Mechanism for testing model-based prediction accuracy

Abstract

Embodiments of the present disclosure relate to a test framework for evaluating CSI prediction accuracy for AI / ML-based CSI prediction cases without requiring DUTs to separately send truth values to test devices. In addition, embodiments of the present disclosure propose a step of independently obtaining a parameter value predicted by the DUT and a corresponding truth value at the TE side during a conformance test.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to and the benefit of Indian Provisional Application No. 202341064597, filed on September 26, 2023, the contents of which are incorporated herein by reference in their entirety. Technical Field

[0002] Embodiments of the present disclosure relate generally to the field of telecommunications, and more particularly to devices, methods, apparatuses, and computer-readable storage media for testing the accuracy of model-based predictions. Background Art

[0003] Several techniques have been proposed to improve communication performance. For example, communication devices can adopt artificial intelligence / machine learning (AI / ML) models to improve communication quality. AI / ML models can be applied to different scenarios to achieve better performance. For example, AI / ML can be used to predict channel state information (CSI). In addition, based on the collection of various measurements and feedback from UE and network nodes, historical data, etc., solutions based on AI / ML models and predicted CSI can improve system performance. Therefore, it is worth studying to determine the prediction accuracy of AI / ML models. Summary of the invention

[0004] Generally speaking, example embodiments of the present disclosure provide a solution for testing the accuracy of model-based predictions.

[0005] In a first aspect of the present disclosure, a first device is provided. The first device includes: at least one processor; and at least one memory, the memory storing instructions, which, when executed by the at least one processor, enable the first device to: receive multiple measurement values ​​of channel state information from a second device, wherein each measurement value of the measurement value corresponds to one channel parameter set in a plurality of channel parameter sets, and each channel parameter set corresponds to the condition of a channel between the first device and the second device; receive multiple prediction values ​​of the channel state information from the second device, wherein the multiple prediction values ​​are predicted by a model based on machine learning, wherein each prediction value of the prediction value corresponds to one channel parameter set in a plurality of channel parameter sets; and determine the prediction accuracy of the model based on machine learning by comparing the multiple measurement values ​​and the multiple prediction values ​​of the channel state information for each channel parameter set.

[0006] In a second aspect of the present disclosure, a second device is provided. The second device includes: at least one processor; and at least one memory, the memory storing instructions, which, when executed by the at least one processor, cause the second device to: transmit multiple measurement values ​​of channel state information to the first device, wherein each measurement value of the measurement value corresponds to one channel parameter set in multiple channel parameter sets, and each channel parameter set corresponds to the condition of the channel between the first device and the second device; and transmit multiple predicted values ​​of the channel state information to the first device, wherein the multiple predicted values ​​are predicted by a model based on machine learning, wherein each predicted value of the predicted value corresponds to one channel parameter set in multiple channel parameter sets.

[0007] In a third aspect of the present disclosure, a method is provided. The method includes: receiving multiple measurement values ​​of channel state information from a second device, wherein each measurement value of the measurement value corresponds to one channel parameter set in a plurality of channel parameter sets, and each channel parameter set corresponds to a condition of a channel between a first device and a second device; receiving multiple prediction values ​​of the channel state information from the second device, wherein the multiple prediction values ​​are predicted by a model based on machine learning, wherein each prediction value of the prediction value corresponds to one channel parameter set in a plurality of channel parameter sets; and determining the prediction accuracy of the model based on machine learning by comparing the multiple measurement values ​​and the multiple prediction values ​​of the channel state information for each channel parameter set.

[0008] In a fourth aspect of the present disclosure, a method is provided. The method includes: transmitting multiple measurement values ​​of channel state information to a first device, wherein each measurement value of the measurement value corresponds to one channel parameter set in multiple channel parameter sets, and each channel parameter set corresponds to a condition of a channel between the first device and the second device; and transmitting multiple prediction values ​​of the channel state information to the first device, wherein the multiple prediction values ​​are predicted by a model based on machine learning, wherein each prediction value of the prediction value corresponds to one channel parameter set in the multiple channel parameter sets.

[0009] In a fifth aspect of the present disclosure, a first device is provided. The first device includes: a component for receiving multiple measurement values ​​of channel state information from a second device, wherein each measurement value of the measurement value corresponds to one channel parameter set in a plurality of channel parameter sets, and each channel parameter set corresponds to the condition of a channel between the first device and the second device; a component for receiving multiple prediction values ​​of the channel state information from the second device, wherein the multiple prediction values ​​are predicted by a model based on machine learning, wherein each prediction value of the prediction value corresponds to one channel parameter set in a plurality of channel parameter sets; and a component for determining the prediction accuracy of the model based on machine learning by comparing the multiple measurement values ​​and the multiple prediction values ​​of the channel state information for each channel parameter set.

[0010] In a sixth aspect of the present disclosure, a second device is provided. The second device includes a component for transmitting a plurality of measurement values ​​of channel state information to a first device, wherein each measurement value of the measurement value corresponds to one channel parameter set in a plurality of channel parameter sets, and each channel parameter set corresponds to a condition of a channel between the first device and the second device; and a component for transmitting a plurality of prediction values ​​of the channel state information to the first device, wherein the plurality of prediction values ​​are predicted by a model based on machine learning, wherein each prediction value of the prediction value corresponds to one channel parameter set in the plurality of channel parameter sets.

[0011] In a seventh aspect of the present disclosure, a computer-readable medium is provided, wherein the computer-readable medium includes instructions stored thereon, and the instructions are used to cause a device to at least execute the method according to the third aspect.

[0012] In an eighth aspect of the present disclosure, a computer-readable medium is provided, wherein the computer-readable medium includes instructions stored thereon, and the instructions are used to cause a device to at least execute the method according to the fourth aspect.

[0013] Other features and advantages of the embodiments of the present disclosure will also be apparent from the following description of specific embodiments when read in conjunction with the accompanying drawings, which illustrate, by way of example, the principles of the embodiments of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] With reference to the accompanying drawings, exemplary embodiments of the present disclosure are presented by way of example and their advantages are explained in more detail below.

[0015] Figure 1 The concept of channel prediction is shown, where the radio channel is observed over a period of time and measured by a CSI reference signal (RS) and predicted into the future;

[0016] Figure 2 illustrates an example environment in which example embodiments of the present disclosure may be implemented;

[0017] Figure 3A illustrates a block diagram of a conducted mode conformance test;

[0018] Figure 3B A block diagram of an Over-the-Air (OTA) mode conformance test is illustrated;

[0019] Figure 4 shows a signaling diagram illustrating a process of testing model-based prediction accuracy according to some example embodiments of the present disclosure;

[0020] Figure 5 A flowchart illustrating an example method of testing the accuracy of model-based predictions according to some example embodiments of the present disclosure;

[0021] Figure 6 A flowchart illustrating an example method of testing the accuracy of model-based predictions according to some example embodiments of the present disclosure;

[0022] Figure 7 shows a simplified block diagram of a device suitable for implementing an example embodiment of the present disclosure; and

[0023] Figure 8 A block diagram of an example computer-readable medium is shown in accordance with some embodiments of the present disclosure.

