传输参数。
可选地,获取模块510,具体用于接收第一设备发送的第二误差反馈信息;第二误差反馈信息用于反馈以下至少一项:第一模型的输出结果与第二模型的输出结果是否一致、第一模型的输出结果与第二模型的输出结果之间的第一误差结果或第一误差结果超出第一误差范围的指示信息。
可选地,在目标模式为第三模式或第四模式的情况下,获取模块510,具体用于:
接收第一设备发送的第一反馈信息,第一反馈信息包括以下至少一项:第一模型的输入信息、测量信息;
发送模块,用于向第一设备发送第二模型的输出结果;第二模型的输出结果为基于第一反馈信息得到的。
可选地,在目标模式为第一模式的情况下,获取模块510,具体用于:
接收第一设备发送的第一反馈信息,第一反馈信息包括第一模型的输出结果以及以下至少一项:第一模型的输入信息、测量信息;
发送模块,用于向第一设备发送第二模型的输出结果;
处理模块520具体用于:
使用第一模型的输出结果或第二模型的输出结果确定传输参数,满足以下至少一项:
第一模型的输出结果和第二模型的输出结果一致;
第一模型和/或第二模型的输出结果生效;
第一模型和/或第二模型的功能生效;
第一设备和传输装置通过信令交互确定的传输参数一致。
可选地,在目标模式为第三模式的情况下,获取模块510,具体用于:
接收第一设备发送的第一反馈信息,第一反馈信息包括以下至少一项:第一模型的输入信息、测量信息;
发送模块,用于向第一设备发送第二模型的输出结果;
处理模块520具体用于:
使用第一模型的输出结果或第二模型的输出结果确定传输参数,满足以下至少一项:
第一模型的输出结果和第二模型的输出结果一致;
第一模型和/或第二模型的输出结果生效;
第一模型和/或第二模型的功能生效;
第一设备和传输装置通过信令交互确定的传输参数一致。
可选地,在第一设备和传输装置确定的传输参数不一致的情况下,发送模块还用于:
向第一设备发送第二指示信息,第二指示信息用于指示第一设备调整第一模型的模型参和/或调整目标模式。
可选地,发送模块还用于向第一设备发送第二反馈信息,第二反馈信息包括以下至少一项:第二模型的输出结果、第二模型的输入信息、测量信息;第二反馈信息用于第一设备调整第一模型。
可选地,目标模式为周期性生效或行为触发生效的。
本实施例的装置,可以用于执行前述第二设备方法实施例中任一实施例的方法,其具体实现过程与技术效果与第二设备方法实施例中类似,具体可以参见第二设备方法实施例中的详细介绍,此处不再赘述。
本申请实施例中的传输装置可以是电子设备,例如具有操作系统的电子设备,也可以是电子设备中的部件,例如集成电路或芯片。该电子设备可以是终端,也可以为除终端之外的其他设备。示例性的,终端可以包括但不限于上述所列举的终端11的类型,其他设备可以为服务器、网络附属存储器(Network Attached Storage,NAS)等,本申请实施例不作具体限定。
本申请实施例提供的传输装置能够实现图1至图8的方法实施例实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。
可选的,如图6所示,本申请实施例还提供一种通信设备600,包括处理 器601和存储器602,存储器602上存储有可在所述处理器601上运行的程序或指令,例如,该通信设备600为第一设备时,该程序或指令被处理器601执行时实现上述传输方法实施例的各个步骤,且能达到相同的技术效果。该通信设备600为第二设备时,该程序或指令被处理器601执行时实现上述传输方法实施例的各个步骤,且能达到相同的技术效果,为避免重复,这里不再赘述。
本申请实施例还提供一种第一设备,包括处理器和通信接口,处理器用于获取目标模型的输出结果,目标模型包括终端的第一模型和/或第二设备的第二模型;第一模型与第二模型具有相关性,通信接口用于根据目标模型的输出结果确定传输参数。该终端实施例与上述第一设备和/或第二设备侧方法实施例对应,上述方法实施例的各个实施过程和实现方式均可适用于该第一设备实施例中,且能达到相同的技术效果。具体地,图7为实现本申请实施例的一种终端的硬件结构示意图。
该终端1000包括但不限于:射频单元1001、网络模块1002、音频输出单元1003、输入单元1004、传感器1005、显示单元1006、用户输入单元1007、接口单元1008、存储器1009、以及处理器1010等中的至少部分部件。
本领域技术人员可以理解,终端1000还可以包括给各个部件供电的电源(比如电池),电源可以通过电源管理系统与处理器1010逻辑相连,从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。图7中示出的终端结构并不构成对终端的限定,终端可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置,在此不再赘述。
应理解的是,本申请实施例中,输入单元1004可以包括图形处理单元(Graphics Processing Unit,GPU)10041和麦克风10042,图形处理器10041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元1006可包括显示面板10061,可以采用液晶显示器、有机发光二极管等形式来配置显示面板10061。用户输入单元1007包括触控面板10071以及其它输入设备10072中的至少一种。触 控面板10071,也称为触摸屏。触控面板10071可包括触摸检测装置和触摸控制器两个部分。其它输入设备10072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆,在此不再赘述。
本申请实施例中,射频单元1001获取目标模型的输出结果后,可以传输给处理器1010进行处理;另外,射频单元1001可以将上行的数据发送给向网络侧设备发送上行数据。通常,射频单元1001包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器、双工器等。
