User equipment ADN method performed by the same

Abstract

The embodiments of the present disclosure provide a user equipment and a method performed by a user equipment, which involves the field of artificial intelligence. The method includes: predicting a first wireless channel condition component related to a radio access technology (RAT) change and a second wireless channel condition component related to a cell characteristic; obtaining a predicted wireless channel condition based on the first wireless channel condition component and the second wireless channel condition component. Alternatively, the above method executed by electronic apparatus may be executed by using artificial intelligence models.

Description

USER EQUIPMENT ADN METHOD PERFORMED BY THE SAME

[0001] The present disclosure relates to a communication field and an artificial intelligence field, and specifically to a method performed by a user equipment, a user equipment, a computer-readable storage medium and a computer program product.

[0002] Accurate prediction of a wireless channel condition facilitates improving the Quality of Experience (QoE) for users. For example, if a future wireless channel condition may be accurately predicted, a user equipment (e.g., a network-aware mobile application in the user equipment) may use this prediction to make informed optimization decisions, which ultimately improves the QoE for users. For example, video streaming applications commonly use an Adaptive Bitrate (ABR) algorithm to dynamically adjust the video bitrate based on the predicted wireless channel condition (e.g., throughput). Moreover, accurate wireless channel condition prediction is essential for latency-sensitive services such as live streaming and extended reality (XR). However, current wireless channel condition prediction techniques do not predict the wireless channel condition with sufficient accuracy, and there is a need for a technique that may more accurately predict the wireless channel condition and thus improve the QoE for users.

[0003] According to a first aspect of embodiments of the present disclosure, there is provided a method performed by a user equipment, the method includes: predicting a first wireless channel condition component related to a radio access technology (RAT) change and a second wireless channel condition component related to a cell characteristic; and obtaining a predicted wireless channel condition based on the first wireless channel condition component and the second wireless channel condition component.

[0004] Alternatively, the predicting of the first wireless channel condition component includes: predicting a RAT to be accessed by the user equipment; predicting the first wireless channel condition component related to the RAT change based on the predicted RAT to be accessed by the user equipment and historical wireless channel condition information.

[0005] Alternatively, the predicting of the RAT to be accessed by the user equipment includes: predicting the RAT to be accessed by the user equipment based on a historical radio resource management (RRM) related feature in the historical wireless channel condition information, the predicting of the first wireless channel condition component related to the RAT change based on the predicted RAT to be accessed by the user equipment and the historical wireless channel condition information includes: predicting the first wireless channel condition component related to the RAT change based on the predicted RAT to be accessed by the user equipment and a historical scheduling related feature in the historical wireless channel condition information.

[0006] Alternatively, the scheduling related feature includes at least one of a parameter related to a scheduling algorithm and a parameter for evaluating scheduling performance, wherein the parameter related to the scheduling algorithm includes at least one of throughput, a transmission block size, a number of resource blocks, a number of scheduling times, and a scheduling delay, and the parameter for evaluating the scheduling performance includes at least one of throughput and a one-way delay.

[0007] Alternatively, the predicting of the RAT to be accessed by the user equipment based on the historical RRM related feature in the historical wireless channel condition information includes: predicting a RRM related feature difference between cells under different RATs based on the historical RRM related feature, wherein the RRM related feature difference indicates a RRM related feature difference between a serving cell under a first RAT and a neighbor cell under a second RAT; predicting the RAT to be accessed by the user equipment based on the RRM related feature difference.

[0008] Alternatively, the RRM related feature includes at least one of a reference signal received power (RSRP), a reference signal received quality (RSRQ), a signal-to-noise ratio (SNR), and a received signal strength indication (RSSI).

[0009] Alternatively, the predicting of the RAT to be accessed by the user equipment based on the RRM related feature difference includes: determining a relationship between the RRM related feature difference between cells under different RATs and a RAT change event based on historical data related to the RRM related feature difference between cells under different RATs; predicting the RAT to be accessed by the user equipment by using the relationship based on the predicted RRM related feature difference.

[0010] Alternatively, the predicting of the RAT to be accessed by the user equipment by using the relationship based on the predicted RRM related feature difference includes: determining a difference interval to which the predicted RRM related feature difference belongs; calculating, based on the difference interval, a probability of a RAT change event occurring under the difference interval and a confidence interval corresponding to the probability using the relationship; predicting, based on the confidence interval, the RAT to be accessed by the user equipment.

[0011] Alternatively, the predicting of the first wireless channel condition component related to the RAT change based on the predicted RAT to be accessed by the user equipment and the historical scheduling related feature in the historical wireless channel condition information includes: obtaining a first historical wireless channel condition component related to the RAT change based on the historical scheduling related feature in the historical wireless channel condition information; predicting the first wireless channel condition component related to the RAT change based on the first historical wireless channel condition component and the predicted RAT to be accessed by the user equipment.

[0012] Alternatively, the predicting the first wireless channel condition component related to the RAT change based on the first historical wireless channel condition component and the predicted RAT to be accessed by the user equipment includes: performing a weighted summation of the first historical wireless channel condition component within a historically predetermined time; predicting the first wireless channel condition component based on a result of the weighted summation and the predicted RAT to be accessed by the user equipment.

[0013] Alternatively, the predicting of the second wireless channel condition component related to a cell characteristic includes: predicting the second wireless channel condition component related to the cell characteristic based on historical wireless channel condition information and historical cell characteristic information related to a network configuration.

[0014] Alternatively, the predicting of the second wireless channel condition component related to the cell characteristic based on the historical wireless channel condition information and the historical cell characteristic information related to the network configuration includes: obtaining a second historical wireless channel condition component related to the cell characteristic based on a historical scheduling related feature in the historical wireless channel condition information; predicting the second wireless channel condition component based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration.

[0015] Alternatively, the predicting of the second wireless channel condition component based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration includes: predicting, based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration, a third wireless channel condition component corresponding to a cell characteristic related to the network configuration and a fourth wireless channel condition component corresponding to a cell characteristic unrelated to the network configuration; predicting the second wireless channel condition component based on the predicted third wireless channel condition component and the fourth wireless channel condition component.

[0016] Alternatively, the predicting of, based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration, the third wireless channel condition component corresponding to the cell characteristic related to the network configuration and the fourth wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration includes: obtaining a first feature component corresponding to the cell characteristic related to the network configuration and a second feature component corresponding to the cell characteristic unrelated to the network configuration based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration; predicting the third wireless channel condition component based on the first feature component and the historical cell characteristic information related to the network configuration; predicting the fourth wireless channel condition component based on the second feature component.

[0017] Alternatively, the predicting of the second wireless channel condition component based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration includes: obtaining a wireless channel condition change mode corresponding to a behavior of the user equipment; predicting the second wireless channel condition component based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration.

[0018] Alternatively, the predicting of the second wireless channel condition component based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration includes: predicting a third wireless channel condition component corresponding to a cell characteristic related to the network configuration and a fourth wireless channel condition component corresponding to a cell characteristic unrelated to the network configuration based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration; predicting the second wireless channel condition component based on the predicted third wireless channel condition component and the fourth wireless channel condition component.

[0019] Alternatively, the predicting of the third wireless channel condition component corresponding to the cell characteristic related to the network configuration and the fourth wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration includes: obtaining a first feature component corresponding to the cell characteristic related to the network configuration and a second feature component corresponding to the cell characteristic unrelated to the network configuration based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration; predicting the third wireless channel condition component based on the first feature component and the historical cell characteristic information related to the network configuration; predicting the fourth wireless channel condition component based on the second feature component.

[0020] Alternatively, the obtaining of the first feature component corresponding to the cell characteristic related to the network configuration and the second feature component corresponding to the cell characteristic unrelated to the network configuration based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration includes: dividing the second historical wireless channel condition component into a third feature component possibly corresponding to a cell characteristic related to the network configuration and a fourth feature component corresponding to a cell characteristic unrelated to the network configuration, based on a correlation between the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration; performing feature mapping on the fourth feature component; obtaining the first feature component and the second feature component based on the mapped feature component.

[0021] Alternatively, the obtaining of the first feature component and the second feature component based on the mapped feature component includes: dividing the mapped feature component into the first feature component and a fifth feature component corresponding to the cell characteristic unrelated to the network configuration; obtaining the second feature component based on the fourth feature component and the fifth feature component.

[0022] Alternatively, the method further includes: obtaining a log file related to communication of the user equipment; obtaining historical wireless channel condition raw information based on the log file; performing data completion on a feature with a missing value in the historical wireless channel condition raw information to obtain the historical wireless channel condition information.

[0023] According to a second aspect of embodiments of the present disclosure, there is provided a user equipment, the user equipment includes: a memory; a processor coupled to the memory and configured to perform the above method.

[0024] According to a third aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium storing　computer programs or instructions that, when executed by at least one processor, cause the at least one processor to perform the above method.

[0025] According to a fourth aspect of embodiments of the present disclosure, there is provided a computer program product including computer programs, the computer programs, when being executed by a processor, implement the above method.

[0026] The method and device according to embodiments of the present disclosure firstly predicts the first wireless channel condition component related to the RAT change and the second wireless channel condition component related to the cell characteristic, and then obtains the predicted wireless channel condition based on the predicted first wireless channel condition component and the second wireless channel condition component, and since it is possible to separately predict the first wireless channel condition component related to the RAT change and the wireless channel condition component related to the cell characteristic, i.e., decouple the wireless channel condition changes caused by different influencing factors (such as the RAT change and the cell characteristic), and then obtain the predicted wireless channel condition based on this, instead of directly predicting the wireless channel condition change caused by the combination of all the influencing factors, the decrease in the accuracy of the wireless channel condition prediction caused by the interactions between the different influencing factors may be avoided, and thus the method according to embodiments of the present disclosure may predict the wireless channel condition more accurately, thereby improving the QoE for users.

[0027] It should be understood that the above general description and the detailed descriptions that follow are merely exemplary and explanatory and do not limit the present disclosure.

[0028] The accompanying drawings herein are incorporated into and form part of the specification, illustrate embodiments consistent with the disclosure, which are used in conjunction with the specification to explain the principles of the disclosure and do not constitute an undue limitation of the disclosure.

[0029] FIG. 1 is a schematic diagram illustrating an example scenario of problems that may result from incorrect throughput prediction according to embodiments of the present disclosure.

[0030] FIG. 2 is a schematic diagram illustrating an example of a relationship between signal strength and throughput according to embodiments of the present disclosure.

[0031] FIG. 3 is a schematic diagram illustrating an example of factors affecting the throughput according to embodiments of the present disclosure.

[0032] FIG. 4 is a flowchart illustrating a method performed by a user equipment (UE) according to embodiments of the present disclosure.

[0033] FIG. 5 is a schematic diagram illustrating an example of factors affecting the throughput according to embodiments of the present disclosure.

[0034] FIG. 6 is a schematic diagram illustrating intra-RAT fluctuations of the throughput affected by cell characteristics under a given RAT, according to embodiments of the present disclosure.

[0035] FIG. 7 is a schematic diagram illustrating difference in distribution of the throughput at different cell bandwidths according to embodiments of the present disclosure.

[0036] FIG. 8 is a schematic diagram illustrating an exemplary architecture for predicting a wireless channel condition according to embodiments of the present disclosure.

[0037] FIG. 9 is a schematic diagram illustrating a detailed exemplary architecture for predicting a wireless channel condition according to embodiments of the present disclosure.

[0038] FIG. 10 is a schematic diagram illustrating an example of predicting a RAT to be accessed by a user equipment according to embodiments of the present disclosure.

[0039] FIGS. 11 and 12 are schematic diagrams illustrating a method for predicting a RSRP difference according to embodiments of the present disclosure.

