WO2024093771A1

WO2024093771A1 - Reference signal determination methods, terminal, and network side device

Info

Publication number: WO2024093771A1
Application number: PCT/CN2023/126672
Authority: WO
Inventors: 袁江伟; 孙鹏; 刘昊; 宋扬; 吴昊; 王臣玺
Original assignee: 维沃移动通信有限公司
Priority date: 2022-10-31
Filing date: 2023-10-26
Publication date: 2024-05-10
Also published as: CN117997457A

Abstract

Disclosed in the present application are reference signal determination methods, a terminal and a network side device, belonging to the technical field of communications. A reference signal determination method of the embodiments of the present application comprises: a terminal determines at least one of a first CSI-RS, a second CSI-RS and a third CSI-RS, the first CSI-RS being used for channel prediction, the second CSI-RS being used for training a prediction model, and the third CSI-RS being used for monitoring the channel prediction performance of the terminal.

Description

Reference signal determination method, terminal and network side equipment

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese Patent Application No. 202211352315.3 filed in China on October 31, 2022, the entire contents of which are incorporated herein by reference.

Technical Field

The present application belongs to the field of communication technology, and specifically relates to a reference signal determination method, a terminal, and a network side device.

Background technique

At present, the terminal mainly performs channel prediction based on the channel state information reference signal (CSI-RS). In other words, the CSI-RS transmitted between target communication devices is always used for channel prediction, which leads to poor transmission performance between communication devices.

Summary of the invention

The embodiments of the present application provide a reference signal determination method, a terminal, and a network-side device, which can solve the problem of poor transmission performance between communication devices.

In a first aspect, a reference signal determination method is provided, comprising:

The terminal determines at least one of a first CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

In a second aspect, a reference signal determination method is provided, comprising:

The network side device sends network signaling to the terminal, and the network signaling is used by the terminal to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

According to a third aspect, a reference signal determination device is provided, including:

A determination module is used for the terminal to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

In a fourth aspect, a reference signal determination device is provided, including:

The first sending module is used to send network signaling to the terminal, where the network signaling is used by the terminal to determine the first channel measurement At least one of a reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

In a fifth aspect, a terminal is provided, which includes a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the reference signal determination method on the terminal side as provided in an embodiment of the present application are implemented.

In a sixth aspect, a terminal is provided, comprising a processor and a communication interface, wherein the processor is used to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

In the seventh aspect, a network side device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the reference signal determination method on the network side device side provided in an embodiment of the present application are implemented.

In the eighth aspect, a network side device is provided, comprising a processor and a communication interface, wherein the communication interface is used to send network signaling to a terminal, and the network signaling is used by the terminal to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

In the ninth aspect, a reference signal determination system is provided, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the reference signal determination method on the terminal side as provided in the embodiment of the present application, and the network side device can be used to execute the steps of the reference signal determination method on the network side device side as provided in the embodiment of the present application.

In the tenth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the reference signal determination method on the terminal side as provided in the embodiment of the present application are implemented, or the steps of the reference signal determination method on the network side device side as provided in the embodiment of the present application are implemented.

In the eleventh aspect, a chip is provided, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement a reference signal determination method on the terminal side as provided in an embodiment of the present application, or to implement a reference signal determination method on the network side device side as provided in an embodiment of the present application.

In the twelfth aspect, a computer program/program product is provided, wherein 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 steps of the reference signal determination method on the terminal side as provided in the embodiment of the present application, or the computer program/program product is executed by at least one processor to implement the steps of the reference signal determination method on the network side device side as provided in the embodiment of the present application.

In the embodiment of the present application, the terminal determines at least one of the first CSI-RS, the second CSI-RS and the third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal. In this way, the CSI-RS transmitted between communication devices can support multiple uses, thereby improving the transmission performance between communication devices.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a block diagram of a wireless communication system to which an embodiment of the present application can be applied;

FIG2 is a flow chart of a reference signal determination method provided in an embodiment of the present application;

FIG3 is a flow chart of another reference signal determination method provided in an embodiment of the present application;

FIG4 is a structural diagram of a reference signal determination device provided in an embodiment of the present application;

FIG5 is a structural diagram of another reference signal determination device provided in an embodiment of the present application;

FIG6 is a structural diagram of a communication device provided in an embodiment of the present application;

FIG7 is a structural diagram of a terminal provided in an embodiment of the present application;

FIG8 is a structural diagram of a network-side device provided in an embodiment of the present application.

Detailed ways

The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of this application.

The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and/or" in the specification and claims represents at least one of the connected objects, and the character "/" generally represents that the objects associated with each other are in an "or" relationship.

It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE)/LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency Division Multiple Access (SC-FDMA) and other systems. The terms "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 systems and radio technologies as well as other systems and radio technologies. The following description describes a new radio (NR) system for example purposes, and NR terms are used in most of the following descriptions, but these technologies can also be applied to applications other than NR system applications, such as the ^6th Generation (6G) communication system.

FIG1 is a block diagram of a wireless communication system applicable to the embodiment of the present application. The wireless communication system includes a terminal 11 and a network side device 12. The terminal 11 may 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 palm computer, a netbook, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), Mobile Internet Device (MID), augmented reality (AR)/virtual reality (VR) equipment, robot, wearable device (Wearable Device), vehicle user equipment (VUE), pedestrian terminal (PUE), smart home (home equipment with wireless communication function, such as refrigerator, TV, washing machine or furniture, etc.), game console, personal computer (PC), teller machine or self-service machine and other terminal side equipment, wearable devices include: smart watch, smart bracelet, smart headset, smart glasses, smart jewelry (smart bracelet, smart bracelet, smart ring, smart necklace, smart anklet, smart anklet, etc.), smart wristband, smart clothing, etc. It should be noted that the specific type of terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include access network equipment or core network equipment, wherein the access network equipment may also be called wireless access network equipment, wireless access network (RAN), wireless access network function or wireless access network unit. The access network equipment may include a base station, a wireless local area network (WLAN) access point or a WiFi node, etc. The base station may be referred to as a node B, an evolved node B (eNB), an access point, a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home node B, a home evolved node B, a transmission reception point (TRP) or some other suitable term in the field. 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 the embodiment of the present 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 core network equipment may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (Mobility Management Entity, MME), access mobility management function (Access and Mobility Management Function, AMF), session management function (Session Management Function, SMF), user plane function (User Plane Function, UPF), policy control function (Policy Control Function, PCF), policy and charging rules function unit (Policy and Charging Rules Function, PCRF), edge application service discovery function (Edge Application Server Discovery Function, EASDF), unified data management (Unified Data Management, UDM), unified data storage (Unified Data Repository, UDR), home user server (Home Subscriber Server, HSS), centralized network configuration (CNC), network storage function (Network Repository Function, NRF), network exposure function (Network Exposure Function, NEF), local NEF (Local NEF, or L-NEF), binding support function (Binding Support Function, BSF), application function (Application Function, AF), etc. It should be noted that in the embodiments of the present application, only the core network device in the NR system is introduced as an example, and the specific type of the core network device is not limited.

In the following, in combination with the accompanying drawings, a reference signal determination method, a terminal, and a network side device provided in an embodiment of the present application are described in detail through some embodiments and their application scenarios.

Please refer to FIG. 2 , which is a flow chart of a reference signal determination method provided in an embodiment of the present application. As shown in FIG. 2 , the method includes the following steps:

Step 201: The terminal determines at least one of a first CSI-RS, a second CSI-RS, and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

The terminal determines the first CSI-RS by determining the first CSI-RS for channel prediction based on at least one of network-side signaling, default rules, and the like.

The first CSI-RS may be one or more CSI-RSs, or one or more measurement opportunities of one CSI-RS.

In some implementations, the CSI-RS in the present application may be a channel measurement CSI-RS (CSI-RS for channel measurement, CMR), or other CSI-RS, and the CSI-RS defined in the protocol is not limited to this.

The terminal determines the second CSI-RS by determining the second CSI-RS for the terminal to train a prediction model based on at least one of network-side signaling, default rules, and the like.

The second CSI-RS may be one or more CSI-RSs, or one or more measurement opportunities of one CSI-RS.

The second CSI-RS being used for training the prediction model may be understood as the terminal training the prediction model based on the second CSI-RS.

The above prediction model can be a prediction model for predicting channels, such as: an artificial intelligence (AI) network or an autoregressive (AR) network, or a prediction filter, or a prediction algorithm.

The second CSI-RS used for training the prediction model may be that the second CSI-RS is used for training the AI network model, or the second CSI-RS is used for training the prediction filter, or the second CSI-RS is used for training the AR coefficient, or the second CSI-RS is used for the prediction algorithm.

The terminal determines the third CSI-RS based on at least one of network-side signaling, default rules, etc. to determine the third CSI-RS for monitoring the channel prediction performance of the terminal.

The third CSI-RS may be one or more CSI-RSs, or one or more measurement opportunities of one CSI-RS.

The third CSI-RS is used to monitor the channel prediction performance of the terminal, which can be understood as monitoring or verifying the channel prediction performance of the terminal based on the channel prediction result of the third CSI-RS. For example, the channel obtained by the third CSI-RS is verified with the previously predicted channel result to monitor the channel prediction performance of the terminal.

In addition, the first CSI-RS, the second CSI-RS and the third CSI-RS may be CSI-RS sent by the terminal and received by the network side device. In some implementations, the first CSI-RS, the second CSI-RS and the third CSI-RS may also be CSI-RS sent by other terminals and received by the terminal.

In the embodiment of the present application, the CSI-RS transmitted between communication devices can support multiple uses, thereby improving the transmission performance between communication devices.

In some embodiments, the method may further include the terminal predicting a channel at a future time based on the channel obtained by the first CSI-RS. In addition, the channel at a future time may be predicted based on the channel obtained by the first CSI-RS and a trained prediction model.

In addition, the above method may further include at least one of the following:

Training the prediction model based on the second CSI-RS, for example: training prediction filter coefficients and training an AI network based on the second CSI-RS;

The channel prediction performance of the terminal is monitored or verified based on the third CSI-RS, for example: a channel is acquired based on the third CSI-RS, and the acquired channel is compared with a previous prediction result to acquire the channel prediction performance of the terminal.

In addition, the predicted performance can be fed back to the network side equipment to facilitate network optimization measurement configuration.

In this implementation, the prediction model is trained based on the second CSI-RS, so that the parameters in the prediction model can be more accurate, thereby improving the prediction performance of the terminal. The prediction performance of the terminal can be monitored through the monitoring. In this way, when it is monitored that the prediction performance of the terminal decreases or is relatively poor, the prediction method is optimized, or the network side device optimizes the measurement configuration, thereby improving the prediction performance of the terminal.

As an optional implementation manner, at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are signals of the same CSI-RS at different measurement times;

or,

At least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are different CSI-RSs.

The at least two items mentioned above are the same CMS, which means that the network sends a CSI-RS configuration, and at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are obtained based on the one configuration. The at least two items mentioned above are different CSI-RS, which means that the network sends multiple configurations, and different CSI-RS are CSI-RS obtained according to different configurations.

In addition, at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are signals of the same CSI-RS at different measurement times, which can be understood as at least one of the following:

The first CSI-RS and the second CSI-RS are signals of the same CSI-RS at different measurement times;

The first CSI-RS and the third CSI-RS are signals of the same CSI-RS at different measurement times;

The second CSI-RS and the third CSI-RS are signals of the same CSI-RS at different measurement times;

The first CSI-RS, the second CSI-RS and the third CSI-RS are signals of the same CSI-RS at different measurement times.

In addition, the first CSI-RS may be a signal of one or more measurement opportunities in the signal, the second CSI-RS may be a signal of one or more measurement opportunities in the signal, and the third CSI-RS may be a signal of one or more measurement opportunities in the signal.

Since at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are signals of the same CSI-RS at different measurement times, channel prediction, training of prediction models, and/or monitoring of terminal prediction performance can be achieved through the same signal, so that other signals do not need to be introduced, thereby reducing complexity. For example, training of prediction models, channel prediction, and monitoring of terminal prediction performance can be completed based on multiple measurement times of one CSI-RS.