[0024] The same or similar reference numbers may refer to the same or similar elements throughout the drawings. DETAILED DESCRIPTION

[0025] The principles of the present disclosure will now be described with reference to some example embodiments. It should be understood that these embodiments are described only for illustrative purposes and to help those skilled in the art understand and implement the present disclosure without implying any limitation on the scope of the present disclosure. The embodiments described herein can be implemented in various ways except for the ways described below.

[0026] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein may have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0027] In this disclosure, references to "one embodiment," "an embodiment," "an example embodiment," etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment necessarily includes the particular feature, structure, or characteristic. Moreover, such phrases do not necessarily refer to the same embodiment. Further, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is considered to be within the knowledge of those skilled in the art to affect such feature, structure, or characteristic in conjunction with other embodiments, whether or not explicitly described.

[0028] It should be understood that, although the terms "first", "second" etc. in front of nouns etc. can be used to describe various elements in this article, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element, and they do not limit the order of nouns. For example, without departing from the scope of the exemplary embodiment, the first element can be referred to as the second element, and similarly, the second element can be referred to as the first element. As used herein, the term "and / or" includes any and all combinations of one or more listed terms.

[0029] As used herein, “at least one of: ” and “at least one of ” and similar expressions (wherein a list of two or more elements is connected by “and” or “or”) refer to at least any one of the elements, or at least any two or more of the elements, or at least all of the elements.

[0030] As used herein, unless explicitly stated, performing a step “in response to A” does not mean performing the step immediately after “A” occurs, but may include one or more intermediate steps.

[0031] The terms used herein are only used for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that when used herein, the terms "include", "comprise", "have", "have", "include" and / or "include" specify the presence of features, elements and / or parts, etc., but do not exclude the presence or addition of one or more other features, elements, parts and / or combinations thereof.

[0032] As used in this application, the term "circuitry" may refer to one or more or all of the following: (a) hardware circuit implementation only (e.g., implementation only in analog and / or digital circuits), and (b) a combination of hardware circuitry and software such as (where applicable): (i) a combination of analog and / or digital hardware circuitry and software / firmware, and (ii) hardware processors (including digital signal processors) with software, Any portion of software and memory that work together to enable a device such as a mobile phone or server to perform various functions; and (c) A hardware circuit and / or processor that requires software (eg, firmware) for operation, such as a microprocessor or portion of a microprocessor, but the software may not be present when not required for operation.

[0033] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of only a hardware circuit or processor (or multiple processors) or a portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to a particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in a server, cellular network device, or other computing or network device.

[0034] As used herein, the term "communication network" refers to a network that complies with any suitable communication standard, for example, New Radio (NR), Long Term Evolution (LTE), Advanced LTE (LTE-A), Wideband Code Division Multiple Access (WCDMA), High Speed ​​Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), etc. In addition, the communication between the terminal device and the network device in the communication network can be performed according to any suitable generation communication protocol, including but not limited to the first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, fifth generation (5G), sixth generation (6G) communication protocol and / or any other protocol currently known or developed in the future. The embodiments of the present disclosure can be applied to various communication systems. In view of the rapid development of communication, there are of course future types of communication technologies and systems that can implement the present disclosure. It should not be considered that the scope of the present disclosure is limited to the above-mentioned system.

[0035] As used herein, the term "network device" refers to a node in a communication network via which a terminal device accesses the network and receives services from it. A network device may refer to a base station (BS) or an access point (AP), such as a Node B (NodeB or NB), an evolved Node B (eNodeB or eNB), a NR NB (also referred to as a gNB), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), a repeater, an integrated access and backhaul (IAB) node, a low-power node such as a femto, a micro), a non-terrestrial network (NTN) or a non-terrestrial network device (such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous orbit (GEO) satellite, an aircraft network device, etc.), depending on the terminology and technology applied. In some example embodiments, a radio access network (RAN) split architecture includes a centralized unit (CU) and a distributed unit (DU) at an IAB donor node. An IAB node includes a mobile terminal (IAB-MT) portion that behaves like a UE toward a parent node, and a DU portion of an IAB node behaves like a base station toward a next-hop IAB node.

[0036] The term "terminal device" refers to any terminal device capable of wireless communication. As an example and not limitation, the terminal device may also be referred to as a communication device, a user equipment (UE), a subscriber station (SS), a portable subscriber station, a mobile station (MS) or an access terminal (AT). The terminal device may include, but is not limited to, a mobile phone, a cellular phone, a smart phone, a voice over IP (VoIP) phone, a wireless local loop phone, a tablet computer, a wearable terminal device, a personal digital assistant (PDA), a portable computer, a desktop computer, an image capture terminal device such as a digital camera, a game terminal device, a music storage and playback facility, a vehicle-mounted wireless terminal device, a wireless endpoint, a mobile station, a laptop embedded device (LEE), a laptop mounted device (LME), a USB dongle, a smart device, a wireless user equipment (CPE), an Internet of Things (IoT) device, a watch or other wearable device, a head mounted display (HMD), a vehicle, a drone, medical equipment and applications (e.g., remote surgery), industrial equipment and applications (e.g., robots and / or other wireless devices operating in industrial and / or automatic processing chain environments), consumer electronic devices, equipment operating on commercial and / or industrial wireless networks, etc. The terminal device may also correspond to the mobile terminal (MT) part of an IAB node (eg, a relay node).In the following description, the terms "terminal device", "communication device", "terminal", "user equipment" and "UE" may be used interchangeably.

[0037] As used herein, the terms "resource", "transmission resource", "resource block", "physical resource block" (PRB), "uplink resource" or "downlink resource" may refer to any resource used to perform communication (e.g., communication between a terminal device and a network device), such as a resource in the time domain, a resource in the frequency domain, a resource in the spatial domain, a resource in the code domain, or any other combination of time domain, frequency domain, spatial domain and / or code domain resources to achieve communication. In the following, unless explicitly stated, resources in the frequency domain and the time domain will be used as examples of transmission resources for describing some example embodiments of the present disclosure. It should be noted that the example embodiments of the present disclosure are also applicable to other resources in other domains.

[0038] The term "AI / ML model" as used herein may refer to a data-driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. The term "AI / ML model" may be used interchangeably with the term "model". The term "channel state information (CSI)" as used herein may refer to the channel characteristics of a communication link. CSI describes how a signal propagates from a transmitter to a receiver and represents combined effects such as scattering, fading, and power attenuation with distance. The term "CSI report" may refer to a report indicating how good or bad a channel is. The terms "AI / ML features" or "AI / ML functions" as used herein may refer to features or functions implemented using an AI / ML model.

[0039] As mentioned above, AI / ML models can be applied to predict CSI. AI / ML enabled CSI feedback enhancement is one of the use cases selected for study. One of the selected sub-use cases for CSI feedback enhancement is CSI prediction. CSI prediction accuracy is one of the test metrics / key performance indicators (KPIs) selected for further study of the performance evaluation of inference.