[0040] FIG. 13 is a schematic diagram illustrating a method of determining a difference interval to which an RSRP difference belongs, according to an embodiment of the present disclosure.

[0041] FIG. 14 is a schematic diagram illustrating an example of predicting a first wireless channel condition component according to embodiments of the present disclosure.

[0042] FIG. 15 is a schematic diagram illustrating a second AI model for predicting a second wireless channel condition component, according to embodiments of the present disclosure.

[0043] FIG. 16 is a schematic diagram illustrating a detailed structure of a second AI model for predicting a second wireless channel condition component according to embodiments of the present disclosure.

[0044] FIG. 17 illustrates an example of a throughput change of a UE during a user repeatedly browses a short video.

[0045] FIG. 18 is a schematic diagram illustrating a method in which a sequence of historical RAT fluctuation components is divided.

[0046] FIG. 19 is a schematic diagram illustrating an example of extracting a wireless channel condition change mode corresponding to behaviors of a UE.

[0047] FIG. 20 is a schematic diagram illustrating completion of data required for performing wireless channel condition prediction, according to embodiments of the present disclosure.

[0048] FIG. 21 is a schematic diagram illustrating an example method for predicting the throughput according to embodiments of the present disclosure.

[0049] FIG. 22 is a schematic diagram illustrating a portion of an operation of extracting a throughput change mode corresponding to a behavior of a user equipment.

[0050] FIG. 23 is a schematic diagram illustrating prediction of a RRM related feature according to embodiments of the present disclosure.

[0051] FIG. 24 illustrates an example of a probability distribution of RAT change events.

[0052] FIG. 25 illustrates an example of a cumulative distribution function of a scheduling related feature according to embodiments of the present disclosure.

[0053] FIG. 26 illustrates an exemplary deployment of a method performed by a user equipment according to embodiments of the present disclosure.

[0054] FIG. 27 is a block diagram illustrating a user equipment according to embodiments of the present disclosure.

[0055] FIG. 28 illustrates a schematic diagram of a structure of an electronic apparatus applicable to embodiments of the present disclosure.

[0056] The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of various embodiments of the disclosure as defined by the claims and their equivalents. It includes various specific details to assist in that understanding but these are to be regarded as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the various embodiments described herein can be made without departing from the scope of the disclosure. In addition, descriptions of well-known functions and constructions may be omitted for clarity and conciseness.

[0057] The terms and words used in the following description and claims are not be limited to the bibliographical meanings, but, are merely used by the inventor to enable a clear and consistent understanding of the disclosure. Accordingly, it should be apparent to those skilled in the art that the following description of various embodiments of the disclosure is provided for illustration purpose only and not for the purpose of limiting the disclosure as defined by the appended claims and their equivalents.

[0058] It is to be understood that the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a component surface" includes reference to one or more of such surfaces.

[0059] In various examples of the disclosure described below, a hardware approach will be described as an example. However, since various embodiments of the disclosure may include a technology that utilizes both the hardware-based and the software-based approaches, they are not intended to exclude the software-based approach.

[0060] As used herein, the terms referring to merging (e.g., merging, grouping, combination, aggregation, joint, integration, unifying), the terms referring to signals (e.g., packet, message, signal, information, signaling), the terms referring to resources (e.g. section, symbol, slot, subframe, radio frame, subcarrier, resource element (RE), resource block (RB), bandwidth part (BWP), opportunity), the terms used to refer to any operation state (e.g., step, operation, procedure), the terms referring to data (e.g. packet, message, user stream, information, bit, symbol, codeword), the terms referring to a channel, the terms referring to a network entity (e.g., distributed unit (DU), radio unit (RU), central unit (CU), control plane (CU-CP), user plane (CU-UP), O-DU -open radio access network (O-RAN) DU), O-RU (O-RAN RU), O-CU (O-RAN CU), O-CU-UP (O-RAN CU-CP), O-CU-CP (O-RAN CU-CP)), the terms referring to the components of an apparatus or device, or the like are only illustrated for convenience of description in the disclosure. Therefore, the disclosure is not limited to those terms described below, and other terms having the same or equivalent technical meaning may be used therefor. Further, as used herein, the terms, such as '~ module', '~ unit', '~ part', '~ body’, or the like may refer to at least one shape of structure or a unit for processing a certain function.

[0061] Further, throughout the disclosure, an expression, such as e.g., 'above' or 'below' may be used to determine whether a specific condition is satisfied or fulfilled, but it is merely of a description for expressing an example and is not intended to exclude the meaning of 'more than or equal to' or 'less than or equal to'. A condition described as 'more than or equal to' may be replaced with an expression, such as 'above', a condition described as 'less than or equal to' may be replaced with an expression, such as 'below', and a condition described as 'more than or equal to and below' may be replaced with 'above and less than or equal to', respectively. Furthermore, hereinafter, 'A' to 'B' means at least one of the elements from A (including A) to B (including B). Hereinafter, 'C' and / or 'D' means including at least one of 'C' or 'D', that is, {'C', 'D', or 'C' and 'D'}.

[0062] The disclosure describes various embodiments using terms used in some communication standards (e.g., 3rd Generation Partnership Project (3GPP), extensible radio access network (xRAN), open-radio access network (O-RAN) or the like), but it is only of an example for explanation, and the various embodiments of the disclosure may be easily modified even in other communication systems and applied thereto.

[0063] Other technical features may be readily apparent to one skilled in the art from the following figures, descriptions, and claims.

[0064] Before undertaking the disclosure below, it may be advantageous to set forth definitions of certain words and phrases used throughout this patent document. The term "couple" and its derivatives refer to any direct or indirect communication between two or more elements, whether or not those elements are in physical contact with one another. The terms "transmit", "receive", and "communicate" as well as derivatives thereof, encompass both direct and indirect communication. The terms "include" and "comprise" as well as derivatives thereof, mean inclusion without limitation. The term "or" is inclusive, meaning and / or. The phrase "associated with" as well as derivatives thereof, means to include, be included within, interconnect with, contain, be contained within, connect to or with, couple to or with, be communicable with, cooperate with, interleave, juxtapose, be proximate to, be bound to or with, have, have a property of, have a relationship to or with, or the like. The term "controller" means any device, system or part thereof that controls at least one operation. Such a controller may be implemented in hardware or a combination of hardware and software and / or firmware. The functionality associated with any particular controller may be centralized or distributed, whether locally or remotely. The phrase "at least one of," when used with a list of items, means that different combinations of one or more of the listed items may be used, and only one item in the list may be needed. For example, "at least one of: A, B, and C" includes any of the following combinations: A, B, C, A and B, A and C, B and C, and A and B and C.

[0065] Moreover, various functions described below can be implemented or supported by one or more computer programs, each of which is formed from computer readable program code and embodied in a computer readable medium. The terms "application" and "program" refer to one or more computer programs, software components, sets of instructions, procedures, functions, objects, classes, instances, related data, or a portion thereof adapted for implementation in a suitable computer readable program code. The phrase "computer readable program code" includes any type of computer code, including source code, object code, and executable code. The phrase "computer readable medium" includes any type of medium capable of being accessed by a computer, such as read only memory (ROM), random access memory (RAM), a hard disk drive, a compact disc (CD), a digital video disc (DVD), or any other type of memory. A "non-transitory" computer readable medium excludes wired, wireless, optical, or other communication links that transport transitory electrical or other signals. A non-transitory computer readable medium includes media where data can be permanently stored and media where data can be stored and later overwritten, such as a rewritable optical disc or an erasable memory device.

[0066] Definitions for other certain words and phrases are provided throughout this patent document. Those of ordinary skill in the art should understand that in many if not most instances, such definitions apply to prior as well as future uses of such defined words and phrases.

[0067] The following description with reference to the accompanying drawings is provided to aid in a thorough understanding of various embodiments of the present disclosure as defined by claims and equivalents thereof. This description includes various specific details to aid in understanding but should only be considered exemplary. Accordingly, those ordinary skills in the art will recognize that various changes and modifications may be made to the various embodiments described herein without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known features and structures may be omitted for the sake of clarity and brevity.

[0068] The terms and phrases used in the claims and the following description are not limited to dictionary meaning thereof, but are used only by the inventor to enable a clear and consistent understanding of the present disclosure. Accordingly, it should be apparent to those skilled in the art that, the following description of the various embodiments of the present disclosure is provided for an illustrative purpose only and is not intended to a purpose of limiting the present disclosure as defined by the appended claims and equivalents thereof.

[0069] It should be understood that, "a", "an" and "the" in a singular form may also include a plural reference, unless the context clearly indicates otherwise. Thus, for example, a reference to a "part surface" includes a reference to one or more such surfaces. When it refers to one element as being "connected" or "coupled" to another element, the one element may be directly connected or coupled to the other element, or it may refer to a connection relationship between the one element and the other element established through an intermediate element. In addition, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled.

[0070] The term "include" or "may include" refers to the presence of a function, operation, or component of the corresponding disclosure that may be used in the various embodiments of the present disclosure, and does not limit the presence of one or more additional functions, operations, or features. In addition, the terms "include" or "have" may be interpreted to denote certain features, figures, steps, operations, constituent elements, components, or combinations thereof, but should not be interpreted to exclude the possibility of the presence of one or more other features, figures, steps, operations, constituent elements, components, or combinations thereof.

[0071] The term "or" as used in the various embodiments of the present disclosure includes any of the listed terms and all combinations thereof. For example, "A or B" may include A, may include B, or may include both A and B. When describing a plurality of (two or more) items, the plurality of items may refer to one, more, or all of the plurality of items if a relationship among the plurality of items is not explicitly defined. For example, for the description "a parameter A comprises A1, A2, A3", it may be implemented as parameter A comprising A1, A2 or A3, or as parameter A comprising at least two of the three items of the parameter A1, A2, A3.

[0072] All terms (including technical or scientific terms) used in the present disclosure have the same meaning as understood by those skilled in the art to which the present disclosure belongs, unless defined differently. Common terms as defined in dictionaries are interpreted to have a meaning consistent with the context in the relevant technology art and should not be interpreted in an idealized or overly formalistic manner, unless expressly so defined in the present disclosure.

[0073] At least part of the functions in a device or electronic apparatus provided in the embodiments of the present disclosure may be implemented through an AI model, such as, at least one of a plurality of modules of the device or electronic apparatus may be implemented through the AI model. A function associated with AI may be performed through the non-volatile memory, the volatile memory, and the processor.

[0074] The processor may include one or more processors. At this time, the one or more processors may be a general purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, or may be a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an AI-dedicated processor such as a neural processing unit (NPU).

[0075] The one or more processors control processing of input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning.

[0076] Here, being provided through learning means that, by applying a learning algorithm to a plurality of learning data, a predefined operating rule or an AI model of a desired characteristic is made. The learning may be performed in a device or electronic apparatus itself in which AI according to embodiments is performed, and / or may be implemented through a separate server / system.

[0077] The AI model may consist of a plurality of neural network layers. Each layer has a plurality of weight values, and performs a neural network calculation by calculating between the input data of this layer (such as, a calculation result of the previous layer and / or the input data of the AI model) and the plurality of weight values of the current layer. Examples of neural networks include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted Boltzmann Machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a generative adversarial networks (GAN), and a deep Q-network.

[0078] The learning algorithm is a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to make a determination or prediction. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0079] In the present application, at least one step of a method performed in an electronic apparatus may be implemented using an artificial intelligence model. A processor of the electronic apparatus may perform pre-processing operations on data to convert it into a form suitable for use as an input to the artificial intelligence model. The artificial intelligence model may be obtained by training. Here, "obtained by training" means that a predefined operation rule or artificial intelligence model configured to perform a desired feature (or purpose) is obtained by training a basic artificial intelligence model with multiple pieces of training data by a training algorithm.

