Communication method and apparatus

Abstract

Embodiments of the present application relate to the technical field of communications, and provide a communication method and apparatus. The method comprises: a terminal device determines a first information set of related information of predicted received powers, and determines first reporting information on the basis of the first information set. First reporting information is determined on the basis of a first information set; therefore, the first reporting information reflects to a certain extent the conditions such as a normalization result of predicted received powers, relative predicted received powers, a sorting result of the predicted received powers, or the predicted received powers, thereby realizing model monitoring and providing a model monitoring mechanism. Moreover, the first reporting information reflects the conditions after processing such as normalization, relative results, or sorting of the predicted received powers; therefore, which is equivalent to performing certain processing on the predicted received powers, so that the impacts of errors of individual predicted received powers on model monitoring are reduced, thereby facilitating the overall improvement of the accuracy of model monitoring.

Description

A communication method and apparatus

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202410579892.9, filed on May 10, 2024, entitled "A Communication Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of communication technology, and in particular to a communication method and apparatus. Background Technology

[0004] Models (such as artificial intelligence (AI) or machine learning (ML) models) can be applied to improve communication. For example, terminal devices can use models to select appropriate beams to improve the communication quality between the terminal device and network devices. However, there is currently no solution for monitoring these models. Summary of the Invention

[0005] This application provides a communication method and apparatus for providing a mechanism for a monitoring model.

[0006] Firstly, embodiments of this application provide a communication method. This method can be applied to a first device side. The first device side can be, for example, a terminal device, a module within a terminal device, or a device (such as an AI network element) that deploys a model (such as an AI model or AI), such as an over-the-top (OTT) device or server (such as a third-party server) that deploys a model, or software containing terminal device functions (such as a control subsystem). A module within a terminal device can be, for example, a communication module within the terminal device, a circuit or chip responsible for communication functions, such as a modem chip (also known as a baseband chip), or a system-on-a-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip, etc. The method includes: determining a first information set, the first information set including at least one first piece of information, the type of the at least one first piece of information including one of the following: normalized predicted received power information, first relative received power information, predicted received power ranking information, or predicted received power information; sending first reporting information, the first reporting information being related to the first information set (or can be described as the first reporting information being determined based on the first information set).

[0007] A first information set is used to indicate information related to a first predicted received power set, wherein one of the first pieces of information indicates information related to at least one predicted received power in the first predicted received power set. Any of the at least one pieces of first information includes, indicates, or is used to determine one of the following: normalized predicted received power, such as normalized predicted received power corresponding to a single resource identifier; a single relative received power, such as the relative value (e.g., difference or ratio) of predicted received power corresponding to two resource identifiers; a predicted received power ranking, such as a ranking of a certain predicted received power relative to one or more other predicted received powers, or a ranking of a resource identifier corresponding to a certain predicted received power to one or more other resource identifiers corresponding to other predicted received powers; a single predicted received power, such as the predicted received power corresponding to a single resource identifier, or a compensation result for the predicted received power corresponding to a single resource identifier. The first reported information may correspond to, indicate, or be used to determine an inference result for the received power (e.g., including predicted received power), for example, the first reported information includes an inference result for the received power, or is determined based on the inference result. Alternatively, the first reported information may correspond to or indicate or be used to determine the monitoring results of the inference results for the received power, such as indicating the error between the inference results and the measurement results (e.g., the measured received power).

[0008] In this embodiment, the first device determines a first information set reflecting relevant information about the predicted received power, and determines first reporting information based on the first information set. Since the first reporting information is determined based on the first information set, it reflects, to some extent, the normalized result of the predicted received power, the relative predicted received power, the ranking result of the predicted received power, or other situations related to the predicted received power, thus enabling model monitoring and providing a model monitoring mechanism. Furthermore, because the first reporting information reflects the normalized, relative, or ranked results of the predicted received power, it is equivalent to processing the predicted received power to a certain extent, reducing the impact of individual predicted received power errors on model monitoring, and contributing to improving the overall accuracy of model monitoring.

[0009] In one possible implementation, the type of at least one first piece of information includes normalized predicted received power information; one of the first pieces of information corresponds to the relative value of the predicted received power and the first reference received power.

[0010] The first reference received power may be pre-stored in the first device, pre-configured or pre-defined in the first device, or indicated to the first device by the second device, or determined by the first device based on the first set of information. For example, the first reference received power may be the maximum or minimum value in the first predicted received power set corresponding to the first set of information. The relative value between the predicted received power and the first reference received power corresponding to a piece of first information may be obtained by subtracting or dividing the relative value between the predicted received power and the first reference received power corresponding to a piece of first information. The power type of the predicted received power and the first reference received power corresponding to a piece of first information may be a linear value or a decibel (dB) value.