存储器1009可用于存储软件程序或指令以及各种数据。存储器1009可主要包括存储程序或指令的第一存储区和存储数据的第二存储区,其中,第一存储程序或指令区可存储操作系统、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外,存储器1009可以包括易失性存储器或非易失性存储器,或者,存储器1009可以包括易失性和非易失性存储器两者。包括高速随机存取存储器,还可以包括非易失性存储器,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(RandomAccess Memory,RAM),静态随机存取存储器(Static RAM,SRAM)、动态随机存取存储器(Dynamic RAM,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,DDRSDRAM)、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(Synch link DRAM,SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM,DRRAM)。本申请实施例中的存储器1009包括但不限于这些和任意其它适合类型的存储器例如至少一个磁盘存储器件、闪存器件、或其它非易失性固态存储器件。
处理器1010可包括一个或多个处理单元;可选的,处理器1010可集成应用处理器和调制解调处理器,其中,应用处理器主要处理涉及操作系统、 用户界面和应用程序或指令等的操作,调制解调处理器主要处理无线通信信号,如基带处理器。可以理解的是,上述调制解调处理器也可以不集成到处理器1010中。
其中,射频单元1001,用于获取目标模型的输出结果,目标模型包括第一设备的第一模型和/或第二设备的第二模型;第一模型与第二模型具有相关性;
处理器1010,用于根据目标模型的输出结果确定传输参数。
可选地,第一模型与第二模型具有相关性,满足以下至少一项:
第一模型与第二模型相同;
第一模型为基于第一模型和/或第二模型进行第一目标处理得到的。
可选地,处理器1010基于第一模型和/或第二模型进行第一目标处理包括以下至少一项:
基于第二模型的输出结果进行对第一模型进行训练;
对第二模型的网络结构进行第二目标处理;
对第二模型的参数进行量化;
对第二模型进行分解处理;
对第二模型进行教师学生方式的模型生成处理,第一模型为第二模型的学生模型或子模型;
其中,第二目标处理包括以下至少一项:剪枝、删减和增加;
分解处理包括以下至少一项:张量分解和低秩分解。
可选地,第一模型是通过以下至少一种方式获取到的:
从第三设备获取到的;
从第二设备获取到的,第一模型为第二设备从第三设备获取到的,或第二设备生成的;
终端生成的。
可选地,处理器1010基于第一模型和/或第二模型进行第一目标处理,包括以下至少一项:
通过第二设备基于第一模型和/或第二模型进行第一目标处理;
通过第三设备基于第一模型和/或第二模型进行第一目标处理;
通过终端基于第一模型和/或第二模型进行第一目标处理。
可选地,射频单元1001,具体用于向第二设备发送第一模型的能力信息;和/或,
基于第一模型的能力信息向第二设备发送请求消息,请求消息用于请求传输参数相关的第一信息;和/或,
根据第一模型的输出结果向第二设备发送第一指示信息,第一指示信息用于指示传输参数相关的第二信息。
可选地,第一信息和/或第二信息包括以下至少一项:
发送波束信息、接收波束信息和发送接收波束对信息。
可选地,发送波束信息包括以下至少一项:发送波束数量、发送波束重复次数、增加发送波束数量差值、减小发送波束数量差值、增加发送波束重复次数差值、减小发送波束重复次数差值增加发送波束数量指示、减小发送波束数量指示、增加发送波束重复次数指示、减小发送波束数量指示、达到目标值的最少发送波束数量、达到目标精度值的最少发送波束数量、达到目标值的最少发送波束次数或达到目标精度值的最少发送波束次数;
接收波束信息包括以下至少一项:接收波束数量、接收波束重复次数、增加接收波束数量差值、减小接收波束数量差值、增加接收波束重复次数差值、减小接收波束重复次数差值、增加接收波束数量指示、减小接收波束数量指示、增加接收波束重复次数指示或减小接收波束数量指示;
发送接收波束对信息包括以下至少一项:发送接收波束对数量、发送接收波束对重复次数、增加发送接收波束对数量差值、减小发送接收波束对数量差值、增加发送接收波束对重复次数差值、减小发送接收波束对重复次数差值、增加发送接收波束对数量指示、减小发送接收波束对数量指示、增加发送接收波束对重复次数指示、减小发送接收波束对数量指示。
可选地,处理器1010,具体用于:
根据目标模型的输出结果以及目标模式确定传输参数;目标模式包括以下任一模式:第一模式、第二模式、第三模式和第四模式;
其中,第一模式为终端输出第一反馈信息,且第一反馈信息包括第一模型的输出结果的模式;第二模式为终端输出第一反馈信息,第一反馈信息包括第一模型的输出结果,且第一反馈信息用于对第二模型进行调整的模式,第三模式为终端输出第一反馈信息,第一反馈信息不包括第一模型的输出结果,且第二设备输出基于第一反馈信息得到的第二模型的输出结果的模式,第四模式为终端输出第一反馈信息,第一反馈信息不包括第一模型的输出结果,第二设备输出基于第一反馈信息得到的第二模型的输出结果,且第二模型的输出结果用于对第一模型进行调整的模式。
可选地,射频单元1001,具体用于:
在目标模式为第一模式或第二模式的情况下,向第二设备发送第一反馈信息,第一反馈信息包括第一模型的输出结果以及以下至少一项:第一模型的输入信息、测量信息;
第一反馈信息用于第二设备确定传输参数。
可选地,射频单元1001,具体用于:
接收第二设备发送的第一误差反馈信息,第一误差反馈信息用于反馈以下至少一项:第一模型的输出结果与第二模型的输出结果是否一致、第一模型的输出结果与第二模型的输出结果之间的第一误差结果或第一误差结果超出第一误差范围的指示信息。
可选地,射频单元1001,具体用于:
接收第二设备发送的第二反馈信息,第二反馈信息包括以下至少一项:第二模型的输出结果、第二模型的输入信息、测量信息;
第二反馈信息用于确定传输参数。
可选地,处理器1010,具体用于:
根据第二反馈信息对第一模型进行调整,得到调整后的第一模型;和/或,
确定第一模型的输出结果与第二模型的输出结果是否一致,或第一模型 的输出结果与第二模型的输出结果之间的第二误差结果是否处于第二误差范围内。
可选地,射频单元1001,具体用于:
向第二设备发送第二误差反馈信息;第二误差反馈信息用于反馈以下至少一项:第一模型的输出结果与第二模型的输出结果是否一致、第一模型的输出结果与第二模型的输出结果之间的第一误差结果或第一误差结果超出第一误差范围的指示信息。
可选地,射频单元1001,具体用于:
在目标模式为第三模式或第四模式的情况下,向第二设备发送第一反馈信息,第一反馈信息包括以下至少一项:第一模型的输入信息、测量信息;
接收第二设备发送的第二模型的输出结果;第二模型的输出结果为基于第一反馈信息得到的。
可选地,射频单元1001,具体用于:
在目标模式为第一模式的情况下,向第二设备发送第一反馈信息,第一反馈信息包括第一模型的输出结果以及以下至少一项:第一模型的输入信息、测量信息;