[0080] Below, the technical solutions of the embodiments of the disclosure and the technical effects produced by the technical solutions of the disclosure will be explained by describing several optional embodiments. It should be noted that, the following embodiments may be referred to, imitated or combined with each other, and the same term, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0081] As described in the background art of the present disclosure, accurate prediction of the wireless channel condition facilitates improving the QoE for users. For example, taking the throughput as an example of the wireless channel condition, if the throughput may be accurately predicted, an application for playing a video in the user equipment may adaptively adjust a streaming bitrate based on the predicted throughput. However, inaccurate prediction of the available throughput may lead to incorrect selection of the streaming bitrate, thereby ultimately leading to stuttering during video playback. For example, using a widely used open-source video player, a video of 10 minutes and 34 seconds is played based on the throughput predicted by conventional techniques. As shown in FIG. 1, the available throughput is significantly reduced, if the throughput is incorrectly predicted with the adopted wireless channel condition prediction technique, the video player is unable to adjust the bitrate in time, and when video blocks in a buffer finish playing, video playback stutters, which affects the QoE for users. Current wireless channel condition prediction techniques are usually used to predict the wireless channel condition directly based on historical data of features related to the wireless channel condition. For example, taking the throughput as an example of the wireless channel condition, the specific reasons for the inaccuracy of the throughput predicted by the existing techniques are reflected in two aspects: on one hand, some of input features used for prediction do not have a direct relationship with the throughput. For example, the prior art predicts a future throughput only based on historical throughput and signal strength-related features. However, the signal strength-related features do not directly lead to the throughput change. For example, as shown in FIG. 2, a high service cell load may limit the throughput achievable by the UE even when the signal strength is strong. In addition, the available throughput may also vary significantly between radio access technologies (RATs), even though similar signal strengths are observed in cells under different RATs. On the other hand, accurate throughput prediction cannot be obtained using only the historical throughput. For example, as shown in FIG. 3, there are a number of factors that affect the throughput change, including a RAT accessed by the UE, a cell load, a UE speed, a UE position and a UE behavior. These factors are coupled to affect the throughput change. Therefore, directly using the historical throughput to predict future changes cannot effectively analyze these factors, resulting in inaccurate prediction.

[0082] With respect to this, the present disclosure proposes to decouple the factors affecting the wireless channel condition change in the historical information, such as a network format, a cell characteristic, etc., to separately predict a wireless channel condition change caused by each factor (i.e., to separately predict a wireless channel condition component associated with each factor), and finally to obtain an accurate wireless channel condition based on the predicted respective components. This allows predicting a more accurate wireless channel condition based on various influencing factor, while avoiding the mutual influence of respective factors.

[0083] FIG. 4 is a flowchart illustrating a method performed by a user equipment (UE) according to embodiments of the present disclosure.

[0084] Referring to FIG. 4, at step S410, a first wireless channel condition component related to a radio access technology (RAT) change and a second wireless channel condition component related to a cell characteristic are predicted, respectively. According to embodiments, the first wireless channel condition component indicates a wireless channel condition change due to the RAT change, and the second wireless channel condition component indicates a wireless channel condition change due to the cell characteristic. Next, at step S420, a predicted wireless channel condition is obtained based on the first wireless channel condition component and the second wireless channel condition component. According to embodiments, the cell characteristic is a cell characteristic in the case of the RAT being unchanged. According to embodiments, the RAT change may lead to a wireless channel condition change, and different cell characteristics under the same RAT may also lead to different wireless channel condition changes, therefore, the present disclosure separately predicts wireless channel condition changes due to different factors affecting the wireless channel condition (i.e., the RAT change and the cell characteristic) (i.e., may decouple different wireless channel condition changes caused by different influencing factors), and then the predicted wireless channel condition is obtained based on the wireless channel condition changes due to different factors, instead of directly predicting the wireless channel condition change caused by the combination of all the influencing factors, thereby making it possible to avoid the decrease in the accuracy of the wireless channel condition prediction caused by the interactions between the different influencing factors, and thus the method according to embodiments of the present disclosure may predict the wireless channel condition more accurately, thereby improving the QoE for users.

[0085] Hereinafter, step S410 will be described in further detail with reference to the accompanying drawings.

[0086] In the following, the RAT may also be referred to as a "network format", which may include, for example, GSM, CDMA, LTE, NR, and the like. Optionally, according to embodiments, the wireless channel condition may include throughput, a degree of signal degradation, packet loss rate, spectrum utilization rate, signal strength, and the like. For convenience of description, in the following, a method performed by a user equipment according to embodiments of the present disclosure is described by taking the throughput as an example of the wireless channel condition, however, the wireless channel condition is not limited to including only the throughput.

[0087] For example, it has been found through research by the inventors of the present application that when the RAT is changed, an available throughput of the UE undergoes a significant change, and a throughput distribution corresponding to different cell characteristics under the same RAT varies greatly, which indicates that both the RAT change and the cell characteristics under the same RAT have a direct impact on the throughput change. Accurate throughput prediction may be realized if the throughput change caused by the RAT change and the throughput change corresponding to different cell characteristics under the same RAT may be accurately predicted. The effects of the RAT change and the cell characteristics under the same RAT on the throughput change are coupled together, and if they may be decoupled before obtaining the respective throughput effects corresponding to the RAT change and the cell characteristics, more accurate throughput prediction may be achieved.

[0088] According to embodiments, the predicted wireless channel condition may be obtained by combining the first wireless channel condition component related to the RAT change and the second wireless channel condition component related to the cell characteristic. In the following, the first wireless channel condition component related to the RAT change may also be referred to as an "inter-RAT change component of the wireless channel condition" or may be abbreviated as an "inter-RAT change component" or "inter-RAT changes", meaning that the change in the wireless channel condition due to the RAT change. The second wireless channel condition component related to the cell characteristic may also be referred to as an "intra-RAT fluctuation component of the wireless channel condition" or may be abbreviated as an "intra-RAT fluctuation component" or "intra-RAT fluctuations", meaning that the change in the wireless channel condition due to the cell characteristics under the same RAT.

[0089] As shown in FIG. 5, the throughput change may be caused by the RAT change and the cell characteristics in the case of the RAT being unchanged, and the throughput change may be decoupled into the "inter-RAT changes" and the "intra-RAT fluctuations". As may also be seen in FIG. 5, the inter-RAT changes are several orders of magnitude higher than the intra-RAT fluctuations, and these significant changes result in a non-stationary throughput time sequence, whereas the intra-RAT fluctuations are close to be stationary.

[0090] According to embodiments, for the same RAT, the throughput corresponding to different cell characteristics also vary significantly. As shown in FIG. 6, cell characteristics under the same RAT may include a cell characteristic related to a network configuration and a cell characteristic unrelated to the network configuration. For example, the cell characteristic related to the network configuration may include a cell characteristic that is configured for the UE by a base station, such as a cell bandwidth, a number of subcarriers, a frequency point, and so on. For example, the cell characteristic unrelated to the network configuration may include a cell characteristic that is not explicitly configured for the UE by the base station, which is typically related to a cell load and a scheduling scheme deployed by the base station, and may include, for example, the cell load and a traffic condition. As shown in FIG. 6, the cell characteristics may directly affect the intra-RAT fluctuations of the throughput. For example, as shown in FIG. 7, for the same RAT, the throughput distribution varies greatly under different cell bandwidths.

[0091] In the following, an exemplary way of predicting the first wireless channel condition component and an exemplary way of predicting the second wireless channel condition component according to embodiments of the present disclosure will be described in connection with FIGS. 8 and 9, respectively. FIG. 8 is a schematic diagram illustrating an exemplary architecture for predicting a wireless channel condition according to embodiments of the present disclosure. FIG. 9 is a schematic diagram illustrating a detailed exemplary architecture for predicting a wireless channel condition according to embodiments of the present disclosure.

[0092] As shown in FIG. 8, a first wireless channel condition component related to a RAT change and a second wireless channel condition component related to a cell characteristic may be predicted separately, and then the first wireless channel condition component and the second wireless channel condition component may be combined to obtain a predicted wireless channel condition.

[0093] According to embodiments, predicting the first wireless channel condition component may include: predicting a RAT to be accessed by the user equipment; and predicting the first wireless channel condition component related to the RAT change based on the predicted RAT to be accessed by the user equipment and historical wireless channel condition information.

[0094] According to embodiments, for example, as shown in FIG. 9, predicting the RAT to be accessed by the user equipment may include: predicting the RAT to be accessed by the user equipment based on a historical radio resource management (RRM) related feature in the historical wireless channel condition information. Then, for example, the first wireless channel condition component may be predicted based on the predicted RAT to be accessed by the user equipment and a historical scheduling related feature in the historical wireless channel condition information.

[0095] According to embodiments, a first artificial intelligence (AI) model may be used to predict the RAT to be accessed by the user equipment based on the RRM related feature. Optionally, according to embodiments, predicting the RAT to be accessed by the user equipment based on the historical RRM related feature in the historical wireless channel condition information may include: predicting a RRM related feature difference between cells under different RATs based on the historical RRM related feature, wherein the RRM related feature difference indicates a RRM related feature difference between a serving cell under a first RAT and a neighbor cell under a second RAT; and predicting the RAT to be accessed by the user equipment based on the RRM related feature difference.

[0096] According to embodiments, for example, the historical wireless channel condition information may include a RRM related feature and a scheduling related feature. For example, the historical wireless channel condition information may be obtained from log information of the UE (e.g., log information of a communication processor of the UE).

[0097] For example, the RRM related feature may include, but not be limited to, at least one of a Reference Signal Receiving Power (RSRP), a Reference Signal Receiving Quality (RSRQ), a Signal-to-Noise Ratio (SNR) and a Received Signal Strength Indication (RSSI). For example, the scheduling related feature may include, but not be limited to, at least one of a parameter related to a scheduling algorithm and a parameter for evaluating scheduling performance, and may also include other scheduling related features and are not described herein. As an example, the parameter related to the scheduling algorithm may include, but not be limited to, at least one of throughput, a transmission block size, a number of resource blocks, a number of scheduling times, and a scheduling delay, and the parameter for evaluating the scheduling performance may include, but not be limited to, at least one of throughput and a one-way delay. Here, the one-way delay is a time for data from a transmitting end to a receiving end.

[0098] As an example, the first AI model may be utilized to predict the RRM related feature difference between cells under different RATs based on the historical RRM related feature. For example, the RRM related feature difference may include a RSRP difference, a RSRQ difference, a RSRQ difference, a RSSI difference, and the like.

[0099] In the following, a way of predicting the RAT to be accessed by the user equipment is described using the RSRP difference as an example of the RRM related feature difference.

[0100] For the convenience of description, definitions of some terms and parameters are first given below:

[0101]

[0102]

[0103]

[0104] According to embodiments, predicting the RAT to be accessed by the user equipment based on the historical RRM related feature in the historical wireless channel condition information may include: determining a relationship between the RRM related feature difference between cells under different RATs and a RAT change event based on historical data related to the RRM related feature difference between cells under different RATs; and predicting the RAT to be accessed by the user equipment by using the relationship based on the predicted RRM related feature difference. Optionally, predicting the RAT to be accessed by the user equipment by using the relationship based on the predicted RRM related feature difference may include: determining a difference interval to which the predicted RRM related feature difference belongs; calculating, based on the difference interval, a probability of occurrence of a RAT change event under the difference interval and a confidence interval corresponding to the probability using the relationship; and predicting, based on the confidence interval, the RAT to be accessed by the user equipment.