[0011] In this way, the predicted received power corresponding to at least one piece of first information can be normalized using the first reference received power. This can reduce the impact of some predicted received power with large errors, thereby improving the accuracy of the first reported information and thus improving the accuracy of the monitoring model.

[0012] In one possible implementation, the type of at least one first information includes first relative received power information; one of the first information corresponds to the relative value of a first predicted received power and a second predicted received power, the first predicted received power corresponding to a first resource identifier, and the second predicted received power corresponding to a second resource identifier.

[0013] The first resource identifier and the second resource identifier can be two adjacent resource identifiers, or the first resource identifier can be the resource identifier with the smallest difference between it and the second resource identifier.

[0014] In this way, the relative values ​​of the two predicted received powers can be determined, which is equivalent to normalizing the other predicted received power using one predicted received power. This also reduces the impact of some predicted received powers with larger errors, thereby improving the accuracy of the first reported information and thus improving the accuracy of the monitoring model. Furthermore, considering the predicted received power of the model across multiple resources allows for more accurate and comprehensive monitoring of the model.

[0015] In one possible implementation, the type of at least one first piece of information includes predicted received power ranking information; one of the first pieces of information includes ranking information of a third predicted received power and one or more fourth predicted received powers; or, one of the first pieces of information includes ranking information of a third resource identifier and one or more fourth resource identifiers, wherein the ranking of the third resource identifier and one or more fourth resource identifiers is determined by the magnitude of the third predicted received power corresponding to the third resource identifier and the one or more fourth predicted received powers corresponding to the one or more fourth resource identifiers.

[0016] In this way, at least one piece of information reflects the ranking of predicted received power, avoiding excessive focus on the value of the predicted received power. This reduces the impact of errors in the predicted received power on the first reported information and improves the accuracy of model monitoring. Furthermore, by considering the predicted received power of the model across multiple resources, model monitoring can be performed more accurately and comprehensively.

[0017] In one possible implementation, the type of at least one first piece of information includes predicted received power information; the first reported information includes at least one second piece of information, one of the at least one second piece of information corresponds to one of the at least one first piece of information, and the received power corresponding to one second piece of information differs from the predicted received power corresponding to one first piece of information by a first power compensation value. Optionally, first indication information is received, which is used to determine the first power compensation value. For example, the first indication information explicitly or implicitly indicates the first power compensation value.

[0018] At least one second piece of information corresponds one-to-one with at least one first piece of information, that is, each of the at least one second piece of information corresponds to one of the at least one first piece of information. The first piece of information can be any one of the at least one second piece of information.

[0019] In this way, the first device compensates for the predicted received power corresponding to the first information, which can report more accurate first reported information and also helps to improve the accuracy of model monitoring.

[0020] In one possible implementation, the method further includes: determining a third information set, the third information set including at least one third piece of information, the type of the at least one third piece of information including: normalized measured received power information, second relative received power information, measured received power ranking information, or measured received power information; determining first reported information based on a first information set includes: determining the first reported information based on the first information set and the third information set, wherein the first reported information is determined based on the degree of similarity or difference between at least one first piece of information and at least one third piece of information.

[0021] A third set of information is used to indicate information related to a first set of predicted received power, wherein one of the third sets of information is used to indicate information related to at least one measured received power in a first set of measured received power.

[0022] Thus, the third information set reflects the relevant information of the received power measured by the first device, which enables the first reported information to intuitively, comprehensively and accurately reflect the difference between the received power predicted by the model and the measured received power, and thus to intuitively, comprehensively and accurately monitor the model.

[0023] In one possible implementation, at least one type of first information includes normalized predicted received power information, and at least one type of third information includes normalized predicted received power information; one of the at least one third information corresponds to the relative value of the measured received power and the second reference received power.

[0024] The determination of the second reference received power can refer to the determination of the first reference received power discussed earlier. A third piece of information corresponds to the relative value between the measured received power and the second reference received power, for example, it is obtained by taking the difference or dividing the received power corresponding to the first target measured received power information and the second reference received power.

[0025] This is equivalent to normalizing the measured received power, which can reduce the impact of individual measured received power with large errors on the first reported information and improve the accuracy of the first reported information.

