A channel prediction method, device, UE and system

Abstract

Embodiments of the present application disclose a channel prediction method, device, UE and system, and relate to the technical field of communication. The method comprises: the UE can send first information to a network side device; the network side device can receive the first information and perform channel prediction according to the first information; the first information comprises a channel prediction result and model parameters of a target specific operator model, or comprises model parameters of the target specific operator model; wherein the channel prediction result is a channel result predicted by the UE based on the model parameters of the target specific operator model and historical channel estimation results, and the target specific operator model is a specific operator model constructed by the UE based on the historical channel estimation results; the network side device performs channel prediction according to the first information.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of communication, and particularly relate to a channel prediction method, device, UE and system. BACKGROUND

[0002] At present, a specific operator model (for example, a linear model, a polynomial fitting model, etc.) can be used to recursively predict a time-varying channel, the specific operator model is a time filter, inputs a historical channel estimation, and outputs a channel at a future time interval; and since the specific operator model only needs endogenous variables and does not need to rely on other exogenous variables, modeling of channel prediction using the specific operator model is relatively simple.

[0003] However, when the specific operator model is used to predict a channel in a complex environment, the specific operator model has more model parameters, and therefore, the calculation complexity of channel prediction using the specific operator model is relatively high. SUMMARY

[0004] Embodiments of the present application provide a channel prediction method, device, UE and system, which can solve the problem of high calculation complexity of channel prediction using a specific operator model.

[0005] In a first aspect, a channel prediction method is provided, applied to a user equipment (UE), and the method can include: sending, by the UE, first information to a network side device, the first information being used for channel prediction by the network side device, the first information including a channel prediction result and model parameters of a target specific operator model, or including the model parameters of the target specific operator model; wherein the channel prediction result is a channel result predicted by the UE based on the model parameters of the target specific operator model and a historical channel estimation result, and the target specific operator model is a specific operator model constructed by the UE based on the historical channel estimation result.

[0006] In a second aspect, a channel prediction device is provided, including: a sending module. The sending module is configured to send first information to a network side device, the first information being used for channel prediction by the network side device, the first information including a channel prediction result and model parameters of a target specific operator model, or including the model parameters of the target specific operator model; wherein the channel prediction result is a channel result predicted by the UE based on the model parameters of the target specific operator model and a historical channel estimation result, and the target specific operator model is a specific operator model constructed by the UE based on the historical channel estimation result.

[0007] In a third aspect, a channel prediction method is provided, applied to a network side device, and the method comprises: the network side device obtaining first information, the first information comprising a channel prediction result and model parameters of a target specific operator model, or comprising model parameters of the target specific operator model; wherein the channel prediction result is a channel result predicted by the UE based on the model parameters of the target specific operator model and historical channel estimation results, and the target specific operator model is a specific operator model constructed by the UE based on the historical channel estimation results; and the network side device performing channel prediction according to the first information.

[0008] In a fourth aspect, a channel prediction apparatus is provided, comprising: an obtaining module and a prediction module. The obtaining module is configured to obtain first information, the first information comprising a channel prediction result and model parameters of a target specific operator model, or comprising model parameters of the target specific operator model; wherein the channel prediction result is a channel result predicted by the UE based on the model parameters of the target specific operator model and historical channel estimation results, and the target specific operator model is a specific operator model constructed by the UE based on the historical channel estimation results; and the prediction module is configured to perform channel prediction according to the first information obtained by the obtaining module.

[0009] In a fifth aspect, a user equipment (UE) is provided, comprising a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement the steps of the method according to the first aspect.

[0010] In a sixth aspect, a user equipment (UE) is provided, comprising a processor and a communication interface, wherein the processor is configured to: construct a target specific operator model, or to construct the target specific operator model and a channel result predicted based on model parameters of the target specific operator model and historical channel estimation results, and perform channel prediction to obtain a channel prediction result; the target specific operator model is a specific operator model constructed by the UE based on the historical channel estimation results; and the communication interface is configured to send first information to a network side device, the first information comprising the model parameters and / or the channel prediction result.

[0011] In a seventh aspect, a network side device is provided, comprising a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement the steps of the method according to the third aspect.

[0012] In an eighth aspect, a network-side device is provided, comprising a processor and a communication interface, wherein the communication interface is configured to obtain first information, the first information comprising a channel prediction result and model parameters of a target specific operator model, or comprising model parameters of a target specific operator model; the target specific operator model is a specific operator model constructed by a UE based on historical channel estimation results; the channel prediction result is a channel result predicted by the UE based on the model parameters of the target specific operator model and the historical channel estimation results; and the processor is configured to perform channel prediction according to the first information.

[0013] In a ninth aspect, a communication system is provided, comprising a UE and a network-side device, the UE is configured to perform the steps of the channel prediction method according to the first aspect, and the network-side device is configured to perform the steps of the channel prediction method according to the third aspect.

[0014] In a tenth aspect, a readable storage medium is provided, the readable storage medium stores a program or instructions, the program or instructions are executed by a processor to implement the steps of the method according to the first aspect, or to implement the steps of the method according to the third aspect.

[0015] In an eleventh aspect, a chip is provided, the chip comprises a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or instructions to implement the method according to the first aspect, or to implement the method according to the third aspect.

[0016] In a twelfth aspect, a computer program / program product is provided, 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 channel prediction method according to the first aspect, or to implement the steps of the channel prediction method according to the third aspect.

[0017] In the embodiment of the present application, the UE can send first information (for the network side device to perform channel prediction) to the network side device; the network side device can receive the first information and perform channel prediction according to the first information; the first information includes a channel prediction result and model parameters of a target specific operator model, or includes model parameters of the target specific operator model; wherein the channel prediction result is a channel result predicted by the UE based on the model parameters of the target specific operator model and historical channel estimation results, and the target specific operator model is a specific operator model constructed by the UE based on the historical channel estimation results; the network side device performs channel prediction according to the first information. Through the scheme, since the UE can send first information including model parameters of a specific operator model constructed by the UE based on historical channel estimation results, or including model parameters of a specific operator model constructed by the UE based on historical channel estimation results and a channel prediction result based on the model parameters to the network side device, the network side device can perform channel prediction according to the first information after receiving the first information; that is, the channel prediction method provided in the embodiment of the present application can indirectly predict the channel based on the model parameters sent by the UE, or based on the model parameters and the channel prediction result, thereby reducing the calculation complexity of channel prediction through a specific operator model. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A schematic diagram of an architecture of a communication system provided in the embodiment of the present application;

[0019] Figure 2 A schematic diagram of a channel prediction method provided in the embodiment of the present application;

[0020] Figure 3 A schematic diagram of sampling in a historical time domain channel through a sliding window in the channel prediction method provided in the embodiment of the present application;

[0021] Figure 4 A schematic diagram of a channel prediction process of the channel prediction method provided in the embodiment of the present application;

[0022] Figure 5 A schematic diagram of a structure of a channel prediction device provided in the embodiment of the present application;

[0023] Figure 6 A schematic diagram of a structure of a channel prediction device provided in the embodiment of the present application;

[0024] Figure 7 A schematic diagram of a hardware structure of a communication device provided in the embodiment of the present application;

[0025] Figure 8 A schematic diagram of a hardware structure of a UE provided in the embodiment of the present application;

[0026] Figure 9 Fig. 1 is a schematic diagram of a hardware structure of a network-side device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art belong to the scope of protection of the present application.

[0028] The terms “first”, “second”, and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than that illustrated or described herein, and the objects distinguished by “first”, “second” are generally of a kind and do not limit the number of objects, for example, the first object can be one or more. In addition, “and / or” in the specification and claims means at least one of the connected objects, and the character “ / ” generally represents an “or” relationship between the associated objects before and after.

[0029] It is worth noting that the technology described in the embodiments of the present application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, 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 in 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 terminology is used in most of the following description, but these technologies can also be applied to applications other than NR system applications, such as 6th Generation (6G) communication systems.

[0030] Figure 1 A block diagram of a wireless communication system to which embodiments of the present application can be applied is shown. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a terminal-side device such as a mobile phone, a Tablet Personal Computer, a Laptop Computer, a Personal Digital Assistant (PDA), a palmtop computer, a netbook, an ultra-mobile personal computer (UMPC), a Mobile Internet Device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, a vehicle-mounted device (VUE), a pedestrian terminal (PUE), a smart home (a home device with a wireless communication function such as a refrigerator, a television, a washing machine, or furniture), a game console, a personal computer (PC), a kiosk, or a self-service machine, and the wearable device includes a smart watch, a smart bracelet, a smart earphone, smart glasses, smart jewelry (a smart bracelet, a smart necklace, a smart ring, a smart necklace, a smart anklet, a smart necklace, and the like), a smart wristband, smart clothing, and the like. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device, and the access network device 12 can also be referred to as a radio access network device, a radio access network (RAN), a radio access network function, or a radio access network unit. The access network device 12 can include a base station, a WLAN access point, or a WiFi node, and the base station can 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 transmitting receiving point (TRP), or some other appropriate terminology in the art, as long as the same technical effects are achieved. The base station is not limited to a specific technical term, and it should be noted that only a base station in an NR system is taken as an example for description in the embodiments of the present application, and the specific type of the base station is not limited.

[0031] According to the Taylor expansion formula, anything nonlinear can be fitted by something linear, so theoretically, linear models can simulate most phenomena in the physical world.

[0032] Suppose that phenomenon P has N attributes to describe it:

[0033] X = [x1, x2, ..., x N Where X is the set of attributes of phenomenon P, x N Let N be the attribute of phenomenon P.

[0034] Linear model: This refers to an attempt to learn a function that predicts linear P using a linear combination of N attributes. A linear model can be defined as: f(X) = (w1x1 + b1) + (w2x2 + b2) + ... + (w...). N x N +b N ), w N and b N These are the linear coefficient and offset value of the Nth attribute of phenomenon P, respectively.

[0035] The linear model can be written in vector form as follows:

[0036] f(X) = WX T +b

[0037] W = [w1, w2, ..., w N ]

[0038] b = [b1, b2, ..., b N ]

[0039] If the linear model f(X) is a real-valued function in the real number field, then the linear model f(X) is called a linear regression model. Theoretically, if the parameters W and b of the linear model f(X) can be solved, then the phenomenon P can be deduced and predicted using this linear model f(X).