[0105] For example, a relationship between the RSRP difference between cells under different RATs and the RAT change event may be determined based on historical statistical values related to the RSRP difference between cells under different RATs, and then, the RAT to be accessed by the user equipment may be predicted based on the predicted RSRP difference and the relationship. As an example, the relationship between the RSRP difference between cells under different RATs and the RAT change event may be represented by a posterior probability in the following. According to embodiments, a RAT to be accessed by the user within each prediction window may be predicted separately. For example, the RSRP difference between different RATs in the future may be predicted by an AI model, then a posterior probability of occurrence of a RAT change event in the future and its corresponding confidence interval may be calculated, and finally a RAT to be accessed by the user in the future may be derived based on the calculated confidence interval.

[0106] Specifically, for example, a RAT to be accessed by a user equipment may be predicted by the following steps:

[0107]

[0108]

[0109]

[0110]

[0111]

[0112]

[0113]

[0114]

[0115]

[0116]

[0117]

[0118]

[0119]

[0120] For example, the steps may be as follows:

[0121]

[0122] - is clustered using a bottom-up distance clustering algorithm.

[0123]

[0124]

[0125]

[0126]

[0127] In the case of predicting the RAT to be accessed by the user equipment, the first wireless channel condition component related to the RAT change may be predicted based on the predicted RAT to be accessed by the user equipment and the historical wireless channel condition information as described above. For example, the first wireless channel condition component related to the RAT change may be predicted based on the predicted RAT to be accessed by the user equipment and the historical scheduling related feature in the historical wireless channel condition information. According to embodiments, predicting a first wireless channel condition component related to the RAT change based on the predicted RAT to be accessed by the user equipment and the historical scheduling related feature in the historical wireless channel condition information may include: obtaining the first historical wireless channel condition component related to the RAT change based on the historical scheduling related feature in the historical wireless channel condition information; predicting the first wireless channel condition component based on the first historical wireless channel condition component and the predicted RAT to be accessed by the user equipment. The first historical wireless channel condition component may indicate a historical wireless channel condition change due to the historical RAT change.

[0128] For example, the historical wireless channel condition change due to the RAT change (i.e., the first historical wireless channel condition component, which may also be referred to as the "historical inter-RAT change component") and the historical wireless channel condition change due to the cell characteristic (i.e., the second historical wireless channel condition component, which may also be referred to as the "historical intra-RAT fluctuation component") may be separated from the historical scheduling related feature in the historical wireless channel condition information. The first wireless channel condition component in the future may then be predicted based on the first historical wireless channel condition component and the predicted RAT to be accessed by the user equipment.

[0129] According to embodiments, predicting the first wireless channel condition component related to the RAT change based on the first historical wireless channel condition component and the predicted RAT to be accessed by the predicted user equipment may include: performing a weighted summation of the first historical wireless channel condition component within a historically predetermined time; and predicting the first wireless channel condition component based on a result of the weighted summation and the predicted RAT to be accessed by the user equipment. For example, the weighted summation is firstly performed on inter-RAT change components of a historical wireless channel condition so as to estimate an inter-RAT change component in a corresponding wireless channel condition when a RAT change occurs in the future, and then, based on the estimated inter-RAT change component and the predicted RAT to be accessed by the UE as predicted above, a predicted inter-RAT change component (i.e., the first wireless channel condition component) of the wireless channel condition is obtained.

[0130] For example, the specific steps for predicting the inter-RAT change component of the wireless channel condition may be as follows:

[0131]

[0132]

[0133]

[0134] For example, it is assumed that the wireless channel condition includes the throughput, an inter-RAT change component of a future throughput may be predicted as shown in FIG. 14, following steps 1 through 3 above.

[0135] In the above, the method of predicting the first wireless channel condition component in step S410 has been described. According to embodiments of the present disclosure, as described above, the historical wireless channel condition change due to the RAT change (the first historical wireless channel condition component, i.e., the historical inter-RAT change component) may be firstly decoupled from the historical wireless channel condition information, and then, based on the first historical wireless channel condition component and the predicted RAT to be accessed by the user equipment, the first wireless channel condition component (i.e., the inter-RAT change component) in the future wireless channel condition may be predicted. The wireless channel condition change due to the RAT change is a large fluctuation for the wireless channel condition, which may cause the wireless channel condition to become unstable, but this component is characterized by the magnitude of each change remaining relatively constant, so it is only necessary to determine the RAT within the prediction window, and then it is possible to predict the inter-RAT change component in the future wireless channel condition. After the large fluctuation caused by the RAT change is eliminated, the second wireless channel condition component related to the cell characteristic in the wireless channel condition exhibits relative stability, which is more conducive to analysis and prediction. Next, the way of predicting the second wireless channel condition component in step S410 will continue to be described with reference to the accompanying drawings.

[0136] According to embodiments, predicting the second wireless channel condition component related to the cell characteristic may include: predicting the second wireless channel condition component related to the cell characteristic based on historical wireless channel condition information and historical cell characteristic information related to a network configuration. According to embodiments, for example, predicting the second wireless channel condition component related to the cell characteristic based on the historical wireless channel condition information and the historical cell characteristic information related to the network configuration may include: obtaining the second historical wireless channel condition component related to the cell characteristic based on a historical scheduling related feature in the historical wireless channel condition information; predicting the second wireless channel condition component related to the cell characteristic based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration. According to embodiments, the second historical wireless channel condition component may indicate a historical wireless channel condition change due to the cell characteristic.

[0137] For example, as described above, the historical wireless channel condition change due to the RAT change (i.e., the first historical wireless channel condition component, which may also be referred to as the "historical inter-RAT change component") and the historical wireless channel condition change due to the cell characteristic (i.e., the second historical wireless channel condition component) may be separated from the historical scheduling related feature in the historical wireless channel condition information. The second wireless channel condition component, i.e., the intra-RAT fluctuation component, may then be predicted based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration.

[0138] According to embodiments, the cell characteristic may include a cell characteristic related to the network configuration and a cell characteristic unrelated to the network configuration, and the intra-RAT fluctuation component may be affected by both the cell characteristic related to the network configuration and the cell characteristic unrelated to the network configuration, and thus, according to embodiments of the present disclosure, a wireless channel condition component corresponding to the cell characteristic related to the network configuration and a wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration may be predicted separately, and then the intra-RAT fluctuation component in the wireless channel condition is predicted based on the predicted wireless channel condition component corresponding to the cell characteristic related to the network configuration and the wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration.

[0139] Referring back to FIG. 8, for example, after obtaining the second historical wireless channel condition component based on the historical scheduling related feature in the historical wireless channel condition information, predicting the second wireless channel condition component based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration may include: predicting, based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration, a third wireless channel condition component corresponding to a cell characteristic related to the network configuration and a fourth wireless channel condition component corresponding to a cell characteristic unrelated to the network configuration; and predicting the second wireless channel condition component based on the predicted third wireless channel condition component and the fourth wireless channel condition component. This separation operation avoids coupled interference between the cell characteristic related to the network configuration and the cell characteristic unrelated to the network configuration on the throughput change, and may improve the accuracy of predicting the second wireless channel condition component.

[0140] Referring back to FIG. 9, optionally, according to embodiments, predicting the third wireless channel condition component corresponding to the cell characteristic related to the network configuration and the fourth wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration may include: obtaining a first feature component corresponding to the cell characteristic related to the network configuration and a second feature component corresponding to the cell characteristic unrelated to the network configuration based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration; predicting the third wireless channel condition component based on the first feature component and the historical cell characteristic information related to the network configuration; and predicting the fourth wireless channel condition component based on the second feature component. After predicting the third wireless channel condition component corresponding to the cell characteristic related to the network configuration and the fourth wireless channel condition component corresponding to the cell characteristic not related to the network configuration, the second wireless channel condition component may be predicted based on the predicted third wireless channel condition component and the fourth wireless channel condition component.

[0141] For example, obtaining the first feature component corresponding to the cell characteristic related to the network configuration and the second feature component corresponding to the cell characteristic unrelated to the network configuration based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration may include: dividing the second historical wireless channel condition component into a third feature component possibly corresponding to a cell characteristic related to the network configuration and a fourth feature component corresponding to a cell characteristic unrelated to the network configuration, based on a correlation between the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration; performing feature mapping on the fourth feature component; and obtaining the first feature component and the second feature component based on the mapped feature component.

[0142] Optionally, according to embodiments, obtaining the first feature component and the second feature component based on the mapped feature component may include: dividing the mapped feature component into the first feature component and a fifth feature component corresponding to the cell characteristic unrelated to the network configuration; and obtaining the second feature component based on the fourth feature component and the fifth feature component.

[0143] According to embodiments, a second AI model may be utilized to perform the above operations to predict the second wireless channel condition component. FIG. 15 is a schematic diagram illustrating a second AI model for predicting a second wireless channel condition component, according to embodiments of the present disclosure. As shown in FIG. 15, for example, the second AI model may include a feature selection module and a prediction module. Inputs to the second AI model may be the historical cell characteristic information related to the network configuration and the second historical wireless channel condition component obtained based on the historical scheduling related feature. As shown in FIG. 15, the feature selection module may obtain the first feature component corresponding to the cell characteristic related to the network configuration (denoted as A in FIG. 15) and the second feature component corresponding to the cell characteristic unrelated to the network configuration (denoted as B in FIG. 15) based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration. Subsequently, the prediction module may predict the third wireless channel condition component corresponding to the cell characteristic related to the network configuration and the fourth wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration based on the first feature component and the second feature component, respectively, and combine the third wireless channel condition component and the fourth wireless channel condition component to obtain the second wireless channel condition component (intra-RAT fluctuation component).

[0144] According to embodiments, the principle of using the above AI model prediction is:

[0145] 1. Most scheduling related features may be affected by both the cell characteristic related to the network configuration and the cell characteristic unrelated to the network configuration. For example, a transmission block size is affected by both a cell bandwidth and a cell load. When the cell bandwidth is low, the transmission block size is correspondingly small to minimize the transmission delay. In addition, if the cell load is very low, the transmission block size may become correspondingly large to maximize the transmission efficiency.

[0146] 2. Unlike the cell characteristic unrelated to the network configuration, the cell characteristic related to the network configuration is usually easy to be obtained, e.g., it may be obtained from a log file of a communication processor of the UE. Therefore, it is feasible to perform feature mapping of the scheduling related feature used for prediction through an AI model, and then separate the mapped feature based on a correlation with the cell characteristic related to the network configuration.

[0147] 3. By separating these feature components, the intra-RAT fluctuation component of the wireless channel condition may be divided into two components: a component corresponding to the cell characteristic related to the network configuration and a component corresponding to the cell characteristic unrelated to the network configuration. This separation operation may avoid the coupled interference between the cell characteristic related to the network configuration and the cell characteristic unrelated to the network configuration on the throughput change, and may improve the accuracy of predicting the intra-RAT fluctuation component.

[0148] FIG. 16 is a schematic diagram illustrating a detailed structure of a second AI model for predicting a second wireless channel condition component according to embodiments of the present disclosure. A process for predicting the second wireless channel condition component using the second AI model will be described in further detail below with reference to FIG. 16.

[0149] As shown in FIG. 16, the feature selection module in the second AI model may include a separation module, a first neural network unit (denoted by "NNU-1"), and a similarity module, and the prediction module in the second AI model may include a combination module, a second neural network unit (denoted by "NNU-2") and a third neural network unit (denoted by "NNU-3"). NNU-1, NNU-2, and NNU-3 may be neural network modules, and the separation module, the similarity module, and the combination module may be operation modules.