[0026] In one possible implementation, at least one type of first information includes first relative received power information, and at least one type of third information includes second relative received power information; one of the at least one third information corresponds to the relative value of the first measured received power and the second measured received power, the first measured received power corresponds to the first resource identifier, and the second measured received power corresponds to the second resource identifier.

[0027] The relative value of the first measured received power and the second measured received power can be obtained by taking the difference between the first measured received power and the second measured received power or by division.

[0028] This effectively normalizes the measured received power, reducing the impact of individual measured received power values ​​with larger errors on the first reported information and improving its accuracy. Furthermore, by determining the first reported information based on the similarity or difference between the measured and predicted received power corresponding to the same resource identifier, the first reported information can more accurately reflect the error between the model-predicted received power and the measured received power, thereby enabling more accurate monitoring of the model.

[0029] In one possible implementation, the type of at least one first piece of information includes predicted power ranking information, and the type of at least one third piece of information includes measured power ranking information; one of the at least one third piece of information includes ranking information of a third measured received power and one or more fourth measured received powers; or, one of the at least one third piece of information includes ranking information of a third resource identifier and one or more fourth resource identifiers, wherein the ranking of the third resource identifier and one or more fourth resource identifiers is determined by the magnitude of the third measured received power corresponding to the third resource identifier and the one or more fourth measured received powers corresponding to the one or more fourth resource identifiers.

[0030] Thus, at least one third piece of information reflects the ranking of the measured received power, avoiding excessive focus on the measured received power value. This relatively reduces the impact of measured received power errors on the first reported information and improves the accuracy of model monitoring. Furthermore, the first reported information can be obtained by comparing the ranking of measured received power corresponding to the same resource identifier with the ranking of predicted received power. The first device does not need to directly calculate a large number of power values, relatively reducing the computational load on the first device and also contributing to improving the accuracy of the first reported information.

[0031] In one possible implementation, at least one type of first information includes predicted received power information, and at least one type of third information includes measured received power information; the measured received power corresponding to one of the at least one third information differs from a fifth measured received power by a second power compensation value, wherein the fifth measured received power is the received power measured for a resource associated with a resource identifier corresponding to one of the third information. Optionally, second indication information is received, which is used to determine the second power compensation value. For example, the second indication information explicitly or implicitly indicates the second power compensation value.

[0032] The third piece of information can be any one of at least one third piece of information.

[0033] This is equivalent to compensating for the received power of the measurement, which allows for the determination of more accurate third information, and thus more accurate first reporting information, which also helps improve the accuracy of model monitoring.

[0034] In one possible implementation, the type of at least one first piece of information includes predicted received power information, and the type of at least one third piece of information includes measured received power information; the first reported information is determined based on a first difference and a third power compensation value, wherein the first difference is the difference between the predicted received power corresponding to a first piece of information and the measured received power corresponding to a third piece of information; a first piece of information belongs to at least one first piece of information, and a third piece of information is the measured received power information corresponding to a first piece of information among at least one third piece of information.

[0035] This is equivalent to compensating for the difference between the measured received power and the predicted received power, which can determine a more accurate first reporting information and also help improve the accuracy of model monitoring.

[0036] In one possible implementation, the type of at least one first piece of information includes predicted received power information, and the method further includes sending transmit power information corresponding to the at least one first piece of information, wherein the transmit power information is the transmit power corresponding to the training data used to train the first model, and the at least one first piece of information is determined according to the first model.

[0037] Thus, the transmitted power information can be used to determine the power compensation value, such as the first power compensation value mentioned above.

[0038] Secondly, embodiments of this application provide a communication method. This method can be applied to a second device side. The second device side is, for example, a network device (such as an access network device), a module within a network device (such as an access network device), or a device deploying a model (such as an AI network element), such as an OTT device or server deploying a model, or software containing network device functions (such as a control subsystem). For example, a module within an access network device may be a circuit, chip, or chip system within the access network device. Alternatively, a module within an access network device may also be at least one of a central unit (CU), a distributed unit (DU), a central unit control plane (CU-CP), a central unit user plane (CU-UP), an open central unit (O-CU), or a radio access network intelligent controller (RIC). The RIC may include, for example, a non-real-time radio access network intelligent controller (Non-RT RIC) and / or a near-real-time RAN intelligent controller (Near-RT RIC).

[0039] The method includes: receiving first reported information, the first reported information being related to a first information set, the first information set including at least one piece of first information, the type of the at least one piece of first information including one of the following: normalized predicted received power information, first relative received power information, predicted received power ranking information, or predicted received power information.