[0040] Time-varying channel processes can be viewed as time-autoregressive moving average processes, which can be considered completely predictable given sufficient signal-to-noise ratio. Time-varying channels can be recursively predicted using linear models; in this case, the linear model is a time filter that takes historical channel estimation results as input and outputs the channel at future time intervals.

[0041] The channel can be modeled as a linear process of order P:

[0042]

[0043] Where H(n) represents the channel information at time n, P is the order of the linear model, and w(n) is white noise. The filter coefficients of the linear model, the coefficients and the order of the linear model are referred to as linear model parameters.

[0044] To utilize the linear model to perform channel prediction, the parameters (specifically, parameter values) of the linear model must be obtained. There are many methods for obtaining the parameter values of the linear model, and here, the least square method is taken as an example to construct an overdetermined equation set:

[0045]

[0046] where H n represents channel information at the nth moment, Y is a channel information matrix at a moment to be fitted, and has a dimension of N x 1; X is a channel information matrix at historical moments used to fit Y, and has a dimension of N x n; a is a linear coefficient of the linear model; and w is usually referred to as a residual error. Here, n = P,

[0047] It can be understood that for the above formula (1), it is assumed that, for example, the channel sample contains channel information at 10 continuous moments, and it is assumed that the 10 moments are t1, t2, t3, t4, t5, t6, t7, t8, t9, and t10. It is assumed that the order of the linear model is set to 4, so that four historical moments of channel information are used to fit the channel information at the 10th moment, and thus the channel information at the 10th moment can be represented as H10 = [H6, H7, H8, H9] * a + w, or H10 = [H5H6, H7, H8] * a + w, or H10 = [H4, H5, H6, H7] * a + w, and so on.

[0048] The least square estimation of the linear model coefficient a is:

[0049] a = (X H X) -1 X H Y.

[0050] Through the overdetermined equation set, it can be known that the residual error w is:

[0051] w = Y - Xa.

[0052] The residual error w represents the difference between the theoretical value and the actual value, and the linear model coefficient a that makes the residual error square sum reach the minimum indicates that the linear model fits the data sample best, that is, the channel prediction at a future moment can be realized. The residual error square sum formula (equation) is:

[0053]

[0054] That is, the coefficient equation of the linear model can be determined based on the residual sum of squares formula (equation). It can be seen that the equation is also missing the column number of the matrix X, that is, the order P of the linear model; the column number of the matrix X can also be understood as how many historical channel samples of the input linear model are needed for channel prediction at future time.

[0055] It can be understood that a good linear model generally requires a small residual, and at the same time the model is relatively simple, that is, the order of the linear model is required to be low, so that some order determination criteria can be used to compare the pros and cons of linear models of different orders. Common order determination criteria include the final prediction error criterion FPE (Final Prediction Error, FPE), Akaike information criterion AIC (Akaike information criterion, AIC) and Bayesian information criterion BIC (Bayesian information criterion, BIC) criterion function.

[0056] It can be seen from the above discussion that the advantage of using a linear model for channel prediction is that the model is very simple, and the linear model only needs endogenous variables and does not need to rely on other exogenous variables; thus the linear model modeling is relatively simple. However, the disadvantage of the linear model is also obvious, specifically: when using a linear model for channel prediction in a complex environment, the model parameters will be large and the calculation amount will be large; further, the current channel prediction based on the linear model has certain limitations, and can only predict the channel at a future time interval with the historical input data.

[0057] In the channel prediction method provided by the embodiments of the present application, the UE can send the first information including the model parameters of the specific operator model constructed by the UE based on the historical channel estimation result and / or the channel prediction result based on the model parameters to the network side device, so that the network side device can perform channel prediction according to the first information after receiving the first information, that is, the network side device can indirectly predict the channel based on the model parameters and / or the channel prediction result sent by the UE, thereby reducing the calculation complexity of channel prediction by the specific operator model.

[0058] The information processing method provided by the embodiments of the present application will be described in detail in combination with the specific embodiments and application scenarios thereof and the accompanying drawings.

[0059] The embodiments of the present application provide a signal transmission method, Figure 2 A flowchart of a channel prediction method provided by the embodiments of the present application is shown. As shown in Figure 2 The signal transmission method provided by the embodiments of the present application can include the following steps 201 and 203.

[0060] Step 201, the UE sends the first information to the network side device.

[0061] The first information can be used for the network-side device to perform channel prediction, and the first information includes a channel prediction result and model parameters of the target specific operator model, or includes model parameters of the target specific operator model. The channel prediction result is a channel result predicted by the UE based on historical channel estimation results and model parameters of the target specific operator model, and the target specific operator model is a specific operator model constructed by the UE based on the historical channel estimation results.

[0062] Optionally, in the embodiments of the present application, the target specific operator model can be a linear model, a polynomial fitting model, an esprit algorithm model, a music algorithm model, or any other model that can be used for channel prediction. The specific model can be determined according to actual use requirements, and the embodiments of the present application are not limited.

[0063] Optionally, in the embodiments of the present application, the historical channel estimation result is a channel estimation result obtained by the UE using a conventional method (such as estimating the channel by measuring CSI-RS / DMRS).

[0064] Optionally, in the embodiments of the present application, the UE can construct the target specific operator model based on multiple historical channel estimation results.

[0065] Optionally, in the embodiments of the present application, the model parameters can include a first model order and a first model coefficient. The first model order can be used for the network-side device to determine a target coefficient prediction component, and the first model coefficient can be used for the network-side device to perform channel prediction based on the target coefficient prediction component.

[0066] Optionally, in the embodiments of the present application, when the target specific operator model is a linear model, the model parameters can be linear filter parameters, which can include an order (i.e., the first model order) and a coefficient (i.e., the first model coefficient) of a linear filter.

[0067] In the embodiments of the present application, the UE performs channel prediction based on the target specific operator model, and reports the obtained channel prediction result and the model parameters of the target specific operator model, so as to ensure that the model parameters used by the UE and the network-side device are uniform, and facilitate the network-side device (such as a base station) to select a suitable target coefficient prediction component to perform model coefficient prediction in the future. After obtaining the model coefficient in the future, the network-side device can predict the channel in the future based on the obtained model coefficient.

[0068] Optionally, in the embodiments of the present application, the target coefficient prediction component can be at least one of: a coefficient prediction component constructed by one or more cell identifiers, a coefficient prediction component constructed by one or more transmission and reception point (TRP) identifiers, a coefficient prediction component constructed by one or more channel feature information, a coefficient prediction component constructed by one or more beam identifiers in a cell, and a coefficient prediction component constructed by one or more geographical locations.

[0069] Optionally, in the embodiments of the present application, the channel feature information refers to a precoding matrix indicator (PMI), a channel quality indication (CQI), a rank indicator (RI), and the like obtained through channel state information (CSI) feedback.

[0070] It can be understood that, in the embodiments of the present application, the network side device can construct UEs with the same channel feature information into one coefficient prediction component.

[0071] It should be noted that the geographical locations can be artificially divided, and the division method of the geographical locations is not limited.

[0072] Optionally, in the embodiments of the present application, when the target coefficient prediction component is a coefficient prediction component constructed by one or more cell identifiers, the cell identifiers include a cell identifier of a cell of the UE. When the target coefficient prediction component is a coefficient prediction component constructed by one or more TRP identifiers, the TRP identifiers include a TRP identifier of the UE.

[0073] Optionally, in the embodiments of the present application, the network side device can construct a coefficient prediction component in units of one or more cell identifiers, or construct a coefficient prediction component in units of one or more TRP identifiers.

[0074] Optionally, in the embodiments of the present application, the target coefficient prediction component can be any one of: a linear coefficient prediction component specific to each RB, a coefficient prediction component specific to each subband, a coefficient prediction component for multiple RBs or multiple subbands, and a coefficient prediction component for a wideband.

[0075] In a case where the target coefficient prediction component is a linear coefficient prediction component specific to each RB, the frequency domain prediction granularity of the target coefficient prediction component is the RB; in a case where the target coefficient prediction component is a linear coefficient prediction component specific to each subband, the frequency domain prediction granularity of the target coefficient prediction component is the subband; in a case where the target coefficient prediction component is a linear coefficient prediction component specific to multiple RBs, the frequency domain prediction granularity of the target coefficient prediction component is the multiple RBs; in a case where the target coefficient prediction component is a linear coefficient prediction component specific to multiple subbands, the frequency domain prediction granularity of the target coefficient prediction component is the multiple subbands; and in a case where the target coefficient prediction component is a linear coefficient prediction component specific to a wideband, the frequency domain prediction granularity of the target coefficient prediction component is the wideband.

[0076] Optionally, in an embodiment of the present application, the target coefficient prediction component can be a coefficient prediction component based on a neural network (for example, a convolutional neural network) or a coefficient prediction component based on any artificial intelligence (AI) network with learning ability, and the specific implementation can be determined according to actual use requirements, which is not limited in the embodiment of the present application.

[0077] Optionally, in an embodiment of the present application, the channel prediction result can be obtained by performing channel prediction based on the model parameters and the historical channel estimation result in a case where the first model order is less than or equal to a target number (for the convenience of description, referred to as a target number below) of the historical channel estimation results on which the target operator model is constructed.

[0078] It can be understood that, in an embodiment of the present application, whether the first model order is less than or equal to the target number is a channel prediction condition for whether the UE performs channel prediction based on the target specific operator model. If the first model order is less than or equal to the target number, the UE can perform channel prediction based on the model parameters and the historical channel estimation result, and the network side device sends the channel prediction result and the model parameters of the target specific operator; if the first model order is greater than the target number, the UE does not perform channel prediction based on the model parameters and the historical channel estimation result this time, and does not report the model parameters of the target specific operator model to the network side device, so that the UE needs to re-construct the specific operator model.

[0079] Exemplarily, assuming that the target specific operator model is a linear model, when the first model order is less than or equal to the target order, the UE can perform channel prediction at equal interval time through the model parameters and the historical channel estimation results. It can be understood that, due to the characteristics of the linear model, the time of UE prediction cannot be arbitrarily specified, and only the channel at a time interval equal to the historical data (i.e., the historical channel estimation results) from the current prediction time can be predicted, and only the channel at one time interval in the future can be predicted; then the UE can send the channel prediction result of this prediction and the model parameters of the target specific operator to the network side device.