接收第二设备发送的第二模型的输出结果;
处理器1010,具体用于:
使用第一模型的输出结果确定传输参数,满足以下至少一项:
第一模型的输出结果和第二模型的输出结果一致;
第一模型和/或第二模型的输出结果生效;
第一模型和/或第二模型的功能生效;
和第二设备通过信令交互确定的传输参数一致。
可选地,在目标模式为第三模式的情况下,射频单元1001,具体用于:
向第二设备发送第一反馈信息,第一反馈信息包括以下至少一项:第一模型的输入信息、测量信息;
接收第二设备发送的第二模型的输出结果;
处理器1010,具体用于:
使用第一模型的输出结果确定传输参数,满足以下至少一项:
第一模型的输出结果和第二模型的输出结果一致;
第一模型和/或第二模型的输出结果生效;
第一模型和/或第二模型的功能生效;
终端和第二设备通过信令交互确定的传输参数一致。
可选地,在终端和第二设备确定的传输参数不一致的情况下,射频单元1001,具体用于:
接收第二设备发送的第二指示信息,第二指示信息用于指示终端调整第一模型的模型参数,和/或调整目标模式。
可选地,射频单元1001,具体用于:
接收第二设备发送的第二反馈信息,第二反馈信息包括以下至少一项:第二模型的输出结果、第二模型的输入信息、测量信息。
可选地,目标模式为周期性生效或行为触发生效的。
可选地,终端和第二设备交互的反馈信息中包括以下至少一项:
第一模型和/或第二模型的输出结果中全部输出参数;
第一模型和/或第二模型的输出结果中至少部分输出参数;
第一模型和/或第二模型的输出结果中预配置、配置或协议预定义的上报的输出参数;
第一模型和/或第二模型中输入参数数量;
第一模型和/或第二模型中输出参数数量;
第一模型和/或第二模型中所有输入参数;
第一模型和/或第二模型中至少部分输入参数;
第一模型和/或第二模型中预配置、配置或协议预定义的上报的输入参数;
终端和第二设备的反馈信息关联的输入参数;
终端和第二设备的反馈信息关联的参考信号ID;
终端和第二设备的反馈信息关联的参考信号对应的波束相关信息;
终端和第二设备的反馈信息关联的参考信号对应的角度相关信息;
波束相关信息;
角度相关信息;
波束确认信息;
指定波束信息。
可选地,输入参数和/或输出参数为以下至少一个周期的参数,以下至少一个周期包括:最近周期、当前周期或反馈报告关联的周期。
可选地,终端和第二设备交互的反馈信息包括第一模型或第二模型的输出结果时,还包括以下至少一项:反馈端模型的输入信息和反馈端测量信息。
可选地,终端和第二设备交互的反馈信息中包括的参数的顺序为按照预配置、配置或协议预定义确定的。
可选地,在传输参数包括波束信息的情况下,输出结果包括以下至少一项:
空间相关信息;时间相关信息;波束质量信息;波束ID;角度信息。
本申请实施例中第一设备还可以是网络侧设备。具体地,本申请实施例还提供了一种网络侧设备。如图8所示,该网络侧设备700包括:天线71、射频装置72、基带装置73、处理器75和存储器75。天线71与射频装置72连接。在上行方向上,射频装置72通过天线71接收信息,将接收的信息发送给基带装置73进行处理。在下行方向上,基带装置73对要发送的信息进行处理,并发送给射频装置72,射频装置72对收到的信息进行处理后经过天线71发送出去。
上述频带处理装置可以位于基带装置73中,以上实施例中网络侧设备执行的方法可以在基带装置73中实现,该基带装置73包括基带处理器75和存储器75。
基带装置73例如可以包括至少一个基带板,该基带板上设置有多个芯片,如图8所示,其中一个芯片例如为基带处理器75,通过总线接口与存储器75连接,以调用存储器75中的程序,执行以上方法实施例中所示的网络设备操 作。
该基带装置73网络侧设备还可以包括网络接口76,用于与射频装置72交互信息,该接口例如为通用公共无线接口(common public radio interface,简称CPRI)。
具体地,本发明实施例的网络侧设备700还包括:存储在存储器75上并可在处理器75上运行的指令或程序,处理器75调用存储器75中的指令或程序执行图4或图5所示各模块执行的方法,并达到相同的技术效果,为避免重复,故不在此赘述。
第二设备与第一设备类似,此处不再赘述,
本申请实施例还提供一种可读存储介质,所述可读存储介质上存储有程序或指令,该程序或指令被处理器执行时实现上述传输方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
其中,所述处理器为上述实施例中所述的终端中的处理器。所述可读存储介质,包括计算机可读存储介质,如计算机只读存储器ROM、随机存取存储器RAM、磁碟或者光盘等。
本申请实施例另提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现上述传输方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
应理解,本申请实施例提到的芯片还可以称为系统级芯片,系统芯片,芯片系统或片上系统芯片等。
本申请实施例另提供了一种计算机程序/程序产品,所述计算机程序/程序产品被存储在存储介质中,所述计算机程序/程序产品被至少一个处理器执行以实现上述传输方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
本申请实施例还提供了一种通信系统,包括:终端及网络侧设备,所述终端可用于执行如上所述的传输方法的步骤,所述网络侧设备可用于执行如 上所述的传输方法的步骤。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外,需要指出的是,本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能,还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能,例如,可以按不同于所描述的次序来执行所描述的方法,并且还可以添加、省去、或组合各种步骤。另外,参照某些示例所描述的特征可在其他示例中被组合。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以计算机软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例所述的方法。上面结合附图对本申请的实施例进行了描述,但是本申请并不局限于上述的具体实施方式,上述的具体实施方式仅仅是示意性的,而不是限制性的,本领域的普通技术人员在本申请的启示下,在不脱离本申请宗旨和权利要求所保护的范围情况下,还可做出很多形式,均属于本申请的保护之内。