[0040] In one possible implementation, the type of at least one first piece of information includes normalized predicted received power information; one of the first pieces of information corresponds to the relative value of the predicted received power and the first reference received power.

[0041] In one possible implementation, the type of at least one first piece of information includes relative received power information; one of the first pieces of information corresponds to a relative value of a first predicted received power and a second predicted received power, the first predicted received power corresponding to a first resource identifier and the second predicted received power corresponding to a second resource identifier.

[0042] In one possible implementation, the type of at least one first piece of information includes predicted received power ranking information; one of the first pieces of information includes ranking information of a third predicted received power and one or more fourth predicted received powers; or, one of the first pieces of information includes ranking information of a third resource identifier and one or more fourth resource identifiers, wherein the ranking of the third resource identifier and one or more fourth resource identifiers is determined by the magnitude of the third predicted received power corresponding to the third resource identifier and the one or more fourth predicted received powers corresponding to the one or more fourth resource identifiers.

[0043] In one possible implementation, the type of at least one first piece of information includes predicted received power information; the first reported information includes at least one second piece of information, one of the second pieces of information corresponds to one of the first pieces of information, and the received power corresponding to one second piece of information differs from the predicted received power corresponding to one first piece of information by a first power compensation value.

[0044] In one possible implementation, the method further includes: sending first indication information, wherein the first indication information is used to determine a first power compensation value.

[0045] In one possible implementation, the method further includes: determining a third information set, the third information set including at least one third piece of information, the type of the at least one third piece of information including: normalized measured received power information, second relative received power information, measured received power ranking information, or measured received power information; determining first reported information based on a first information set includes: determining the first reported information based on the first information set and the third information set, wherein the first reported information is determined based on the degree of similarity or difference between at least one first piece of information and at least one third piece of information.

[0046] In one possible implementation, at least one type of first information includes normalized predicted received power information, and at least one type of third information includes normalized predicted received power information; one of the at least one third information corresponds to the relative value of the measured received power and the second reference received power.

[0047] In one possible implementation, at least one type of first information includes first relative received power information, and at least one type of third information includes second relative received power information; one of the at least one third information corresponds to the relative value of the first measured received power and the second measured received power, the first measured received power corresponds to the first resource identifier, and the second measured received power corresponds to the second resource identifier.

[0048] In one possible implementation, the type of at least one first piece of information includes predicted power ranking information, and the type of at least one third piece of information includes measured power ranking information; one of the at least one third piece of information includes ranking information of a third measured received power and one or more fourth measured received powers; or, one of the at least one third piece of information includes ranking information of a third resource identifier and one or more fourth resource identifiers, wherein the ranking of the third resource identifier and one or more fourth resource identifiers is determined by the magnitude of the third measured received power corresponding to the third resource identifier and the one or more fourth measured received powers corresponding to the one or more fourth resource identifiers.

[0049] In one possible implementation, at least one type of first information includes predicted received power information, and at least one type of third information includes measured received power information; the measured received power corresponding to one of the at least one third information differs from the fifth measured received power by a second power compensation value, wherein the fifth measured received power is the received power measured for the resource associated with the resource identifier corresponding to one of the third information.

[0050] In one possible implementation, the method further includes: sending second indication information, wherein the second indication information is used to determine a second power compensation value.

[0051] In one possible implementation, the type of at least one first piece of information includes predicted received power information, and the type of at least one third piece of information includes measured received power information; the first reported information is determined based on a first difference and a third power compensation value, wherein the first difference is the difference between the predicted received power corresponding to a first piece of information and the measured received power corresponding to a third piece of information; a first piece of information belongs to at least one first piece of information, and a third piece of information is the measured received power information corresponding to a first piece of information among at least one third piece of information.

[0052] In one possible implementation, at least one type of first information includes predicted received power information, and the method further includes,

[0053] Receive at least one first piece of information corresponding to transmission power information, wherein the transmission power information is the transmission power corresponding to the training data used to train the first model, and the at least one first piece of information is determined according to the first model.

[0054] Thirdly, this application provides a communication device. The communication device can be the first device described in the first aspect above, or a module (e.g., a chip system) configured in the first device. The communication device includes corresponding means or modules for performing the first aspect or any possible implementation described above. For example, the communication device includes a processing unit (sometimes also called a processing module) and a communication unit (sometimes also called a communication module). The communication unit is used to perform transmit and receive operations, such as functions related to sending and receiving; the communication unit can be called a transceiver unit; optionally, the communication unit includes a receiving unit and a sending unit. The processing unit is used to perform processing operations. Alternatively, the communication unit can be a transmitter (or transmitter unit) and a receiver (or receiver unit), or a transceiver, or an input / output circuit, or an interface circuit. Optionally, the communication device also includes a storage unit (sometimes also called a storage module).