[0150] According to embodiments, the historical intra-RAT fluctuation component may be obtained based on the historical scheduling related feature, and subsequently, the separation module may classify the historical intra-RAT fluctuation component into two categories based on the correlation between the historical intra-RAT fluctuation component and the cell characteristic related to the network configuration. The two categories are a third feature component possibly corresponding to a cell characteristic related to the network configuration and a fourth feature component corresponding to a cell characteristic unrelated to the network configuration, respectively. In other words, the inputs of this module are the historical intra-RAT fluctuation component and the historical cell characteristic information related to the network configuration, and the outputs are: i) the third feature component (denoted as O1) possibly corresponding to the cell characteristic related to the network configuration (e.g., a transmission block size, etc.); and ii) the fourth feature component (denoted as O2) corresponding to the cell characteristic unrelated to the network configuration (e.g., a scheduling delay, etc.). For example, the classification of the historical intra-RAT fluctuation component is based on the difference in its distribution under different cell characteristics configured by a network .

[0151] The NNU-1 module performs feature mapping on the third feature component (O1), e.g., mapping O1 to a feature space of a higher dimension than a dimension of O1, and in FIG. 16, labeling the mapped feature component as O3. The physical meaning of O3 is a combination of multiple weightings, and it is assumed that a number of features in O1 is N, a number of feature components in O3 expands to a N Х m dimension, and each feature component in O3 is related to the features in O1.

[0152] The similarity module divides the mapped feature component (O3) into two categories: the first feature component corresponding to the cell characteristic related to the network configuration (labeled as "O4" in FIG. 16) and a fifth feature component corresponding to the cell characteristic unrelated to the network configuration (labeled as "O5"). This separation is achieved by comparing the correlation between each feature component of O3 and the cell characteristic related to the network configuration within the observation window. For example, a Pearson correlation coefficient may be used as the similarity measure. For example, the Pearson correlation coefficient between one feature component and one cell characteristic related to the network configuration within the observation window is denoted as wherein is a similarity threshold, it is considered that the feature component may be affected by the cell characteristic related to the network configuration; otherwise it is considered that the feature component is affected by the cell characteristic unrelated to the network configuration.

[0153] According to embodiments, the prediction module may predict the intra-RAT fluctuation component by separately predicting the wireless channel condition component corresponding to the cell characteristic related to the network configuration (the above third wireless channel condition component) and the wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration (the above fourth wireless channel condition component). For example, the third wireless channel condition component (labeled as "O6" in FIG. 16) is predicted based on historical cell characteristic information related to the network configuration and a feature component corresponding to the cell characteristic related to the network configuration (the above first feature component O4), and the fourth wireless channel condition component is predicted based on a feature component corresponding to the cell characteristic unrelated to the network configuration (the above second feature component, labeled as "O7" in FIG. 16). For example, the fourth feature component (O2) corresponding to the cell characteristic unrelated to the network configuration separated by the separation module and the fifth feature component (O5) corresponding to the cell characteristic unrelated to the network configuration separated by the similarity module are combined to obtain the second feature component (O7), and then the fourth wireless channel condition component (labeled as "O8" in FIG. 16) is predicted based on the second feature component. Finally, the intra-RAT fluctuation component of a future wireless channel condition is obtained by combining the third wireless channel condition component (O6) and the fourth wireless channel condition component (O8).

[0154] Specifically, for example, the NNU-2 module in the prediction module may predict the third wireless channel condition component corresponding to the cell characteristic related to the network configuration. The inputs to the module are historical cell characteristic information related to the network configuration and the first feature component (O4) corresponding to the cell characteristic related to the network configuration, and the output is the third wireless channel condition component (O6) corresponding to the cell characteristic related to the network configuration.

[0155] The combination module may combine the fourth feature component (O2) with the fifth feature component (O5) to obtain the second feature component (O7) corresponding to the cell characteristic unrelated to the network configuration. The second feature component is a component of the historical intra-RAT fluctuation component that is affected by the cell characteristic unrelated to the network configuration.

[0156] The NNU-3 module may predict the fourth wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration based on the second feature component corresponding to the cell characteristic unrelated to the network configuration.

[0157] The NNU-4 module may obtain the intra-RAT fluctuation component of the future wireless channel condition by combining the outputs of the NNU-2 module and the NNU-3 module. For example, the output of the NNU-4 module may be an intra-RAT fluctuation component within the prediction window, denoted as

[0158] Finally, the predicted inter-RAT change component and the intra-RAT fluctuation component of the wireless channel condition may be summed to obtain a predicted result of the future wireless channel condition, i.e.,

[0159] Optionally, an impact of a behavior of the UE on the wireless channel condition may also be taken into account when predicting the second wireless channel condition component related to the cell characteristic in the wireless channel condition. According to embodiments, in addition to the RAT change and the cell characteristics under the same RAT affecting the wireless channel condition, some behaviors of the UE, such as browsing short videos and traveling from one stop to the next on a subway, also affect the wireless channel condition change. According to embodiments, the behavior of the UE may include repetitive behaviors of the UE, but are not limited thereto. For example, FIG. 17 illustrates a throughput change of a UE during a user repeatedly browses a short video, and as may be seen in FIG. 17, when the UE performs repeated behaviors (e.g., browsing a short video), the throughput tends to show similar fluctuations. Therefore, the impact of these behaviors on the intra-RAT fluctuation component may also be considered when predicting the intra-RAT fluctuation component. For example, wireless channel condition change modes corresponding to the UE behaviors may be extracted from the historical wireless channel condition. These extracted wireless channel condition change modes are then used to improve the accuracy of predicting the second wireless channel condition component related to the cell characteristic in the wireless channel condition.

[0160] Optionally, according to embodiments, predicting the second wireless channel condition component based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration, as mentioned above in describing how to predict the second wireless channel condition component, may include: obtaining a wireless channel condition change mode corresponding to a behavior of the user equipment; and predicting the second wireless channel condition component based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration.

[0161] According to embodiments, the wireless channel condition change mode corresponding to the behavior of the user equipment may be obtained based on the second historical wireless channel condition component (e.g., the intra-RAT fluctuation component). For example, based on a plurality of periodic scales corresponding to repeated behaviors of the UE, wireless channel condition change modes corresponding to the repeated behaviors of the UE are extracted from the intra-RAT fluctuation component of the historical wireless channel condition. These extracted wireless channel condition change modes are then used as additional input features into an AI model for predicting the second wireless channel condition component to help more accurately predict the intra-RAT fluctuation component of the future wireless channel condition.

[0162] For example, the wireless channel condition change mode corresponding to the behavior of the UE may be extracted by the following operations:

[0163]

[0164]

[0165]

[0166]

[0167]

[0168]

[0169] v) These wireless channel condition change modes are used as additional input features when predicting the intra-RAT fluctuation component of the future wireless channel condition.

[0170] After obtaining the wireless channel condition change mode corresponding to the behavior of the user equipment, when performing the prediction of the second wireless channel condition component using the wireless channel condition change mode, in a similar manner to the prediction mentioned above, it is still possible to separately predict the third wireless channel condition component corresponding to the cell characteristic related to the network configuration and the fourth wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration component, and then, predict, based on these two components, the second wireless channel condition component. According to embodiments, predicting the second wireless channel condition component based on the wireless channel condition change mode, the second historical wireless channel condition component, and the historical cell characteristic information related to the network configuration may include: predicting the third wireless channel condition component corresponding to the cell characteristic related to the network configuration and the fourth wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration based on the wireless channel condition change mode, the second historical wireless channel condition component, and the historical cell characteristic information related to the network configuration, and predicting the second wireless channel condition component based on the predicted third wireless channel condition component and the fourth wireless channel condition component. For example, a first feature component corresponding to the cell characteristic related to the network configuration and a second feature component corresponding to the cell characteristic unrelated to the network configuration may firstly be obtained based on the wireless channel condition change mode, the second historical wireless channel condition component, and the historical cell characteristic information related to the network configuration; then, the third wireless channel condition component is predicted based on the first feature component and the historical cell characteristic information related to the network configuration, and the fourth wireless channel condition component is predicted based on the second feature component. Finally, the second wireless channel condition component may be predicted based on the predicted third wireless channel condition component and the fourth wireless channel condition component.

[0171] Above, exemplary ways of how to predict the first wireless channel condition component and the second wireless channel condition component have been described in connection with the accompanying figures and examples, respectively. The data (e.g., the RRM related feature and the historical scheduling related feature in the historical wireless channel condition information, the mobility information of the UE) required for predicting the first wireless channel condition component and the second wireless channel condition component as mentioned in the exemplary methods above may be incomplete in practice, e.g., the data for predicting the wireless channel condition component may be collected from a log file of a communication processor (CP) of the UE, and these collected data may have missing values due to various reasons such as lack of measurements or out of service at the UE. These missing values may significantly affect the accuracy of subsequent analysis and prediction. With respect to this, different data completion methods may be used to perform data completion based on specific reasons for data missing in order to obtain continuous data, thereby facilitating more accurate prediction of the wireless channel condition components.

[0172] For example, optionally, the method shown in FIG. 4 further includes: obtaining a log file related to communication of the user equipment; obtaining historical wireless channel condition raw information based on the log file; and performing data completion on a feature with a missing value in the historical wireless channel condition raw information to obtain the historical wireless channel condition information. For example, the historical wireless channel condition raw information may include a raw RRM related feature and a raw scheduling related feature. Accordingly, the completed historical wireless channel condition information includes the historical RRM related feature and the historical scheduling related feature after performing the completion.

[0173] As mentioned above, for example, the historical RRM related feature may include the RSRP, the RSRQ, the SNR, the RSSI, and the like. Ways of performing data completion on the historical RRM related feature may, for example, include: a) the UE is located within a servicing range of a cell, but the UE does not measure the RRM. In this case, the missing values may be completed with a RRM predicted based on the historical related data; and b) the UE is outside of the servicing range of the cell, at this time the data completion should not be performed.

[0174] As mentioned above, the historical scheduling related feature may include the throughput, the transmission block size, the number of resource blocks, the number of scheduling times, the scheduling delay, and so on. Methods for performing data completion on the historical scheduling related feature may, for example, include: a) if the data is missing due to out of service, in this case, all scheduling related features are missing, and at this time, the missing data should be completed with 0; b) if the data is missing due to the device, in this case, only part of the scheduling related features may be missing, and at this time, a third AI model may be used to complete the missing values. For example, as shown in FIG. 20, for a feature with missing data, mask processing may be performed on the missing data to obtain a masked data sequence , and the masked data sequence is input into the third AI model, and the missing data may be completed by an output sequence of the third AI model.

[0175] Optionally, as mentioned above in predicting the first wireless channel condition component, the mobility information of the UE may also be used in predicting the first wireless channel condition component. If there is missing data in the mobility information, data completion may also be performed. For example, the mobility information may include speed information and position information of the UE, etc. For example, performing data completion on the mobility information may include that the missing data may be completed by a simple linear interpolation method, since neither the speed information nor the position information of the UE will change significantly in a short period of time.

[0176] Above, the method performed by the user equipment according to embodiments of the present disclosure has been described in connection with FIGS. 1 to 20. According to the above methods, since it is possible to separately predict the wireless channel condition component related to the RAT change and the wireless channel condition component related to the cell characteristic, i.e., to separately predict the wireless channel condition changes due to the RAT change and the cell characteristic, and then obtain the predicted wireless channel condition based on the above wireless channel condition components, instead of directly predicting the wireless channel condition change caused by the combination of the RAT change and the cell characteristic, it is possible to avoid the decrease in the accuracy of the wireless channel condition prediction caused by the interactions between the different influencing factors, and thus the wireless channel condition may be predicted more accurately according to the above method, thereby improving the quality of the user's experience.