[0080] Optionally, in the embodiment of the application, the first information can further include a model coefficient prediction granularity expected by the UE, the model coefficient prediction granularity being used for the network side device to perform prediction of the model coefficient; wherein the model coefficient prediction granularity can include at least one of the following: a time domain granularity, a frequency domain granularity.

[0081] In the embodiment of the application, since the model coefficient prediction granularity expected by the UE is included in the first information, after the network side device receives the first information, the network side device can refer to the model prediction granularity expected by the UE to perform prediction of the model coefficient, thereby ensuring the accuracy of channel prediction by the network side device.

[0082] Optionally, in the embodiment of the application, the step 201 can be implemented through the following step 201a or step 201b.

[0083] Step 201a, the UE sends the first information to the network side device on a target resource.

[0084] Wherein, the target resource can include at least one of the following: a radio resource control (RRC) pre-configured fixed resource, a medium access control-control element (MAC CE) indicated resource, and a downlink control information (DCI) indicated resource.

[0085] Step 201b, the UE sends the first information to the network side device on a resource for sending CSI measurement information.

[0086] It should be noted that, in the embodiment of the application, the UE sends the first information to the network side device on the resource for sending CSI measurement information, which can avoid additional time delay and resource configuration caused by signaling interaction for reporting the first information.

[0087] In the embodiments of the present application, the first information can be sent to the network side device on different resources, so that the flexibility of sending the first information can be improved.

[0088] In step 202, the network side device acquires the first information.

[0089] For the description of the first information, refer to the related description of the first information in the above embodiments, and details are not described herein again to avoid repetition.

[0090] Optionally, in the embodiments of the present application, the network side device acquiring the first information can be that the network side device receives the first information sent by the UE, or the network side device can acquire the first information by other means (for example, the first information is pre-stored in the network side device), and the specific method can be determined according to actual use requirements, which is not limited in the embodiments of the present application.

[0091] In step 203, the network side device performs channel prediction according to the first information.

[0092] Optionally, in the embodiments of the present application, the model parameters include the first model order and the first model coefficient, and the step 203 can be implemented by the following steps A to C.

[0093] In step A, the network side device determines a target coefficient prediction component corresponding to the first model order according to the first model order.

[0094] Optionally, in the embodiments of the present application, the order corresponding to the target coefficient prediction component is the same as the first model order. For the description of the order corresponding to the target coefficient prediction component, refer to the related description of the order corresponding to the coefficient prediction component in the following embodiments, and details are not described herein again to avoid repetition.

[0095] In step B, the network side device performs model coefficient prediction according to the first model coefficient by using the target coefficient prediction component, to obtain a second model coefficient.

[0096] Optionally, in the embodiments of the present application, the network side device can input the first model coefficient into the target coefficient prediction component, so as to predict the model coefficient at the future time by using the target coefficient prediction component and the first model coefficient, to obtain the second model coefficient. That is, the second model coefficient is the model coefficient at the future time.

[0097] Optionally, in the embodiments of the present application, the time-domain granularity of the second model coefficient can be any one of the following: one time slot, multiple time slots, the remaining time slots of the current frame, the measurement time of the CSI, multiple CSI measurement times, every time slot within a CSI measurement period, every time slot within multiple CSI measurement periods; and / or the frequency-domain granularity of the second model coefficient can be any one of the following: a resource block (RB), a sub-band, and a wideband.

[0098] In the embodiments of the present application, without changing the target specific operator model (specifically, a linear model), the channel prediction method provided by the embodiments of the present application introduces a target coefficient prediction component to predict the linear coefficients of the linear model at multiple time points with equal intervals, and then the channel states at multiple time points with equal time intervals can be obtained, so that the channel prediction accuracy can be improved.

[0099] Optionally, in the embodiments of the present application, when the first information further includes the model coefficient prediction granularity expected by the UE, the above step B can be implemented through the following step B1.

[0100] In step B1, when the first information further includes the model coefficient prediction granularity expected by the UE, the network side device adopts the target coefficient prediction component to perform prediction on the model coefficient according to the first model coefficient, the model coefficient prediction granularity expected by the UE, and other model coefficient prediction granularities expected by other UEs, to obtain the second model coefficient.

[0101] For the description of the model coefficient prediction granularity expected by the UE, refer to the related description of the model coefficient prediction granularity expected by the UE in the above step 101, and details are not described here again to avoid repetition.

[0102] In the embodiments of the present application, when the first information further includes the model coefficient prediction granularity expected by the UE, the base station (network side device) can perform reasonable granularity allocation according to the model parameter, the model coefficient prediction granularity expected by the UE, and the linear coefficient prediction demand (i.e., the linear model prediction granularity expected by other UEs) from other UEs at this time, and perform prediction on the second model coefficient; that is, the network side device can comprehensively predict the model parameter according to the first model coefficient, the model coefficient prediction granularity expected by the UE, and other model coefficient prediction granularities expected by other UEs, so as to improve the accuracy and rationality of the network side device in predicting the model coefficient.

[0103] Optionally, in the embodiments of the present application, if the first information includes the model coefficient prediction granularity expected by the UE, the network side device can first compare the model coefficient prediction granularity expected by the UE with the target prediction granularity of the target coefficient prediction component after determining the target coefficient prediction component, and if the model coefficient prediction granularity expected by the UE matches the target prediction granularity (for example, both are the same), the network side device can perform prediction of the model coefficient according to the model coefficient prediction granularity expected by the UE to obtain the second model coefficient. If the model coefficient prediction granularity expected by the UE does not match the target prediction granularity (for example, both are different), the network side device can perform prediction of the model coefficient according to the target prediction granularity to obtain the second model coefficient.

[0104] It should be noted that in the embodiments of the present application, when the model coefficient prediction granularity expected by the UE does not match the target prediction granularity, the network side device can determine the prediction granularity for performing prediction of the model coefficient according to the upward (wide granularity) or downward (narrow granularity) compatible strategy.

[0105] It can be understood that in the embodiments of the present application, the frequency domain granularity is arranged in the order from wide to narrow as follows: wideband, subband, RB; that is, the size order of the frequency domain granularity is: wideband>subband>RB.

[0106] Optionally, in the embodiments of the present application, the above step B can be implemented by the following step B2.

[0107] Step B2, in the case that the model coefficient prediction granularity expected by the UE does not match the target prediction granularity, the network side device adopts the target coefficient prediction component to perform prediction of the model coefficient according to the first model coefficient and the target prediction granularity, and obtains the second model coefficient.

[0108] In the following, the step B2 is exemplarily described in combination with five cases that the model coefficient prediction granularity expected by the UE does not match the target prediction granularity, which are (a-e) as follows.

[0109] a, the model coefficient prediction granularity expected by the UE is a subband / RB in a wideband, and the target prediction granularity is a wideband;

[0110] Optionally, in the embodiments of the present application, in the case that the model coefficient prediction granularity expected by the UE is a subband / RB in a wideband, and the target prediction granularity is a wideband, the second model coefficient is the prediction result of the wideband shared by each subband / RB in the wideband.

[0111] b, the model coefficient prediction granularity expected by the UE is a wideband, and the target prediction granularity is a subband in the wideband.

[0112] Optionally, in the embodiment of the present application, when the UE expected model coefficient prediction granularity is a subband and the target prediction granularity is a subband, the second model coefficient is the prediction result of the subband.

[0113] c. The UE expected model coefficient prediction granularity is a RB in a subband, and the target prediction granularity is a subband.

[0114] Optionally, in the embodiment of the present application, when the UE expected model coefficient prediction granularity is a RB in a subband and the target prediction granularity is a subband, the second model coefficient is the prediction result of the subband shared by each RB in the subband.

[0115] d. The UE expected model coefficient prediction granularity is a subband, and the target prediction granularity is a RB in a subband.

[0116] Optionally, in the embodiment of the present application, when the UE expected model coefficient prediction granularity is a subband and the target prediction granularity is a RB in a subband, the second model coefficient is the prediction result of the RB with the lowest CQI among all RBs in the subband.

[0117] e. The UE expected model coefficient prediction granularity is a wideband, and the target prediction granularity is a RB under a subband in the wideband.

[0118] Optionally, in the embodiment of the present application, when the UE expected model coefficient prediction granularity is a wideband and the target prediction granularity is a RB under a subband in the wideband, the second model coefficient uses the result of the RB with the lowest CQI among all RBs in the wideband.

[0119] The step B is exemplarily described below in combination with a specific example.

[0120] Exemplarily, assuming that the base station (i.e., the network side device) receives the first information that the UE expected frequency domain granularity is a subband, the base station can determine whether to set the prediction granularity to the granularity (i.e., the subband) expected by the terminal according to the actual situation of the current predicted business requirement. Specifically, if the determined target prediction granularity is sufficient, the base station can use the target coefficient prediction component to perform model coefficient prediction of the granularity expected by the UE. If the target prediction granularity determined by the base station is a wideband, i.e., the target prediction granularity does not match the subband expected by the UE, the base station can perform channel prediction shared by the wideband for each subband in the wideband, i.e., the obtained prediction result is the prediction result of the wideband shared by each subband in the wideband. That is, each subband shares the wideband, and each subband performs slot-level model coefficient prediction using the wideband.

[0121] In the embodiments of the present application, in the case that the model coefficient prediction granularity expected by the UE does not match the target prediction granularity, the network side device can perform model coefficient prediction based on the target prediction granularity, so as to improve the success probability of the network side device in performing model coefficient prediction.

[0122] Step C, the network side device performs channel prediction according to the second model coefficient and the first model order.

[0123] Optionally, in the embodiments of the present application, the network side device can perform channel prediction according to the second model coefficient, the first model order and the channel prediction result sent by the UE.

[0124] Optionally, in the embodiments of the present application, when the target specific operator model is a linear model, the network side device can predict the channel at multiple time intervals in the future according to the second model coefficient, the first model order, the channel prediction result sent by the UE and the historical channel estimation result sent by the UE.