[0040] Obtaining accurate CSI is challenging due to rapid channel variations and multipath fading. CSI inaccuracy has a serious impact on the performance of a wide range of adaptive wireless systems. Therefore, being able to optimize channel prediction of current CSI by predicting future CSI in advance can help improve the accuracy of CSI. AI / ML-based solutions can help predict the channel at future times.

[0041] Figure 1 The basic idea for channel prediction is illustrated, where the radio channel is measured at a few time instances, typically for frequency division duplex (FDD) systems based on periodically transmitted CSI reference signals (RS). The UE or gNB can then input the estimated CSI directly or after some pre-processing into a pre-trained ML model, which outputs predicted CSI for one or a few time steps.

[0042] Additionally, predicting the explicit radio channel evolution in the time and / or frequency domain as CSI would be useful, as this would enable any type of precoding, would support any type of multi-user multiple input multiple output (MU-MIMO) user grouping and scheduling, and would therefore be the basis for more advanced future concepts such as massive massive MIMO or cell-free massive MIMO. Alternatively, the CSI prediction could be close to the current Type IICSI reporting and prediction parameters such as precoding matrix indicator (PMI), rank indicator (RI), channel quality indicator (CQI), etc. Note that the possible reasoning and reporting options for channel prediction are closely related to the options for channel compression as discussed above.

[0043] Figure 2 An example communication environment 200 in which an example embodiment of the present disclosure may be implemented is illustrated. The communication environment 200 includes a first device 210, a second device 220, and a third device 230. The first device 210 may include a test device. As an example, the first device 210 may be a network device. The second device 220 may include a device under test (DUT). For example, the second device 220 may be a UE. The second device 220 may interact with the first device 210. For example, the second device 220 may interact directly with the first device 210. Alternatively or additionally, the second device 220 may interact with the first device 210 through the third device 230. In some other example embodiments, the second device 220 and the first device 210 may interact with each other directly and / or through the third device 230. The third device 230 may include a channel emulator used to simulate a communication condition. In some example embodiments, the third device 230 may be implemented using the first device 210.

[0044] In some example embodiments, if second device 220 is a terminal device and first device 210 is a network device, a link from first device 210 to second device 220 is referred to as a downlink (DL), and a link from second device 220 to first device 210 is referred to as an uplink (UL). In DL, first device 210 is a transmitting (TX) device (or transmitter), and second device 220 is a receiving (RX) device (or receiver). In UL, second device 220 is a TX device (or transmitter), and first device 210 is an RX device (or receiver).

[0045] Communications in the communication environment 200 may be implemented according to any appropriate communication protocol, including but not limited to cellular communication protocols of the first generation (1G), second generation (2G), third generation (3G), fourth generation (4G), fifth generation (5G), sixth generation (6G), etc., wireless local area network communication protocols such as Institute of Electrical and Electronics Engineers (IEEE) 802.11, and / or any other protocol currently known or developed in the future. In addition, communications may utilize any appropriate wireless communication technology, including but not limited to: code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), frequency division duplex (FDD), time division duplex (TDD), multiple input multiple output (MIMO), orthogonal frequency division multiple access (OFDM), discrete Fourier transform spread OFDM (DFT-s-OFDM) and / or any other technology currently known or developed in the future.

[0046] AI / ML model performance testing may be applied to the communication environment 200. Conformance testing may be performed in two modes: conducted mode and over-the-air (OTA) mode.

[0047] In conducted mode testing, each UE antenna port is connected to the test system via a 50 ohm coaxial cable. Conducted mode testing is only used for frequency range (FR1) test cases, and an example of such a test system is shown in Figure 3A , where for consistency testing purposes, a third device 230 (i.e., a channel emulator) is used to model a specific implementation of a wireless fading channel in a controlled manner. Thus, for consistency testing purposes, the crosstalk generated by the wireless channel for the UE deployed in the field is modeled in the channel emulator H L middle. For a conducted test system, the signal received at the DUT in the DL can be modeled as: y=H L x, (1) Where x represents the signal vector to be transmitted, H L represents the simulated channel matrix, and y represents the signal vector received at the UE / DUT.

[0048] In OTA mode testing, the UE / DUT is placed inside an anechoic (or test) chamber, and the test system is connected to one or more probes installed at different locations (fixed or mobile) inside this chamber. OTA mode testing is used in the 3GPP framework for both FR1 and FR2 test cases, and an example of such a test system is illustrated in Figure 3B , where the functions of the third device 230 and the first device 210 are the same as explained in the conducted mode test, and the test probe is installed inside a test room (e.g., an anechoic chamber) to transmit / receive signals to / from the DUT using an OTA wireless medium.

[0049] For the OTA test system, the signal received at the DUT in DL can be modeled as: y=H OTA H L x, (2) Where x represents the signal vector to be transmitted, H L represents the simulated channel matrix, H OTA Includes the OTA test room and UE (including spatial filter), and y represents the signal vector received at the UE / DUT.

[0050] As mentioned above, CSI prediction accuracy is one of the test metrics for the CSI prediction use case that is currently considered for inference performance validation. Therefore, it is important to find test steps to obtain CSI prediction accuracy. One of the main challenges in such validation is the extraction of the true value.

[0051] The CSI prediction accuracy for the AI / ML based CSI prediction use case can be potentially evaluated by comparing the predicted CSI values ​​with the actual measurements performed by the DUT which are considered as the true values. The DUT reports both (measured CSI report and predicted) CSI reports back to the test equipment, where the predicted values ​​are compared with the reported true values ​​to get the prediction accuracy. However, both functionalities (i.e., CSI measurement and prediction) can be active at the same time in this case, and this may not be supported by all devices.

[0052] Since two CSI reports (one corresponding to the true value and the other for prediction) need to be sent to the network / TE, more signaling support is required. The DUT vendor may be reluctant to share the true value related information with the test equipment. Before starting the actual consistency test of the AI / ML features, it is not clear how to obtain the training data set, which is based on the true value and is required to train the AI / ML model for future predictions. Therefore, a solution is needed regarding the prediction accuracy based on the test model.

[0053] According to an embodiment of the present disclosure, a test framework is provided to evaluate the CSI prediction accuracy for AI / ML-based CSI prediction use cases without requiring the DUT to send true values ​​to the test equipment separately. In addition, an embodiment of the present disclosure proposes a step of independently obtaining the parameter value predicted by the DUT and the corresponding true value on the TE side during the consistency test.

[0054] In some example embodiments, there may be 2 phases: Phase I (ground truth collection) and Phase II (evaluation by comparing predicted outputs to ground truth).

[0055] During phase I, the first device 210 may configure the second device 220 to use a non-AI / ML-based function, and configure the channel parameters at the third device 230 to simulate a given channel condition. The output of the second device 220 may be stored at the first device 210 as a true value to be used in the next phase. In particular, during phase I, the first device 210 may configure the test environment using at least the third device 230 and the test parameters for the second device 220. Additionally, other conditions such as the test probe position, the DUT (i.e., the second device 220) orientation may also be configured by the first device 210. The third device 230 may simulate the channel condition according to each configuration. Then, the first device 210 may configure the second device 220, and start the measurement using the non-AI / ML function, and send the configured CSI RS according to each channel configuration. The second device 220 may report the measurement output, which may be used as a true value by the first device 210. The true value may be stored at the first device 210, which may also be used as a source of a training set.