[0055] For example, the processing unit is used to determine the first information set and the first reported information, and the communication unit is used to send the first reported information.

[0056] The communication device can also implement any of the possible implementations in the first aspect described above, which will not be listed here.

[0057] In one possible design, the communication device is a communication chip, the processing unit can be one or more processors or processor cores, and the communication unit can be the input / output circuit or input / output interface of the communication chip.

[0058] Fourthly, this application provides a communication device. The communication device can be the second device described in the second aspect above, or a module (e.g., a chip system) configured in the second device, or a larger device including the second device. For example, if the second device is a CU, then the communication device can be an access network node or device including the CU. The communication device includes corresponding means or modules for performing the second aspect above or any possible implementation. For example, the communication device includes a processing unit (sometimes also called a processing module) and a communication unit (sometimes also called a communication module). The communication unit is used to perform transmit and receive operations, such as functions related to sending and receiving; the communication unit can be called a transceiver unit; optionally, the communication unit includes a receiving unit and a sending unit. The processing unit is used to perform processing operations. Alternatively, the communication unit can be a transmitter and a receiver, or a transceiver, or an input / output circuit, or an interface circuit. Optionally, the communication device also includes a storage unit (sometimes also called a storage module).

[0059] For example, the communication unit is used to receive the first reported information.

[0060] The communication device can also implement any of the possible implementations in the second aspect described above, which will not be listed here.

[0061] In one possible design, the communication device is a communication chip, the processing unit can be one or more processors or processor cores, and the communication unit can be the input / output circuit or input / output interface of the communication chip.

[0062] Fifthly, this application provides a communication device. The communication device includes one or more processors. The one or more processors are capable of executing computer programs or instructions stored in a memory, which, when executed, cause the communication device to implement the methods described in the first aspect, any possible implementation of the first aspect, the second aspect, or any possible implementation of the second aspect.

[0063] In one possible design, the communication device may also include a memory, in which case the memory may be coupled to one or more processors, or the memory may be configured relatively independently of one or more processors. Alternatively, the memory may exist independently of the communication device.

[0064] In one possible design, the communication device may further include an interface circuit, through which the processor communicates with other devices or components.

[0065] The aforementioned communication device may be a terminal device, or a communication module within a terminal device, or a chip in the terminal responsible for communication functions, such as a modem chip (also known as a baseband chip), or a SoC or SIP chip containing a modem module. Alternatively, the aforementioned communication device may be an access network device, or a module within an access network device.

[0066] Sixthly, embodiments of this application provide a communication device. The communication device includes a processor and an interface circuit. The interface circuit is used to receive signals from other communication devices besides the communication device and transmit them to the processor, or to send signals from the processor to other communication devices besides the communication device. The processor, through logic circuits or executable code instructions, is used to implement the methods of the first aspect, any possible implementation of the first aspect, the second aspect, or any possible implementation of the second aspect. The number of processors can be one or more, and is not limited thereto.

[0067] In the specific implementation process, the communication device can be a chip, and the processor can be a transistor, gate circuit, flip-flop, and various logic circuits, etc. The specific implementation method of the processor is not limited in the embodiments of this application.

[0068] In one implementation, the communication device can be a wireless communication device, i.e., a device that supports wireless communication functionality. Specifically, the wireless communication device can be a terminal device such as a smartphone, or a network device such as a wireless access network device (e.g., a base station).

[0069] In another implementation, the communication device can be a component of a wireless communication device, such as an integrated circuit product like a system-on-a-chip (SoC) or communication chip. A SoC can also be called a System-on-a-Chip (SoC). A communication chip may include a baseband processing chip and a radio frequency (RF) processing chip. A baseband processing chip is sometimes referred to as a modem or baseband chip. An RF processing chip is sometimes referred to as an RF transceiver or RF chip. In physical implementation, some or all of the communication chip's components can be integrated within the SoC. For example, the baseband processing chip may be integrated into the SoC, while the RF processing chip may not be integrated. The interface circuit can be the RF processing chip in the wireless communication device, and the processor can be the baseband processing chip in the wireless communication device. The interface circuit can be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip or chip system. The processor can also be represented as a processing circuit or logic circuit.