[0125] In the embodiments of the present application, the network side device can determine the target coefficient prediction component corresponding to the first model order based on the acquired first model order, and perform prediction of the model coefficient according to the first model coefficient by using the target coefficient prediction component to obtain the second model coefficient, and perform channel prediction according to the second model coefficient and the first model order, that is, the network side device can indirectly perform channel prediction according to the model coefficient predicted by the network side device and the model order predicted by the UE, so that compared with the scheme in the related art in which the network side device directly uses a specific operator model to perform channel prediction, the channel prediction method provided in the embodiments of the present application indirectly predicts the channel by predicting the model coefficient, thereby reducing the complexity of channel prediction.

[0126] In the channel prediction method provided in the embodiments of the present application, the UE can send the first information including the model parameters of the specific operator model constructed by the UE based on the historical channel estimation result and / or the channel prediction result based on the model parameters to the network side device, so that the network side device can perform channel prediction according to the first information after receiving the first information, that is, the channel prediction method provided in the embodiments of the present application can indirectly predict the channel based on the model parameters and / or the channel prediction result sent by the UE, thereby reducing the calculation complexity of channel prediction by using a specific operator model.

[0127] Optionally, before step 201, the channel prediction method provided in the embodiments of the present application can further include the following steps 204 and 205.

[0128] Step 204, the network side device sends second information to the UE.

[0129] Step 205, the UE receives the second information.

[0130] In the embodiments of the present application, the second information can be used to indicate a minimum number threshold of historical channel estimation results required by the UE to construct the target specific operator model.

[0131] Optionally, in the embodiments of the present application, the minimum number threshold is an empirical value obtained by the network side device when performing offline training of the coefficient prediction component. The minimum number threshold is determined by the network side device according to at least one order value, the at least one order value being an order value corresponding to at least one order set, the number of orders in the at least one order set satisfying a preset condition, and each order set including a plurality of orders with the same order value.

[0132] Optionally, in the embodiments of the present application, the preset condition includes any one of the following: the number of orders in the at least one order set is greater than or equal to a preset number threshold, and the at least one order set is the first M order sets in N order sets arranged in descending order of order number; wherein M is the same as the number of the at least one order set, and M is a positive integer.

[0133] Optionally, in the embodiments of the present application, assuming that the orders in the at least one order set satisfying the preset condition are N orders, then the N orders include any one of the following:

[0134] all orders used by the network side device when performing offline training of the coefficient prediction component corresponding to the beam of the UE;

[0135] all orders used by the network side device when performing offline training of the coefficient prediction component corresponding to the geographic area where the UE is located;

[0136] all orders used by the network side device when performing offline training of the coefficient prediction component corresponding to the tracking area (TA) corresponding to the UE;

[0137] all orders used by the network side device when performing offline training of the coefficient prediction component corresponding to the same channel feature information.

[0138] It should be noted that, in the embodiments of the present application, the network side device can use the model coefficients of a plurality of specific operator models with the same order to perform offline training of the coefficient prediction component, and obtain a coefficient prediction component; the order corresponding to the coefficient prediction component is the same as the order of the plurality of specific operator models.

[0139] It can be understood that, in the embodiments of the present application, after receiving the second information, the UE can use conventional means to perform channel estimation to collect historical channel estimation results; when the number of collected historical channel estimation results reaches the above-mentioned minimum number threshold, the UE can start to attempt to construct the target specific operator model based on all collected historical channel estimation results.

[0140] Optionally, in embodiments of the present application, the second information can include at least one of the following: one parameter or a set of parameters pre-configured by RRC, MAC CE, and DCI.

[0141] Optionally, in embodiments of the present application, when one parameter is pre-configured by RRC, the minimum number threshold can be indicated by the parameter only, and the parameter is the minimum number threshold. When a set of parameters is pre-configured by RRC, for example, the set of parameters can be a set of order values, respectively 7, 9, and 11, the second information can further include MAC CE or DCI to determine one parameter from the set of parameters as the minimum number threshold through the MAC CE and the DCI.

[0142] Optionally, in embodiments of the present application, when the second information includes MAC CE or DCI, the minimum number threshold can be included in the MAC CE or the DCI, and the UE can directly obtain the minimum number threshold by decoding the DCI and the MAC CE; for example, an indication information can be carried on the MAC CE or the DCI to indicate the minimum number threshold through the indication information.

[0143] In embodiments of the present application, the difference between the MAC CE and the DCI is the delay, and the delay of the MAC CE > the delay of the DCI.

[0144] In addition, in terms of delay, RRC > MAC CE > DCI, that is, the higher the signaling of the upper layer, the higher the delay, and the more information can be carried.

[0145] In embodiments of the present application, since the network side device can determine the minimum number threshold of the historical channel estimation results required by the UE to construct the target specific operator model through the second information, after the UE receives the second information, the target specific operator model can be created after the number of the collected historical channel estimation results is greater than or equal to the minimum number threshold, thereby saving the UE's overhead and improving the accuracy of the target specific operator model.

[0146] Optionally, in embodiments of the present application, before the above step C, the channel prediction method provided by the embodiments of the present application can further include the following step 206.

[0147] Step 206, the network side device determines a target coefficient prediction module according to the target information.

[0148] In embodiments of the present application, the target coefficient prediction module can include a plurality of coefficient prediction components, and the plurality of coefficient prediction components can include a target coefficient prediction component.

[0149] The target information can include at least one of the following: geographical location information of the UE, CSI measurement information sent by the UE, a tracking area identifier (TAI) corresponding to the UE, a beam coverage range of the UE, a beam identifier of the UE, and scene information corresponding to the UE.

[0150] Optionally, in the embodiments of the present application, the scene information corresponding to the UE can be scene information of a geographical location indicated by the geographical location information of the UE. The scene information of the geographical location can indicate at least one of the following: a dense building group scene, an open scene (for example, a highway), and a town scene.

[0151] It can be understood that, in the embodiments of the present application, the target information is different, and the target coefficient prediction module determined by the network side device can also be different, so that the target coefficient prediction component is also different. The specific determination can be made according to actual use requirements, and the embodiments of the present application are not limited.

[0152] In order to better understand the channel prediction method provided in the embodiments of the present application, the way in which the network side device builds the coefficient prediction model is exemplarily described below.

[0153] i. Considering the generality and prediction accuracy of the coefficient prediction module, the network side device can divide (classify) the coefficient prediction components built by the network side device according to factors affecting the channel state, to form a plurality of coefficient prediction modules, and each coefficient prediction module includes a plurality of coefficient prediction components. The coefficient prediction components can be built according to one of the following standards:

[0154] According to the beam coverage range or the beam identifier to which the UE belongs, the coefficient prediction modules of different beams are divided;

[0155] According to the TAI, the coefficient prediction modules of different TAs are built;

[0156] According to the geographical location information of the UE, the coefficient prediction modules on different geographical locations are built;

[0157] According to the CSI measurement information (result) with a large difference, such as CQI and PMI, the coefficient prediction modules of different CSI measurement information are built.

[0158] Optionally, in the embodiments of the present application, the network side device builds the coefficient prediction modules under different standards according to the factors that most affect the channel state, and each coefficient prediction module can include linear coefficient prediction components under different model orders.

[0159] ii. Considering the influence of different model orders on model coefficient prediction, the network side device can build coefficient prediction modules of different model orders.

[0160] iii. Considering channel prediction in different scenarios, network-side devices can construct one or more of the following coefficient prediction modules:

[0161] Each RB has a unique coefficient prediction module, which is suitable for dense building cluster scenarios;

[0162] Each sub-band has a unique coefficient prediction module, suitable for rural scenarios;

[0163] A coefficient prediction module with multiple RBs or multiple sub-bands, suitable for open scenes;

[0164] The broadband coefficient prediction module is suitable for open environments.

[0165] It should be noted that the channel state of the UE can change significantly with different surrounding environments. The coefficient prediction module can be built based on the factors that have the greatest impact on the channel transformation conditions, rather than a terminal-specific coefficient prediction module, which increases the versatility of the coefficient prediction module.

[0166] Furthermore, as the UE moves and the environment changes, the target coefficient prediction module determined by the network-side equipment for predicting model coefficients will also change accordingly, improving prediction flexibility and accuracy.

[0167] Optionally, in the embodiments of this application, if the model coefficients in each time slot within the prediction interval are known, the channel prediction method provided in the embodiments of this application can perform channel prediction in each time slot within the future interval.

[0168] To facilitate understanding of the channel prediction method provided in the embodiments of this application, the execution process of the channel prediction method provided in the embodiments of this application will be exemplarily described below using a specific operator model (e.g., a target specific operator model) as a linear model.

[0169] I. Construction of the training dataset for the coefficient prediction component:

[0170] To simplify the description, this scheme is briefly described using t+k channels of a single UE's historical time under a beam.

[0171] Assuming UE i The historical time-domain channel is: H = [H1, H2, ... H t ,...,H t+k ],like Figure 3 As shown, solid box 30 is a sliding window whose size can be configured; and assume that a sliding window of size T (note: K >> T) is in the UE isliding in the historical channel. Each time sliding one slot and each time sliding, the overdetermined equation set of linear model is constructed with the time domain channel sample values in the current sliding window as data samples, the interval of time domain channel samples is consistent with the CSI-RS measurement period configured by the network side RRC, the order P (P > 1) and linear coefficient a of the linear model are calculated. The specific steps are as follows:

[0172] Step 1, assuming that at time t, the sampling interval is g, the total number of samples is n, and the window size is T, then in the sliding window, specifically Figure 3 The historical channel sample set Y1 in the implementation block 30 in the above formula is

[0173] Y1 = [H t-T+1*g+1*1 ,...,H t-T+(n-1)*g+(n-1)*1 ];

[0174] A linear model is constructed according to the historical channel sample set Y1, the optimal order P1 of the linear model is obtained according to the criterion function, and then the linear coefficient under the historical channel sample set Y1 is calculated.

[0175]

[0176] Wherein, is the first linear coefficient element under the optimal order P1, There are P1 linear coefficient elements in total.

[0177] Step 2, the linear coefficient a P2 of the historical channel sample set Y1 is calculated. After the calculation is completed, the sliding window is moved forward by one slot, and after the sliding window is moved by one slot, the channel sample values in the sliding window are Figure 3 The channel sample values in the implementation block 31 in the above formula are used as another historical channel sample set Y2; according to step 1, a linear model is constructed according to the historical channel sample set Y2, and the optimal order P2 of the linear model is obtained according to the criterion function, and then the linear coefficient under the historical channel sample set Y2 is calculated.