Claims (50)

  1. 一种传输方法,包括:
    第一设备获取目标模型的输出结果,所述目标模型包括所述第一设备的第一模型和/或第二设备的第二模型;所述第一模型与所述第二模型具有相关性;
    所述第一设备根据所述目标模型的输出结果确定传输参数。
  2. 根据权利要求1所述的传输方法,其中,
    所述第一模型与所述第二模型具有相关性,满足以下至少一项:
    所述第一模型与所述第二模型相同;
    所述第一模型为基于所述第一模型和/或第二模型进行第一目标处理得到的。
  3. 根据权利要求2所述的传输方法,其中,所述基于所述第一模型和/或第二模型进行第一目标处理包括以下至少一项:
    基于所述第二模型的输出结果进行对所述第一模型进行训练;
    对所述第二模型的网络结构进行第二目标处理;
    对所述第二模型的参数进行量化;
    对所述第二模型进行分解处理;
    对所述第二模型进行教师学生方式的模型生成处理,所述第一模型为所述第二模型的学生模型或子模型;
    其中,所述第二目标处理包括以下至少一项:剪枝、删减和增加;
    所述分解处理包括以下至少一项:张量分解和低秩分解。
  4. 根据权利要求1-3任一项所述的传输方法,其中,所述第一设备的第一模型是通过以下至少一种方式获取到的:
    所述第一设备从第三设备获取到的;
    所述第一设备从所述第二设备获取到的,所述第一模型为所述第二设备从所述第三设备获取到的,或所述第二设备生成的;
    所述第一设备生成的。
  5. 根据权利要求2或3所述的传输方法,其中,所述基于所述第一模型和/或第二模型进行第一目标处理,包括以下至少一项:
    通过所述第二设备基于所述第一模型和/或第二模型进行第一目标处理;
    通过第三设备基于所述第一模型和/或第二模型进行第一目标处理;
    通过所述第一设备基于所述第一模型和/或第二模型进行第一目标处理。
  6. 根据权利要求1-3任一项所述的传输方法,其中,所述方法还包括:
    所述第一设备向所述第二设备发送所述第一模型的能力信息;和/或,
    所述第一设备基于所述第一模型的能力信息向所述第二设备发送请求消息,所述请求消息用于请求所述传输参数相关的第一信息;和/或,
    所述第一设备根据所述第一模型的输出结果向所述第二设备发送第一指示信息,所述第一指示信息用于指示所述传输参数相关的第二信息。
  7. 根据权利要求6所述的传输方法,其中,所述第一信息和/或第二信息包括以下至少一项:
    发送波束信息、接收波束信息和发送接收波束对信息。
  8. 根据权利要求7所述的传输方法,其中,
    所述发送波束信息包括以下至少一项:发送波束数量、发送波束重复次数、增加发送波束数量差值、减小发送波束数量差值、增加发送波束重复次数差值、减小发送波束重复次数差值增加发送波束数量指示、减小发送波束数量指示、增加发送波束重复次数指示、减小发送波束数量指示、达到目标值的最少发送波束数量、达到目标精度值的最少发送波束数量、达到目标值的最少发送波束次数或达到目标精度值的最少发送波束次数;
    所述接收波束信息包括以下至少一项:接收波束数量、接收波束重复次数、增加接收波束数量差值、减小接收波束数量差值、增加接收波束重复次数差值、减小接收波束重复次数差值、增加接收波束数量指示、减小接收波束数量指示、增加接收波束重复次数指示或减小接收波束数量指示;
    所述发送接收波束对信息包括以下至少一项:发送接收波束对数量、发 送接收波束对重复次数、增加发送接收波束对数量差值、减小发送接收波束对数量差值、增加发送接收波束对重复次数差值、减小发送接收波束对重复次数差值、增加发送接收波束对数量指示、减小发送接收波束对数量指示、增加发送接收波束对重复次数指示、减小发送接收波束对数量指示。
  9. 根据权利要求1或2所述的传输方法,其中,所述第一设备根据所述目标模型的输出结果确定传输参数,包括:
    所述第一设备根据所述目标模型的输出结果以及目标模式确定传输参数;所述目标模式包括以下任一模式:第一模式、第二模式、第三模式和第四模式;
    其中,所述第一模式为所述第一设备输出第一反馈信息,且所述第一反馈信息包括所述第一模型的输出结果的模式;所述第二模式为所述第一设备输出第一反馈信息,所述第一反馈信息包括所述第一模型的输出结果,且所述第一反馈信息用于对所述第二模型进行调整的模式,所述第三模式为所述第一设备输出第一反馈信息,所述第一反馈信息不包括所述第一模型的输出结果,且所述第二设备输出基于所述第一反馈信息得到的第二模型的输出结果的模式,所述第四模式为所述第一设备输出第一反馈信息,所述第一反馈信息不包括所述第一模型的输出结果,所述第二设备输出基于所述第一反馈信息得到的第二模型的输出结果,且所述第二模型的输出结果用于对所述第一模型进行调整的模式。
  10. 根据权利要求9所述的传输方法,其中,在所述目标模式为所述第一模式或所述第二模式的情况下,所述方法还包括:
    所述第一设备向所述第二设备发送所述第一反馈信息,所述第一反馈信息包括所述第一模型的输出结果以及以下至少一项:所述第一模型的输入信息、测量信息;
    所述第一反馈信息用于所述第二设备确定传输参数。
  11. 根据权利要求10所述的传输方法,其中,所述方法还包括:
    所述第一设备接收所述第二设备发送的第一误差反馈信息,所述第一误 差反馈信息用于反馈以下至少一项:所述第一模型的输出结果与所述第二模型的输出结果是否一致、所述第一模型的输出结果与所述第二模型的输出结果之间的第一误差结果或所述第一误差结果超出第一误差范围的指示信息。
  12. 根据权利要求9所述的传输方法,其中,在所述目标模式为所述第三模式或所述第四模式的情况下,所述方法还包括:
    所述第一设备接收所述第二设备发送的第二反馈信息,所述第二反馈信息包括以下至少一项:所述第二模型的输出结果、所述第二模型的输入信息、测量信息;
    所述第二反馈信息用于所述第一设备确定传输参数。
  13. 根据权利要求12所述的传输方法,其中,所述第一设备根据所述目标模型的输出结果以及目标模式确定传输参数,包括:
    所述第一设备根据所述第二反馈信息对所述第一模型进行调整,得到调整后的第一模型;和/或,
    所述第一设备确定所述第一模型的输出结果与所述第二模型的输出结果是否一致,或所述第一模型的输出结果与所述第二模型的输出结果之间的第二误差结果是否处于第二误差范围内。
  14. 根据权利要求12所述的传输方法,其中,所述方法还包括:
    所述第一设备向所述第二设备发送第二误差反馈信息;所述第二误差反馈信息用于反馈以下至少一项:所述第一模型的输出结果与所述第二模型的输出结果是否一致、所述第一模型的输出结果与所述第二模型的输出结果之间的第二误差结果或所述第二误差结果超出第二误差范围的指示信息。
  15. 根据权利要求9所述的传输方法,其中,在所述目标模式为第三模式或第四模式的情况下,所述方法还包括:
    所述第一设备向所述第二设备发送所述第一反馈信息,所述第一反馈信息包括以下至少一项:所述第一模型的输入信息、测量信息;
    所述第一设备接收所述第二设备发送的所述第二模型的输出结果;所述第二模型的输出结果为基于所述第一反馈信息得到的。
  16. 根据权利要求9所述的传输方法,其中,在所述目标模式为第一模式的情况下,所述方法还包括:
    所述第一设备向所述第二设备发送所述第一反馈信息,所述第一反馈信息包括所述第一模型的输出结果以及以下至少一项:所述第一模型的输入信息、测量信息;
    所述第一设备接收所述第二设备发送的所述第二模型的输出结果;
    所述第一设备根据所述目标模型的输出结果以及目标模式确定传输参数,包括:
    所述第一设备使用所述第一模型的输出结果确定传输参数,满足以下至少一项:
    所述第一模型的输出结果和所述第二模型的输出结果一致;
    所述第一模型和/或所述第二模型的输出结果生效;
    所述第一模型和/或所述第二模型的功能生效;
    所述第一设备和所述第二设备通过信令交互确定的传输参数一致。
  17. 根据权利要求9所述的传输方法,其中,在所述目标模式为第三模式的情况下,所述方法还包括:
    所述第一设备向所述第二设备发送所述第一反馈信息,所述第一反馈信息包括以下至少一项:所述第一模型的输入信息、测量信息;
    所述第一设备接收所述第二设备发送的所述第二模型的输出结果;
    所述第一设备根据所述目标模型的输出结果以及目标模式确定传输参数,包括:
    所述第一设备使用所述第一模型的输出结果确定传输参数,满足以下至少一项:
    所述第一模型的输出结果和所述第二模型的输出结果一致;
    所述第一模型和/或所述第二模型的输出结果生效;
    所述第一模型和/或所述第二模型的功能生效;
    所述第一设备和所述第二设备通过信令交互确定的传输参数一致。
  18. 根据权利要求16或17所述的传输方法,其中,在所述第一设备和所述第二设备确定的传输参数不一致的情况下,所述方法还包括:
    所述第一设备接收所述第二设备发送的第二指示信息,所述第二指示信息用于指示所述第一设备调整所述第一模型的模型参数和/或调整所述目标模式。
  19. 根据权利要求18所述的传输方法,其中,所述方法还包括:
    所述第一设备接收所述第二设备发送的第二反馈信息,所述第二反馈信息包括以下至少一项:所述第二模型的输出结果、所述第二模型的输入信息、测量信息。
  20. 根据权利要求9所述的传输方法,其中,
    所述目标模式为周期性生效或行为触发生效的。
  21. 根据权利要求9-20任一项所述的传输方法,其中,
    所述第一设备和第二设备交互的反馈信息中包括以下至少一项:
    所述第一模型和/或第二模型的输出结果中全部输出参数;
    所述第一模型和/或第二模型的输出结果中至少部分输出参数;
    所述第一模型和/或第二模型的输出结果中预配置、配置或协议预定义的上报的输出参数;
    所述第一模型和/或第二模型中输入参数数量;
    所述第一模型和/或第二模型中输出参数数量;
    所述第一模型和/或第二模型中所有输入参数;
    所述第一模型和/或第二模型中至少部分输入参数;
    所述第一模型和/或第二模型中预配置、配置或协议预定义的上报的输入参数;
    所述第一设备和第二设备的反馈信息关联的输入参数;
    所述第一设备和第二设备的反馈信息关联的参考信号ID;
    所述第一设备和第二设备的反馈信息关联的参考信号对应的波束相关信息;
    所述第一设备和第二设备的反馈信息关联的参考信号对应的角度相关信息;
    波束相关信息;
    角度相关信息;
    波束确认信息;
    指定波束信息。
  22. 根据权利要求21所述的传输方法,其中,
    所述输入参数和/或输出参数为以下至少一个周期的参数,所述以下至少一个周期包括:最近周期、当前周期或反馈信息关联的周期。
  23. 根据权利要求9-20任一项所述的传输方法,其中,
    所述第一设备和第二设备交互的反馈信息包括第一模型或第二模型的输出结果时,还包括以下至少一项:反馈端模型的输入信息和反馈端测量信息。
  24. 根据权利要求9-20任一项所述的传输方法,其中,
    所述第一设备和第二设备交互的反馈信息中包括的参数的顺序为按照预配置、配置或协议预定义确定的。
  25. 根据权利要求1-3任一项所述的传输方法,其中,在所述传输参数包括波束信息的情况下,所述输出结果包括以下至少一项:
    空间相关信息;时间相关信息;波束质量信息。
  26. 根据权利要求1-3任一项所述的传输方法,其中,
    所述第一设备为以下任一:终端、网络侧设备或辅助网络中心单元,所述第二设备为以下任一:终端、网络侧设备或辅助网络中心单元。
  27. 一种传输方法,包括:
    第二设备获取目标模型的输出结果,所述目标模型包括第一设备的第一模型和/或第二设备的第二模型;所述第一模型与所述第二模型具有相关性;
    所述第二设备根据所述目标模型的输出结果确定传输参数。
  28. 根据权利要求27所述的传输方法,其中,
    所述第一模型与所述第二模型具有相关性,满足以下至少一项:
    所述第一模型与所述第二模型相同;
    所述第一模型为基于所述第一模型和/或第二模型进行第一目标处理得到的。
  29. 根据权利要求28所述的传输方法,其中,所述基于所述第一模型和/或第二模型进行第一目标处理包括以下至少一项:
    基于所述第二模型的输出结果进行对所述第一模型进行训练;
    对所述第二模型的网络结构进行第二目标处理;
    对所述第二模型的参数进行量化;
    对所述第二模型进行分解处理;
    对所述第二模型进行教师学生方式的模型生成处理,所述第一模型为所述第二模型的学生模型或子模型;
    其中,所述第二目标处理包括以下至少一项:剪枝、删减和增加;
    所述分解处理包括以下至少一项:张量分解和低秩分解。
  30. 根据权利要求27-29任一项所述的传输方法,其中,所述第二设备的第二模型是通过以下至少一种方式获取到的:
    所述第二设备从第三设备获取到的;
    所述第二设备从所述第一设备获取到的,所述第二模型为所述第一设备从所述第三设备获取到的,或所述第一设备生成的;
    所述第二设备生成的。
  31. 根据权利要求28或29所述的传输方法,其中,所述基于所述第一模型和/或第二模型进行第一目标处理,包括以下至少一项:
    通过所述第二设备基于所述第一模型和/或第二模型进行第一目标处理;
    通过第三设备基于所述第一模型和/或第二模型进行第一目标处理;
    通过所述第一设备基于所述第一模型和/或第二模型进行第一目标处理。
  32. 根据权利要求27-29任一项所述的传输方法,其中,所述方法还包括:
    所述第二设备接收所述第一设备发送的所述第一模型的能力信息;和/或,
    所述第二设备向所述第一设备发送响应消息,所述响应消息为基于所述 第一设备发送的请求消息发送的,所述响应消息用于携带所述传输参数相关的第一信息;和/或,
    所述第二设备接收所述第一设备发送的第一指示信息,所述第一指示信息用于指示所述传输参数相关的第二信息。
  33. 根据权利要求32所述的传输方法,其中,所述第一信息和/或第二信息包括以下至少一项:
    发送波束信息、接收波束信息和发送接收波束对信息。
  34. 根据权利要求33所述的传输方法,其中,
    所述发送波束信息包括以下至少一项:发送波束数量、发送波束重复次数、增加发送波束数量差值、减小发送波束数量差值、增加发送波束重复次数差值、减小发送波束重复次数差值增加发送波束数量指示、减小发送波束数量指示、增加发送波束重复次数指示、减小发送波束数量指示、达到目标值的最少发送波束数量、达到目标精度值的最少发送波束数量、达到目标值的最少发送波束次数或达到目标精度值的最少发送波束次数;
    所述接收波束信息包括以下至少一项:接收波束数量、接收波束重复次数、增加接收波束数量差值、减小接收波束数量差值、增加接收波束重复次数差值、减小接收波束重复次数差值、增加接收波束数量指示、减小接收波束数量指示、增加接收波束重复次数指示或减小接收波束数量指示;
    所述发送接收波束对信息包括以下至少一项:发送接收波束对数量、发送接收波束对重复次数、增加发送接收波束对数量差值、减小发送接收波束对数量差值、增加发送接收波束对重复次数差值、减小发送接收波束对重复次数差值、增加发送接收波束对数量指示、减小发送接收波束对数量指示、增加发送接收波束对重复次数指示、减小发送接收波束对数量指示。
  35. 根据权利要求27-29任一项所述的传输方法,其中,所述第二设备根据所述目标模型的输出结果确定传输参数,包括:
    所述第二设备根据所述目标模型的输出结果以及目标模式确定传输参数;所述目标模式包括以下任一模式:第一模式、第二模式、第三模式和第四模 式;
    其中,所述第一模式为所述第一设备输出第一反馈信息,且所述第一反馈信息包括所述第一模型的输出结果的模式;所述第二模式为所述第一设备输出第一反馈信息,所述第一反馈信息包括所述第一模型的输出结果,且所述第一反馈信息用于对所述第二模型进行调整的模式,所述第三模式为所述第一设备输出第一反馈信息,所述第一反馈信息不包括所述第一模型的输出结果,且所述第二设备输出基于所述第一反馈信息得到的第二模型的输出结果的模式,所述第四模式为所述第一设备输出第一反馈信息,所述第一反馈信息不包括所述第一模型的输出结果,所述第二设备输出基于所述第一反馈信息得到的第二模型的输出结果,且所述第二模型的输出结果用于对所述第一模型进行调整的模式。
  36. 根据权利要求35所述的传输方法,其中,在所述目标模式为所述第一模式或所述第二模式的情况下,所述方法还包括:
    所述第二设备接收所述第一设备发送的第一反馈信息,所述第一反馈信息包括所述第一模型的输出结果以及以下至少一项:所述第一模型的输入信息、测量信息;
    所述第一反馈信息用于所述第二设备确定传输参数。
  37. 根据权利要求36所述的传输方法,其中,所述方法还包括:
    所述第二设备向所述第一设备发送第一误差反馈信息,所述第一误差反馈信息用于反馈以下至少一项:所述第一模型的输出结果与所述第二模型的输出结果是否一致、所述第一模型的输出结果与所述第二模型的输出结果之间的第一误差结果或所述第一误差结果超出第一误差范围的指示信息。
  38. 根据权利要求36所述的传输方法,其中,所述第一设备根据所述目标模型的输出结果以及目标模式确定传输参数,包括:
    所述第二设备根据所述第一反馈信息对所述第二模型进行调整,得到调整后的第二模型;和/或,
    所述第二设备确定所述第一模型的输出结果与所述第二模型的输出结果 是否一致,或所述第一模型的输出结果与所述第二模型的输出结果之间的第一误差结果是否处于第一误差范围内。
  39. 根据权利要求35所述的传输方法,其中,在所述目标模式为所述第三模式或所述第四模式的情况下,所述方法还包括:
    所述第二设备向所述第一设备发送第二反馈信息,所述第二反馈信息包括以下至少一项:所述第二模型的输出结果、所述第二模型的输入信息、测量信息;
    所述第二反馈信息用于所述第一设备确定传输参数。
  40. 根据权利要求39所述的传输方法,其中,所述方法还包括:
    所述第二设备接收所述第一设备发送的第二误差反馈信息;所述第二误差反馈信息用于反馈以下至少一项:所述第一模型的输出结果与所述第二模型的输出结果是否一致、所述第一模型的输出结果与所述第二模型的输出结果之间的第一误差结果或所述第一误差结果超出第一误差范围的指示信息。
  41. 根据权利要求35所述的传输方法,其中,在所述目标模式为第三模式或第四模式的情况下,所述方法还包括:
    所述第二设备接收所述第一设备发送的所述第一反馈信息,所述第一反馈信息包括以下至少一项:所述第一模型的输入信息、测量信息;
    所述第二设备向所述第一设备发送所述第二模型的输出结果;所述第二模型的输出结果为基于所述第一反馈信息得到的。
  42. 根据权利要求35所述的传输方法,其中,在所述目标模式为第一模式的情况下,所述方法还包括:
    所述第二设备接收所述第一设备发送的所述第一反馈信息,所述第一反馈信息包括所述第一模型的输出结果以及以下至少一项:所述第一模型的输入信息、测量信息;
    所述第二设备向所述第一设备发送所述第二模型的输出结果;
    所述第二设备根据所述目标模型的输出结果以及目标模式确定传输参数,包括:
    所述第二设备使用所述第一模型的输出结果或所述第二模型的输出结果确定传输参数,满足以下至少一项:
    所述第一模型的输出结果和所述第二模型的输出结果一致;
    所述第一模型和/或所述第二模型的输出结果生效;
    所述第一模型和/或所述第二模型的功能生效;
    所述第一设备和所述第二设备通过信令交互确定的传输参数一致。
  43. 根据权利要求35所述的传输方法,其中,在所述目标模式为第三模式的情况下,所述方法还包括:
    所述第二设备接收所述第一设备发送的所述第一反馈信息,所述第一反馈信息包括以下至少一项:所述第一模型的输入信息、测量信息;
    所述第二设备向所述第一设备发送所述第二模型的输出结果;
    所述第二设备根据所述目标模型的输出结果以及目标模式确定传输参数,包括:
    所述第二设备使用所述第一模型的输出结果或所述第二模型的输出结果确定传输参数,满足以下至少一项:
    所述第一模型的输出结果和所述第二模型的输出结果一致;
    所述第一模型和/或所述第二模型的输出结果生效;
    所述第一模型和/或所述第二模型的功能生效;
    所述第一设备和所述第二设备通过信令交互确定的传输参数一致。
  44. 根据权利要求42或43所述的传输方法,其中,在所述第一设备和所述第二设备确定的传输参数不一致的情况下,所述方法还包括:
    所述第二设备向所述第一设备发送第二指示信息,所述第二指示信息用于指示所述第一设备调整所述第一模型的模型参数和/或调整所述目标模式。
  45. 根据权利要求44所述的传输方法,其中,所述方法还包括:
    所述第二设备向所述第一设备发送第二反馈信息,所述第二反馈信息包括以下至少一项:所述第二模型的输出结果、所述第二模型的输入信息、测量信息;所述第二反馈信息用于所述第一设备调整所述第一模型。
  46. 根据权利要求35所述的传输方法,其中,
    所述目标模式为周期性生效或行为触发生效的。
  47. 一种传输装置,包括:
    获取装置,用于获取目标模型的输出结果,所述目标模型包括第一设备的第一模型和/或第二设备的第二模型;所述第一模型与所述第二模型具有相关性;
    处理装置,用于根据所述目标模型的输出结果确定传输参数。
  48. 一种第一设备,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1至26任一项所述的传输方法的步骤。
  49. 一种第二设备,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求27至46任一项所述的传输方法的步骤。
  50. 一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如权利要求1-26任一项所述的传输方法,或者实现如权利要求27至46任一项所述的传输方法的步骤。
PCT/CN2023/071321 2022-01-14 2023-01-09 传输方法、装置和设备 WO2023134628A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210045072.2 2022-01-14
CN202210045072.2A CN116488751A (zh) 2022-01-14 2022-01-14 传输方法、装置和设备