[0070] In another implementation, the communication device can be a chip system, which may consist of chips or include chips and other discrete devices. Chip systems may include, for example, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs), CPUs, network processors (NPs), digital signal processors (DSPs), microcontroller units (MCUs), programmable logic devices (PLDs), or other integrated chips.

[0071] In another implementation, the communication device can be a device with a deployed model (such as AI), or a module within a device with a deployed model, such as a circuit, chip, or chip system within the device. For example, the communication device can be an OTT device or a server.

[0072] In a seventh aspect, embodiments of this application provide a communication system. The communication system is used to implement the methods described in the first aspect, any possible implementation of the first aspect, the second aspect, or any possible implementation of the second aspect.

[0073] For example, the communication device includes any of the communication devices described in the third aspect and any of the possible embodiments described above, as well as any of the communication devices described in the fourth aspect and any of the possible embodiments described above.

[0074] Eighthly, embodiments of this application provide a chip system. The chip system includes a processor. Optionally, the chip system may further include an interface (such as a communication interface). The processor can be used to implement any of the methods described in the first aspect and possible implementations to the fourth aspect and possible implementations. Optionally, the chip system also includes a memory. The memory is used to store a computer program (also referred to as code or instructions). The processor is used to call and run the computer program from the memory, causing a device equipped with the chip system to perform the methods described in the first aspect, any possible implementation of the first aspect, the second aspect, or any possible implementation of the second aspect. Implementations of the chip system can be referred to the content of the chip system discussed above, and will not be listed here.

[0075] Ninthly, embodiments of this application provide a readable storage medium. This readable storage medium is used to store a program or instructions that, when executed, implement the method as described in the first aspect and possible implementations of the first aspect, any possible implementation of the first aspect, the second aspect, or any possible implementation of the second aspect.

[0076] In a tenth aspect, embodiments of this application provide a program product. When the program product is executed, it causes a processor to perform a method as described in the first aspect, any possible implementation of the first aspect, the second aspect, or any possible implementation of the second aspect. The program product includes, for example, a program and / or instructions.

[0077] Regarding the beneficial effects of any of the technical solutions in the second to tenth aspects mentioned above, please refer to the discussion of the beneficial effects of the corresponding technical solutions in the first aspect, which will not be listed here again. Attached Figure Description

[0078] Figure 1 is a schematic diagram of the model;

[0079] Figure 2 is a schematic diagram of the neuron structure;

[0080] Figure 3 is a schematic diagram of a beam management application model;

[0081] Figures 4 to 7 are schematic diagrams of several architectures of the communication system applicable to the embodiments of this application;

[0082] Figure 8 is a schematic diagram of a communication method provided in an embodiment of this application;

[0083] Figure 9 is a schematic diagram of determining the first predicted received power set according to an embodiment of this application;

[0084] Figures 10 to 12 are schematic diagrams illustrating several methods for determining the first reported information provided in the embodiments of this application;

[0085] Figures 13 to 15 are schematic diagrams of the structures of several communication devices provided in the embodiments of this application. Detailed Implementation

[0086] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0087] The following explanations of some terms used in the embodiments of this application are provided to facilitate understanding by those skilled in the art.

[0088] 1. Artificial intelligence (AI)

[0089] Artificial intelligence is about giving machines human-like intelligence by using computer hardware and software to simulate certain intelligent behaviors of humans, including machine learning and many other methods.

[0090] 2. Machine learning (ML)

[0091] Machine learning aims to endow machines with human-like intelligence by using computer hardware and software to simulate certain intelligent human behaviors. This includes machine learning and many other methods. Machine learning can be categorized into supervised learning, unsupervised learning, and reinforcement learning.

[0092] Supervised learning learns the mapping relationship between samples and labels, expressing this learned mapping relationship in a model. The process of training the model can be viewed as learning this mapping relationship. For example, in signal detection, noisy signals can be used as samples, and the corresponding ground truth points are used as labels. Machine learning aims to learn the mapping relationship between samples and labels through training, thus enabling the model to learn how to detect signals. During model training, the error between the model's predictions and the labels is used to optimize the model's parameters. After training, the model can be used to predict the label of each new sample. The mapping relationships learned in supervised learning include linear and nonlinear mappings. Based on the type of label, the learning task can be divided into classification and regression tasks.