[0178]

[0179] Wherein, is the first linear coefficient element under the optimal order P2, There are P2 linear coefficient elements in total.

[0180] Step 3, the linear coefficient a of the historical channel sample set Y2 is calculated. After the calculation is completed, the sliding window continues to move forward by one slot. Without loss of generality, when the sliding window moves to the t+k time, the sliding window is Figure 3 ​ Figure 3 the historical channel sample set Y N is:

[0181] Y N = [H t+k-T , H t+k ,..., H t+k-T+(n-1)*g+(n-1)*1 ];

[0182] According to the historical channel sample set Y N , a linear model is constructed, and the optimal order P of the linear model is obtained according to the criterion function N , and then the linear coefficients under the historical channel sample set Y N are calculated is:

[0183]

[0184] In this way, the linear coefficients of the N linear models are obtained, which are a P1 , a P2 ,..., and a PN .

[0185] II. Offline training of the coefficient prediction component, also known as coefficient prediction component creation:

[0186] The linear coefficients corresponding to the same order of the linear coefficients of the N linear models are combined together to construct a linear coefficient set under different orders. The linear coefficients under each linear order are sorted according to the chronological order of the sliding window (for example: if time j < k, then the arrangement order of the linear coefficient a j calculated by the sliding window at time j and the linear coefficient a k calculated by the sliding window at time k is [a j , a k ]). Then the sorted linear coefficient set under different orders is taken as the input of the AI network model for training to obtain the coefficient prediction component under different orders.

[0187] Specifically, assuming that the linear coefficient set under the combined order P k is and the linear coefficient set includes S linear coefficients, then can be represented as:

[0188]

[0189] wherein, represents the s-th linear coefficient under the linear order P k , and can be represented as:

[0190]

[0191] wherein, represents the p k th element of the s k th linear coefficient of the linear model of order P

[0192] The AI network model is trained by inputting the training data set into the AI network model, and a generalized coefficient prediction component is obtained.

[0193] It can be seen that each coefficient prediction component is obtained by offline training of a linear coefficient set of the same order, and different coefficient prediction components are obtained by offline training of linear coefficient sets of different orders.

[0194] It should be noted that in the embodiments of the present application, the base station can use a time sliding window to construct a linear coefficient set of a linear model in the historical time domain channel, and put the linear coefficient set into an AI network model for offline training to learn the linear model coefficients at any prediction time.

[0195] III. Channel prediction process:

[0196] Assuming that the network side device is a base station in an open scene (such as a highway), since there are few obstacles near the base station, most of the propagation conditions are line of sight (LOS), so the multipath effect is not obvious, and the channels between different RBs will not change much, so the coefficient prediction module of the base station in the open scene is a wideband coefficient prediction module.

[0197] Figure 4 The flowchart for using a linear model to predict a channel is shown in FIG. 5, and the specific steps are as follows:

[0198] 1. The UE determines the model parameters of the linear model (i.e., the target specific operator model).

[0199] a) After the UE accesses the base station, the base station can indicate a channel estimation collection quantity reference value N to the UE by RRC signaling (i.e., second information), that is, the minimum number threshold of historical channel estimation results required by the UE to construct the target specific operator model, and N is a positive integer.

[0200] b) If the UE has not yet collected N historical channel estimation results, the UE can continue to collect historical channel estimation results until the number of collected historical channel estimation results reaches N. Figure 4 ​As shown, after the number of historical channel estimation results collected by the UE reaches N, the UE can use the N historical channel estimation results to attempt to construct an over-determined equation set of the linear model; then, the UE can determine the order P (i.e., the first model order) of the linear model according to the information theory criterion function. After determining the order P, the UE can first determine whether the order P satisfies the channel prediction condition, and if the order P satisfies the channel prediction condition, calculate the linear coefficient a of the linear model, otherwise do not calculate the linear coefficient a of the linear model.

[0201] Specifically:

[0202] i. If P > N, it is determined that the linear model does not satisfy the channel prediction condition, so that the UE does not perform channel prediction of the linear model this time, specifically, the calculation of the linear coefficient of the linear model is not performed.

[0203] ii. If P ≤ N, it is determined that the linear model satisfies the channel prediction condition, so that the UE can calculate the linear coefficient a of the linear model.

[0204] 2. Channel prediction based on the linear model by the UE.

[0205] After the UE determines the model parameters of the linear model, the UE can perform channel prediction at equal intervals of time (limited by the linear model, the predicted time cannot be arbitrarily specified, and only the channel at a time interval equal to the historical data from the current prediction time can be predicted, and the channel at one interval time in the future is predicted), Specifically, as shown Figure 4 As shown, assuming that the Nth historical channel estimation result in the N historical channel estimation results is the channel result at time t1, then the UE can perform channel prediction at time t2 according to the model parameters of the linear model and the N historical channel estimation results, that is, the channel prediction result at time t2 can be obtained.

[0206] 3. Parameter reporting, i.e., sending the first information to the network side device.

[0207] After determining the linear coefficient of the linear model, the UE can report the model parameters of the linear model to the network side device, which can include the order P of the linear model and the linear coefficient a of the linear model.

[0208] a) In the reporting stage, in order to avoid additional time delay and resource configuration caused by signaling interaction of reported parameters, therefore, the UE can report the channel prediction result and the model parameters of the linear model (i.e., the first information) to the base station when performing CSI measurement information reporting.

[0209] b) Since the terminal is in high-speed movement, the Doppler shift can cause the phase and / or frequency of the channel at different times to change greatly, so in order to make the base station more accurately predict the channel, the UE can carry the linear coefficient prediction frequency domain granularity required by the UE (i.e., the linear coefficient prediction granularity expected by the UE) in the reported information (i.e., the first information), and the linear coefficient prediction frequency domain granularity is a sub-band.

[0210] 4. The base station performs linear coefficient prediction.

[0211] a) After the base station receives the first information sent by the UE, it can determine the target coefficient prediction module according to which beam coverage the UE is in (i.e., the beam coverage of the UE) or the beam identifier to which the UE belongs (i.e., the beam identifier of the UE), and the target coefficient prediction module includes a plurality of coefficient prediction components.

[0212] b) The base station determines which linear coefficient prediction component (i.e., the target coefficient prediction component) in the target coefficient prediction module to use according to the order P in the model parameters reported by the UE, for example, the target coefficient prediction component is the coefficient prediction component with order P.

[0213] c) The base station inputs the linear coefficient a of the linear model reported by the UE into the target coefficient prediction component, i.e., uses the linear coefficient prediction component finally determined by the base station to perform linear coefficient prediction at the next interval (e.g., t3 in Figure 5 ) of the current linear parameter prediction time (e.g., t2 in Figure 5 ), to obtain a linear coefficient (i.e., the second model coefficient).

[0214] d) The information reported by the UE includes the frequency domain granularity required by the UE for prediction, i.e., the linear coefficient frequency domain prediction granularity expected by the UE, so that the base station can determine whether to determine the prediction frequency domain granularity as the granularity expected by the terminal according to the actual situation of the current predicted business requirement.

[0215] Specifically, if the base station has sufficient processing unit resources (i.e., the target prediction granularity) to schedule, for example, the target prediction granularity is the same as the model coefficient prediction granularity expected by the UE, then the base station can determine to perform channel prediction with the model coefficient prediction granularity expected by the UE; however, since the target coefficient prediction component is a coefficient prediction component in a wideband coefficient prediction module, i.e., the prediction granularity (also referred to as the target prediction granularity) of the target coefficient prediction component is wideband, the base station can determine that the target prediction granularity does not match the model coefficient prediction granularity expected by the UE (i.e., a sub-band), so the base station can perform time slot level linear coefficient prediction based on the target coefficient prediction component, using the target prediction granularity and the first model coefficient, to obtain the second model coefficient (which is a linear coefficient).

[0216] 5. Channel prediction under linear coefficient (e.g., AI coefficient) prediction.

[0217] The base station adopts a target coefficient prediction component to predict the linear coefficient at the next interval time (e.g., t3 in FIG. 3) according to the linear coefficient a of the linear model reported by the UE. Figure 5 Then, the base station can use the predicted information (e.g., the channel result at t2 in FIG. 3 predicted by the UE based on the linear model) reported by the UE and the channel information (e.g., N historical channel estimation results) reported by the historical measurement to predict the channel at the next interval time. Figure 5 Figure 5 The base station can use the predicted information (e.g., the channel result at t2 in FIG. 3 predicted by the UE based on the linear model) reported by the UE and the channel information (e.g., N historical channel estimation results) reported by the historical measurement to predict the channel at the next interval time.

[0218] The channel information reported by the historical measurement can include at least one of the following: the channel result predicted by the UE based on the model parameters and the N historical channel estimation results, the N historical channel estimation results, and the channel result reported by other UEs.

[0219] In the embodiments of the present application, compared with the scheme in the related art in which the base station can construct model parameters based on the channel information at t2 (slot) and earlier (e.g., N historical channel estimation results) and then predict the channel at a future time based on the constructed model parameters and the information, the channel prediction method provided in the embodiments of the present application can directly predict the second model coefficient through the target coefficient prediction component, thereby simplifying the complexity of channel prediction.

[0220] In the embodiments of the present application, the base station can indirectly predict the channel through the target coefficient prediction component capable of predicting the linear coefficient, thereby reducing the complexity of channel prediction.

[0221] The execution subject of the channel prediction method provided in the embodiments of the present application can also be a channel prediction device. In the embodiments of the present application, the channel prediction device performing the channel prediction method is taken as an example to illustrate the channel prediction device provided in the embodiments of the present application.

[0222] Figure 5 FIG. 5 shows a possible structural schematic diagram of the channel prediction device involved in the embodiments of the present application. As shown in FIG. 5, the channel prediction device 50 can include a sending module 51. Figure 5

[0223] The sending module 51 is configured to send first information to a network side device, the first information including a channel prediction result and model parameters of a target specific operator model, or including the model parameters of the target specific operator model; the channel prediction result is a channel result predicted by the UE based on the model parameters of the target specific operator model and historical channel estimation results, and the target specific operator model is a specific operator model constructed by the UE based on the historical channel estimation results.​​

[0224] In a possible implementation, the model parameters include a first model order and first model coefficients, the first model order is used by the network-side device to determine the target coefficient prediction component, and the first model coefficients are used by the network-side device to perform channel prediction based on the target coefficient prediction component.