That at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are different CSI-RSs may be understood as at least one of the following:

The first CSI-RS and the second CSI-RS are the same CSI-RS or different CSI-RSs;

The first CSI-RS and the third CSI-RS are the same CSI-RS or different CSI-RSs;

The second CSI-RS and the third CSI-RS are the same CSI-RS or different CSI-RSs;

The first CSI-RS, the second CSI-RS and the third CSI-RS are different CSI-RSs.

This makes it possible to train prediction models, predict channels, and monitor terminal prediction performance using different CSI-RS. The configuration of the network can be more flexible.

Optionally, when at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are signals of the same CSI-RS at different measurement times: the same CSI-RS is a periodic CSI-RS configured or activated by the network, or the same CSI-RS is a semi-persistent CSI-RS configured or activated by the network, or the same CSI-RS is a non-periodic CSI-RS configured or activated by the network.

The same CSI-RS mentioned above is a periodic CSI-RS configured or activated by the network, and at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are different measurement times of the periodic CSI-RS. For example, the first CSI-RS and the second CSI-RS are different measurement times of the same periodic CSI-RS, and the first CSI-RS and the third CSI-RS are different measurement times of the same periodic CSI-RS.

The same CSI-RS mentioned above is a semi-persistent CSI-RS configured or activated by the network, and at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are different measurement times of the semi-persistent CSI-RS. For example, the first CSI-RS and the second CSI-RS are different measurement times of the same semi-persistent CSI-RS, and the first CSI-RS and the third CSI-RS are different measurement times of the same semi-persistent CSI-RS.

The same CSI-RS mentioned above is a non-periodic CSI-RS that is repeatedly transmitted and configured by the network. It can be that at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are different measurement timings of the repeatedly transmitted non-periodic CSI-RS, for example: the first CSI-RS and the second CSI-RS are different measurement timings of the repeatedly transmitted non-periodic CSI-RS, and the first CSI-RS and the third CSI-RS are different measurement timings of the same repeatedly transmitted non-periodic CSI-RS.

Optionally, when at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are different CSI-RSs: at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, or at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS belong to different CSI-RS sets.

In the embodiment of the present application, the CSI-RS belonging to the CSI-RS set can be understood as the CSI-RS being associated with or configured in the CSI-RS set.

At least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, which can be understood as at least one of the following:

The first CSI-RS and the second CSI-RS are associated with a CSI-RS set;

The first CSI-RS and the third CSI-RS are associated with one CSI-RS set;

The second CSI-RS and the third CSI-RS are associated with one CSI-RS set;

The first CSI-RS, the second CSI-RS, and the third CSI-RS are associated with one CSI-RS set.

At least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RS sets to be understood as at least one of the following:

The first CSI-RS and the second CSI-RS are associated with two CSI-RS sets;

The first CSI-RS and the third CSI-RS are associated with two CSI-RS sets;

The second CSI-RS and the third CSI-RS are associated with two CSI-RS sets;

The first CSI-RS, the second CSI-RS and the third CSI-RS are associated with three CSI-RS sets.

Optionally, when at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, at least one of the following features exists:

The same CSI-RS set is a periodic CSI-RS set configured or activated by the network, or the same CSI-RS set is a semi-persistent CSI-RS set configured or activated by the network, or the same CSI-RS set is an aperiodic CSI-RS set configured or activated by the network;

At least two of the first CSI-RS, the second CSI-RS and the third CSI-RS have the same transmission configuration indicator (TCI) information or quasi co-location information;

At least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS have different frequency domain densities;

At least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS have different bandwidths;

At least two of the first CSI-RS, the second CSI-RS and the third CSI-RS have different port configurations.

The same CSI-RS set being a periodic, semi-persistent or aperiodic CSI-RS set can achieve association of at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS to the same periodic, semi-persistent or aperiodic CSI-RS set.

In the case where the above at least two items have different frequency domain densities, if the above second CSI-RS and the above first CSI-RS or the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, then the above second CSI-RS may have a smaller frequency domain density, which is utilized for the training of the prediction model.

In the case where the above at least two items have different bandwidths, if the above second CSI-RS and the above first CSI-RS or the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, the above second CSI-RS may have a smaller bandwidth, which is utilized for training the prediction model.

The second CSI-RS belongs to one CSI-RS set, the first CSI-RS and the third CSI-RS belong to another CSI-RS set, the third CSI-RS belongs to one CSI-RS set, and the first CSI-RS and the second CSI-RS belong to another CSI-RS set, or the first CSI-RS, the first CSI-RS and the third CSI-RS belong to different CSI-RS sets respectively;

Among the multiple CSI-RS sets associated with the first CSI-RS, the second CSI-RS and the third CSI-RS, different CSI-RS sets have different time domain characteristics;

Among the multiple CSI-RS sets associated with the first CSI-RS, the second CSI-RS, and the third CSI-RS, different CSI-RS sets have different frequency domain densities;

Among the multiple CSI-RS sets associated with the first CSI-RS, the second CSI-RS and the third CSI-RS, different CSI-RS sets have different bandwidths;

Among the multiple CSI-RS sets associated with the first CSI-RS, the second CSI-RS, and the third CSI-RS, Different CSI-RS sets have different port configurations.

In this implementation, it is possible to achieve that prediction model training is associated with one CSI-RS set, and predicted channel and monitoring prediction performance are associated with another CSI-RS set; or, prediction model training, channel prediction, and monitoring prediction performance are associated with different CSI-RS sets respectively; or, prediction model training and channel prediction are associated with one CSI-RS set, and monitoring prediction performance is associated with another CSI-RS set.

The different CSI-RS sets having different time domain characteristics may be that different CSI-RS sets have different periodic, non-periodic or semi-persistent characteristics.

The above-mentioned different CSI-RS sets have different frequency domain densities. If the above-mentioned second CSI-RS is associated with the above-mentioned first CSI-RS or the third CSI-RS to different CSI-RS sets, the CSI-RS set associated with the above-mentioned second CSI-RS has a smaller frequency domain density, which is utilized for the training of the prediction model.

The above-mentioned different CSI-RS sets have different bandwidths. If the above-mentioned second CSI-RS is associated with the above-mentioned first CSI-RS or the third CSI-RS to different CSI-RS sets, the CSI-RS set associated with the above-mentioned second CSI-RS has a smaller bandwidth, which is utilized for the training of the prediction model.

In some embodiments, in the process of associating with the same predicted channel, the first CSI-RS, the second CSI-RS and the third CSI-RS may have the same port configuration.

Optionally, when the time domain characteristic of a CSI-RS set associated with the first CSI-RS, the second CSI-RS, and the third CSI-RS is aperiodic:

The time domain offset of each CSI-RS in the CSI-RS set associated with the first CSI-RS, the second CSI-RS, and the third CSI-RS is determined by at least one of the following:

Network signaling, default rules.

The above-mentioned network signaling may be high-level signaling, the above-mentioned default rule may be a pre-configured rule or a protocol agreement, the above-mentioned time domain offset may be a time slot offset, a symbol offset or a sub-time slot offset, etc. In addition, the above-mentioned time domain offset may be an offset relative to the time domain position of the triggering signaling that triggers the above-mentioned CSI-RS set, such as relative to the time domain position of the downlink control information (Downlink Control Information, DCI) that triggers the above-mentioned CSI-RS set, or the above-mentioned time domain offset may be an offset relative to a specific reference time domain position, and there is no specific limitation on this.

For example: the network side indicates a time slot offset value n for the above CSI-RS set through network signaling. The time slot offset value associated with the first CSI-RS in the CSI-RS set is n, the time slot offset value of the second CSI-RS is n+m, the time slot offset value of the third CSI-RS is n+2*m, and so on. The value of m can be a default rule, such as 1. Or the value of m is indicated by the network.

For another example: the network side indicates a time slot offset value n for the above CSI-RS set through network signaling, the time slot offset value associated with the CSI-RS with the smallest CSI-RS ID in the CSI-RS set is n, the time slot offset value of the CSI-RS with the second smallest CSI-RS ID is n+m, the time slot offset value of the CSI-RS with the third smallest CSI-RS ID is n+2*m, and so on. The value of m can be a default rule, such as 1, or the value of m can be indicated by the network.

As an optional implementation, the method further includes:

The terminal sends feedback information to the network side device, where the feedback information is used to indicate at least one of the following:

The need for the terminal to train a prediction model;

The terminal predicts demand for a channel.

Among them, the above-mentioned demand for terminal training prediction model may be the demand for terminal training AI network model, or the demand for terminal training prediction filter, or the demand for terminal training AR coefficient, or the demand for training prediction algorithm, etc.

In addition, the above requirements may be measurement opportunity quantity requirements, time domain density requirements, and CSI-RS quantity requirements.

For example, the requirements for the terminal training prediction model may include at least one of the following:

the number of measurement opportunities required to train the prediction model;

the number of time domain resources required to train the prediction model;

The required time domain density for training the prediction model;

The number of CSI-RS required for training the prediction model;

The requirement of the terminal to predict the channel may include at least one of the following:

Predict the number of measurement opportunities required for the channel;

Predicting the amount of time domain resources required for the channel;

Predicting the required time domain density of the channel;

Predict the required number of CSI-RS for the channel.

For example: the terminal feeds back at least one of the number of measurement opportunities, the number of measurement time slots, the number of measurement symbols, and the time domain density required for the training process and/or the prediction process.

Optionally, the requirement for the terminal to train the prediction model includes at least one of the following:

A requirement for the terminal to train the prediction model under at least one CSI-RS configuration;

A requirement for the terminal to train the prediction model under at least one time domain channel characteristic;

The terminal predicts the channel requirements including:

Under at least one CSI-RS configuration, the terminal predicts channel demand;

The terminal predicts channel requirements under at least one time-domain channel characteristic.

The above CSI-RS configuration may be at least one of period configuration, port configuration, and frequency domain density configuration.

In this implementation, the terminal may feed back the number of measurement opportunities, the number of measurement time slots or the number of measurement symbols required for the training process and/or the prediction process under multiple cycle configurations, multiple port configurations, and multiple frequency domain density configurations.

In this implementation, the terminal may provide feedback on at least one of the number of measurement opportunities, number of measurement time slots, number of measurement symbols, time domain density, frequency domain density, and frequency domain bandwidth required for the training process and/or prediction process under multiple different time domain channel characteristics.

In some embodiments, the above requirements or quantities are minimum requirements or minimum quantities.

In some implementations, the network side device may obtain the terminal's requirements for training and/or prediction based on the time domain channel characteristics fed back by the terminal. In addition, for configurations that do not meet the requirements, the terminal may not feed back or update the corresponding predicted channel information, such as CSI.

Optionally, the requirements for the terminal training prediction model include: minimum requirements for the terminal training prediction model;

The terminal predicts the channel requirement, including: the minimum channel requirement predicted by the terminal.

Among them, the minimum requirements for the above-mentioned terminal training prediction model can be the minimum number of measurement opportunities required for the terminal training prediction model, the minimum number of time domain resources required, the minimum time domain density required, and the minimum number of CSI-RS required. That is, the prediction model training can be completed by meeting this minimum requirement, but the network can be configured with more configurations than the minimum requirement.

The minimum requirements for the above-mentioned terminal to predict the channel may be the minimum number of measurement opportunities required for the terminal to train the predicted channel, the minimum number of time domain resources required, the minimum time domain density required, and the minimum number of CSI-RS required. That is, channel prediction can be completed by meeting this minimum requirement, but the network may be configured with more configurations than the minimum requirement.

In this implementation, the above minimum requirements can save resource configuration. For example, when resources are tight, the network side device can configure the above minimum requirements for the terminal. When resources are loose, more resources than the minimum requirements can be configured so that the terminal can better complete channel prediction, prediction model training and prediction performance monitoring.