Publications (1)

Publication Number Publication Date
WO2023134628A1 true WO2023134628A1 (zh) 2023-07-20

Family

ID=87210586

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/071321 WO2023134628A1 (zh) 2022-01-14 2023-01-09 传输方法、装置和设备

Country Status (2)

Country Link
CN (1) CN116488751A (zh)
WO (1) WO2023134628A1 (zh)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111478783A (zh) * 2019-01-23 2020-07-31 中国移动通信有限公司研究院 一种配置无线传输参数的方法和设备
CN112152948A (zh) * 2019-06-28 2020-12-29 华为技术有限公司 一种无线通信处理的方法和装置
CN112152741A (zh) * 2019-06-28 2020-12-29 华为技术有限公司 信道模型的训练方法及装置
WO2021022479A1 (zh) * 2019-08-06 2021-02-11 华为技术有限公司 波束赋形方法、装置、无线接入网设备及可读存储介质
CN112512069A (zh) * 2021-02-02 2021-03-16 网络通信与安全紫金山实验室 基于信道波束图样的网络智能优化方法及装置
WO2021112592A1 (ko) * 2019-12-03 2021-06-10 엘지전자 주식회사 무선 통신 시스템에서 인공 지능 기반의 빔 관리 방법 및 이에 대한 장치
US20210185515A1 (en) * 2019-12-16 2021-06-17 Qualcomm Incorporated Neural network configuration for wireless communication system assistance
WO2021175103A1 (zh) * 2020-03-06 2021-09-10 华为技术有限公司 通信方法及装置

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111478783A (zh) * 2019-01-23 2020-07-31 中国移动通信有限公司研究院 一种配置无线传输参数的方法和设备
CN112152948A (zh) * 2019-06-28 2020-12-29 华为技术有限公司 一种无线通信处理的方法和装置
CN112152741A (zh) * 2019-06-28 2020-12-29 华为技术有限公司 信道模型的训练方法及装置
WO2021022479A1 (zh) * 2019-08-06 2021-02-11 华为技术有限公司 波束赋形方法、装置、无线接入网设备及可读存储介质
WO2021112592A1 (ko) * 2019-12-03 2021-06-10 엘지전자 주식회사 무선 통신 시스템에서 인공 지능 기반의 빔 관리 방법 및 이에 대한 장치
US20210185515A1 (en) * 2019-12-16 2021-06-17 Qualcomm Incorporated Neural network configuration for wireless communication system assistance
WO2021175103A1 (zh) * 2020-03-06 2021-09-10 华为技术有限公司 通信方法及装置
CN112512069A (zh) * 2021-02-02 2021-03-16 网络通信与安全紫金山实验室 基于信道波束图样的网络智能优化方法及装置

Also Published As

Publication number Publication date
CN116488751A (zh) 2023-07-25

Similar Documents

Publication Publication Date Title
US20230262506A1 (en) Beam reporting method, beam information determining method, and related device
WO2023185978A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023134628A1 (zh) 传输方法、装置和设备
WO2023134761A1 (zh) 波束信息交互方法、装置、设备及存储介质
WO2024041421A1 (zh) 测量反馈处理方法、装置、终端及网络侧设备
WO2024041420A1 (zh) 测量反馈处理方法、装置、终端及网络侧设备
WO2024046206A1 (zh) 接收方法、设备及可读存储介质
WO2024041419A1 (zh) 信息传输方法、装置、终端及网络侧设备
WO2024032606A1 (zh) 信息传输方法、装置、设备、系统及存储介质
WO2024046202A1 (zh) 发送方法、用户设备、网络侧设备及可读存储介质
WO2024093713A1 (zh) 资源配置方法、装置、通信设备及可读存储介质
WO2023160456A1 (zh) 信道信息上报方法、装置、网络侧设备、终端及介质
WO2024067281A1 (zh) Ai模型的处理方法、装置及通信设备
WO2024067665A1 (zh) Csi预测处理方法、装置、通信设备及可读存储介质
WO2024032694A1 (zh) Csi预测处理方法、装置、通信设备及可读存储介质
WO2024088161A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024088162A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024104070A1 (zh) 波束报告的发送方法、接收方法、装置及通信设备
WO2024037380A1 (zh) 信道信息处理方法、装置、通信设备及存储介质
WO2024067280A1 (zh) 更新ai模型参数的方法、装置及通信设备
WO2024027683A1 (zh) 模型匹配方法、装置、通信设备及可读存储介质
WO2024032695A1 (zh) Csi预测处理方法、装置、通信设备及可读存储介质
WO2023040888A1 (zh) 数据传输方法及装置
WO2023179476A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
CN117411527A (zh) 信道特征信息上报及恢复方法、终端和网络侧设备

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: 23739970

Country of ref document: EP

Kind code of ref document: A1