[0177] For a clearer understanding of the above method, a specific operation process for predicting the throughput using the above method is described below with reference to FIG. 21, taking the throughput as an example of the wireless channel condition. However, the wireless channel condition is not limited to including only the throughput, and the above method is not limited to the specific examples that will be described next.

[0178] FIG. 21 is a schematic diagram illustrating an example method for predicting the throughput according to embodiments of the present disclosure.

[0179] As shown in FIG. 21, predicting the throughput may include the following steps:

[0180] S1: acquiring and processing data and extracting features.

[0181] Step S1 may specifically include the following operations:

[0182] S1.1: determining whether the data is available, and completing the data according to different circumstances when it is not available.

[0183] For example, raw data required for predicting the throughput includes log information of a communication processor of the UE and GPS information of the UE. For example, the following features may be obtained after data extraction: 1. a RRM related feature; 2. a scheduling related feature; 3. historical cell characteristic information related to a network configuration; 4. a UE speed; and 5. a UE position (latitude and longitude).

[0184] Since an AI model requires continuous time-sequence inputs to perform the prediction more accurately, however, the input features extracted from the raw data may be missing for various reasons (including lack of measurements or out of service, etc.), different methods may be used to complete the missing data in different situations where different categories of features are obtained. Through data completion, continuous data that accurately represents the actual network environment and the transmission condition may be obtained, which may help the subsequent process to make a more accurate prediction. How to perform data completion has been described above and will not be repeated here.

[0185] S1.2: separating a historical inter-RAT change component and a historical intra-RAT fluctuation component from a time sequence of a historical scheduling related feature. The two separated components will be used in the prediction in Step S2. In addition, statistic data related to the RAT change is calculated, and the obtained statistic data will be used in the prediction of step S2.

[0186] For example, the time sequence of the historical scheduling related feature may be divided into a historical inter-RAT change component and a historical intra-RAT fluctuation component based on RATs historically accessed by the UE.

[0187] ●Data Representation

[0188]

[0189]

[0190] For each feature, the historical inter-RAT change component of the sequence may be obtained by calculating a difference between its averages in two neighboring durations of different RATs accessed by the UE, and the time sequence of the historical intra-RAT fluctuation component may be obtained by subtracting the time sequence of the historical inter-RAT change component from the original time sequence of the throughput.

[0191] Specific Steps:

[0192]

[0193]

[0194]

[0195]

[0196]

[0197]

[0198] Since the value of the inter-RAT change component is generally several orders of magnitude larger than that of the intra-RAT fluctuation component, separating the inter-RAT change component from the non-stationary time sequence may result in an approximately stationary intra-RAT fluctuation component, and the approximately stationary sequence may result in better prediction performance.

[0199] By separately processing and utilizing the historical inter-RAT change component and the historical intra-RAT fluctuation component to predict the corresponding inter-RAT change component and the intra-RAT fluctuation component of the future throughput, a more accurate prediction result may be obtained as compared to the throughput prediction using the raw time sequence directly.

[0200] As described above, statistic data related to the historical RAT change may also be calculated in this step, and the obtained statistic data will be used in the prediction of step S2.

[0201]

[0202] Specific steps include, for example:

[0203]

[0204]

[0205]

[0206]

[0207]

[0208]

[0209]

[0210]

[0211] S1.3: extracting throughput change modes corresponding to behaviors of the UE from the time sequence of the historical intra-RAT fluctuation component of the throughput, and then using these modes as additional features for predicting intra-RAT fluctuations in the future throughput. These additional features may improve the accuracy of predicting the throughput during repeated behaviors of the UE.

[0212] For example, corresponding throughput change modes may be extracted from the intra-RAT fluctuation component of the historical throughput based on a plurality of periodic scales corresponding to repeated behaviors of the UE.

[0213] ● Data Representation

[0214] - For example, raw input features for predicting the intra-RAT fluctuation component of the future throughput may be represented as

[0215]

[0216] Several periods corresponding to common user behaviors are selected in advance. For each period, the sequence is divided into a plurality of subsequences using a length of that period as a sliding window, and a subsequence that has the most similar subsequences is searched for and used as a similar mode corresponding to that period.

[0217] The specific steps may, for example, be as follows:

[0218]

[0219]

[0220]

[0221]

[0222]

[0223]

[0224]

[0225]

[0226]

[0227]

[0228]

[0229]

[0230]

[0231]

[0232] Finally, all the throughput modes corresponding to different periods are used as additional features. A new set of features for predicting the intra-RAT fluctuation component of the future throughput is denoted as

[0233] S2: predicting the future throughput.

[0234] The prediction of the throughput is divided into two steps: 1. predicting an inter-RAT change component of the future throughput (Step S2.1); 2. predicting an intra-RAT fluctuation component of the future throughput (Step S2.2). Eventually, the prediction results of these two steps are added together to obtain the future throughput.

[0235] S2.1: predicting the inter-RAT change component of the future throughput

[0236] For example, a RAT to be accessed by the UE within a prediction window may be predicted, and then the inter-RAT change component of the future throughput may be obtained based on a weighted combination of the predicted RAT to be accessed by the UE and the historical inter-RAT change component of the throughput extracted from the historical scheduling related feature.

[0237] First, regarding how to predict the RAT to be accessed by the UE within the prediction window, the following two methods may be used: 1) directly using the current RAT accessed by the UE as the predicted RAT to be accessed by the UE; 2) predicting the RAT to be accessed by the UE based on an AI model, using the historical RRM related feature and the mobility information of the UE.

[0238]

[0239] For example, the specific steps may be as follows:

[0240]

[0241] As shown in FIG. 23, the input features for RSRP prediction may include two categories: 1) RRM related features: the RSRP, the RSRQ, the SNR, the RSSI; 2) mobility information: the UE speed and the UE position. Before entering the AI model, input data at a time granularity required by the model may be obtained by sampling raw data at equal intervals in the time domain.

[0242]

[0243]

[0244]

[0245]

[0246]

[0247]

[0248]

[0249]

[0250]

[0251]

[0252] ◇the RAT to be accessed by the UE within the prediction window is determined

[0253]

[0254]

[0255] ◇The inter-RAT change component of the throughput is predicted.

[0256] A value of the inter-RAT change component at a time point is estimated by weighted summation of the historical inter-RAT change components. Then the inter-RAT change component within the prediction window is obtained based on the estimated value and the predicted RAT to be accessed by the UE.

[0257] For example, the specific steps are as follows:

[0258]

[0259]

[0260] S2.2 the intra-RAT fluctuation component of the future throughput is predicted.

[0261] The intra-RAT fluctuation component of the throughput is affected by the cell characteristic, the cell characteristic includes the cell characteristic related to the network configuration and the cell characteristic unrelated to the network configuration. For example, the historical cell characteristic information related to the network configuration may be obtained from logs of a communication processor of the UE, and the impact of these characteristics on throughput fluctuations may be analyzed based on the historical cell characteristic information related to the network configuration. For example, the feature component corresponding to the cell characteristic related to the network configuration and the feature component corresponding to the cell characteristic unrelated to the network configuration are firstly separated. Finally, the intra-RAT fluctuation component of the future throughput is predicted based on the separated feature component and the historical cell characteristic information related to the network configuration.

[0262] As an example, the second AI model described above with reference to FIGS. 15 and 16 may be utilized to predict the intra-RAT fluctuation component of the future throughput, and herein, the structure of the model is not repeated.

[0263]

[0264] The process of predicting the intra-RAT fluctuation component of the throughput using the second AI model is described below.

[0265] 1: the feature component corresponding to the cell characteristic related to the network configuration and the feature component corresponding to the cell characteristic unrelated to the network configuration are separated from the input features of the model.

[0266] For example, using the separation module in the second AI model, the feature component corresponding to the cell characteristic unrelated to the network configuration is separated based on the distribution under the cell characteristics with different network configurations, and the remaining feature components are considered to be possibly affected by the cell characteristic related to the network configuration. Here a Kolmogorov-Smirnov (KS) test is used to determine whether a feature component corresponds to the cell characteristic related to the network configuration:

[0267]

[0268]

[0269]

[0270]

[0271]

[0272]

[0273] 2: intra-RAT fluctuations of the future throughput are predicted.

[0274]

[0275]

[0276] The NNU-3 module in the second AI model predicts the throughput component corresponding to the cell characteristic unrelated to the network configuration based on the output of the combination module, i.e., the throughput component that is affected by the cell characteristic unrelated to the network configuration

[0277]

[0278]

[0279] Above, the method performed by the UE according to embodiments of the present disclosure has been further described in connection with examples, however, the method is not limited to the above examples.

[0280] FIG. 26 illustrates an exemplary deployment of a method according to embodiments of the present disclosure. As shown in FIG. 26, a wireless channel condition prediction module for performing the method according to embodiments of the present disclosure may be deployed, for example, in a communication processor of the UE. For example, the wireless channel condition prediction module may receive relevant information (such as the historical cell characteristic information related to the network configuration) required for performing prediction that is transmitted by a physical layer controller (PHY-C). In addition, the wireless channel condition prediction module collects historical wireless channel condition information from, for example, the physical layer (PHY), a media access control layer (MAC), a radio link control layer (RLC), and a packet data convergence protocol layer (PDCP), and utilizes the collected information to predict a future wireless channel condition based on AI models and other algorithms. In addition, as mentioned above, the RRM related feature may be predicted in predicting the inter-RAT change component of the wireless channel condition, and optionally, the predicted RRM related feature may be transmitted to the PHY for use in performing the prediction of the RRM related feature. In addition, information about the wireless channel condition predicted by the wireless channel condition prediction module may be transmitted to an application processor of the UE so as to facilitate the application processor to perform operations appropriate to the wireless channel condition based on the predicted wireless channel condition. The above description with reference to FIG. 26 is only an exemplary deployment of the method according to embodiments of the present disclosure, and the deployment is not limited to the example shown in FIG. 26.

[0281] FIG. 27 is a block diagram illustrating a user equipment according to embodiments of the present disclosure. Referring to FIG. 27, a user equipment 2700 may include a memory 2701 and a processor 2702, wherein the processor 2702 is coupled to the memory 2701 and configured to perform the method described above.

[0282] In embodiments of the present disclosure, there is also provided an electronic apparatus that includes at least one processor, and alternatively, further includes at least one transceiver and / or at least one memory coupled to the at least one processor, wherein the at least one processor is configured to perform the steps of the method provided in any alternative embodiment of the present disclosure.

[0283] FIG. 28 illustrates a schematic diagram of a structure of an electronic apparatus applicable to an exemplary embodiment of the present application. As shown in FIG. 28, the electronic apparatus 4000 shown in FIG. 28 includes: a processor 4001 and a memory 4003. Wherein the processor 4001 and the memory 4003 are coupled, e.g., through a bus 4002. Alternatively, the electronic apparatus 4000 may further include a transceiver 4004 which may be used for data interaction between the electronic apparatus and other electronic apparatuses, such as transmitting of data and / or receiving of data. It should be noted that, each of the processor 4001, the memory 4003, and the transceiver 4004 is not limited to one in a practice application, and the structure of the electronic apparatus 4000 does not constitute a limitation of the embodiments of the present disclosure. Alternatively, the electronic apparatus may be the first network node, the second network node, or the third network node.

[0284] The processor 4001 may be a Central Processing Unit (CPU), general purpose processor, Digital Signal Processor (DSP), Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA) or other programmable logic device, transistor logic device, hardware part, or any combination thereof. It may implement or perform various exemplary logic boxes, modules, and circuits described in conjunction with the disclosed contents of the present disclosure. The processor 4001 may also be a combination that implements computing functions, such as a combination containing one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0285] The bus 4002 may include a pathway to transfer information between the above components. The bus 4002 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, and the like. The bus 4002 may be classed as an address bus, a data bus, a control bus, and the like. For ease of representation, only one bold line is shown in FIG. 28, but it does not mean that there is only one bus or one type of bus.