In some implementations, the requirements for the terminal to train the prediction model may include at least one of the following:

the minimum number of measurement opportunities required to train the prediction model;

The minimum number of time domain resources required to train the prediction model;

The minimum required time domain density for training the prediction model;

The minimum number of CSI-RS required to train the prediction model;

The terminal's requirement for predicting the channel may include at least one of the following:

Predict the minimum number of measurement opportunities required for the channel;

Predict the minimum amount of time domain resources required for the channel;

Predict the minimum requirements for the channel's time-domain density;

Predict the minimum number of CSI-RS required for a channel.

In some implementations, the requirement for the terminal to train a prediction model may include at least one of the following:

The terminal trains a minimum requirement for the prediction model under at least one CSI-RS configuration;

the minimum requirement for the terminal to train the prediction model under at least one time domain channel characteristic;

The requirements of the terminal for predicting the channel may include:

Under at least one CSI-RS configuration, the terminal predicts a minimum requirement of a channel;

Under at least one time-domain channel characteristic, the terminal predicts a minimum requirement of the channel.

Optionally, when the resources for training the prediction model do not meet the requirements for training the prediction model of the terminal:

The terminal reports the channel information that is not predicted based on the prediction model to the network side device, or the terminal does not report the channel information;

or,

In the case where the resources of the prediction channel configured by the network are in the training period of the terminal training the prediction model:

The terminal reports the channel information that is not predicted based on the prediction model to the network side device, or the terminal does not report the channel information.

The fact that the resources used for training the prediction model do not meet the requirements of the terminal for training the prediction model may be that at least one of the number of measurement opportunities, the number of time domain resources, the time domain density, and the number of CSI-RSs does not meet the corresponding requirements.

The resource of the prediction channel configured by the network may be in a training period when the terminal trains the prediction model, and the resource of the prediction channel configured by the network may overlap with the training period when the terminal trains the prediction model.

In the above implementation manner, the first CSI-RS and the second CSI-RS may be the same CSI-RS.

In this implementation, it can be realized that for configurations that do not meet the requirements, the terminal may not feedback channel information, such as not feedback CSI, or feedback channel information that is not predicted based on the prediction model, such as feedback channel information predicted based on other methods. In some implementations, when the resources trained by the prediction model do not meet the requirements of the terminal training prediction model or the resources of the predicted channel configured by the network do not meet the requirements of the terminal predicting the channel, the channel information may not be fed back or the corresponding predicted channel information may not be updated.

By reporting channel information that is not predicted based on the prediction model, the channel information reporting performance of the terminal can be improved.

In some implementations, when training and prediction are completed through one CSI-RS, if the number of training opportunities does not meet the terminal's requirement to complete training, the terminal can only feedback non-predicted channel state information, specifically feedback channel state information that is not predicted based on the prediction model. That is, during the training process, the network can configure non-predicted channel state information feedback; or, if the predicted channel state information feedback configured by the network is during training, the terminal can feedback non-predicted channel state information or not feedback or update.

As an optional implementation manner, when the first CSI-RS and the second CSI-RS are the same CSI-RS, the terminal determines the same CSI-RS by at least one of the following:

Network signaling, default rules.

In this implementation, prediction model training and channel prediction can be completed through one CSI-RS, which can reduce the signal overhead of prediction model training and channel prediction.

The above-mentioned network signaling indicates that the above-mentioned CSI-RS is used for both prediction model training and channel prediction, or the above-mentioned default rule indicates that the above-mentioned CSI-RS is used for both prediction model training and channel prediction. For example: when a CSI-RS is configured, the terminal defaults to using the CSI-RS for both prediction model training and channel prediction. When a CSI-RS of a specific configuration or specific resource is configured, the terminal defaults to using the CSI-RS for both prediction model training and channel prediction.

As an optional implementation manner, when the first CSI-RS and the second CSI-RS belong to different CSI-RSs in the same CSI-RS set:

The same CSI-RS set includes two CSI-RS subsets, the CSI-RS in one of the two CSI-RS subsets includes the first CSI-RS, and the CSI-RS in the other CSI-RS subset includes the second CSI-RS; or

The N CSI-RSs in the same CSI-RS set are the first CSI-RSs, and the remaining CSI-RSs are the second CSI-RSs, where N is the number of time domain units.

In some implementations, the above N may be the number of time domain units indicated by the network through codebook configuration signaling, or may be indicated by other signaling or defined by a protocol.

The above-mentioned first CSI-RS and the second CSI-RS belong to different CSI-RS in the same CSI-RS set. Channel prediction and prediction model training are completed through multiple CSI-RSs, and these multiple CSI-RSs are associated or configured in a CSI-RS set.

The above-mentioned N CSI-RS may be the N CSI-RS determined by the number of time domain units N indicated by the above-mentioned codebook configuration signaling, and the above-mentioned remaining CSI-RS as the second CSI-RS may be the CSI-RS in the above-mentioned CSI-RS set except the above-mentioned N CSI-RS as the above-mentioned second CSI-RS.

In some implementations, the time domain offset of the N CSI-RSs may be greater than the time domain offset of the remaining CSI-RSs. In this way, the N CSI-RSs with larger time domain offsets in the CSI-RS set may be used for channel prediction, and the remaining CSI-RSs may be used for prediction model training, so that prediction model training may be performed based on CSI-RSs with earlier time domain positions, thereby predicting channel information based on the trained prediction model to improve the prediction accuracy of channel information.

Optionally, the two CSI-RS subsets have at least one of the following characteristics:

The terminal does not expect that the time domain offset of the CSI-RS subset including the second CSI-RS is greater than the time domain offset of the CSI-RS subset of the first CSI-RS;

The two CSI-RS subsets are divided by at least one of the following: network signaling and time domain offset.

The above-mentioned terminal does not expect the time domain offset of the CSI-RS subset including the second CSI-RS to be greater than the time domain offset of the CSI-RS subset including the first CSI-RS. It can be that the terminal does not expect the time domain offset of the CSI-RS used for prediction model training to be greater than the time domain offset of the CSI-RS used for channel prediction. If this happens, the terminal does not perform the channel prediction process, that is, does not feed back the corresponding channel information, which can avoid the terminal from feeding back inaccurate channel information.

The two CSI-RS subsets are divided by at least one of network signaling and time domain offset. The network signaling explicitly indicates the CSI-RS subset used for prediction model training and the CSI-RS subset used for channel prediction, or the first subset is used for prediction model training and the second subset is used for channel prediction by default. The network signaling implicitly indicates the CSI-RS subset used for prediction model training and the CSI-RS subset used for channel prediction.

Optionally, the sum of the time domain offsets of all CSI-RSs in the CSI-RS subset corresponding to the second CSI-RS is less than the sum of the time domain offsets of all CSI-RSs in the CSI-RS subset corresponding to the first CSI-RS; or,

The time domain offset of each CSI-RS in the CSI-RS subset corresponding to the second CSI-RS is smaller than the time domain offset of each CSI-RS in the CSI-RS subset corresponding to the first CSI-RS; or,

The CSI-RS subset corresponding to the second CSI-RS is the subset to which the CSI-RS with the smallest time domain offset belongs; or,

The CSI-RS subset corresponding to the first CSI-RS is the subset to which the CSI-RS with the largest time domain offset belongs.

For example, when the two CSI-RS subsets can be divided by time domain offset:

The CSI-RS in the CSI-RS subset with a smaller time domain offset is the second CSI-RS, and the CSI-RS in the CSI-RS subset with a larger time domain offset is the first CSI-RS.

Alternatively, the terminal obtains a reference time slot, and a CSI-RS that is greater than or greater than or equal to the reference time slot is the first CSI-RS, and a CSI-RS that is less than or less than or equal to the reference time slot is the second CSI-RS.

The above-mentioned smaller time domain offset means that the sum of the time domain offsets of all CSI-RSs in the CSI-RS subset is smaller, or the CSI-RS subset with smaller time domain offset means the subset to which the CSI-RS with the smallest time domain offset in the CSI-RS set belongs;

The larger time domain offset means that the sum of the time domain offsets of all CSI-RSs in the CSI-RS subset is larger, or the CSI-RS subset with a larger time domain offset refers to the subset to which the CSI-RS with the largest time domain offset in the CSI-RS set belongs.

In this implementation, since the CSI-RS subset with a smaller time domain offset includes the second CSI-RS, the final The terminal performs prediction model training based on the earlier CSI-RS in the above CSI-RS set, so as to predict the channel information based on the trained prediction model, so as to improve the prediction accuracy of the channel information.

As an optional implementation manner, when the first CSI-RS and the second CSI-RS belong to different CSI-RS sets:

The terminal determines a first CSI-RS set including the first CSI-RS and a second CSI-RS set including the second CSI-RS by at least one of the following:

Network signaling, time domain offset, set identification, time domain characteristics.

The above network signaling may explicitly indicate a CSI-RS for prediction model training and a CSI-RS set for channel prediction.

In addition, in this embodiment, the terminal does not expect the time domain offset of the CSI-RS used for prediction model training to be greater than the time domain offset of the CSI-RS used for channel prediction. If this occurs, the terminal does not perform the channel prediction process and does not feed back the corresponding channel information.

The above-mentioned determination of the first CSI-RS set and the second CSI-RS set by time domain offset may be that the terminal defaults to the CSI-RS set associated with the CSI-RS with a smaller time domain offset as the above-mentioned second CSI-RS set, that is, the terminal defaults to the CSI-RS set associated with the CSI-RS with a smaller time domain offset for prediction model training, and the CSI-RS set associated with the CSI-RS with a larger time domain offset as the above-mentioned first CSI-RS set, that is, the CSI-RS set associated with the CSI-RS with a larger time domain offset is used for channel prediction.

The above-mentioned determination of the first CSI-RS set and the second CSI-RS set by time domain offset may be that the terminal distinguishes the first CSI-RS set and the second CSI-RS set by a CSI-RS set identifier, for example: the CSI-RS set with a smaller set ID is the above-mentioned second CSI-RS set, that is, the CSI-RS set with the set identifier is used for prediction model training, and the CSI-RS set with a larger set ID is the above-mentioned first CSI-RS set, that is, the CSI-RS set with the set identifier is used for channel prediction.

The above-mentioned determination of the first CSI-RS set and the second CSI-RS set by time domain characteristics may be that the terminal distinguishes the first CSI-RS set and the second CSI-RS set by the time domain characteristics of the CSI-RS set, for example: the set where the periodic or semi-continuous CSI-RS is located is used for prediction model training, that is, the above-mentioned second CSI-RS set, and the set where the non-periodic CSI-RS is located is used for channel prediction, that is, the above-mentioned first CSI-RS set.

In some embodiments, the first CSI-RS set and the second CSI-RS set are two associated CSI-RS sets, for example, the network side indicates that the terminal has two associated CSI-RS sets for prediction model training and channel prediction respectively.

Optionally, the first CSI-RS set and the second CSI-RS set are two CSI-RS sets corresponding to the same CSI report configuration; or,

The first CSI-RS set and the second CSI-RS set are two CSI-RS sets corresponding to two CSI reporting configurations, and the two CSI reporting configurations are associated; or,

The first CSI-RS set is a CSI-RS set corresponding to a first CSI report configuration, and the second CSI-RS set is a CSI-RS set corresponding to a second CSI report configuration; wherein, when the first CSI report configuration corresponds to multiple CSI-RS sets, the first CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI as the second CSI-RS set; or, when the second CSI report configuration corresponds to multiple CSI-RS sets In the case of a combination, the second CSI-RS set is a CSI-RS set having the same TCI or quasi co-location (QCL) as the first CSI-RS set among the multiple CSI-RS sets; or

The first CSI-RS set and the second CSI-RS set are two CSI-RS sets with the same TCI or QCL among multiple CSI-RS sets configured or activated by the network.

The above CSI reporting configuration may be a CSI reporting configuration configured or activated by the network side. The CSI-RS set corresponding to the CSI reporting configuration may be a CSI-RS set associated with or configured by the CSI reporting configuration.