[0056] During Phase II, the first device 210 may configure the second device 220 to use an AI / ML-based function and configure the channel parameters as configured in Phase I to extract a true value. The output of the second device 220 may then be compared with the true value from Phase I to evaluate the prediction accuracy of the enabled AI / ML function. In particular, the first device 210 may configure the third device 230 to have similar channel parameters configured in Phase I, which ensures that the same channel conditions are available for the second device 220 as used for true value extraction. The first device 210 may configure the second device 220 to use an AI / ML-based function, for example, configuring the second device 220 to use an AI / ML-based CSI prediction. In this case, the second device 220 may use the AI / ML function and transmit a test output, such as a CSI report based on the AI / ML prediction, to the first device 210. At this point, the first device 210 may have obtained the collected true values ​​for a set of channel conditions, as well as the output of the prediction from the AI / ML-based function for the same set of channel conditions. Therefore, the first device 210 can evaluate the prediction accuracy by comparing the predicted output with the collected true values.

[0057] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Figure 4 , which illustrates a signaling flow 400 for testing the accuracy of model-based predictions according to some example embodiments of the present disclosure. For discussion purposes, reference will be made to Figure 2 The signaling flow 400 is discussed by using the first device 210 and the second device 220, for example.

[0058] First device 210 may transmit (4001) a first indication to second device 220, the first indication disabling the AI / ML feature at second device 220. In other words, second device 220 may receive the first indication from first device 210. In this way, it may be ensured that second device 220 does not operate in AI / ML mode. If AI / ML mode is currently active, first device 210 may instruct second device 220 to turn off use of its AI / ML feature. In some example embodiments, the first indication may be transmitted in a radio resource control (RRC) message.

[0059] The second device 220 may disable (4002) the AI / ML feature. For example, if the AI / ML feature is currently enabled, it is only required to disable the AI / ML feature. Upon receiving the first indication from the first device, the second device 220 may turn off its AI / ML feature.

[0060] After the second device 220 disables the model, the second device 220 may transmit (4003) an acknowledgement to the first device 210, which confirms that the second device 220 turns off its AI / ML feature. The acknowledgement may be indicated from the second device 220 to the first device 210 via, for example, an RRC message.

[0061] After the first device 210 obtains confirmation indicating that the model is turned off at the second device 220, the first device 210 may configure (4004) the second device 220 to measure CSI using a non-AI / ML based method. The first device 210 may also configure the second device 220 to send a measured CSI report to the first device 210. After receiving the configuration to measure and report CSI from the first device 210, the second device 220 may transmit (4005) a confirmation confirming receipt of the configuration for measuring and reporting CSI.

[0062] The first device 210 may determine (4006) the number of true CSI reports. For example, the first device 210 may determine N true CSI reports that are required to construct a training set for future reasoning purposes. As an example, the first device 210 may decide that the second device 220 will measure and send CSI for 1000 different combinations of channel realizations and / or environmental conditions.

[0063] The first device 210 may begin to build a truth table (or list) for future reasoning deductions (e.g., CSI accuracy prediction). For example, the first device 210 may configure multiple channel parameter sets. In this case, each channel parameter set may correspond to the condition of the channel between the first device and the second device. The second device 220 may transmit multiple measurements of channel state information. Each measurement of the measurement value may correspond to one of the multiple channel parameter sets. In some example embodiments, the channel parameter set may include one or more of the following: a channel implementation for the second device 220, an orientation of the second device 220, a location of a test probe for the second device 220, or a power level of the test probe. The measurement value of the channel state information may include one or more of the following: channel quality indicator (CQI), precoding matrix indicator (PMI), CSI-RS resource indicator (CRI), synchronization signal physical broadcast channel (SS / PBCH) block resource indicator (SSBRI), layer indicator (LI), rank indicator (RI), layer 1 reference signal received power (L1-RSRP), layer 1 signal to interference plus noise ratio (L1-SINR), or capability index.

[0064] As an example, to construct the truth table, the first device 210 may configure (4007-1) a first channel parameter set (also referred to as a "first feature set"). For example, the first device 210 may configure the first feature set, for example, by setting the third device 230 to produce a specific implementation of the channel, and / or by setting the second device 220 in a specific orientation during the test (for OTA testing only), and / or by selecting the location of the test probe and setting its power level (for OTA testing only) to set the test chamber configuration. In some example embodiments, the first device 210 may transmit the CSI RS set to the second device 220.

[0065] The second device 220 may measure (4007-1.A) the CSI corresponding to the first channel parameter set. For example, the second device 220 may measure the CQI corresponding to the first channel parameter set. The second device 220 may generate a first measured CSI report, the first measured CSI report including a first measured value of the CSI.

[0066] The second device 220 may transmit (4007-1.B) a first measured CSI report to the first device 210. In other words, the first device 210 may receive the first measured CSI report from the second device 220. The first device 210 may store (4007-1.C) the first channel parameter set and the first measured value of the CSI in a truth table or list. If N true CSI reports are needed, the operations of 4007-1, 4007-1.A, 4007-1.B, and 4007-1.C may be repeated N times.

[0067] like Figure 4 As shown, the first device 210 may configure (4007-N) an Nth channel parameter set (also referred to as an "Nth feature set"). The second device 220 may measure (4007-NA) the CSI corresponding to the Nth channel parameter set. For example, the second device 220 may measure the CQI corresponding to the Nth channel parameter set. The second device 220 may generate an Nth measured CSI report, the Nth measured CSI report including an Nth measured value of the CSI.

[0068] The second device 220 may transmit (4007-NB) the Nth measured CSI report to the first device 210. In other words, the first device 210 may receive the Nth measured CSI report from the second device 220. The first device 210 may store (4007-1.C) the Nth channel parameter set and the Nth measured value of the CSI in a truth table or list. Table 1 below shows an example of a truth table. Note that Table 1 is only an example and not a limitation. Table 1

[0069] For example, as shown in Table 1, the first channel parameter set (i.e., configuration #1) may include feature sets such as feature "channel implementation" for implementation 1, and feature "DUT orientation" for orientation 5. The first measurement value of the CSI corresponding to the first channel parameter set may be denoted as T1 in the above table.

[0070] The first device 210 may transmit (4008) a second indication to the second device 220, the second indication enabling the model at the second device 220. In other words, the second device 220 may receive the second indication from the first device 210. For example, after the truth table has been fully constructed, the first device 210 may instruct the second device 220 to turn on its AI / ML feature. The second indication may be indicated from the first device 210 to the second device 220 via, for example, an RRC message.

[0071] The second device 220 may enable (4009) the AI / ML feature. Upon receiving the second indication from the first device, the second device 220 may turn on its AI / ML feature.