[0286] The memory 4003 may be a Read Only Memory (ROM) or other types of static storage apparatuses that can store static information and instructions, a Random Access Memory (RAM) or other types of dynamic storage apparatuses that can store information and instructions, may be an Electrically Erasable Programmable Read Only Memory (EEPROM), Compact Disc Read Only Memory (CD-ROM) or other optical disc storages, an optical disc storage (including a compressed disc, laser disc, optical disc, digital universal disc, Blu-ray disc, etc.), a disk storage medium, other magnetic storage apparatuses, or any other medium that may be used to carry or store computer programs and may be read by a computer, it is not limited herein.

[0287] The memory 4003 is used to store computer programs or executable instructions for performing the embodiments of the present disclosure, and is controlled for execution by the processor 4001. The processor 4001 is used to execute the computer programs or executable instructions stored in the memory 4003 to implement the steps shown in the preceding method of the embodiments.

[0288] According to an embodiment, a method performed by a user equipment may comprise predicting a first wireless channel condition component related to a radio access technology (RAT) change and a second wireless channel condition component related to a cell characteristic, and obtaining a predicted wireless channel condition based on the first wireless channel condition component and the second wireless channel condition component.

[0289] For example, the predicting of the first wireless channel condition component may comprise predicting a RAT to be accessed by the user equipment, and predicting the first wireless channel condition component related to the RAT change based on the predicted RAT to be accessed by the user equipment and historical wireless channel condition information.

[0290] For example, the predicting of the RAT to be accessed by the user equipment may comprise predicting the RAT to be accessed by the user equipment based on a historical radio resource management (RRM) related feature in the historical wireless channel condition information. The predicting of the first wireless channel condition component related to the RAT change based on the predicted RAT to be accessed by the user equipment and the historical wireless channel condition information may comprise predicting the first wireless channel condition component related to the RAT change based on the predicted RAT to be accessed by the user equipment and a historical scheduling related feature in the historical wireless channel condition information.

[0291] For example, the scheduling related feature may comprise at least one of a parameter related to a scheduling algorithm and a parameter for evaluating scheduling performance. The parameter related to the scheduling algorithm may comprise at least one of throughput, a transmission block size, a number of resource blocks, a number of scheduling times, and a scheduling delay, and the parameter for evaluating the scheduling performance may comprise at least one of the throughput and a one-way delay.

[0292] For example, the predicting of the RAT to be accessed by the user equipment based on the historical RRM related feature in the historical wireless channel condition information may comprise predicting a RRM related feature difference between cells under different RATs based on the historical RRM related feature, wherein the RRM related feature difference indicates a RRM related feature difference between a serving cell under a first RAT and a neighbor cell under a second RAT, and predicting the RAT to be accessed by the user equipment based on the RRM related feature difference.

[0293] For example, the RRM related feature may comprise at least one of a reference signal received power (RSRP), a reference signal received quality (RSRQ), a signal-to-noise ratio (SNR), and a received signal strength indication (RSSI).

[0294] For example, the predicting of the RAT to be accessed by the user equipment based on the RRM related feature difference may comprise determining a relationship between the RRM related feature difference between cells under different RATs and a RAT change event based on historical data related to the RRM related feature difference between cells under different RATs, and predicting the RAT to be accessed by the user equipment by using the relationship based on the predicted RRM related feature difference.

[0295] For example, the predicting of the RAT to be accessed by the user equipment by using the relationship based on the predicted RRM related feature difference may comprise determining a difference interval to which the predicted RRM related feature difference belongs, calculating, based on the difference interval, a probability of a RAT change event occurring under the difference interval and a confidence interval corresponding to the probability using the relationship, and predicting, based on the confidence interval, the RAT to be accessed by the user equipment.

[0296] For example, the predicting of the first wireless channel condition component related to the RAT change based on the predicted RAT to be accessed by the user equipment and the historical scheduling related feature in the historical wireless channel condition information may comprise obtaining a first historical wireless channel condition component related to the RAT change based on the historical scheduling related feature in the historical wireless channel condition information, and predicting the first wireless channel condition component related to the RAT change based on the first historical wireless channel condition component and the predicted RAT to be accessed by the user equipment.

[0297] For example, the predicting the first wireless channel condition component related to the RAT change based on the first historical wireless channel condition component and the predicted RAT to be accessed by the user equipment may comprise performing a weighted summation of the first historical wireless channel condition component within a historically predetermined time, and predicting the first wireless channel condition component based on a result of the weighted summation and the predicted RAT to be accessed by the user equipment.

[0298] For example, the predicting of the second wireless channel condition component related to a cell characteristic may comprise predicting the second wireless channel condition component related to the cell characteristic based on historical wireless channel condition information and historical cell characteristic information related to a network configuration.

[0299] For example, the predicting of the second wireless channel condition component related to the cell characteristic based on the historical wireless channel condition information and the historical cell characteristic information related to the network configuration may comprise obtaining a second historical wireless channel condition component related to the cell characteristic based on a historical scheduling related feature in the historical wireless channel condition information, andpredicting the second wireless channel condition component based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration.

[0300] For example, the predicting of the second wireless channel condition component based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration may comprise predicting, based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration, a third wireless channel condition component corresponding to a cell characteristic related to the network configuration and a fourth wireless channel condition component corresponding to a cell characteristic unrelated to the network configuration, and predicting the second wireless channel condition component based on the predicted third wireless channel condition component and the fourth wireless channel condition component.

[0301] For example, the predicting of, based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration, the third wireless channel condition component corresponding to the cell characteristic related to the network configuration and the fourth wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration may comprise obtaining a first feature component corresponding to the cell characteristic related to the network configuration and a second feature component corresponding to the cell characteristic unrelated to the network configuration based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration, predicting the third wireless channel condition component based on the first feature component and the historical cell characteristic information related to the network configuration, and predicting the fourth wireless channel condition component based on the second feature component.

[0302] For example, the predicting of the second wireless channel condition component based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration may comprise obtaining a wireless channel condition change mode corresponding to a behavior of the user equipment, and predicting the second wireless channel condition component based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration.

[0303] For example, the predicting of the second wireless channel condition component based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration may comprise predicting a third wireless channel condition component corresponding to a cell characteristic related to the network configuration and a fourth wireless channel condition component corresponding to a cell characteristic unrelated to the network configuration based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration, and predicting the second wireless channel condition component based on the predicted third wireless channel condition component and the fourth wireless channel condition component.

[0304] For example, the predicting of the third wireless channel condition component corresponding to the cell characteristic related to the network configuration and the fourth wireless channel condition component corresponding to the cell characteristic unrelated to the network configuration based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration may comprise obtaining a first feature component corresponding to the cell characteristic related to the network configuration and a second feature component corresponding to the cell characteristic unrelated to the network configuration based on the wireless channel condition change mode, the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration, predicting the third wireless channel condition component based on the first feature component and the historical cell characteristic information related to the network configuration, and predicting the fourth wireless channel condition component based on the second feature component.

[0305] For example, the obtaining of the first feature component corresponding to the cell characteristic related to the network configuration and the second feature component corresponding to the cell characteristic unrelated to the network configuration based on the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration may comprise dividing the second historical wireless channel condition component into a third feature component possibly corresponding to a cell characteristic related to the network configuration and a fourth feature component corresponding to a cell characteristic unrelated to the network configuration, based on a correlation between the second historical wireless channel condition component and the historical cell characteristic information related to the network configuration, performing feature mapping on the fourth feature component, and obtaining the first feature component and the second feature component based on the mapped feature component.

[0306] For example, the obtaining of the first feature component and the second feature component based on the mapped feature component may comprise dividing the mapped feature component into the first feature component and a fifth feature component corresponding to the cell characteristic unrelated to the network configuration, and obtaining the second feature component based on the fourth feature component and the fifth feature component.

[0307] For example, the method may further comprise obtaining a log file related to communication of the user equipment, obtaining historical wireless channel condition raw information based on the log file, and performing data completion on a feature with a missing value in the historical wireless channel condition raw information to obtain the historical wireless channel condition information.

[0308] According to an embodiment, a user equipment may comprise a memory, a processor coupled to the memory and configured to perform any one of the above methods.

[0309] According to an embodiment, a computer-readable storage medium may store computer programs or instructions. The computer programs or the instructions, when executed by at least one processor, may cause the at least one processor to perform any one of the above methods.

[0310] According to an embodiment, a computer program product may comprise computer programs. The computer programs, when being executed by a processor, may implement any one of the above methods.

[0311] According to an embodiment, a method performed by a user equipment, may comprise identifying a RAT to be accessed by the user equipment, obtaining, based on the RAT to be accessed by the user equipment, a first wireless channel condition information related to a radio access technology (RAT) change, obtaining a second wireless channel condition information related to a cell characteristic, and obtaining a predicted wireless channel condition based on the first wireless channel condition information and the second wireless channel condition information.

[0312] For example, first wireless channel condition information may be obtained based on the RAT to be accessed by the user equipment and historical wireless channel condition information.

[0313] For example, the identifying of the RAT to be accessed by the user equipment may comprise identifying the RAT to be accessed by the user equipment based on a historical radio resource management (RRM) related feature in the historical wireless channel condition information. The obtaining of the first wireless channel condition information related to the RAT change based on the predicted RAT to be accessed by the user equipment and the historical wireless channel condition information may comprise obtaining the first wireless channel condition information related to the RAT change based on the RAT to be accessed by the user equipment and a historical scheduling related feature in the historical wireless channel condition information.

[0314] For example, the scheduling related feature may comprise at least one of a parameter related to a scheduling algorithm and a parameter for evaluating scheduling performance. The parameter related to the scheduling algorithm may comprise at least one of throughput, a transmission block size, a number of resource blocks, a number of scheduling times, and a scheduling delay, and the parameter for evaluating the scheduling performance may comprise at least one of the throughput and a one-way delay.

[0315] For example, the identifying of the RAT to be accessed by the user equipment based on the historical RRM related feature in the historical wireless channel condition information may comprise predicting a RRM related feature difference between cells under different RATs based on the historical RRM related feature, wherein the RRM related feature difference indicates a RRM related feature difference between a serving cell under a first RAT and a neighbor cell under a second RAT, and identifying the RAT to be accessed by the user equipment based on the RRM related feature difference.

[0316] For example, the RRM related feature may comprise at least one of a reference signal received power (RSRP), a reference signal received quality (RSRQ), a signal-to-noise ratio (SNR), and a received signal strength indication (RSSI).

[0317] For example, the identifying of the RAT to be accessed by the user equipment based on the RRM related feature difference may comprise determining a relationship between the RRM related feature difference between cells under different RATs and a RAT change event based on historical data related to the RRM related feature difference between cells under different RATs, and identifying the RAT to be accessed by the user equipment by using the relationship based on the predicted RRM related feature difference.

[0318] For example, the identifying of the RAT to be accessed by the user equipment by using the relationship based on the predicted RRM related feature difference may comprise determining a difference interval to which the predicted RRM related feature difference belongs, calculating, based on the difference interval, a probability of a RAT change event occurring under the difference interval and a confidence interval corresponding to the probability using the relationship, and identifying, based on the confidence interval, the RAT to be accessed by the user equipment.

[0319] For example, the obtaining of the first wireless channel condition information related to the RAT change based on the predicted RAT to be accessed by the user equipment and the historical scheduling related feature in the historical wireless channel condition information may comprise obtaining a first historical wireless channel condition information related to the RAT change based on the historical scheduling related feature in the historical wireless channel condition information, and obtaining the first wireless channel condition information related to the RAT change based on the first historical wireless channel condition information and the predicted RAT to be accessed by the user equipment.