For example, the network configures or activates a CSI report configuration, and the CSI report configuration is associated with two CSI-RS sets for prediction model training and channel prediction, namely, the second CSI-RS set and the first CSI-RS set.

The above-mentioned first CSI report configuration and the second CSI report configuration can be two CSI pre-configurations with an associated relationship, for example: the network side configures or activates two CSI report configurations, and indicates through signaling that the two CSI report configurations have an associated relationship, and each CI report configuration is associated with or configured with a CSI-RS set, then the two CSI-RS sets associated with the two report configurations are used for prediction model training and channel prediction, namely the above-mentioned second CSI-RS set and the first CSI-RS set.

The above-mentioned CSI-RS set with the same TCI may be that the CSI-RS in the two CSI-RS sets are associated with the same TCI. For example: the network configures or activates two CSI report configurations, and indicates through signaling that the two CSI report configurations have an associated relationship, wherein one CSI report configuration (the first CSI report configuration or the second CSI report configuration) is associated with multiple CSI-RS sets, and the other report configuration (the second CSI report configuration or the first CSI report configuration) is associated with one CSI-RS set, then the terminal considers that among the multiple CSI-RS sets associated with the first CSI report configuration, the CSI-RS set associated with the second CSI report configuration has the same TCI as the CSI-RS set, which has an associated relationship with the CSI-RS set associated with the second CSI report configuration, and thus determines the above-mentioned first CRM set and the second CSI-RS set.

The CSI-RS sets with the same QCL may be that the CSI-RSs in the two CSI-RS sets are associated with the same QCL.

The above-mentioned first CSI-RS set and the second CSI-RS set are two CSI-RS sets with the same TCI or QCL. When multiple (greater than 2) CSI-RS sets are configured or activated on the network side, the two CSI-RS sets with the same TCI or QCL are used for prediction model training and channel prediction, respectively.

In this implementation, it is possible to determine the CSI-RS used for prediction model training and channel prediction based on the CSI report configuration, and it is also possible to use the CSI-RS with the same TCI or QCL as the CSI-RS for prediction model training and channel prediction. In this way, it is possible to use the CSI-RS with the same TCI and QCL for prediction model training and channel prediction, thereby improving the accuracy of channel prediction.

As an optional implementation manner, the third CSI-RS and the first CSI-RS are the same periodic CSI-RS or the same semi-persistent CSI-RS; and/or,

The third CSI-RS and the second CSI-RS are the same periodic CSI-RS or the same semi-persistent CSI-RS.

Among them, the above-mentioned third CSI-RS and the first CSI-RS are the same periodic CSI-RS or the same semi-continuous CSI-RS. It can be that the third CSI-RS and the first CSI-RS are the same CSI-RS, and the CSI-RS is a periodic or semi-continuous CSI-RS, that is, the monitoring is completed through a periodic or semi-continuous CSI-RS that is the same as the prediction.

The above and/or means at least one of the following:

The third CSI-RS and the first CSI-RS are the same periodic CSI-RS or the same semi-persistent CSI-RS;

The third CSI-RS and the second CSI-RS are the same periodic CSI-RS or the same semi-persistent CSI-RS;

The third CSI-RS, the second CSI-RS and the first CSI-RS are the same periodic CSI-RS or the same semi-persistent CSI-RS.

In addition, the relationship between the first CSI-RS, the second CSI-RS and the third CSI-RS can be an indication on the network side, for example: the network side indicates to the terminal that a certain CSI-RS is used for monitoring in addition to prediction model training and/or channel prediction, or, the relationship between the first CSI-RS, the second CSI-RS and the third CSI-RS can also be determined by a default rule, for example: when configuring a CSI-RS, the terminal defaults to that the CSI-RS is used for prediction model training, channel prediction, and monitoring.

In this implementation, since the third CSI-RS and the second CSI-RS and/or the first CSI-RS are the same periodic CSI-RS or the same semi-persistent CSI-RS, the configuration overhead of the CSI-RS can be saved.

As an optional implementation manner, when the first CSI-RS and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set:

The same CSI-RS set includes two CSI-RS subsets, the CSI-RS in one of the two CSI-RS subsets is the first CSI-RS, and the CSI-RS in the other CSI-RS subset is the third CSI-RS.

The first CSI-RS and the third CSI-RS may belong to different CSI-RSs in the same CSI-RS set, including:

The first CSI-RS and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, and the second CSI-RS does not belong to the CSI-RS set; or

The first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set.

The same CSI-RS set including two CSI-RS subsets may be that the same CSI-RS set includes at least two CSI-RS subsets, for example, when the first CSI-RS, the second CSI-RS and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, the CSI-RS set includes three CSI-RS subsets, and the three CSI-RS subsets include the first CSI-RS, the second CSI-RS and the third CSI-RS, respectively.

In this implementation, it can be achieved that the first CSI-RS and the third CSI-RS belong to the same CSI-RS set, which can save CSI-RS set configuration overhead.

Optionally, the time domain positions of the CSI-RS in the CSI-RS subset associated with the third CSI-RS are all later than or equal to the CSI reference time domain position or the CSI report time domain position; and/or

The two CSI-RS subsets are divided by at least one of the following: network signaling, default rule, and time domain offset.

The time domain position of the CSI-RS in the CSI-RS subset associated with the third CSI-RS is later than or equal to the CSI reference time domain position or the CSI report time domain position. The time slot associated with the time domain position of the CSI-RS in the CSI-RS subset associated with the third CSI-RS is greater than or greater than or equal to the time slot associated with the CSI reference time domain position or the time slot associated with the CSI report time domain position, that is, the terminal does not expect the time domain position of the CSI-RS in the CSI-RS subset including the third CSI-RS to be earlier than the CSI reference time domain position or the CSI report time domain position, or the terminal does not expect the third CSI-RS for monitoring to appear. The time slot of CSI-RS is smaller than the CSI reference time slot or the CSI report time slot. If this occurs, the terminal does not perform the monitoring process.

The above network signaling is used to divide the above CSI-RS set into multiple CSI-RS subsets, and explicitly indicate the CSI-RS subset used for monitoring, and may also indicate the CSI-RS subset used for channel prediction.

The above default rule can be that the CSI-RS subset is used for monitoring by default, for example: when the CSI-RS set has two subsets, the first one is used for channel prediction and the second one is used for monitoring; when the CSI-RS set has three subsets, the first one is used for prediction model training, the second one is used for channel prediction, and the third one is used for monitoring.

The above-mentioned time domain offset can be, by determining the above-mentioned two CSI-RS subsets through the position of the time domain offset, for example: when the time slot associated with the CSI-RS is greater than the CSI reference time slot or the CSI report time slot, the CSI-RS is determined as the third CSI-RS for monitoring the prediction performance, and then the CSI-RS subset to which the third CSI-RS belongs is determined, and the remaining CSI-RS is determined as the first CSI-RS for channel prediction, and then the CSI-RS subset to which the first CSI-RS belongs is determined.

As an optional implementation manner, when the first CSI-RS and the third CSI-RS belong to different CSI-RS sets:

The terminal determines a first CSI-RS set including the first CSI-RS and a third CSI-RS set including the third CSI-RS by at least one of the following:

Network signaling, default rules, time domain offset, set identification, time domain characteristics.

The first CSI-RS and the third CSI-RS belong to different CSI-RS sets and may include the following:

The first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RS sets respectively; or

The first CSI-RS and the third CSI-RS belong to different CSI-RS sets, but the second CSI-RS set to which the second CSI-RS belongs is the same as the first CSI-RS set or the second CSI-RS set, that is, the first CSI-RS, the second CSI-RS and the third CSI-RS are associated with two CSI-RS sets.

The above network signaling may explicitly indicate that one of the multiple CSI-RS sets contains a CSI-RS for monitoring predicted performance, or explicitly indicate a first CSI-RS set including a first CSI-RS and a third CSI-RS set including a third CSI-RS.

The above default rule determination may be that there is a CSI-RS for monitoring the prediction performance in the CSI-RS set with a larger default time domain offset, or there is a CSI-RS for monitoring the prediction performance in the CSI-RS set with a smaller default set identifier.

The above-mentioned time domain offset can be determined by determining the CSI-RS set with a larger time domain offset as the CSI-RS set to which the above-mentioned third CSI-RS belongs. For example: in a CSI-RS set, if some or all of the CSI-RS-associated time slots are larger than the CSI reference time slot or the CSI report time slot, the terminal considers that there are CSI-RS for monitoring in the CSI-RS set.

The above set identifier determination may be that the terminal distinguishes by the CSI-RS set identifier, for example: a CSI-RS set with a smaller set ID contains a CSI-RS for monitoring, or a CSI-RS set with a larger set ID contains a CSI-RS for monitoring.

The above-mentioned time domain characteristic determination can be that the terminal distinguishes by the time domain characteristics of the CSI-RS set, for example: there is a CSI-RS for monitoring in the set where the periodic or semi-continuous CSI-RS is located, or there is a CSI-RS for monitoring in the set where the non-periodic CSI-RS is located.

Optionally, when the third CSI-RS set also includes the second CSI-RS: The CSI-RS set is a periodic or semi-persistent CSI-RS set; or

When the third CSI-RS and the second CSI-RS are the same CSI-RS: the third CSI-RS set is a periodic or semi-persistent CSI-RS set.

In this implementation, it can be achieved that the CSI-RS set including the CSI-RS for monitoring also includes the CSI-RS for channel prediction, or the CSI-RS for monitoring and the CSI-RS for channel prediction are the same CSI-RS, and the CSI-RS is a periodic or semi-continuous CSI-RS, which can save CSI-RS configuration overhead.

In some implementations, the first CSI-RS set and the third CSI-RS set are two CSI-RS sets with an associated relationship.

Optionally, the first CSI-RS set and the third CSI-RS set are two CSI-RS sets corresponding to the same channel state information CSI report configuration; or,

The first CSI-RS set and the third CSI-RS set are two CSI-RS sets corresponding to two CSI reporting configurations, and the two CSI reporting configurations are associated; or,

The first CSI-RS set is a CSI-RS set corresponding to a first CSI report configuration, and the third CSI-RS set is a CSI-RS set corresponding to a third CSI report configuration; wherein, in a case where the first CSI report configuration corresponds to multiple CSI-RS sets, the first CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI as the third CSI-RS set; or, in a case where the third CSI report configuration corresponds to multiple CSI-RS sets, the third CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI or QCL as the first CSI-RS set; or,

The first CSI-RS set and the third CSI-RS set are two CSI-RS sets with the same TCI or QCL among multiple CSI-RS sets configured or activated by the network.

The association relationship between the first CSI-RS set and the third CSI-RS set can be found in the corresponding description of the association relationship between the first CSI-RS set and the second CSI-RS set in the above-mentioned embodiment, which will not be repeated here.

As an optional implementation manner, when the first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RS sets:

The terminal determines a first CSI-RS set including the first CSI-RS, a second CSI-RS set including the second CSI-RS, and a third CSI-RS set including the third CSI-RS by at least one of the following:

The above network signaling may explicitly indicate at least one of a first CSI-RS set including a first CSI-RS, a second CSI-RS set including a second CSI-RS, and a third CSI-RS set including a third CSI-RS.

The above default rule determination may be that the CSI-RS set with a larger default time domain offset contains a CSI-RS for monitoring prediction performance, and the CSI-RS set with the smallest default time domain offset contains a CSI-RS for prediction model training.

The above-mentioned time domain offset determination can be that the CSI-RS set with a larger time domain offset is determined as the CSI-RS set to which the above-mentioned third CSI-RS belongs, and the CSI-RS used for prediction model training exists in the CSI-RS set with a smaller or smallest time domain offset by default.

The above set identification can be determined by the terminal distinguishing by the CSI-RS set identification, for example: the set ID is smaller There is a CSI-RS for monitoring in the CSI-RS set, or the set ID is smaller or there is a CSI-RS for prediction model training in the minimum CSI-RS set.