[0072] After the second device 220 enables the AI / ML feature, the second device 220 can transmit (4010) a confirmation to the first device 210, which confirms that the second device 220 turns on its AI / ML feature. The confirmation can be indicated from the second device 220 to the first device 210 through, for example, an RRC message.

[0073] After the first device 210 obtains a confirmation indicating that the model is turned on at the second device 220, the first device 210 may configure (4011) the second device 220 to measure CSI using an AI / ML-based method. The first device 210 may also configure the second device 220 to send a predicted CSI report to the first device 210. After receiving a configuration from the first device 210 to predict CSI, the second device 220 may transmit (4012) a confirmation confirming receipt of the configuration for predicting CSI.

[0074] The first device 210 may start building a prediction table (list) for future reasoning derivation (e.g., CSI accuracy prediction). As an example, the first device 210 may configure multiple channel parameter sets in a random manner, for example. The second device 220 may transmit multiple predicted values ​​of channel state information. Each predicted value of the predicted value may correspond to one channel parameter set in the multiple channel parameter sets.

[0075] As an example, to construct the prediction table, the first device 210 may configure (4013-1) any one channel parameter set (any one feature set) from the plurality of channel parameter sets defined during truth acquisition. As an example only, the Nth channel parameter set for the truth table may be used as the first channel parameter set for the prediction table.

[0076] The second device 220 may predict (4013-1.A) the CSI corresponding to the Nth channel parameter set. For example, the second device 220 may predict the CQI corresponding to the Nth channel parameter set. The second device 220 may generate a first predicted CSI report including a first predicted value of the CSI corresponding to the Nth channel parameter set.

[0077] The second device 220 may transmit (4013-1.B) a first predicted CSI report to the first device 210. In other words, the first device 210 may receive the first predicted CSI report from the second device 220. The first device 210 may store (4013-1.C) the Nth channel parameter set and the first predicted value of the CSI in a prediction table or list. If N true value CSI reports are needed, the operations of 4013-1, 4013-1.A, 4013-1.B, and 4013-1.C may be repeated N times.

[0078] like Figure 4As shown, the first device 210 may configure (4013-N) a first channel parameter set (also referred to as a "first feature set"). The second device 220 may predict (4013-NA) a CSI corresponding to the first channel parameter set. For example, the second device 220 may predict a CQI corresponding to the first channel parameter set. The second device 220 may generate an Nth predicted CSI report, the Nth predicted CSI report including an Nth predicted value of the CSI corresponding to the first channel parameter set.

[0079] The second device 220 may transmit (4013-NB) the Nth predicted CSI report to the first device 210. In other words, the first device 210 may receive the Nth predicted CSI report from the second device 220. The first device 210 may store (4013-1.C) the first channel parameter set and the Nth predicted value of the CSI in a prediction table or list. Table 2 below shows an example of a prediction table. Note that Table 2 is only an example and not a limitation. Table 2

[0080] For example, as shown in Table 2, the Nth channel parameter set (i.e., configuration #N) may include feature sets such as feature "channel implementation" for implementation "R" and feature "DUT orientation" for orientation "O". The corresponding predicted value of CSI may be represented as P_N in the above table.

[0081] The first device 210 determines (4014) the prediction accuracy of the model by comparing multiple measurements and multiple predictions of the channel state information. For example, the first device 210 can compare the truth table and the prediction table, and evaluate the prediction accuracy to determine the test conclusion. For example, for the CSI prediction use case, the first device 210 can verify whether the cosine similarity between the multiple measurements and the multiple predictions is within certain limits. Alternatively, the first device 210 can also use some other metrics, for example, verifying whether the absolute / average / maximum difference between P_i and T_i in each pair (P1, T1)...(P_N, T_N) is less than some threshold "X".

[0082] In some example embodiments, if the prediction accuracy of the determined model is greater than or equal to the accuracy threshold, the model can still be used for a period of time. Alternatively, if the prediction accuracy of the determined model is less than or equal to the accuracy threshold, the model may need to be updated.

[0083] According to an embodiment of the present disclosure, a step of obtaining true values ​​and predicted values ​​on non-overlapping time scales is proposed. In this way, it is possible to avoid the device reporting false predictions because the true value is not available at the device at the prediction time. In addition, it may or may not require new signaling support.

[0084] Figure 5 FIG. 5 is a flowchart of an example method 500 implemented at a first device according to some example embodiments of the present disclosure. For discussion purposes, Figure 2 The method 500 is described from the perspective of the first device 210 in FIG.

[0085] At block 510, a first device receives a plurality of measurements of channel state information from a second device. Each of the measurements corresponds to one of a plurality of channel parameter sets. Each channel parameter set corresponds to a condition of a channel between the first device and the second device.

[0086] At block 520, the first device receives a plurality of predicted values ​​of channel state information from the second device, the plurality of predicted values ​​being predicted by a model based on machine learning, wherein each predicted value corresponds to one of a plurality of channel parameter sets.

[0087] At block 530 , the first device determines a prediction accuracy of the machine learning based model by comparing a plurality of measured values ​​and a plurality of predicted values ​​of the channel state information for each channel parameter set.

[0088] In some example embodiments, each channel parameter set includes at least one of: a specific implementation of a channel between the first device and the second device, an explicit orientation of the second device, an explicit position of at least one test probe, or an explicit power level of at least one test probe or test device.

[0089] In some example embodiments, method 500 further includes: determining a number of true channel state information reports, wherein the true channel state information is obtained by actual channel state information measurements; and determining a plurality of channel parameter sets, wherein the number of sets in the plurality of channel parameter sets corresponds to the number of true channel state information reports.

[0090] In some example embodiments, the method 500 further comprises, prior to the receipt of the plurality of measurements, transmitting a first indication to the second device to disable prediction based on the machine learning model.

[0091] In some example embodiments, method 500 further includes: performing the following operations for multiple rounds until the number of rounds is equal to the number of true channel state information reports: configuring a channel parameter set from multiple channel parameter sets; receiving a measurement value of the channel state information corresponding to the channel parameter set from a second device; and storing the channel parameter set and the measurement value in a truth table.

[0092] In some example embodiments, method 500 further includes, prior to receipt of the plurality of predicted values, transmitting to a second device a second indication to enable prediction based on the machine learning model.

[0093] In some example embodiments, method 500 further includes: performing the following operations for multiple rounds until the number of rounds is equal to the number of true channel state information reports: configuring a channel parameter set from multiple channel parameter sets; receiving a predicted value of channel state information corresponding to the channel parameter set from a second device; and storing the channel parameter set and the predicted value in a prediction table.

[0094] In some example embodiments, method 500 further comprises determining a prediction accuracy of the machine learning model based on a plurality of comparisons, wherein each comparison is between measured values ​​and predicted values ​​corresponding to the same set of channel parameters.

[0095] In some example embodiments, each measured value of the channel state information includes at least one of: a measured channel quality indicator (CQI), a measured precoding matrix indicator (PMI), a measured channel state information reference signal (CSI-RS) resource indicator (CRI), a measured synchronization signal / physical broadcast channel (SS / PBCH) block resource indicator (SSBRI), a measured layer indicator (LI), a measured rank indicator (RI), a measured layer 1 reference signal received power (L1-RSRP), a measured layer 1 signal to interference plus noise ratio (L1-SINR), or a measured capability index.