[0320] For example, the obtaining the first wireless channel condition information related to the RAT change based on the first historical wireless channel condition information and the predicted RAT to be accessed by the user equipment may comprise performing a weighted summation of the first historical wireless channel condition information within a historically predetermined time, and obtaining the first wireless channel condition information based on a result of the weighted summation and the predicted RAT to be accessed by the user equipment.

[0321] For example, the obtaining of the second wireless channel condition information related to a cell characteristic may comprise obtaining the second wireless channel condition information related to the cell characteristic based on historical wireless channel condition information and historical cell characteristic information related to a network configuration.

[0322] For example, the obtaining of the second wireless channel condition information related to the cell characteristic based on the historical wireless channel condition information and the historical cell characteristic information related to the network configuration may comprise obtaining a second historical wireless channel condition information related to the cell characteristic based on a historical scheduling related feature in the historical wireless channel condition information, and obtaining the second wireless channel condition information based on the second historical wireless channel condition information and the historical cell characteristic information related to the network configuration.

[0323] For example, the obtaining of the second wireless channel condition information based on the second historical wireless channel condition information and the historical cell characteristic information related to the network configuration may comprise predicting, based on the second historical wireless channel condition information and the historical cell characteristic information related to the network configuration, a third wireless channel condition information corresponding to a cell characteristic related to the network configuration and a fourth wireless channel condition information corresponding to a cell characteristic unrelated to the network configuration, and obtaining the second wireless channel condition information based on the predicted third wireless channel condition information and the fourth wireless channel condition information.

[0324] According to an embodiment, a user equipment may comprise communication circuitry, memory comprising one or more storage media, storing instructions, and at least one processor comprising processing circuitry. The instructions, when executed by the at least one processor individually or collectively, may cause the user equipment to perform any one of the above methods.

[0325] According to an embodiment, a computer-readable storage medium may store one or more programs. The one or more programs may include instructions that, when executed by at least one processor of a user equipment, cause the user equipment to perform any one of the above methods.

[0326] According to an embodiment, a computer program product may comprise computer programs. The computer programs, when being executed by a processor, may implement any one of the above methods.

[0327] An embodiment of the present disclosure provides a computer readable storage medium storing computer programs or instructions, the computer programs or instructions, when being executed by at least one processor may perform or implement the steps in the preceding method of the embodiments and corresponding contents.

[0328] An embodiment of the present disclosure provides a computer program product including computer programs, the computer programs, when being executed by a processor, may implement the steps shown in the preceding method of the embodiments and corresponding contents.

[0329] The terms "first", "second", "third", "fourth", "1", "2" and the like (if exists) in the specification and claims of the present disclosure and the above drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequence. It should be understood that, data used as such may be interchanged in appropriate situations, so that the embodiments of the present disclosure described here may be implemented in an order other than the illustration or text description.

[0330] It should be understood that, although each operation step is indicated by an arrow in the flowcharts of the embodiments of the present disclosure, an implementation order of these steps is not limited to an order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of the embodiments of the present disclosure, the implementation steps in the flowcharts may be executed in other orders according to requirements. In addition, some or all of the steps in each flowchart may include a plurality of sub steps or stages, based on an actual implementation scenario. Some or all of these sub steps or stages may be executed at the same time, and each sub step or stage in these sub steps or stages may also be executed at different times. In scenarios with different execution times, an execution order of these sub steps or stages may be flexibly configured according to a requirement, which is not limited by the embodiment of the present disclosure.

[0331] The above text and accompanying drawings are provided as examples only to assist readers in understanding the present disclosure. They are not intended and should not be interpreted as limiting the scope of the present disclosure in any way. Although certain embodiments and examples have been provided, based on the content disclosed herein, it is apparent to those skilled in the art that, changes may be made to the illustrated embodiments and examples without departing from the scope of the present disclosure, and other similar implementation methods based on the technical concepts of the present disclosure also belongs to a protection scope of the embodiments of the present disclosure.

[0332] For one or more embodiments, at least one of the components set forth in one or more of the preceding figures may be configured to perform one or more operations, techniques, processes, and / or methods as set forth herein. For example, a processor (e.g., baseband processor) as described herein in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth herein. For another example, circuitry associated with a UE, base station, network element, etc. as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth herein.

[0333] Any of the above described embodiments may be combined with any other embodiment (or combination of embodiments), unless explicitly stated otherwise. The foregoing description of one or more implementations provides illustration and description, but is not intended to be exhaustive or to limit the scope of embodiments to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practice of various embodiments.

[0334] The methods according to various embodiments described in the claims and / or the specification of the disclosure may be implemented in hardware, software, or a combination of hardware and software.

[0335] When implemented by software, a computer-readable storage medium storing one or more programs (software modules) may be provided. One or more programs stored in such a computer-readable storage medium (e.g., non-transitory storage medium) are configured for execution by one or more processors in an electronic device. The one or more programs include instructions that cause the electronic device to execute the methods according to embodiments described in the claims or specification of the disclosure.

[0336] Such a program (e.g., software module, software) may be stored in a random-access memory, a non-volatile memory including a flash memory, a read only memory (ROM), an electrically erasable programmable read only memory (EEPROM), a magnetic disc storage device, a compact disc-ROM (CD-ROM), digital versatile discs (DVDs), other types of optical storage devices, or magnetic cassettes. Alternatively, it may be stored in a memory configured with a combination of some or all of the above. In addition, respective constituent memories may be provided in a multiple number.

[0337] Further, the program may be stored in an attachable storage device that can be accessed via a communication network, such as e.g., Internet, Intranet, local area network (LAN), wide area network (WAN), or storage area network (SAN), or a communication network configured with a combination thereof. Such a storage device may access an apparatus performing an embodiment of the disclosure through an external port. Further, a separate storage device on the communication network may be accessed to an apparatus performing an embodiment of the disclosure.

[0338] In the above-described specific embodiments of the disclosure, a component included therein may be expressed in a singular or plural form according to a proposed specific embodiment. However, such a singular or plural expression may be selected appropriately for the presented context for the convenience of description, and the disclosure is not limited to the singular form or the plural elements. Therefore, either an element expressed in the plural form may be formed of a singular element, or an element expressed in the singular form may be formed of plural elements.

[0339] Meanwhile, specific embodiments have been described in the detailed description of the disclosure, but it goes without saying that various modifications are possible without departing from the scope of the disclosure.

Claims

1.A method performed by a user equipment, comprising:identifying a RAT to be accessed by the user equipment;obtaining, based on the RAT to be accessed by the user equipment, a first wireless channel condition information related to a radio access technology (RAT) change;obtaining a second wireless channel condition information related to a cell characteristic; andobtaining a predicted wireless channel condition based on the first wireless channel condition information and the second wireless channel condition information.2.The method according to claim 1, wherein first wireless channel condition information is obtained based on the RAT to be accessed by the user equipment and historical wireless channel condition information.3.The method according to claim 2, wherein the identifying of the RAT to be accessed by the user equipment comprises: identifying the RAT to be accessed by the user equipment based on a historical radio resource management (RRM) related feature in the historical wireless channel condition information, andwherein the obtaining of the first wireless channel condition information related to the RAT change based on the predicted RAT to be accessed by the user equipment and the historical wireless channel condition information comprises: obtaining the first wireless channel condition information related to the RAT change based on the RAT to be accessed by the user equipment and a historical scheduling related feature in the historical wireless channel condition information.4.The method according to claim 3, wherein the scheduling related feature comprises at least one of a parameter related to a scheduling algorithm and a parameter for evaluating scheduling performance, andwherein the parameter related to the scheduling algorithm comprises at least one of throughput, a transmission block size, a number of resource blocks, a number of scheduling times, and a scheduling delay, and the parameter for evaluating the scheduling performance comprises at least one of the throughput and a one-way delay.5.The method according to claim 3, wherein the identifying of the RAT to be accessed by the user equipment based on the historical RRM related feature in the historical wireless channel condition information comprises:predicting a RRM related feature difference between cells under different RATs based on the historical RRM related feature, wherein the RRM related feature difference indicates a RRM related feature difference between a serving cell under a first RAT and a neighbor cell under a second RAT; andidentifying the RAT to be accessed by the user equipment based on the RRM related feature difference.6.The method according to claim 5, wherein the RRM related feature comprises at least one of a reference signal received power (RSRP), a reference signal received quality (RSRQ), a signal-to-noise ratio (SNR), and a received signal strength indication (RSSI).7.The method according to claim 5, wherein the identifying of the RAT to be accessed by the user equipment based on the RRM related feature difference comprises:determining a relationship between the RRM related feature difference between cells under different RATs and a RAT change event based on historical data related to the RRM related feature difference between cells under different RATs; andidentifying the RAT to be accessed by the user equipment by using the relationship based on the predicted RRM related feature difference.8.The method according to claim 7, wherein the identifying of the RAT to be accessed by the user equipment by using the relationship based on the predicted RRM related feature difference comprises:determining a difference interval to which the predicted RRM related feature difference belongs;calculating, based on the difference interval, a probability of a RAT change event occurring under the difference interval and a confidence interval corresponding to the probability using the relationship; andidentifying, based on the confidence interval, the RAT to be accessed by the user equipment.9.The method according to claim 3, wherein the obtaining of the first wireless channel condition information related to the RAT change based on the predicted RAT to be accessed by the user equipment and the historical scheduling related feature in the historical wireless channel condition information comprises:obtaining a first historical wireless channel condition information related to the RAT change based on the historical scheduling related feature in the historical wireless channel condition information; andobtaining the first wireless channel condition information related to the RAT change based on the first historical wireless channel condition information and the predicted RAT to be accessed by the user equipment.10.The method according to claim 9, wherein the obtaining the first wireless channel condition information related to the RAT change based on the first historical wireless channel condition information and the predicted RAT to be accessed by the user equipment comprises:performing a weighted summation of the first historical wireless channel condition information within a historically predetermined time; andobtaining the first wireless channel condition information based on a result of the weighted summation and the predicted RAT to be accessed by the user equipment.11.The method according to claim 1, wherein the obtaining of the second wireless channel condition information related to a cell characteristic comprises:obtaining the second wireless channel condition information related to the cell characteristic based on historical wireless channel condition information and historical cell characteristic information related to a network configuration.12.The method according to claim 11, wherein the obtaining of the second wireless channel condition information related to the cell characteristic based on the historical wireless channel condition information and the historical cell characteristic information related to the network configuration comprises:obtaining a second historical wireless channel condition information related to the cell characteristic based on a historical scheduling related feature in the historical wireless channel condition information; andobtaining the second wireless channel condition information based on the second historical wireless channel condition information and the historical cell characteristic information related to the network configuration.13.The method according to claim 12, wherein the obtaining of the second wireless channel condition information based on the second historical wireless channel condition information and the historical cell characteristic information related to the network configuration comprises:predicting, based on the second historical wireless channel condition information and the historical cell characteristic information related to the network configuration, a third wireless channel condition information corresponding to a cell characteristic related to the network configuration and a fourth wireless channel condition information corresponding to a cell characteristic unrelated to the network configuration; andobtaining the second wireless channel condition information based on the predicted third wireless channel condition information and the fourth wireless channel condition information.14.A user equipment comprising:communication circuitry;memory comprising one or more storage media, storing instructions; andat least one processor comprising processing circuitry,wherein the instructions, when executed by the at least one processor individually or collectively, cause the user equipment to perform the method of any of claims 1 to 13.15.A computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions that, when executed by at least one processor of a user equipment, cause the user equipment to perform the method of any of claims 1 to 13.

Images