The above-mentioned time domain characteristic determination can be that the terminal distinguishes the CSI-RS set through the time domain characteristics of the CSI-RS set, for example: the set where the periodic or semi-continuous CSI-RS is located contains CSI-RS used for monitoring, or the set where the non-periodic CSI-RS is located contains CSI-RS used for prediction model training.

Optionally, the first CSI-RS set, the second CSI-RS set and the third CSI-RS set are three CSI-RS sets corresponding to the same CSI report configuration; or,

The first CSI-RS set, the second CSI-RS set and the third CSI-RS set are three CSI-RS sets with the same TCI among multiple CSI-RS sets configured or activated by the network.

In this implementation, a network-side configuration or activation of a CSI report configuration may be implemented, and the CSI report configuration is associated with three CSI-RS sets for prediction model training, channel prediction, and monitoring, respectively, thereby saving CSI report configuration overhead.

In this implementation, when the network or multiple (greater than 3) CSI-RS sets are activated, three CSI-RS sets with the same TCI or QCL can be used for prediction model training, channel prediction and monitoring respectively. In this way, the terminal can perform prediction model training, channel prediction and monitoring based on the CSI-RS with the same TCI or QCL to improve the prediction performance of the terminal.

As an optional implementation manner, when the terminal predicts the CSI based on multiple aperiodic CSI-RSs:

The time domain offset of the uplink channel is an offset relative to the time domain position corresponding to the last CSI-RS of the multiple non-periodic CSI-RSs, and the uplink channel is an uplink channel used to carry the CSI; and/or

If there is a target non-periodic CSI-RS among the multiple non-periodic CSI-RSs, the terminal determines that the sending time domain resource of the target non-periodic CSI-RS is the first valid downlink time domain resource before or after the time domain resource corresponding to the target non-periodic CSI-RS indicated by the network; wherein the time domain resource corresponding to the target non-periodic CSI-RS indicated by the network is an uplink time domain resource, or the time domain resource corresponding to the target non-periodic CSI-RS indicated by the network collides with other signals or channels (other signals/channel).

The last CSI-RS mentioned above indicates the CSI-RS with the largest associated time slot among multiple non-periodic CSI-RSs.

The time domain resources corresponding to the target aperiodic CSI-RS may collide with other signals or channels in that the time domain resources corresponding to the target aperiodic CSI-RS overlap with the resources of the other signals or channels.

In this implementation, if the network side instructs the terminal to obtain CSI using multiple non-periodic CSI-RS, the network side instructs or the terminal defaults that the time slot offset of the uplink channel carrying the CSI is the time slot offset of the time slot associated with the last CSI-RS of the multiple non-periodic CSI-RS. For example: the network side indicates a time slot offset Y associated with a physical uplink shared channel (Physical Uplink Shared Channel, PUSCH) through DCI, then the feedback time slot of the CSI report is n+Y, where n corresponds to the time slot associated with the CSI-RS with the largest associated time slot among the multiple non-periodic CSI-RS.

In this way, since the time domain offset of the uplink channel is an offset relative to the time domain position corresponding to the last CSI-RS of the multiple non-periodic CSI-RSs, the terminal can better report the CSI, thereby improving the CSI reporting performance of the terminal.

The above-mentioned downlink time domain resource may be a downlink symbol, or a downlink sub-time slot, etc. The time domain resource corresponding to the above-mentioned target aperiodic CSI-RS may be a symbol or a sub-time slot associated with the target aperiodic CSI-RS, etc. For example: the network side instructs the terminal to obtain CSI using multiple aperiodic CSI-RSs. If the symbol associated with one of the aperiodic CSI-RSs indicated by the network side is an uplink symbol, the terminal may assume that the actual transmission symbol of the CSI-RS is the first valid downlink symbol before or after the symbol indicated by the network.

In some implementations, the first valid downlink time domain resource before or after the time domain resource corresponding to the target aperiodic CSI-RS may include:

The first downlink time domain resource that satisfies the CSI-RS pattern mapping before or after the time domain resource corresponding to the target aperiodic CSI-RS; or

The first valid downlink time domain resource that is before or after the time domain resource corresponding to the target aperiodic CSI-RS and does not collide with the physical channel or signal.

The above-mentioned CSI-RS pattern is a pattern associated with the above-mentioned target non-periodic CSI-RS.

The first downlink time domain resource satisfying the CSI-RS pattern mapping may be the first downlink symbol satisfying the CSI-RS pattern mapping.

The above-mentioned physical channels may be physical uplink shared channel (Physical Uplink Shared Channel, PUSCH), physical downlink shared channel (Physical Downlink Shared Channel, PDSCH), physical downlink control channel (Physical Downlink Control Channel, PDCCH), physical broadcast channel (physical broadcast channel, PBCH), etc.

The above signal may be other CSI-RS or other signals.

The above-mentioned non-collision with physical channels or signals may be downlink time domain resources that do not have time domain collision with other physical channels or signals. For example, if the first valid downlink symbol of the above-mentioned target non-periodic CSI-RS has a time domain collision with other physical channels or signals, then the other physical channels or signals search for their valid downlink symbols according to the same rules to avoid time domain collision between the target non-periodic CSI-RS and other CSI-RS.

In addition, the first valid downlink time domain resource may be a downlink symbol or time slot across time slots. For example, when the valid downlink time domain resource is a symbol, the rule for determining a valid symbol (valid symbol) is as follows: Assuming that the sth symbol on a configured time slot cannot send an aperiodic channel state information reference signal (aperiodic CSI-RS, AP-CSI-RS), then the valid symbol is found in the range [s-j~s+j], the closest valid symbol to s, such as a downlink symbol (DL symbol) that can send CSI-RS. A further search rule may be to search forward and backward at the same time, for example, first search for s-1 and s+1, and if not, continue to search for s-2, s+2, and so on. If at some point, both the front and back symbols are found to meet the requirements, the front symbol or the back symbol is assumed to be a valid symbol. Further restrictions, the valid symbol and the sth symbol must be in the same time slot.

In this implementation, since the terminal determines the actual sending time domain resource of the target aperiodic CSI-RS, the terminal can avoid receiving the target aperiodic CSI-RS, thereby improving the performance of the terminal in receiving CSI-RS.

As an optional implementation manner, the terminal feeds back the first time domain position of the predicted channel information to any The time interval of the CSI-RS is associated with the time interval between multiple CSI-RSs; or,

The terminal sends first indication information to the network side device, where the first indication information is used to indicate that: the time interval from the start position of the prediction window associated with the channel information to any CSI-RS is associated with the time interval between multiple CSI-RSs; or

The terminal receives second indication information sent by a network side device, where the second indication information is used to indicate that a time interval from a starting position of a prediction window associated with channel information to any CSI-RS is associated with a time interval between multiple CSI-RSs.

The first time domain position of the channel information may be the starting time domain position of the channel information.

The prediction window associated with the above-mentioned channel information can be a channel state information reporting (CSI reporting) window or a prediction window associated with a precoding matrix.

The association relationship between the time interval from the starting position of the prediction window to any CSI-RS and the time intervals between multiple CSI-RSs may be configured by the network side, defined by the protocol, or determined by the terminal.

The above time interval may be a time slot interval or a symbol interval.

For example, the time slot interval from the starting slot of the CSI reporting window to any CSI-RS must be an integer multiple of the interval between two adjacent AP CSI-RS resources.

In this implementation, since the time interval from the start position of the prediction window associated with the channel information to any CSI-RS is associated with the time interval between multiple CSI-RSs, this can better match the requirements of the terminal prediction algorithm, thereby providing better performance requirements.

As an optional implementation, the method further includes:

The terminal receives third indication information sent by the network side device, where the third indication information is used to indicate at least one of the following:

The first aperiodic reference signal resource is used for at least one of the following: the terminal trains the prediction model and predicts the predicted channel performance of the terminal, and the first aperiodic reference signal resource is a resource used to transmit at least one of the second CSI-RS and the third CSI-RS;

The second non-periodic reference signal resource is used for at least one of the following: the terminal predicts the channel and the terminal trains the prediction model, and the second non-periodic reference signal resource is a resource used to transmit at least one of the first CSI-RS and the second CSI-RS.

The third indication information may be DCI or other downlink information.

The above-mentioned first non-periodic reference signal resource and the second non-periodic reference signal resource can be AP-CSI Resources, and can include one or more reference signal resources, and CSI-RS can be transmitted on each reference signal resource.

Optionally, the first non-periodic reference signal resources include K1 reference signal resources, and two adjacent reference signals are separated by M1 time domain resources; and/or

The second non-periodic reference signal resources include K2 reference signal resources, and two adjacent reference signals are spaced apart by M2 time domain resources.

The above-mentioned time domain resources may be time slots or sub-time slots.

In some embodiments, the value of at least one of the above K1, K2, M1 and M2 may be determined based on the capabilities and/or feedback requirements of the terminal. In this way, at least one of the first non-periodic reference signal resource and the second non-periodic reference resource can be matched with the terminal, thereby improving the reception performance of the terminal receiving the CSI-RS signal. In some embodiments, the value of at least one of the above K1, K2, M1 and M2 may also be defined by the protocol or configured on the network side. For example: the terminal reports the capability, and the network side determines the value of at least one of the above K1, K2, M1 and M2 based on the capability reported by the terminal.

In addition, the above-mentioned M1 and M2 may be the same (or the same by default), so there is no need to indicate M1 and M2 separately. In some embodiments, M1 and M2 may also be different.

In some implementations, the minimum frequency domain bandwidth of the first non-periodic reference signal resource is determined based on the capability of the terminal. In this way, since the minimum frequency domain bandwidth of the first non-periodic reference signal resource is determined based on the capability of the terminal, the reception performance of the terminal receiving the CSI-RS signal can be improved. In some implementations, the minimum frequency domain bandwidth of the first non-periodic reference signal resource can also be defined by the protocol or configured on the network side.

In some embodiments, the reporting config associated with the first non-periodic reference signal resource may be None.

Optionally, the first non-periodic reference signal resource is earlier than the second non-periodic reference signal resource, and an interval between the first non-periodic reference signal resource and the second non-periodic reference signal resource is greater than or equal to a preset threshold.

The preset threshold may be determined based on a terminal capability report or a protocol agreement.

In this implementation, since the first non-periodic reference signal resource is earlier than the second non-periodic reference signal resource, and the interval between the first non-periodic reference signal resource and the second non-periodic reference signal resource is greater than or equal to a preset threshold, the terminal performs channel prediction based on the trained prediction model, thereby improving the accuracy of channel prediction.

Optionally, the first non-periodic reference signal resource and the second non-periodic reference signal resource are associated with each other.

Optionally, the preset threshold may be a value fed back by the terminal, or may be obtained based on information fed back by the terminal.

The above association relationship may be configured on the network side or agreed upon in a protocol.

For example, the first aperiodic reference signal resource is associated with the second aperiodic reference signal resource, or the second aperiodic reference signal resource is associated with the first aperiodic reference signal resource through network configuration.

In this way, since the first aperiodic reference signal resource and the second aperiodic reference signal resource are associated with each other, one aperiodic reference signal resource can be used to determine another aperiodic reference signal resource, thereby saving configuration overhead.

Specifically, the embodiments of the present application can achieve at least one of the following:

A CSI-RS for CSI prediction may include at least one of the following three purposes: prediction model training, channel prediction, and monitoring prediction performance;

If the prediction model training and channel prediction (or channel prediction and monitoring of channel prediction performance) are completed through a periodic or semi-persistent CSI-RS, the network side indicates to the terminal that the CSI-RS is used for both prediction model training and channel prediction (or can be used to monitor channel prediction performance);

If the prediction model training and channel prediction (or channel prediction and monitoring of channel prediction performance) pass through multiple CSI-RSs, and multiple CSI-RSs are associated or configured in one CSI-RS set, the terminal distinguishes the functions of multiple CSI-RSs through high-layer signaling or default rules;

If the prediction model training and channel prediction (or channel prediction and monitoring of channel prediction performance) pass through multiple CSI-RSs, and the multiple CSI-RSs are associated or configured in two CSI-RS sets, the network side indicates the two CSI-RS sets with the associated relationship through signaling;

If the prediction model training and channel prediction (or channel prediction and monitoring of channel prediction performance) pass through multiple CSI-RSs, and the multiple CSI-RSs are associated or configured in 2 CSI-RS sets, the terminal distinguishes the functions of the CSI-RS sets through high-level signaling or default rules.