[0096] In some example embodiments, each predicted value of the channel state information includes at least one of: a predicted channel quality indicator (CQI), a predicted precoding matrix indicator (PMI), a predicted channel state information reference signal (CSI-RS) resource indicator (CRI), a predicted synchronization signal / physical broadcast channel (SS / PBCH) block resource indicator (SSBRI), a predicted layer indicator (LI), a predicted rank indicator (RI), a predicted layer 1 reference signal received power (L1-RSRP), a predicted layer 1 signal to interference plus noise ratio (L1-SINR), or a predicted capability index.

[0097] In some example embodiments, the first device is one of: a test device, a system simulator, or a network device, and the second device is a device under test.

[0098] Figure 6 FIG. 6 is a flowchart of an example method 600 implemented at a second device according to some example embodiments of the present disclosure. For discussion purposes, Figure 2 The method 600 is described from the perspective of the second device 220 in FIG.

[0099] At box 610, the second device transmits multiple measurements of channel state information to the first device, where each measurement corresponds to one of a plurality of channel parameter sets, and each channel parameter set corresponds to a condition of a channel between the first device and the second device.

[0100] At box 620, the second device transmits a plurality of predicted values ​​of channel state information to the first device, the plurality of predicted values ​​being predicted by a machine learning-based model, wherein each predicted value of the predicted value corresponds to a channel parameter set of a plurality of channel parameter sets.

[0101] In some example embodiments, each channel parameter set includes at least one of: a specific implementation of a channel between the first device and the second device, an explicit orientation of the second device, an explicit position of at least one test probe, or an explicit power level of at least one test probe or test device.

[0102] In some example embodiments, the method 600 further includes, prior to the receipt of the plurality of measurements, receiving a first indication from the first device to disable prediction based on the machine learning model.

[0103] In some example embodiments, method 600 further includes performing the following operations for multiple rounds until the number of rounds equals a predetermined number: measuring a value of channel state information corresponding to a channel parameter set from a plurality of channel parameter sets; and transmitting the measured value of the channel state information to the first device.

[0104] In some example embodiments, the method 600 further includes, prior to the receipt of the plurality of predicted values, receiving a second indication from the first device to enable prediction based on the machine learning model.

[0105] In some example embodiments, method 600 further includes: performing the following operations for multiple rounds until the number of rounds equals a predetermined number: predicting, through a machine learning model, a value of channel state information corresponding to a channel parameter set from a plurality of channel parameter sets; and transmitting the predicted value of the channel state information to the first device.

[0106] In some example embodiments, each measured value of the channel state information includes at least one of: a measured channel quality indicator (CQI), a measured precoding matrix indicator (PMI), a measured channel state information reference signal (CSI-RS) resource indicator (CRI), a measured synchronization signal / physical broadcast channel (SS / PBCH) block resource indicator (SSBRI), a measured layer indicator (LI), a measured rank indicator (RI), a measured layer 1 reference signal received power (L1-RSRP), a measured layer 1 signal to interference plus noise ratio (L1-SINR), or a measured capability index.

[0107] In some example embodiments, each predicted value of the channel state information includes at least one of: a predicted channel quality indicator (CQI), a predicted precoding matrix indicator (PMI), a predicted channel state information reference signal (CSI-RS) resource indicator (CRI), a predicted synchronization signal / physical broadcast channel (SS / PBCH) block resource indicator (SSBRI), a predicted layer indicator (LI), a predicted rank indicator (RI), a predicted layer 1 reference signal received power (L1-RSRP), a predicted layer 1 signal to interference plus noise ratio (L1-SINR), or a predicted capacity index.

[0108] In some example embodiments, the first device is one of: a test device, a system simulator, or a network device, and the second device is a device under test.

[0109] In some example embodiments, any of the methods in method 500 (e.g., Figure 2 The first device of the first device 210 in the embodiment of the present invention may include components for performing the corresponding operations of the method 500. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module. The first device may be implemented as or included in Figure 2 In the first device 210.

[0110] In some example embodiments, the first device includes: a component for receiving a plurality of measurement values ​​of channel state information from a second device, wherein each measurement value corresponds to one channel parameter set in a plurality of channel parameter sets, and each channel parameter set corresponds to a condition of a channel between the first device and the second device; a component for receiving a plurality of prediction values ​​of the channel state information from the second device, the plurality of prediction values ​​being predicted by a model based on machine learning, wherein each prediction value of the prediction value corresponds to one channel parameter set in the plurality of channel parameter sets; and a component for determining a prediction accuracy of the model based on machine learning by comparing the plurality of measurement values ​​and the plurality of prediction values ​​of the channel state information for each channel parameter set.

[0111] In some example embodiments, each channel parameter set includes at least one of: a specific implementation of a channel between the first device and the second device, an explicit orientation of the second device, an explicit position of at least one test probe, or an explicit power level of at least one test probe or test device.

[0112] In some example embodiments, the first device also includes: a component for determining a number of true channel state information reports, wherein the true channel state information is obtained through actual channel state information measurements; and a component for determining multiple channel parameter sets, wherein the number of sets in the multiple channel parameter sets corresponds to the number of true channel state information reports.

[0113] In some example embodiments, the first apparatus further comprises means for transmitting a first indication to the second device to disable prediction based on the machine learning model prior to receipt of the plurality of measurements.

[0114] In some example embodiments, the first apparatus further comprises: a component for performing the following operations for multiple rounds until the number of rounds equals the number of true channel state information reports: configuring a channel parameter set from a plurality of channel parameter sets; receiving a measurement value of the channel state information corresponding to the channel parameter set from a second device; and storing the channel parameter set and the measurement value in a truth table.

[0115] In some example embodiments, the first apparatus further comprises means for transmitting a second indication to the second device to enable prediction based on the machine learning model prior to receipt of the plurality of predicted values.

[0116] In some example embodiments, the first apparatus further comprises: a component for performing the following operations for multiple rounds until the number of rounds equals the number of true channel state information reports: configuring a channel parameter set from a plurality of channel parameter sets; receiving a predicted value of channel state information corresponding to the channel parameter set from a second device; and storing the channel parameter set and the predicted value in a prediction table.

[0117] In some example embodiments, the first apparatus further comprises means for determining a prediction accuracy of the machine learning model based on a plurality of comparisons, wherein each comparison is between a measured value and a predicted value corresponding to the same set of channel parameters.

[0118] In some example embodiments, each measured value of the channel state information includes at least one of: a measured channel quality indicator (CQI), a measured precoding matrix indicator (PMI), a measured channel state information reference signal (CSI-RS) resource indicator (CRI), a measured synchronization signal / physical broadcast channel (SS / PBCH) block resource indicator (SSBRI), a measured layer indicator (LI), a measured rank indicator (RI), a measured layer 1 reference signal received power (L1-RSRP), a measured layer 1 signal to interference plus noise ratio (L1-SINR), or a measured capability index.