[0225] In a possible implementation, the channel prediction result is obtained by performing channel prediction based on the model parameters and the historical channel estimation results in a case where the first model order is less than or equal to a quantity of the historical channel estimation results.

[0226] In a possible implementation, the channel prediction apparatus further includes a receiving module. The receiving module is configured to receive second information sent by the network-side device before the sending module 51 sends the first information to the network-side device, and the second information is used to indicate a minimum quantity threshold of historical channel estimation results required by the UE to construct the target specific operator model.

[0227] The second information includes at least one of the following: one parameter or a set of parameters preconfigured by radio resource control (RRC), a medium access control-control element (MAC CE), and downlink control information (DCI).

[0228] In a possible implementation, the first information further includes a model coefficient prediction granularity expected by the UE, and the model coefficient prediction granularity is used by the network-side device to perform prediction of model coefficients.

[0229] The model coefficient prediction granularity includes at least one of the following: a time domain granularity and a frequency domain granularity.

[0230] In a possible implementation, the sending module 51 is specifically configured to send the first information to the network-side device on a target resource, and the target resource includes at least one of the following: a resource preconfigured by radio resource control (RRC), a resource indicated by a medium access control-control element (MAC CE), and a resource indicated by downlink control information (DCI).

[0231] Or,

[0232] The sending module 51 is specifically configured to send the first information to the network-side device on a resource for sending the CSI measurement information.

[0233] The embodiment of the present application provides a channel prediction device, the channel prediction device can send first information including model parameters of a specific operator model constructed by the channel prediction device based on historical channel estimation results and / or channel prediction results based on the model parameters to a network side device, so that the network side device can perform channel prediction according to the first information after receiving the first information; that is, the channel prediction method provided by the embodiment of the present application can indirectly predict a channel based on the model parameters of the specific operator model constructed by the channel prediction device and / or the channel prediction results predicted based on the specific operator model, so that the calculation complexity of channel prediction by the specific operator model can be reduced.

[0234] The channel measurement device in the embodiment of the present application can be an electronic device, for example, an electronic device with an operating system, or a component in the electronic device, for example, an integrated circuit or a chip. The electronic device can be a terminal or other device except the terminal. For example, the terminal can include but is not limited to the types of the terminal 11 listed above, a network attached storage (NAS) and the like, and the embodiment of the present application is not limited specifically.

[0235] The channel prediction device in the embodiment of the present application can be a device or a UE, or a component, an integrated circuit or a chip in the UE.

[0236] The channel measurement device provided by the embodiment of the present application can realize each process of the method embodiment implemented by the UE and achieve the same technical effects, and details are not repeated here to avoid repetition. Figures 2 to 5 The channel measurement device provided by the embodiment of the present application can realize each process of the method embodiment implemented by the UE and achieve the same technical effects, and details are not repeated here to avoid repetition.

[0237] Figure 6 A possible structure schematic diagram of the channel prediction device involved in the embodiment of the present application is shown. As shown in Figure 6 The channel prediction device 60 can include an acquisition module 61 and a prediction module 62. The acquisition module is used to acquire first information, the first information includes channel prediction results and model parameters of a target specific operator model, or includes the model parameters of the target specific operator model; wherein the channel prediction results are channel results predicted by the UE based on the model parameters of the target specific operator model and historical channel estimation results, and the target specific operator model is a specific operator model constructed by the UE based on the historical channel estimation results; the prediction module is used to perform channel prediction according to the first information acquired by the acquisition module.

[0238] In a possible implementation, the model parameters include a first model order and first model coefficients; and the prediction module includes a determination sub-module and a prediction sub-module. The determination sub-module is configured to determine, according to the first model order, a target coefficient prediction component corresponding to the first model order; and the prediction sub-module is configured to perform prediction of the model coefficients according to the first model coefficients by using the target coefficient prediction component determined by the determination sub-module, to obtain second model coefficients; and perform channel prediction according to the second model coefficients and the first model order.

[0239] In a possible implementation, the determination sub-module is further configured to, before determining, according to the first model order, the target coefficient prediction component corresponding to the first model order, determine, according to target information, a target coefficient prediction module, the target coefficient prediction module including a plurality of coefficient prediction components, and the target coefficient prediction component being included in the plurality of coefficient prediction components.

[0240] The target information includes at least one of the following: geographical location information of the UE, CSI measurement information sent by the UE, a tracking area identifier (TAI) corresponding to the UE, a beam coverage range of the UE, a beam identifier of the UE, and scene information corresponding to the UE.

[0241] In a possible implementation, the first information further includes a model coefficient prediction granularity expected by the UE, and the model coefficient prediction granularity includes at least one of the following: a time domain granularity and a frequency domain granularity.

[0242] The prediction sub-module is specifically configured to perform prediction of the model coefficients according to the first model coefficients, the model coefficient prediction granularity expected by the UE, and other model coefficient prediction granularities expected by the UE by using the target coefficient prediction component, to obtain the second model coefficients.

[0243] In a possible implementation, the time domain granularity of the second model coefficients is any one of the following: one time slot, a plurality of time slots, a remaining time slot of a current frame, a measurement time of next channel state information (CSI), a plurality of CSI measurement times, each time slot in a CSI measurement period, and each time slot in a plurality of CSI measurement periods.

[0244] And / or,

[0245] The frequency domain granularity of the second model coefficients is any one of the following: a resource block (RB), a sub-band, and a wideband.

[0246] In a possible implementation, the prediction sub-module is specifically configured to, in a case where the model coefficient prediction granularity expected by the UE does not match a target prediction granularity, perform prediction of the model coefficients according to the first model coefficients and the target prediction granularity by using the target coefficient prediction component, to obtain the second model coefficients.

[0247] The target prediction granularity is a prediction granularity of the target coefficient prediction component.

[0248] In a possible implementation, when the UE-expected model coefficient prediction granularity is a subband / RB in a wideband, and the target prediction granularity is the wideband, the second model coefficient is a prediction result of the wideband shared by each subband / RB in the wideband; or,

[0249] When the UE-expected model coefficient prediction granularity is a wideband, and the target prediction granularity is a subband in the wideband, the second model coefficient is a prediction result on a subband with a lowest channel quality indicator (CQI) in all subbands in the wideband; or,

[0250] When the UE-expected model coefficient prediction granularity is a RB in a subband, and the target prediction granularity is the subband, the second model coefficient is a prediction result of the subband shared by each RB in the subband; or,

[0251] When the UE-expected model coefficient prediction granularity is a subband, and the target prediction granularity is a RB in the subband, the second model coefficient is a prediction result of a RB with a lowest CQI in all RBs in the subband; or,

[0252] When the UE-expected model coefficient prediction granularity is a wideband, and the target prediction granularity is a RB under a subband in the wideband, the second model coefficient uses a result of a RB with a lowest CQI in all RBs in the wideband.

[0253] In a possible implementation, the target coefficient prediction component is any one of the following: a coefficient prediction component constructed by one or more cell identifiers, or a coefficient prediction component constructed by one or more transmission and reception point (TRP) identifiers.

[0254] In a possible implementation, the channel prediction apparatus further includes a sending module.

[0255] The sending module is configured to send, to the UE, second information before the obtaining module obtains the first information, the second information being used to indicate a minimum number threshold of historical channel estimation results required for the UE to construct the target specific operator model; and the second information includes at least one of the following: one parameter or a set of parameters preconfigured by a radio resource control (RRC), a medium access control-control element (MAC CE), or downlink control information (DCI).

[0256] The channel prediction device can receive first information sent by the UE, the first information comprising model parameters of a specific operator model constructed by the UE based on historical channel estimation results and / or channel prediction results based on the model parameters, so that the channel prediction device can perform channel prediction according to the first information after receiving the first information. That is, the channel prediction method provided in the embodiments of the present application can indirectly predict a channel based on model parameters of a specific operator model constructed by the UE and / or channel prediction results predicted based on the specific operator model, thereby reducing the computational complexity of channel prediction by the specific operator model.

[0257] The channel measurement device in the embodiments of the present application can be an electronic device, for example, an electronic device with an operating system, or a component in an electronic device, for example, an integrated circuit or a chip. The electronic device can be a terminal or other device other than a terminal. For example, the terminal can include, but is not limited to, the types of terminal 11 listed above, a network attached storage (NAS), and the like, and the embodiments of the present application are not limited in this regard.

[0258] The channel prediction device in the embodiments of the present application can be a device or a UE, or a component, an integrated circuit, or a chip in a UE.

[0259] The channel measurement device provided in the embodiments of the present application can implement each process of the method embodiment implemented by the network side device, and achieve the same technical effects. To avoid repetition, details are not repeated here. Figures 2 to 5 The channel prediction device provided in the embodiments of the present application can implement each process of the method embodiment implemented by the network side device, and achieve the same technical effects. To avoid repetition, details are not repeated here.

[0260] Optionally, as shown in Figure 7 The communication device 200 comprises a processor 201 and a memory 202, and the memory 202 stores programs or instructions executable on the processor 201. For example, when the communication device 200 is a UE, the programs or instructions are executed by the processor 201 to implement each step of the UE in the channel prediction method embodiments described above, and achieve the same technical effects. When the communication device 200 is a network side device, the programs or instructions are executed by the processor 201 to implement each step of the network side device in the channel prediction method embodiments described above, and achieve the same technical effects. To avoid repetition, details are not repeated here.

[0261] The embodiment of the present application further provides a UE, comprising a processor and a communication interface, wherein the processor is configured to construct a target-specific operator model, and / or perform channel prediction based on a model parameter of the target-specific operator model and a channel result predicted from a historical channel estimation result to obtain a channel prediction result; the target-specific operator model is a specific operator model constructed by the UE based on the historical channel estimation result; and the communication interface is configured to send first information to a network side device, wherein the first information comprises the model parameter and / or the channel prediction result. The UE embodiment corresponds to the UE side method embodiment described above, and each implementation process and implementation manner of the UE side method embodiment described above can be applied to the UE embodiment and achieve the same technical effects. Specifically, Figure 8 A hardware structure diagram of a UE according to an embodiment of the present application is shown in FIG. 10.