In an embodiment of the present application, the functions of CSI-RS (for example, CSI-RS) are divided into prediction model training, channel prediction and monitoring channel prediction performance, and an association relationship is established for CSI-RS with multiple functions (for example, CSI-RS), so that the terminal and network side equipment can unify the understanding of multiple CSI-RS (for example, CSI-RS) used for prediction, and by introducing CSI-RS (for example, CSI-RS) used for prediction model training and monitoring channel prediction performance, the terminal prediction performance is effectively improved.

Please refer to FIG. 3 , which is a flowchart of another reference signal determination method provided in an embodiment of the present application. As shown in FIG. 3 , the method includes the following steps:

Step 301: The network side device sends network signaling to the terminal, where the network signaling is used by the terminal to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS, and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

Optionally, at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are signals of the same CSI-RS at different measurement times;

or,

Optionally, when at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are signals of the same CSI-RS at different measurement times: the same CSI-RS is a periodic CSI-RS configured or activated by the network, or the same CSI-RS is a semi-persistent CSI-RS configured or activated by the network, or the same CSI-RS is an aperiodic CSI-RS configured or activated by the network and sent repeatedly;

In the case where at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are different CSI-RSs: at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, or at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS belong to different CSI-RS sets.

At least two of the first CSI-RS, the second CSI-RS and the third CSI-RS have the same transmission configuration indication TCI information or quasi co-location information;

Among the multiple CSI-RS sets associated with the first CSI-RS, the second CSI-RS and the third CSI-RS, different CSI-RS sets have different port configurations.

Optionally, the method further includes:

The network side device receives feedback information sent by the terminal, where the feedback information is used to indicate at least one of the following:

The need for the terminal to train a prediction model;

The terminal predicts demand for a channel.

the number of measurement opportunities required to train the prediction model;

the number of time domain resources required to train the prediction model;

The required time domain density for training the prediction model;

The number of CSI-RS required for training the prediction model;

The terminal predicts the channel requirement including at least one of the following:

Predict the number of measurement opportunities required for the channel;

Predicting the amount of time domain resources required for the channel;

Predicting the required time domain density of the channel;

Predict the required number of CSI-RS for the channel.

The terminal predicts the channel requirements including:

Under at least one CSI-RS configuration, the terminal predicts a channel demand;

Optionally, when the first CSI-RS and the second CSI-RS belong to different CSI-RSs in the same CSI-RS set:

Optionally, the time domain offset of the N CSI-RS is greater than the time domain offset of the remaining CSI-RS.

Optionally, the first CSI-RS set and the second CSI-RS set are two CSI-RS sets corresponding to the same channel state information CSI report configuration; or,

The first CSI-RS set is a CSI-RS set corresponding to a first CSI report configuration, and the second CSI-RS set is a CSI-RS set corresponding to a second CSI report configuration; wherein, in the case where the first CSI report configuration corresponds to multiple CSI-RS sets, the first CSI-RS set is a CSI-RS set among the multiple CSI-RS sets corresponding to the second CSI-RS set. a CSI-RS set having the same TCI as the first CSI-RS set; or, in the case where the second CSI report configuration corresponds to multiple CSI-RS sets, the second CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI or quasi-co-located QCL as the first CSI-RS set; or,

Optionally, the third CSI-RS and the first CSI-RS are the same periodic CSI-RS or the same semi-persistent CSI-RS; and/or,

Optionally, when the first CSI-RS and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set:

Optionally, the time domain positions of the CSI-RS in the CSI-RS subset associated with the third CSI-RS are all later than or equal to the CSI reference time domain position or the CSI report time domain position.

Optionally, in a case where the third CSI-RS set also includes the second CSI-RS: the third CSI-RS set is a periodic or semi-persistent CSI-RS set; or

Optionally, the first CSI-RS set, the second CSI-RS set and the third CSI-RS set are three CSI-RS sets corresponding to the same channel state information CSI report configuration; or,

The first CSI-RS set, the second CSI-RS set, and the third CSI-RS set are three CSI-RS sets with the same TCI or QCL among multiple CSI-RS sets configured or activated by the network.

Optionally, the time interval from the first time domain position of the predicted channel information fed back by the terminal to any CSI-RS is associated with the time interval between multiple CSI-RSs; or,

The network side device receives first indication information sent by the terminal, where the first indication information is used to indicate that: the time interval from the starting position of the prediction window associated with the channel information to any CSI-RS is associated with the time interval between multiple CSI-RSs; or

The network side device sends second indication information to the terminal, where the second indication information is used to indicate that the time interval from the starting position of the prediction window associated with the channel information to any CSI-RS is associated with the time interval between multiple CSI-RSs.

Optionally, the method further includes:

The network side device sends third indication information to the terminal, where the third indication information is used to indicate at least one of the following:

Optionally, the value of at least one of K1, K2, M1 and M2 is determined based on the capability and/or feedback requirement of the terminal; and/or

The minimum frequency domain bandwidth of the first non-periodic reference signal resource is determined based on the capability of the terminal.

Optionally, the first non-periodic reference signal resource is earlier than the second non-periodic reference signal resource, and an interval between the first non-periodic reference signal resource and the second non-periodic reference signal resource is greater than or equal to a preset threshold; and/or

The first aperiodic reference signal resource and the second aperiodic reference signal resource have an associated relationship.

It should be noted that this embodiment is an implementation of the network side device corresponding to the embodiment shown in Figure 2. Its specific implementation can refer to the relevant description of the embodiment shown in Figure 2. In order to avoid repeated description, this embodiment will not be repeated.

Please refer to FIG. 4 , which is a structural diagram of a reference signal determination device provided in an embodiment of the present application. As shown in FIG. 4 , the reference signal determination device 400 includes:

The determination module 401 is used to determine at least one of a first CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

or,

Network signaling, default rules.

Optionally, the device further comprises:

The first sending module is configured to send feedback information to a network side device, where the feedback information is used to indicate at least one of the following:

The need for the terminal to train a prediction model;

The terminal predicts demand for a channel.

the number of measurement opportunities required to train the prediction model;

the number of time domain resources required to train the prediction model;

The required time domain density for training the prediction model;

The number of CSI-RS required for training the prediction model;

Predict the number of measurement opportunities required for the channel;

Predicting the amount of time domain resources required for the channel;

Predicting the required time domain density of the channel;

Predict the required number of CSI-RS for the channel.

The terminal predicts the channel requirements including:

Optionally, when the resources for training the prediction model do not reach the resources for training the prediction model at the terminal:

or,

Optionally, when the first CSI-RS and the second CSI-RS are the same CSI-RS, the terminal determines the same CSI-RS by at least one of the following:

Network signaling, default rules.

Optionally, the smaller time domain offset means that the sum of the time domain offsets of all CSI-RSs in the CSI-RS subset is smaller, or the CSI-RS subset with a smaller time domain offset means a subset to which the CSI-RS with the smallest time domain offset in the CSI-RS set belongs;

Optionally, when the first CSI-RS and the second CSI-RS belong to different CSI-RS sets:

Optionally, when the first CSI-RS and the third CSI-RS belong to different CSI-RS sets:

Optionally, when the first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RS sets:

Optionally, when the terminal predicts CSI based on multiple aperiodic CSI-RSs:

If there is a target non-periodic CSI-RS among the multiple non-periodic CSI-RSs, the terminal determines that the sending time domain resource of the target non-periodic CSI-RS is the first valid downlink time domain resource before or after the time domain resource corresponding to the target non-periodic CSI-RS indicated by the network; wherein the time domain resource corresponding to the target non-periodic CSI-RS indicated by the network is an uplink time domain resource, or the time domain resource corresponding to the target non-periodic CSI-RS indicated by the network collides with other signals or channels.

Optionally, the first valid downlink time domain resource before or after the time domain resource corresponding to the target aperiodic CSI-RS includes:

The device also includes the following:

A second sending module is used to send first indication information to the network side device, where the first indication information is used to indicate that: the time interval from the starting position of the prediction window associated with the channel information to any CSI-RS is associated with the time interval between multiple CSI-RSs; or

The first receiving module is used to receive second indication information sent by a network side device, where the second indication information is used to indicate that the time interval from the starting position of the prediction window associated with the channel information to any CSI-RS is associated with the time interval between multiple CSI-RSs.

Optionally, the device further comprises:

The second receiving module is used to receive third indication information sent by the network side device, where the third indication information is used to indicate at least one of the following:

The above-mentioned reference signal determination device can improve the transmission performance between communication devices.

The reference signal determination device in the 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. For example: the electronic device may be a terminal, or may be a device other than a terminal. Exemplarily, the terminal may include but is not limited to the types of terminals listed in the embodiment of the present application, and other devices may be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

The reference signal determination device provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 2 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

Please refer to FIG. 5 , which is a structural diagram of a reference signal determination device provided in an embodiment of the present application. As shown in FIG. 5 , the reference signal determination device 500 includes:

The first sending module 501 is used to send network signaling to the terminal, and the network signaling is used by the terminal to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

or,

Among the multiple CSI-RS sets associated with the first CSI-RS, the second CSI-RS and the third CSI-RS, different CSI-RS sets have different frequency domain densities;

Optionally, the device further comprises:

The first receiving module is configured to receive feedback information sent by the terminal, where the feedback information is used to indicate at least one of the following:

The need for the terminal to train a prediction model;

The terminal predicts demand for a channel.

the number of measurement opportunities required to train the prediction model;

the number of time domain resources required to train the prediction model;

The required time domain density for training the prediction model;

The number of CSI-RS required for training the prediction model;

Predict the number of required measurement opportunities for the channel;

Predicting the amount of time domain resources required for the channel;

Predicting the required time domain density of the channel;

Predict the required number of CSI-RS for the channel.

The terminal predicts the channel requirements including:

The first CSI-RS set is a CSI-RS set corresponding to a first CSI report configuration, and the second CSI-RS set is a CSI-RS set corresponding to a second CSI report configuration; wherein, in a case where the first CSI report configuration corresponds to multiple CSI-RS sets, the first CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI as the second CSI-RS set; or, in a case where the second CSI report configuration corresponds to multiple CSI-RS sets, the second CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI or quasi-co-located QCL as the first CSI-RS set; or,

The first CSI-RS set is a CSI-RS set corresponding to the first CSI report configuration, and the third CSI-RS set is a CSI-RS set corresponding to the third CSI report configuration; wherein, in the case where the first CSI report configuration corresponds to multiple CSI-RS sets, the first CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI as the third CSI-RS set; or, in the case where the third CSI report configuration corresponds to multiple CSI-RS sets In the case of a combination, the third CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI or QCL as the first CSI-RS set; or,

The device also includes the following:

A second receiving module is configured to receive first indication information sent by the terminal, where the first indication information is used to indicate that a time interval from a starting position of a prediction window associated with channel information to any CSI-RS is associated with a time interval between multiple CSI-RSs; or

The second sending module is used to send second indication information to the terminal, where the second indication information is used to indicate that the time interval from the starting position of the prediction window associated with the channel information to any CSI-RS is associated with the time interval between multiple CSI-RSs.

Optionally, the device further comprises:

The third sending module is configured to send third indication information to the terminal, where the third indication information is used to indicate at least one of the following:

Optionally, the first aperiodic reference signal resource is earlier than the second aperiodic reference signal resource, and the interval between the first aperiodic reference signal resource and the second aperiodic reference signal resource is greater than or equal to a preset threshold. and/or

The reference signal determination device in the 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 a network side device.