[0119] In some example embodiments, each predicted value of the channel state information includes at least one of: a predicted channel quality indicator (CQI), a predicted precoding matrix indicator (PMI), a predicted channel state information reference signal (CSI-RS) resource indicator (CRI), a predicted synchronization signal / physical broadcast channel (SS / PBCH) block resource indicator (SSBRI), a predicted layer indicator (LI), a predicted rank indicator (RI), a predicted layer 1 reference signal received power (L1-RSRP), a predicted layer 1 signal to interference plus noise ratio (L1-SINR), or a predicted capacity index.

[0120] In some example embodiments, the first device is one of: a test device, a system simulator, or a network device, and the second device is a device under test.

[0121] In some example embodiments, the first apparatus further comprises means for performing other operations in some example embodiments of the method 500 or the first device 210. In some example embodiments, these means comprise at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause the performance of the first apparatus.

[0122] In some example embodiments, any of the methods in method 600 (e.g., Figure 2 The second device of the second device 220 in the embodiment may include components for performing the corresponding operations of method 600. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module. The second device may be implemented as or included in Figure 2 In the second device 220.

[0123] In some example embodiments, the second device includes a component for transmitting a plurality of measurement values ​​of channel state information to the first device, wherein each measurement value of the measurement value corresponds to one channel parameter set of a plurality of channel parameter sets, and each channel parameter set corresponds to a condition of a channel between the first device and the second device; and a component for transmitting a plurality of prediction values ​​of the channel state information to the first device, the plurality of prediction values ​​being predicted by a model based on machine learning, wherein each prediction value of the prediction value corresponds to one channel parameter set of the plurality of channel parameter sets.

[0124] In some example embodiments, each channel parameter set includes at least one of: a specific implementation of a channel between the first device and the second device, an explicit orientation of the second device, an explicit position of at least one test probe, or an explicit power level of at least one test probe or test device.

[0125] In some example embodiments, the second apparatus further comprises means for receiving a first indication from the first device to disable prediction based on the machine learning model prior to receipt of the plurality of measurements.

[0126] In some example embodiments, the second apparatus further comprises: a component for performing the following operations for multiple rounds until the number of rounds equals a predetermined number: measuring a value of channel state information corresponding to a channel parameter set from a plurality of channel parameter sets; and transmitting the measured value of the channel state information to the first device.

[0127] In some example embodiments, the second apparatus further comprises means for receiving a second indication from the first device to enable prediction based on the machine learning model prior to receipt of the plurality of predicted values.

[0128] In some example embodiments, the second apparatus further comprises: a component for performing the following operations for multiple rounds until the number of rounds equals a predetermined number: predicting, through a machine learning model, a value of channel state information corresponding to a channel parameter set from a plurality of channel parameter sets; and transmitting the predicted value of the channel state information to the first device.

[0129] In some example embodiments, each measured value of the channel state information includes at least one of: a measured channel quality indicator (CQI), a measured precoding matrix indicator (PMI), a measured channel state information reference signal (CSI-RS) resource indicator (CRI), a measured synchronization signal / physical broadcast channel (SS / PBCH) block resource indicator (SSBRI), a measured layer indicator (LI), a measured rank indicator (RI), a measured layer 1 reference signal received power (L1-RSRP), a measured layer 1 signal to interference plus noise ratio (L1-SINR), or a measured capability index.

[0130] In some example embodiments, each predicted value of the channel state information includes at least one of: a predicted channel quality indicator (CQI), a predicted precoding matrix indicator (PMI), a predicted channel state information reference signal (CSI-RS) resource indicator (CRI), a predicted synchronization signal / physical broadcast channel (SS / PBCH) block resource indicator (SSBRI), a predicted layer indicator (LI), a predicted rank indicator (RI), a predicted layer 1 reference signal received power (L1-RSRP), a predicted layer 1 signal to interference plus noise ratio (L1-SINR), or a predicted capability index.

[0131] In some example embodiments, the first device is one of: a test device, a system simulator, or a network device, and the second device is a device under test.

[0132] In some example embodiments, the second apparatus further comprises means for performing other operations in some example embodiments of the method 600 or the second device 220. In some example embodiments, these means comprise at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause performance of the second apparatus.

[0133] Figure 7 700 is a simplified block diagram of a device 700 suitable for implementing an example embodiment of the present disclosure. The device 700 may be provided to implement a communication device, such as Figure 2 The first device 210 or the second device 220 is shown. As shown, the device 700 includes one or more processors 710, one or more memories 720 coupled to the processor 710, and one or more communication modules 740 coupled to the processor 710.

[0134] The communication module 740 is used for two-way communication. The communication module 740 has one or more communication interfaces to support communication with one or more other modules or devices. The communication interface may represent any interface necessary for communication with other network elements. In some example embodiments, the communication module 740 may include at least one antenna.

[0135] As non-limiting examples, processor 710 may be of any type suitable for a local technology network, and may include one or more of the following: a general purpose computer, a special purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture. Device 700 may have multiple processors, such as application specific integrated circuit chips that are time slaved to a clock of a synchronized main processor.

[0136] The memory 720 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 724, electrically programmable read-only memory (EPROM), flash memory, hard disk, compact disk (CD), digital video disk (DVD), optical disk, laser disk, and other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, random access memory (RAM) 722 and other volatile memories that will not persist over the duration of a power outage.

[0137] The computer program 730 includes computer executable instructions executed by the associated processor 710. The instructions of the program 730 may include instructions for performing the operations / actions of some example embodiments of the present disclosure. The program 730 may be stored in a memory (e.g., ROM 724). The processor 710 may perform any suitable actions and processes by loading the program 730 into the RAM 722.

[0138] The exemplary embodiments of the present disclosure may be implemented by a program 730 so that the device 700 may execute the Figures 2 to 6 Any process of the present disclosure discussed. The exemplary embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0139] In some example embodiments, the program 730 may be tangibly embodied in a computer-readable medium that may be included in the device 700 (such as in the memory 720) or in other storage devices accessible to the device 700. The device 700 may load the program 730 from the computer-readable medium to the RAM 722 for execution. In some example embodiments, the computer-readable medium may include any type of non-transitory storage medium, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. The term "non-transitory" as used herein is a limitation on the medium itself (i.e., tangible rather than a signal), not a limitation on the persistence of data storage (e.g., RAM versus ROM).

[0140] Figure 8 An example of a computer readable medium 800 is shown, which may be in the form of a CD, DVD or other optical storage disk. The computer readable medium 800 has a program 730 stored thereon.

[0141] Generally, various embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are illustrated and described as block diagrams, flow charts, or using some other graphical representations, it should be understood that, as non-limiting examples, the boxes, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general hardware or controllers or other computing devices, or some combination thereof.