[0262] The UE 1000 includes, but is not limited to, at least part of the components such as a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010.

[0263] Those skilled in the art can understand that the terminal 1000 can further include a power supply (such as a battery) for supplying power to each component, and the power supply can be logically connected to the processor 1010 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. Figure 8 The UE structure shown in FIG. 10 does not constitute a limitation on the UE, and the UE can include more or fewer components than those shown in the figure, or combine certain components, or different component arrangements, which are not described herein again.

[0264] It should be understood that in the embodiment of the present application, the input unit 1004 can include a graphics processing unit (GPU) 10041 and a microphone 10042. The graphics processor 10041 processes image data of a still picture or a video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1006 can include a display panel 10061, which can be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1007 includes at least one of a touch panel 10071 and other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 can include two parts of a touch detection device and a touch controller. The other input devices 10072 can include, but are not limited to, a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), a trackball, a mouse, a joystick, etc., which are not described herein again.

[0265] In the embodiment of the present application, the radio frequency unit 1001 can transmit the downlink data received from the network side device to the processor 1010 for processing. In addition, the radio frequency unit 1001 can send uplink data to the network side device. Generally, the radio frequency unit 1001 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0266] The memory 1009 can be used to store software programs or instructions and various data. The memory 1009 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), etc. In addition, the memory 1009 can include a volatile memory or a non-volatile memory, or the memory 1009 can include both volatile and non-volatile memories. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 1009 in the embodiment of the present application includes but is not limited to these and any other suitable types of memories.

[0267] The processor 1010 can include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 1010.

[0268] The radio frequency unit 1001 is configured to send first information to a network side device, the first information being used for channel prediction by the network side device, and the first information comprising model parameters of a target specific operator model or comprising model parameters of a target specific operator model and a channel prediction result.

[0269] The UE according to the embodiments of the present application can send first information comprising model parameters of a specific operator model constructed by the UE based on historical channel estimation results and / or a channel prediction result based on the model parameters to a network side device, so that the network side device can perform channel prediction according to the first information after receiving the first information. That is, the channel prediction method provided by the embodiments of the present application can indirectly predict a channel based on model parameters of a specific operator model constructed by the UE and / or a channel prediction result predicted based on the specific operator model, thereby reducing the computational complexity of channel prediction by the specific operator model.

[0270] In a possible implementation, the model parameters comprise a first model order and first model coefficients, the first model order being used for the network side device to determine a target coefficient prediction component, and the first model coefficients being used for the network side device to perform channel prediction based on the target coefficient prediction component.

[0271] In a possible implementation, the radio frequency unit 1001 is further configured to, before sending the first information to the network side device, receive second information sent by the network side device, the second information being used to indicate a minimum number threshold of historical channel estimation results required for the UE to construct a target specific operator model; and the second information comprising at least one of the following: one parameter or a set of parameters preconfigured by a radio resource control (RRC), a medium access control-control element (MAC CE), and downlink control information (DCI).

[0272] The embodiments of the present application further provide a network side device comprising a processor and a communication interface, wherein the communication interface is configured to obtain first information, the first information comprising at least one of model parameters of a target specific operator model and a channel prediction result; the target specific operator model being a specific operator model constructed by a UE based on historical channel estimation results, and the channel prediction result being a channel result predicted by the UE based on model parameters of the target specific operator model and the historical channel estimation results; and the processor is configured to perform channel prediction according to the first information. The network side device embodiment corresponds to the network side device method embodiment described above, and each implementation process and implementation manner of the method embodiment can be applied to the network side device embodiment and achieve the same technical effects.

[0273] Specifically, the embodiment of the present application also provides a network side device. As shown in the Figure 9 The network side device is a base station 700, which comprises an antenna 71, a radio frequency device 72, a baseband device 73, a processor 74 and a memory 75. The antenna 71 is connected with the radio frequency device 72. In the uplink direction, the radio frequency device 72 receives information through the antenna 71 and sends the received information to the baseband device 73 for processing. In the downlink direction, the baseband device 73 processes the information to be sent and sends it to the radio frequency device 72, and the radio frequency device 72 processes the received information and sends it out through the antenna 71.

[0274] The method performed by the network side device in the above embodiment can be implemented in the baseband device 73, which comprises a baseband processor.

[0275] The baseband device 73 may, for example, comprise at least one baseband board, which is provided with a plurality of chips, as shown in the Figure 7 One of the chips is, for example, a baseband processor, which is connected with the memory 75 through a bus interface to call the program in the memory 75 and perform the operation of the network device shown in the above method embodiment.

[0276] The network side device may also comprise a network interface 76, which is, for example, a common public radio interface (CPRI).

[0277] Specifically, the network side device 700 of the embodiment of the present application also comprises instructions or programs stored in the memory 75 and executable on the processor 74, and the processor 74 calls the instructions or programs in the memory 75 to perform the method shown in the Figure 6 The modules shown in the above method embodiment perform the method and achieve the same technical effect, and thus the description is omitted here.

[0278] The embodiment of the present application also provides a readable storage medium, which stores programs or instructions, and the programs or instructions are executed by a processor to implement the processes of the above channel prediction method embodiment and achieve the same technical effect. To avoid repetition, the description is omitted here.

[0279] The processor is the processor in the UE or the network side device in the above embodiment. The readable storage medium comprises a computer readable storage medium, such as a computer readable only memory (ROM), a random access memory (RAM), a magnetic disc or an optical disc, etc.

[0280] The chip provided by the embodiment of the present application also can be called system chip, system on chip, chip system or system on chip, etc.

[0281] It should be understood that the chip mentioned in the embodiment of the present application also can be called system chip, system on chip, chip system or system on chip, etc.

[0282] The embodiment of the present application further provides a computer program / program product, which is stored in a storage medium and is executed by at least one processor to implement the processes of the channel prediction method embodiments and achieve the same technical effects, and details are not repeated here to avoid repetition.

[0283] The embodiment of the present application further provides a communication system, which comprises a UE and a network side device, the UE can be used to execute the steps executed by the UE in the channel prediction method embodiments, and the network side device can be used to execute the steps executed by the network side device in the channel prediction method embodiments.

[0284] It should be noted that, in this document, the term "comprising" or "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present application is not limited to the order of executing the functions shown or discussed, but also can include executing the functions in a substantially simultaneous manner or in a reverse order according to the functions involved, for example, the described method can be executed in an order different from the described order, and various steps can also be added, omitted or combined. In addition, the features described with reference to certain examples can be combined in other examples.

[0285] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned example methods can be realized by means of software and a necessary general hardware platform, and of course, can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a computer software product in essence or in the form of a part that contributes to the prior art, which is stored in a storage medium (such as a ROM / RAM, a magnetic disc, an optical disc), and includes a plurality of instructions for causing 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 various embodiments of the present application.

[0286] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the above-mentioned specific embodiments, and the above-mentioned specific embodiments are only illustrative and not restrictive. Those skilled in the art can make many forms under the inspiration of the present application without departing from the scope of the present application and the scope protected by the claims.

Claims

1. A channel prediction method, characterized in that, include: The user equipment (UE) sends first information to the network-side device. The first information is used by the network-side device to perform channel prediction. The first information includes channel prediction results and model parameters of a target-specific operator model, or includes model parameters of a target-specific operator model. The channel prediction result is the channel result predicted by the UE based on the model parameters of the target-specific operator model and the historical channel estimation result. The target-specific operator model is a specific operator model constructed by the UE based on the historical channel estimation result. The model parameters include a first model order and first model coefficients. The first model order is used by the network-side device to determine a target coefficient prediction component. The first model coefficients are used by the network-side device to determine a second model coefficient based on the target coefficient prediction component. The second model coefficients are used by the network-side device to perform channel prediction based on the first model order.

2. The method according to claim 1, characterized in that, The channel prediction result is obtained by the UE based on the model parameters and the historical channel estimation results when the first model order is less than or equal to the number of historical channel estimation results.

3. The method according to claim 2, characterized in that, Before the UE sends the first information to the network-side device, the method further includes: The UE receives second information sent by the network-side device, the second information being used to indicate the minimum threshold of the number of historical channel estimation results required for the UE to construct the target-specific operator model; The second information includes at least one of the following: a parameter or set of parameters pre-configured by Radio Resource Control (RRC), Media Access Control-Control Unit (MAC CE), and Downlink Control Information (DCI).

4. The method according to any one of claims 1 to 3, characterized in that, The first information also includes the model coefficient prediction granularity expected by the UE, which is used by the network-side device to predict model coefficients; The model coefficient prediction granularity includes at least one of the following: time-domain granularity and frequency-domain granularity.

5. The method according to claim 1, characterized in that, The UE sends first information to the network-side device, including: The UE sends the first information to the network-side device on the target resource, wherein the target resource includes at least one of the following: a resource pre-configured by RRC, a resource indicated by MAC CE, or a resource indicated by DCI; or, The UE sends the first information to the network-side device on the resource for sending Channel State Information (CSI) measurement information.

6. A channel prediction device, characterized in that, include: Sending module; The sending module is used to send first information to the network-side device. The first information is used by the network-side device to perform channel prediction. The first information includes channel prediction results and model parameters of a target-specific operator model, or includes model parameters of a target-specific operator model. The channel prediction result is the channel result predicted by the UE based on the model parameters of the target-specific operator model and the historical channel estimation result. The target-specific operator model is the specific operator model constructed by the UE based on the historical channel estimation result. The model parameters include a first model order and first model coefficients. The first model order is used by the network-side device to determine a target coefficient prediction component. The first model coefficients are used by the network-side device to determine a second model coefficient based on the target coefficient prediction component. The second model coefficients are used by the network-side device to perform channel prediction based on the first model order.

7. The apparatus according to claim 6, characterized in that, The channel prediction result is obtained by the UE based on the model parameters and the historical channel estimation results when the first model order is less than or equal to the number of historical channel estimation results.

8. The apparatus according to claim 7, characterized in that, Also includes: Receiver module; The receiving module is configured to receive second information sent by the network-side device before the sending module sends the first information to the network-side device. The second information is used to indicate the minimum number threshold of historical channel estimation results required for the UE to construct the target-specific operator model. The second information includes at least one of the following: a parameter or set of parameters pre-configured by Radio Resource Control (RRC), Media Access Control-Control Unit (MAC CE), and Downlink Control Information (DCI).