The reference signal determination device provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 3 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

Optionally, as shown in FIG6 , an embodiment of the present application further provides a communication device 600, including a processor 601 and a memory 602, wherein the memory 602 stores a program or instruction that can be run on the processor 601. For example, when the communication device 600 is a terminal, the program or instruction is executed by the processor 601 to implement the various steps of the embodiment of the reference signal determination method on the terminal side, and the same technical effect can be achieved. When the communication device 600 is a network side device, the program or instruction is executed by the processor 601 to implement the various steps of the embodiment of the reference signal determination method on the network side device side, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

The embodiment of the present application also provides a communication device, including a processor and a communication interface, wherein the processor is used to determine at least one of a first CSI-RS, a second CSI-RS, and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal. The communication device embodiment corresponds to the reference signal determination method embodiment on the terminal side, and each implementation process and implementation method of the method embodiment can be applied to the communication device embodiment, and can achieve the same technical effect.

Specifically, FIG7 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

The terminal 700 includes but is not limited to: a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709 and at least some of the components of a processor 710.

Those skilled in the art will appreciate that the terminal 700 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 710 through a power management system, so as to implement functions such as managing charging, discharging, and power consumption management through the power management system. The terminal structure shown in FIG7 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently, which will not be described in detail here.

It should be understood that in the embodiment of the present application, the input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042, and the graphics processing unit 7041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 706 may include a display panel 7061, and the display panel 7061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 707 includes a touch panel 7071 and at least one of other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include two parts: a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

In the embodiment of the present application, after receiving downlink data from the network side device, the RF unit 701 can transmit the data to the processor 710 for processing; in addition, the RF unit 701 can send uplink data to the network side device. Generally, the RF unit 701 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

The memory 709 can be used to store software programs or instructions and various data. The memory 709 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 709 may include a volatile memory or a non-volatile memory, or the memory 709 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 709 in the embodiment of the present application includes but is not limited to these and any other suitable types of memories.

The processor 710 may include one or more processing units; optionally, the processor 710 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 710.

Processor 710 is used to determine at least one of a first CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

or,

When at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are different CSI-RSs: at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, or the first CSI-RS, the second CSI-RS, and the third CSI-RS are different CSI-RSs. At least two of the CSI-RSs belong to different CSI-RS sets.

Network signaling, default rules.

Optionally, the radio frequency unit 701 is used to: send feedback information to the network side device, where the feedback information is used to indicate at least one of the following:

The need for the terminal to train a prediction model;

The terminal predicts demand for a channel.

the number of measurement opportunities required to train the prediction model;

the number of time domain resources required to train the prediction model;

The required time domain density for training the prediction model;

The number of CSI-RS required for training the prediction model;

Predict the number of measurement opportunities required for the channel;

Predicting the amount of time domain resources required for the channel;

Predicting the required time domain density of the channel;

Predict the required number of CSI-RS for the channel.

The terminal predicts the channel requirements including:

or,

Network signaling, default rules.

Optionally, when the terminal predicts CSI based on multiple aperiodic CSI-RSs:

If there is a target aperiodic CSI-RS among the multiple aperiodic CSI-RSs, the terminal determines that the sending time domain resource of the target aperiodic CSI-RS is the first valid downlink time domain resource before or after the time domain resource corresponding to the target aperiodic CSI-RS indicated by the network; wherein the time domain resource corresponding to the target aperiodic CSI-RS indicated by the network The source is an uplink time domain resource, or the time domain resource corresponding to the target aperiodic CSI-RS indicated by the network collides with other signals or channels.

The radio frequency unit 701 is also used for the following:

Sending first indication information to a network side device, where the first indication information is used to indicate that: the time interval from the starting position of the prediction window associated with the channel information to any CSI-RS is associated with the time interval between multiple CSI-RSs; or

Second indication information sent by a network side device is received, where the second indication information is used to indicate that a time interval from a starting position of a prediction window associated with channel information to any CSI-RS is associated with a time interval between multiple CSI-RSs.

Optionally, the radio frequency unit 701 is further configured to:

Receive third indication information sent by the network side device, where the third indication information is used to indicate at least one of the following:

The above-mentioned terminals can improve the transmission performance between communication devices.

The embodiment of the present application also provides a communication device, including a processor and a communication interface, wherein the communication interface is used to send network signaling to a terminal, and the network signaling is used by the terminal to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS, and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal. This communication device embodiment corresponds to the Doppler measurement method embodiment on the network side device side, and each implementation process and implementation method of the above method embodiment can be applied to the communication device embodiment, and can achieve the same technical effect.

Specifically, the embodiment of the present application also provides a network side device. As shown in Figure 8, the network side device 800 includes: an antenna 801, a radio frequency device 802, a baseband device 803, a processor 804 and a memory 805. The antenna 801 is connected to the radio frequency device 802. In the uplink direction, the radio frequency device 802 receives information through the antenna 801 and sends the received information to the baseband device 803 for processing. In the downlink direction, the baseband device 803 processes the information to be sent and sends it to the radio frequency device 802. The radio frequency device 802 processes the received information and sends it out through the antenna 801.

The method executed by the network-side device in the above embodiment may be implemented in the baseband device 803, which includes a baseband processor.

The baseband device 803 may include, for example, at least one baseband board, on which a plurality of chips are arranged, as shown in FIG8 , wherein one of the chips is, for example, a baseband processor, which is connected to the memory 805 through a bus interface to call the program in the memory 805 and execute the network device operations shown in the above method embodiment.

The network side device may also include a network interface 806, which is, for example, a common public radio interface (CPRI).

Specifically, the network side device 800 of the embodiment of the present application also includes: instructions or programs stored in the memory 805 and executable on the processor 804. The processor 804 calls the instructions or programs in the memory 805 to execute the methods executed by the modules shown in Figure 5 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

Among them, the radio frequency device 802 is used to send network signaling to the terminal, and the network signaling is used by the terminal to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.

or,

When at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are different CSI-RSs: at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS belong to the same Different CSI-RSs in a CSI-RS set, or at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS belong to different CSI-RS sets.

Optionally, the radio frequency device 802 is further used for:

receiving feedback information sent by the terminal, where the feedback information is used to indicate at least one of the following:

The need for the terminal to train a prediction model;

The terminal predicts demand for a channel.

the number of measurement opportunities required to train the prediction model;

the number of time domain resources required to train the prediction model;

The required time domain density for training the prediction model;

The number of CSI-RS required for training the prediction model;

Predict the number of measurement opportunities required for the channel;

Predicting the amount of time domain resources required for the channel;

Predicting the required time domain density of the channel;

Predict the required number of CSI-RS for the channel.

The terminal predicts the channel requirements including:

The first CSI-RS set is a CSI-RS set corresponding to the first CSI report configuration, and the second CSI-RS set The first CSI report configuration corresponds to a plurality of CSI-RS sets, wherein the first CSI-RS set is a CSI-RS set having the same TCI as the second CSI-RS set among the plurality of CSI-RS sets; or, the second CSI report configuration corresponds to a plurality of CSI-RS sets, the second CSI-RS set is a CSI-RS set having the same TCI or quasi-co-located QCL as the first CSI-RS set among the plurality of CSI-RS sets; or,

The first CSI-RS set, the second CSI-RS set and the third CSI-RS set are network configuration or or three CSI-RS sets with the same TCI or QCL among the multiple CSI-RS sets activated.

The radio frequency device 802 is further configured to include the following:

receiving first indication information sent by the terminal, where the first indication information is used to indicate that a time interval from a start position of a prediction window associated with channel information to any CSI-RS is associated with a time interval between multiple CSI-RSs; or

Second indication information is sent to the terminal, where the second indication information is used to indicate that a time interval from a starting position of a prediction window associated with the channel information to any CSI-RS is associated with a time interval between multiple CSI-RSs.

Optionally, the radio frequency device 802 is further used for:

Sending third indication information to the terminal, where the third indication information is used to indicate at least one of the following:

The above network side equipment can improve the transmission performance between communication devices.

An embodiment of the present application further provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the reference signal determination method provided in the embodiment of the present application are implemented.

The processor is the processor in the terminal described in the above embodiment. 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.

The present application also provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the above-mentioned reference signal determination method embodiment. Each process can achieve the same technical effect, and will not be described here to avoid repetition.

It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

An embodiment of the present application further provides a computer program/program product, which is stored in a storage medium. The computer program/program product is executed by at least one processor to implement the various processes of the above-mentioned reference signal determination method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

An embodiment of the present application also provides a reference signal determination system, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the reference signal determination method on the terminal side provided in the embodiment of the present application, and the network side device can be used to execute the steps of the reference signal determination method on the network side device side provided in the embodiment of the present application.

It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises one..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be noted that 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, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

A reference signal determination method, comprising:

The terminal determines at least one of a first channel state information reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for training a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.
The method according to claim 1, wherein at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are signals of the same CSI-RS at different measurement times;

or,

At least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are different CSI-RSs.
The method according to claim 2, wherein at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are signals of the same CSI-RS at different measurement times: the same CSI-RS is a periodic CSI-RS configured or activated by the network, or the same CSI-RS is a semi-persistent CSI-RS configured or activated by the network, or the same CSI-RS is a non-periodic CSI-RS configured by the network and repeatedly transmitted;

In the case where at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are different CSI-RSs: at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, or at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS belong to different CSI-RS sets.
The method of claim 3, wherein, when at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, at least one of the following features exists:

The same CSI-RS set is a periodic CSI-RS set configured or activated by the network, or the same CSI-RS set is a semi-persistent CSI-RS set configured or activated by the network, or the same CSI-RS set is an aperiodic CSI-RS set configured or activated by the network;

At least two of the first CSI-RS, the second CSI-RS and the third CSI-RS have the same transmission configuration indication TCI information or quasi co-location information;

At least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS have different frequency domain densities;

At least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS have different bandwidths;

At least two of the first CSI-RS, the second CSI-RS and the third CSI-RS have different port configurations.
The method of claim 3, wherein, when at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, at least one of the following features exists:

The second CSI-RS belongs to one CSI-RS set, the first CSI-RS and the third CSI-RS belong to another CSI-RS set, the third CSI-RS belongs to one CSI-RS set, and the first CSI-RS and the second CSI-RS belong to another CSI-RS set, or the first CSI-RS, the first CSI-RS and the third CSI-RS belong to different CSI-RS sets respectively;

Among the multiple CSI-RS sets associated with the first CSI-RS, the second CSI-RS and the third CSI-RS, different CSI-RS sets have different time domain characteristics;

Among the multiple CSI-RS sets associated with the first CSI-RS, the second CSI-RS, and the third CSI-RS, different CSI-RS sets have different frequency domain densities;

Among the multiple CSI-RS sets associated with the first CSI-RS, the second CSI-RS and the third CSI-RS, different CSI-RS sets have different bandwidths;

Among the multiple CSI-RS sets associated with the first CSI-RS, the second CSI-RS and the third CSI-RS, different CSI-RS sets have different port configurations.
The method according to any one of claims 3 to 5, wherein, when the time domain characteristic of the CSI-RS set associated with the first CSI-RS, the second CSI-RS, and the third CSI-RS is aperiodic:

The time domain offset of each CSI-RS in the CSI-RS set associated with the first CSI-RS, the second CSI-RS, and the third CSI-RS is determined by at least one of the following:

Network signaling, default rules.
The method according to any one of claims 1 to 5, wherein the method further comprises:

The terminal sends feedback information to the network side device, where the feedback information is used to indicate at least one of the following:

The need for the terminal to train a prediction model;

The terminal predicts demand for a channel.
The method according to claim 7, wherein the requirement for the terminal to train the prediction model includes at least one of the following:

the number of measurement opportunities required to train the prediction model;

the number of time domain resources required to train the prediction model;

The required time domain density for training the prediction model;

The number of CSI-RS required for training the prediction model;

The terminal predicts the channel requirement including at least one of the following:

Predict the number of measurement opportunities required for the channel;

Predicting the amount of time domain resources required for the channel;

Predicting the required time domain density of the channel;