[0142] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer-readable medium (such as, a non-transient computer-readable medium). The computer program product includes computer executable instructions, such as those computer executable instructions executed in a device on a target physical or virtual processor included in a program module to perform any method as described above. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The functionality of the program modules can be combined or split between program modules as needed in various embodiments. The machine executable instructions for the program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0143] The program code for executing the method of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, as an independent software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0144] In the context of the present disclosure, computer program codes or related data may be carried by any suitable carrier to enable a device, apparatus or processor to perform various processes and operations as described above. Examples of carriers include signals, computer readable media, etc.

[0145] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or apparatuses, or any suitable combination of the foregoing. More specific examples of computer readable storage media would include an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0146] In addition, although the operations are depicted in a specific order, this should not be understood as requiring the specific order shown or in a sequential order to perform these operations, or to perform all described operations, to achieve the desired result. In some cases, multitasking and parallel processing can be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be interpreted as limitations on the scope of the present disclosure, but should be interpreted as descriptions of features that may be specific to a specific embodiment. Unless explicitly stated, certain features described in the context of a separate embodiment may also be implemented in combination in a single embodiment. On the contrary, unless explicitly stated, the various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0147] Although the disclosure has been described in language specific to structural features and / or methodological acts, it should be understood that the disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Instead, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A first device for communication, comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the first device to: receiving a plurality of measurements of channel state information from a second device, wherein each of the measurements corresponds to one of a plurality of channel parameter sets, and each channel parameter set corresponds to a condition of a channel between the first device and the second device; receiving, from the second device, a plurality of predicted values ​​of the channel state information, the plurality of predicted values ​​being predicted by a model based on machine learning, wherein each predicted value of the predicted values ​​corresponds to one of the plurality of channel parameter sets; as well as The prediction accuracy of the machine learning based model is determined by comparing the multiple measured values ​​and the multiple predicted values ​​of the channel state information for each channel parameter set.

2. The first device according to claim 1, wherein each channel parameter set comprises at least one of the following: a specific implementation of a channel between the first device and the second device, an explicit orientation of the second device, an explicit location for at least one test probe, or An explicit power level of the at least one test probe or the test equipment.

3. The first device according to claim 1, wherein the first device: determining a number of true channel state information reports, wherein the true channel state information is obtained through actual channel state information measurements; and The plurality of channel parameter sets are determined, wherein a number of sets in the plurality of channel parameter sets corresponds to a number of the true channel state information reports.

4. The first device according to claim 1, wherein the first device: Prior to said receiving of said plurality of measurements, transmitting to said second device a first indication to disable prediction based on a machine learning model.

5. The first device according to claim 1, wherein the first device: Perform the following operations for a plurality of rounds until the number of the rounds is equal to the number of true value channel state information reports: configuring a channel parameter set from the plurality of channel parameter sets; receiving, from the second device, a measurement value of channel state information corresponding to the channel parameter set; as well as The channel parameter set and the measured values ​​are stored in a truth table.

6. The first device according to claim 1, wherein the first device: Prior to said receiving of said plurality of predicted values, transmitting to said second device a second indication to enable prediction based on a machine learning model.

7. The first device according to claim 1, wherein the first device: Perform the following operations for a plurality of rounds until the number of the rounds is equal to the number of true value channel state information reports: configuring a channel parameter set from the plurality of channel parameter sets; receiving, from the second device, a predicted value of channel state information corresponding to the channel parameter set; as well as The channel parameter set and the predicted value are stored in a prediction table.

8. The first device according to claim 7, wherein the first device is: The prediction accuracy of the machine learning model is determined based on multiple comparisons, where each comparison is between the measured values ​​and the predicted values ​​corresponding to the same set of channel parameters.

9. The first device according to claim 1, wherein each measured value of the channel state information and / or each predicted value of the channel state information comprises at least one of the following: a measured channel quality indicator, The measured precoding matrix indicator, a measured channel state information reference signal resource indicator, a measured synchronization signal / physical broadcast channel block resource indicator, Measured layer indicators, The measured rank indicator, The measured layer 1 reference signal received power, The measured layer 1 signal to interference plus noise ratio, or Measured capability index.

10. A second device for communication, comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the second device to: transmitting a plurality of measurements of channel state information to a first device, wherein each measurement of the measurements corresponds to one channel parameter set of a plurality of channel parameter sets, and each channel parameter set corresponds to a condition of a channel between the first device and the second device; as well as Transmitting multiple predicted values ​​of the channel state information to the first device, the multiple predicted values ​​are predicted by a model based on machine learning, wherein each predicted value of the predicted value corresponds to a channel parameter set in the multiple channel parameter sets.

11. The second device according to claim 10, wherein each channel parameter set comprises at least one of the following: a specific implementation of a channel between the first device and the second device, an explicit orientation of the second device, an explicit location for at least one test probe, or An explicit power level of the at least one test probe or the test equipment.

12. The second device according to claim 10, wherein the second device: Prior to said receiving of said plurality of measurements, receiving a first indication from said first device to disable prediction based on a machine learning model.

13. The second device according to claim 10, wherein the second device: Perform the following operations for a plurality of rounds until the number of the rounds equals a predetermined number: measuring a value of channel state information corresponding to a channel parameter set from the plurality of channel parameter sets; and The measured value of the channel state information is transmitted to the first device.

14. The second device according to claim 10, wherein the second device: Prior to said receiving of said plurality of predicted values, receiving a second indication from said first device to enable prediction based on a machine learning model.

15. The second device according to claim 10, wherein the second device: Perform the following operations for a plurality of rounds until the number of the rounds equals a predetermined number: predicting, by the machine learning model, a value of channel state information corresponding to a channel parameter set from the plurality of channel parameter sets; and Transmitting the predicted value of the channel state information to the first device.

16. The second device according to claim 10, wherein each measured value of the channel state information and / or each predicted value of the channel state information comprises at least one of the following: a measured channel quality indicator, The measured precoding matrix indicator, a measured channel state information reference signal resource indicator, a measured synchronization signal / physical broadcast channel block resource indicator, Measured layer indicators, The measured rank indicator, The measured layer 1 reference signal received power, The measured layer 1 signal to interference plus noise ratio, or Measured capability index.

17. A method for communication, comprising: receiving, at a first device, a plurality of measurements of channel state information from a second device, wherein each of the measurements corresponds to one of a plurality of channel parameter sets, and each channel parameter set corresponds to a condition of a channel between the first device and the second device; receiving, from the second device, a plurality of predicted values ​​of the channel state information, the plurality of predicted values ​​being predicted by a model based on machine learning, wherein each predicted value of the predicted values ​​corresponds to one of the plurality of channel parameter sets; as well as The prediction accuracy of the machine learning based model is determined by comparing the multiple measured values ​​and the multiple predicted values ​​of the channel state information for each channel parameter set.

18. A method for communication, comprising: At the second device, transmitting to the first device a plurality of measurements of channel state information, wherein each of the measurements corresponds to one of a plurality of channel parameter sets, and each channel parameter set corresponds to a condition of a channel between the first device and the second device; as well as Transmitting multiple predicted values ​​of the channel state information to the first device, the multiple predicted values ​​are predicted by a model based on machine learning, wherein each predicted value of the predicted value corresponds to a channel parameter set in the multiple channel parameter sets.

Images