9. The apparatus according to any one of claims 6 to 8, characterized in that, The first information also includes the model coefficient prediction granularity expected by the UE, which is used by the network-side device to predict model coefficients; The model coefficient prediction granularity includes at least one of the following: time-domain granularity and frequency-domain granularity.

10. The apparatus according to claim 6, characterized in that, The sending module is specifically used to send the first information to the network-side device on the target resource, wherein the target resource includes at least one of the following: a resource pre-configured by RRC, a resource indicated by MAC CE, or a resource indicated by DCI. or, The sending module is specifically used to send the first information to the network-side device on the resource for sending Channel State Information (CSI) measurement information.

11. A channel prediction method, characterized in that, include: The network-side device acquires first information, which includes channel prediction results and model parameters of a target-specific operator model, or includes model parameters of a target-specific operator model. The channel prediction result is the channel result predicted by the UE based on the model parameters of the target-specific operator model and the historical channel estimation result. The target-specific operator model is the specific operator model constructed by the UE based on the historical channel estimation result. The network-side device performs channel prediction based on the first information; The model parameters include a first model order and first model coefficients; the network-side device performs channel prediction based on the first information, including: The network-side device determines the target coefficient prediction component corresponding to the first model order based on the first model order; The network-side device uses the target coefficient prediction component to predict the model coefficients based on the first model coefficients to obtain the second model coefficients; The network-side device performs channel prediction based on the second model coefficients and the first model order.

12. The method according to claim 11, characterized in that, Before the network-side device determines the target coefficient prediction component corresponding to the first model order based on the first model order, the method further includes: The network-side device determines a target coefficient prediction module based on the target information. The target coefficient prediction module includes multiple coefficient prediction components, and the multiple coefficient prediction components include the target coefficient prediction component. The target information includes at least one of the following: the geographical location information of the UE, the CSI measurement information sent by the UE, the tracking area identifier (TAI) corresponding to the UE, the beam coverage range of the UE, the beam identifier of the UE, and the scene information corresponding to the UE.

13. The method according to claim 11, characterized in that, The first information also includes the model coefficient prediction granularity expected by the UE, wherein the model coefficient prediction granularity includes at least one of the following: time-domain granularity and frequency-domain granularity; The network-side device uses the target coefficient prediction component to predict the model coefficients based on the first model coefficients to obtain the second model coefficients, including: The network-side device uses the target coefficient prediction component to predict the model coefficients based on the first model coefficients, the model coefficient prediction granularity desired by the UE, and the model coefficient prediction granularity desired by other UEs, to obtain the second model coefficients.

14. The method according to any one of claims 11 to 13, characterized in that, The temporal granularity of the second model coefficients is any one of the following: one time slot, multiple time slots, the remaining time slots of the current frame, the measurement time of the next channel state information (CSI), multiple CSI measurement times, each time slot within a CSI measurement period, or each time slot within multiple CSI measurement periods. And / or, The frequency domain granularity of the second model coefficients is any one of the following: resource block RB, subband, or broadband.

15. The method according to claim 11, characterized in that, The network-side device uses the target coefficient prediction component to predict the model coefficients based on the first model coefficients to obtain the second model coefficients, including: When the UE's desired model coefficient prediction granularity does not match the target prediction granularity, the network-side device uses the target coefficient prediction component to predict the model coefficients based on the first model coefficients and the target prediction granularity to obtain the second model coefficients. Wherein, the target prediction granularity is the prediction granularity of the target coefficient prediction component.

16. The method according to claim 15, characterized in that, When the UE expects the model coefficient prediction granularity to be a sub-band / RB in the broadband and the target prediction granularity is broadband, the second model coefficient is the prediction result of each sub-band / RB in the broadband sharing the broadband. When the UE expects the model coefficient prediction granularity to be wideband, and the target prediction granularity is a subband within the wideband, the second model coefficient is the prediction result on the subband with the lowest Channel Quality Indication (CQI) among all subbands within the wideband; When the UE expects the model coefficient prediction granularity to be RB in the sub-band and the target prediction granularity is the sub-band, the second model coefficient is the prediction result of the sub-band shared by each RB in the sub-band; When the UE expects the model coefficient prediction granularity to be a sub-band and the target prediction granularity is the RB in the sub-band, the second model coefficient is the prediction result of the RB with the lowest CQI among all RBs in the sub-band; When the UE expects the model coefficient prediction granularity to be broadband and the target prediction granularity is the RB under the subband in the broadband, the second model coefficient uses the result of the RB with the lowest CQI among all RBs in the broadband.

17. The method according to claim 11, characterized in that, The target coefficient prediction component is any one of the following: a coefficient prediction component constructed using one or more cell identifiers, or a coefficient prediction component constructed using one or more transmit and receive point (TRP) identifiers.

18. The method according to claim 11, characterized in that, Before the network-side device obtains the first information, the method further includes: The network-side device sends a second message to the UE, the second message being used to indicate the minimum number of historical channel estimation results required for the UE to construct the target-specific operator model; The second information includes at least one of the following: a parameter or set of parameters pre-configured by Radio Resource Control (RRC), Media Access Control-Control Unit (MAC CE), and Downlink Control Information (DCI).

19. A channel prediction device, characterized in that, include: Acquisition module and prediction module; The acquisition module is used to acquire first information, which includes channel prediction results and model parameters of a target-specific operator model, or includes model parameters of a target-specific operator model; wherein, the channel prediction results are channel results predicted by the UE based on the model parameters of the target-specific operator model and historical channel estimation results, and the target-specific operator model is a specific operator model constructed by the UE based on historical channel estimation results; The prediction module is used to perform channel prediction based on the first information obtained by the acquisition module; The model parameters include a first model order and first model coefficients; the prediction module includes a determination submodule and a prediction submodule. The determining submodule is used to determine the target coefficient prediction component corresponding to the first model order based on the first model order. The prediction submodule is used to use the target coefficient prediction component determined by the determination submodule to predict the model coefficients based on the first model coefficients to obtain the second model coefficients; and to perform channel prediction based on the second model coefficients and the first model order.

20. The apparatus according to claim 19, characterized in that, The determining submodule is further configured to determine a target coefficient prediction module based on target information before determining the target coefficient prediction component corresponding to the first model order based on the first model order. The target coefficient prediction module includes multiple coefficient prediction components, and the multiple coefficient prediction components include the target coefficient prediction component. The target information includes at least one of the following: the geographical location information of the UE, the CSI measurement information sent by the UE, the tracking area identifier (TAI) corresponding to the UE, the beam coverage range of the UE, the beam identifier of the UE, and the scene information corresponding to the UE.

21. The apparatus according to claim 19, characterized in that, The first information also includes the model coefficient prediction granularity expected by the UE, wherein the model coefficient prediction granularity includes at least one of the following: time-domain granularity and frequency-domain granularity; The prediction submodule is specifically used to use the target coefficient prediction component to predict the model coefficients based on the first model coefficients, the model coefficient prediction granularity desired by the UE, and the model coefficient prediction granularity desired by other UEs, so as to obtain the second model coefficients.

22. The apparatus according to any one of claims 19 to 21, characterized in that, The temporal granularity of the second model coefficients is any one of the following: one time slot, multiple time slots, the remaining time slots of the current frame, the measurement time of the next channel state information (CSI), multiple CSI measurement times, each time slot within a CSI measurement period, or each time slot within multiple CSI measurement periods. And / or, The frequency domain granularity of the second model coefficients is any one of the following: resource block RB, subband, or broadband.

23. The apparatus according to claim 19, characterized in that, The prediction submodule is specifically used to predict the model coefficients based on the first model coefficients and the target prediction granularity when the model coefficient prediction granularity expected by the UE does not match the target prediction granularity, and to obtain the second model coefficients by using the target coefficient prediction component. Wherein, the target prediction granularity is the prediction granularity of the target coefficient prediction component.

24. The apparatus according to claim 23, characterized in that, When the UE expects the model coefficient prediction granularity to be a sub-band / RB in the broadband and the target prediction granularity is the broadband, the second model coefficient is the prediction result of each sub-band / RB in the broadband sharing the broadband. When the UE expects the model coefficient prediction granularity to be wideband, and the target prediction granularity is a subband within the wideband, the second model coefficient is the prediction result on the subband with the lowest Channel Quality Indication (CQI) among all subbands within the wideband; When the UE expects the model coefficient prediction granularity to be RB in the sub-band and the target prediction granularity is the sub-band, the second model coefficient is the prediction result of the sub-band shared by each RB in the sub-band; When the UE expects the model coefficient prediction granularity to be a sub-band and the target prediction granularity is the RB in the sub-band, the second model coefficient is the prediction result of the RB with the lowest CQI among all RBs in the sub-band; When the UE expects the model coefficient prediction granularity to be broadband and the target prediction granularity is the RB under the subband in the broadband, the second model coefficient uses the result of the RB with the lowest CQI among all RBs in the broadband.

25. The apparatus according to claim 19, characterized in that, The target coefficient prediction component is any one of the following: a coefficient prediction component constructed using one or more cell identifiers, or a coefficient prediction component constructed using one or more transmit and receive point (TRP) identifiers.

26. The apparatus according to claim 19, characterized in that, Also includes: Sending module; The sending module is configured to send second information to the UE before the acquisition module acquires the first information, wherein the second information is used to indicate the minimum number threshold of historical channel estimation results required by the UE to construct the target-specific operator model; The second information includes at least one of the following: a parameter or set of parameters pre-configured by Radio Resource Control (RRC), Media Access Control-Control Unit (MAC CE), and Downlink Control Information (DCI).

27. A user equipment (UE), characterized in that, It includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the steps of the channel prediction method as described in any one of claims 1 to 5.

28. A network-side device, characterized in that, It includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the steps of the channel prediction method as described in any one of claims 11 to 18.

29. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the channel prediction method as described in any one of claims 1 to 5, or implement the steps of the channel prediction method as described in any one of claims 11 to 18.

30. A communication system, characterized in that, The communication system includes the channel prediction device as described in any one of claims 6 to 10 and the channel prediction device as described in any one of claims 19 to 26; or... The communication system includes the user equipment (UE) as described in claim 27 and the network-side equipment as described in claim 28.

Images