Predict the required number of CSI-RS for the channel.
The method according to claim 7, wherein the requirement for the terminal to train the prediction model includes at least one of the following:

A requirement for the terminal to train the prediction model under at least one CSI-RS configuration;

A requirement for the terminal to train the prediction model under at least one time domain channel characteristic;

The terminal predicts the channel requirements including:

Under at least one CSI-RS configuration, the terminal predicts a channel demand;

The terminal predicts channel requirements under at least one time-domain channel characteristic.
The method of claim 7, wherein the requirements of the terminal training prediction model include: minimum requirements of the terminal training prediction model;

The terminal predicts the channel requirement, including: the minimum channel requirement predicted by the terminal.
The method of claim 7, wherein, when the resources for training the prediction model do not meet the requirements of the terminal for training the prediction model:

The terminal reports the channel information that is not predicted based on the prediction model to the network side device, or the terminal does not report the channel information;

or,

In the case where the resources of the prediction channel configured by the network are in the training period of the terminal training the prediction model:

The terminal reports the channel information that is not predicted based on the prediction model to the network side device, or the terminal does not report the channel information.
The method according to claim 2, wherein, when the first CSI-RS and the second CSI-RS are the same CSI-RS, the terminal determines the same CSI-RS by at least one of the following:

Network signaling, default rules.
The method according to claim 3, wherein the first CSI-RS and the second CSI-RS belong to different CSI-RSs in the same CSI-RS set:

The same CSI-RS set includes two CSI-RS subsets, the CSI-RS in one of the two CSI-RS subsets includes the first CSI-RS, and the CSI-RS in the other CSI-RS subset includes the second CSI-RS; or

The N CSI-RSs in the same CSI-RS set are the first CSI-RSs, and the remaining CSI-RSs are the second CSI-RSs, where N is the number of time domain units.
The method of claim 13, wherein the time domain offset of the N CSI-RS is greater than the time domain offset of the remaining CSI-RS.
The method of claim 13, wherein the sum of the time domain offsets of all CSI-RSs in the CSI-RS subset corresponding to the second CSI-RS is less than the sum of the time domain offsets of all CSI-RSs in the CSI-RS subset corresponding to the first CSI-RS; or

The time domain offset of each CSI-RS in the CSI-RS subset corresponding to the second CSI-RS is smaller than the time domain offset of each CSI-RS in the CSI-RS subset corresponding to the first CSI-RS; or,

The CSI-RS subset corresponding to the second CSI-RS is the subset to which the CSI-RS with the smallest time domain offset belongs; or,

The CSI-RS subset corresponding to the first CSI-RS is the subset to which the CSI-RS with the largest time domain offset belongs.
The method according to claim 3, wherein the first CSI-RS and the second CSI-RS belong to different CSI-RS sets:

The terminal determines a first CSI-RS set including the first CSI-RS and a first CSI-RS set including the first CSI-RS by at least one of the following items: Second CSI-RS set of the second CSI-RS:

Network signaling, time domain offset, set identification, time domain characteristics.
The method according to claim 16, wherein the first CSI-RS set and the second CSI-RS set are two CSI-RS sets corresponding to the same channel state information CSI report configuration; or,

The first CSI-RS set and the second CSI-RS set are two CSI-RS sets corresponding to two CSI reporting configurations, and the two CSI reporting configurations are associated; or,

The first CSI-RS set is a CSI-RS set corresponding to a first CSI report configuration, and the second CSI-RS set is a CSI-RS set corresponding to a second CSI report configuration; wherein, in a case where the first CSI report configuration corresponds to multiple CSI-RS sets, the first CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI as the second CSI-RS set; or, in a case where the second CSI report configuration corresponds to multiple CSI-RS sets, the second CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI or quasi-co-located QCL as the first CSI-RS set; or,

The first CSI-RS set and the second CSI-RS set are two CSI-RS sets with the same TCI or QCL among multiple CSI-RS sets configured or activated by the network.
The method according to claim 3, wherein the third CSI-RS and the first CSI-RS are the same periodic CSI-RS or the same semi-persistent CSI-RS; and/or,

The third CSI-RS and the second CSI-RS are the same periodic CSI-RS or the same semi-persistent CSI-RS.
The method according to claim 3, wherein the first CSI-RS and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set:

The same CSI-RS set includes two CSI-RS subsets, the CSI-RS in one of the two CSI-RS subsets is the first CSI-RS, and the CSI-RS in the other CSI-RS subset is the third CSI-RS.
The method of claim 19, wherein the time domain positions of the CSI-RS in the CSI-RS subset associated with the third CSI-RS are all later than or equal to the CSI reference time domain position or the CSI report time domain position; and/or

The two CSI-RS subsets are divided by at least one of the following: network signaling, default rule, and time domain offset.
The method according to claim 3, wherein the first CSI-RS and the third CSI-RS belong to different CSI-RS sets:

The terminal determines a first CSI-RS set including the first CSI-RS and a third CSI-RS set including the third CSI-RS by at least one of the following:

Network signaling, default rules, time domain offset, set identification, time domain characteristics.
The method of claim 21, wherein, in the case where the third CSI-RS set also includes the second CSI-RS: the third CSI-RS set is a periodic or semi-persistent CSI-RS set; or

When the third CSI-RS and the second CSI-RS are the same CSI-RS: the third CSI-RS set is a periodic or semi-persistent CSI-RS set.
The method according to claim 22, wherein the first CSI-RS set and the third CSI-RS set are two CSI-RS sets corresponding to the same channel state information CSI report configuration; or,

The first CSI-RS set and the third CSI-RS set are two CSI-RS sets corresponding to two CSI reporting configurations, and the two CSI reporting configurations are associated; or,

The first CSI-RS set is a CSI-RS set corresponding to a first CSI report configuration, and the third CSI-RS set is a CSI-RS set corresponding to a third CSI report configuration; wherein, in a case where the first CSI report configuration corresponds to multiple CSI-RS sets, the first CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI as the third CSI-RS set; or, in a case where the third CSI report configuration corresponds to multiple CSI-RS sets, the third CSI-RS set is a CSI-RS set among the multiple CSI-RS sets that has the same TCI or QCL as the first CSI-RS set; or,

The first CSI-RS set and the third CSI-RS set are two CSI-RS sets with the same TCI or QCL among multiple CSI-RS sets configured or activated by the network.
The method according to claim 3, wherein the first CSI-RS, the second CSI-RS, and the third CSI-RS belong to different CSI-RS sets:

The terminal determines a first CSI-RS set including the first CSI-RS, a second CSI-RS set including the second CSI-RS, and a third CSI-RS set including the third CSI-RS by at least one of the following:

Network signaling, default rules, time domain offset, set identification, time domain characteristics.
The method of claim 24, wherein the first CSI-RS set, the second CSI-RS set, and the third CSI-RS set are three CSI-RS sets corresponding to the same channel state information CSI report configuration; or,

The first CSI-RS set, the second CSI-RS set, and the third CSI-RS set are three CSI-RS sets with the same TCI or QCL among multiple CSI-RS sets configured or activated by the network.
A method as described in any one of claims 1 to 5, wherein, when the terminal predicts CSI based on multiple aperiodic CSI-RSs:

The time domain offset of the uplink channel is an offset relative to the time domain position corresponding to the last CSI-RS of the multiple non-periodic CSI-RSs, and the uplink channel is an uplink channel used to carry the CSI; and/or

If there is a target non-periodic CSI-RS among the multiple non-periodic CSI-RSs, the terminal determines that the sending time domain resource of the target non-periodic CSI-RS is the first valid downlink time domain resource before or after the time domain resource corresponding to the target non-periodic CSI-RS indicated by the network; wherein the time domain resource corresponding to the target non-periodic CSI-RS indicated by the network is an uplink time domain resource, or the time domain resource corresponding to the target non-periodic CSI-RS indicated by the network collides with other signals or channels.
A method as claimed in claim 26, wherein the first valid downlink time domain resource before or after the time domain resource corresponding to the target aperiodic CSI-RS includes:

The first downlink time domain resource that satisfies the CSI-RS pattern mapping before or after the time domain resource corresponding to the target aperiodic CSI-RS; or

The first valid downlink time domain resource that is before or after the time domain resource corresponding to the target aperiodic CSI-RS and does not collide with the physical channel or signal.
A method as described in any one of claims 1 to 5, wherein the time interval from the first time domain position of the predicted channel information fed back by the terminal to any CSI-RS is associated with the time interval between multiple CSI-RSs; or

The terminal sends first indication information to the network side device, where the first indication information is used to indicate that: the time interval from the start position of the prediction window associated with the channel information to any CSI-RS is associated with the time interval between multiple CSI-RSs; or

The terminal receives second indication information sent by a network side device, where the second indication information is used to indicate that a time interval from a starting position of a prediction window associated with channel information to any CSI-RS is associated with a time interval between multiple CSI-RSs.
The method according to any one of claims 1 to 5, wherein the method further comprises:

The terminal receives third indication information sent by the network side device, where the third indication information is used to indicate at least one of the following:

The first aperiodic reference signal resource is used for at least one of the following: the terminal trains the prediction model and predicts the predicted channel performance of the terminal, and the first aperiodic reference signal resource is a resource used to transmit at least one of the second CSI-RS and the third CSI-RS;

The second non-periodic reference signal resource is used for at least one of the following: the terminal predicts the channel and the terminal trains the prediction model, and the second non-periodic reference signal resource is a resource used to transmit at least one of the first CSI-RS and the second CSI-RS.
The method of claim 29, wherein the first non-periodic reference signal resource includes K1 reference signal resources, and two adjacent reference signals are separated by M1 time domain resources; and/or

The second non-periodic reference signal resources include K2 reference signal resources, and two adjacent reference signals are spaced apart by M2 time domain resources.
The method of claim 30, wherein the value of at least one of K1, K2, M1 and M2 is determined based on the capability and/or feedback requirement of the terminal; and/or

The minimum frequency domain bandwidth of the first non-periodic reference signal resource is determined based on the capability of the terminal.
The method of claim 29, wherein the first aperiodic reference signal resource is earlier than the second aperiodic reference signal resource, and the interval between the first aperiodic reference signal resource and the second aperiodic reference signal resource is greater than or equal to a preset threshold; and/or

The first aperiodic reference signal resource and the second aperiodic reference signal resource have an associated relationship.
A reference signal determination method, comprising:

The network side device sends network signaling to the terminal, and the network signaling is used by the terminal to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for the terminal to train a prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.
The method of claim 33, wherein at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are signals of the same CSI-RS at different measurement times;

or,

At least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are different CSI-RSs.
The method of claim 34, wherein at least two of the first CSI-RS, the second CSI-RS, and the third CSI-RS are signals of the same CSI-RS at different measurement times: the same CSI-RS is a periodic CSI-RS configured or activated by the network, or the same CSI-RS is a semi-persistent CSI-RS configured or activated by the network, or the same CSI-RS is a non-periodic CSI-RS that is repeatedly transmitted and configured by the network;

In the case where at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS are different CSI-RSs: at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS belong to different CSI-RSs in the same CSI-RS set, or at least two of the first CSI-RS, the second CSI-RS and the third CSI-RS belong to different CSI-RS sets.
A reference signal determination device, comprising:

A determination module is used to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for terminal training prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.
A reference signal determination device, comprising:

The first sending module is used to send network signaling to the terminal, and the network signaling is used by the terminal to determine at least one of a first channel measurement reference signal CSI-RS, a second CSI-RS and a third CSI-RS, wherein the first CSI-RS is used for channel prediction, the second CSI-RS is used for terminal training prediction model, and the third CSI-RS is used to monitor the channel prediction performance of the terminal.
A terminal comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the reference signal determination method as described in any one of claims 1 to 32 are implemented.
A network side device comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the reference signal determination method as described in any one of claims 33 to 35 are implemented.
A readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the steps of the reference signal determination method as described in any one of claims 1 to 32, or the program or instruction, when executed by a processor, implements the steps of the reference signal determination method as described in any one of claims 33 to 35.