[0093] Unsupervised learning relies on sample values ​​to allow algorithms to discover or learn inherent patterns within the samples themselves. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals, meaning the model learns the mapping relationships from samples to samples; this type of learning is therefore called self-supervised learning. During model training, the model parameters are optimized by calculating the error between the model's predictions and the samples. Self-supervised learning can be used for signal compression and decompression recovery applications. Models suitable for self-supervised learning include autoencoders and generative adversarial networks.

[0094] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have a pre-defined "correct" label. The algorithm needs to interact with the environment, obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, a reinforcement learning model adjusts the downlink transmission power of each user based on the total system throughput reported by the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and the optimal decision action. However, because the "correct" label cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct" label. Training in reinforcement learning is achieved through iterative interaction with the environment.

[0095] 3. Model

[0096] A model is an implementation of machine learning; or, in other words, the goal of machine learning is to obtain a model that can perform a given function. A model is a concrete implementation of one or more functions, representing the mapping relationship between the model's input and output. A model can include one or more parameters. A substructure (or submodule) of a model can include one or more parameters. For example, f(x) = ax 2 +b can be viewed as a model, where a and b correspond to the model's parameters, which can be obtained through training. The process of training the model can be seen as optimizing its parameters. The process of using the model to achieve the corresponding function can be considered as the model's inference process. The model's output during inference can be called the inference result.

[0097] In the fields of machine learning (ML) and artificial intelligence (AI), a model can be understood as an algorithm or system that, after being trained and learned from input data, is capable of making predictions or performing tasks. A model can include or be replaced by AI, ML model, AI model, algorithm, characteristic, function, or AI function, etc. An AI model can be at least one of the following: linear regression model, logistic regression model, decision tree model, support vector machine (SVM), neural network model, clustering model, Bayesian network, Q-learning model, generative adversarial network, or other machine learning model, without limitation. A neural network model is a mathematical model that mimics the behavioral characteristics of animal neural networks and performs distributed parallel information processing. A neural network model can be one or more of the following: deep neural network (DNN), feedforward neural network (FNN), convolutional neural network (CNN), and recurrent neural network (RNN), without specific limitation. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings.

[0098] DNNs typically consist of multiple hidden layers. These hidden layers influence the extraction of information and the fitting of functions. Increasing the number of hidden layers or widening each layer can improve the DNN's function fitting ability. The training process optimizes the DNN's model parameters, enabling the network to extract data features and express mapping relationships. Supervised or unsupervised learning strategies are generally used to optimize DNN model parameters.

[0099] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time-series data (such as data obtained by discrete sampling along a time axis) and image data (such as data obtained by two-dimensional discrete sampling) can both be considered as grid-like data. CNNs generally do not use all the input information at once for computation; instead, they use a fixed-size window to extract a portion of the information for convolution operations, thereby reducing the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (e.g., people and objects in the same image represent different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0100] Recurrent Neural Networks (RNNs) are a type of network that utilizes feedback time-series information. The input to an RNN includes the current input value and the output value from the previous time step. RNNs are well-suited for acquiring temporally correlated sequence features and can be applied to fields such as speech recognition or channel coding / decoding.

[0101] Taking a neural network model as an example, a model can include at least one layer, and a "layer" can be a "network layer." Each "network layer" can contain at least one node, which can also be called a "neuron." Please refer to Figure 1, which is a schematic diagram of one model structure. The model shown in Figure 1 includes an input layer, hidden layers, and an output layer. The circles in Figure 1 represent neurons, and the lines connecting the circles between network layers represent connections. Optionally, the model can also include a loss layer, such as a cross-entropy loss function. Any layer mentioned here can be considered a network layer. For example, network layers can include at least one parameter, such as weights or operators, specifically convolution operators, fully connected operators, etc.

[0102] Neurons in a network layer are connected to neurons in adjacent network layers through weights, and each connection can be considered as a computation. Taking the connection between the input layer and the hidden layer shown in Figure 1 as an example, the connection between the input layer and the hidden layer is the parameter of the model, that is, every neuron in the input layer is connected to every neuron in the hidden layer.

[0103] The following example, using the neuron shown in Figure 2, illustrates the concept of a neuron. As shown in Figure 2, each neuron performs a weighted summation operation on its input values, and the result of this weighted summation is used to generate the output through a nonlinear function. Assume the neuron's input is x = [x0, ..., x...]. n The weights corresponding to the inputs are d = [d0, ..., d]. n If the bias of the weighted summation is b, then the output of the neuron...

[0104] In one possible implementation, the model is used to predict CSI, meaning the model's inference result is the CSI prediction result. In this case, the model's input is, for example, a reference signal, specifically, CSI-RS, etc. Alternatively, the model is used to predict beamforming, meaning the model's inference result is the beamforming prediction result. In this case, the model's input is, for example, the measurement result of the reference signal.

[0105] The model can be applied in scenarios such as channel status information reference signal (CSI-RS) feedback enhancement and / or beam management enhancement.

[0106] For scenarios requiring enhanced CSI-RS feedback, the model can provide encoders and quantization tools to the terminal device based on its capabilities. The terminal device then compresses and quantizes the CSI-RS using these tools and transmits it to the network. The network can then determine the terminal's channel quality based on the CSI-RS.

[0107] For scenarios requiring enhanced beam management, the network side can configure beam sets for terminal devices. Based on these beam sets, the terminal devices measure (or scan) reference signals to obtain measurement results corresponding to the sparse beams. These results might include the reference signal receiving power (RSRP) of the corresponding beam. This measurement result can be used as input to a model, allowing the model to output the probability that each beam in the beam set is the optimal beam. This corresponds to classification training. Alternatively, the model can output predicted values ​​(or prediction results, or output results) for the beam set, such as predicted received power, specifically RSRP. This corresponds to regression training. The optimal beam refers to the beam that the device selects from multiple beams that is most likely to be used for communication. The optimal beam can be the beam with the best communication quality, such as the beam with the highest RSRP.

[0108] The following is an example of beam management using a model illustrated in Figure 3. The first and second directions shown in Figure 3 are, for example, the horizontal and vertical directions, respectively. As shown in Figure 3(1), the device measures (or scans) multiple beams corresponding to the reference signal to obtain the measurement results of these multiple beams. As shown in Figure 3(2), the model can use the measurement results of these multiple beams as input to predict the measurement results of these multiple beams, thereby predicting the top 3 beams of RSRP. These 3 beams are specifically shown in Figure 3(3). As shown in Figure 3(4), the device can measure these 3 beams to determine the optimal beam for receiving the signal.

[0109] 4. Reference signal (RS)

[0110] A reference signal, also known as a pilot signal or pilot signal, is a known signal. For example, it can be a known signal provided by the transmitter to the receiver for channel estimation, channel sounding, or data demodulation. Examples of reference signals include the synchronization signal block (SSB) and the channel state information-reference signal (CSI-RS). The SSB is a cell broadcast signal, comprising the primary synchronization signal (PSS), secondary synchronization signal (SSS), physical broadcast channel (PBCH), and demodulation reference signal (DMRS). There are various types of reference signals, and as standards evolve, the names of these reference signals may change, and even more reference signals may emerge; therefore, no specific limitations are imposed.

[0111] CSI includes at least one of the following: rank indication (RI) information, channel quality indicator (CQI) information, precoding matrix indicator (PMI) or layer 1 reference signal receiver power (L1-RSRP).

[0112] 5. Resources

[0113] The resources include at least one of time-domain resources, frequency-domain resources, or spatial-domain resources. The resources are used to transmit signals; in this embodiment, the resources used to transmit reference signals can also be referred to as reference signal resources.

[0114] The unit of time-domain resources can be a slot, symbol, subframe, half-frame, frame, mini-subframe, mini-slot, or transmission occasion (TO), etc., and there is no limitation thereto. The embodiments of this application mainly relate to resources used for transmitting reference signals (also referred to as reference signal resources).

[0115] Frequency domain resources include subchannels, bands, carriers, bandwidth parts (BWPs), resource blocks (RBs), or resource pools. A subchannel is the smallest unit of frequency domain resources occupied by a physical cross-channel shared channel, and a subchannel may include one or more resource blocks (RBs). The bandwidth of a wireless communication system in the frequency domain may include multiple RBs. For example, in the various possible bandwidths of an LTE system, the number of physical resource blocks (PRBs) may be 6, 15, 25, or 50. In the frequency domain, an RB may include several subcarriers. For example, in LTE and NR systems, an RB includes 12 subcarriers, where each subcarrier can be spaced at 15kHz. Other subcarrier spacings, such as 3.75kHz, 30kHz, 60kHz, or 120kHz, can also be used; there are no restrictions here. Spatial domain resources include, for example, beams.

[0116] In this application embodiment, resources can be identified using identifiers, which are called resource identifiers (or indexes, numbers, resource indexes, or resource numbers, etc.). For example, resource identifiers include resource identifier 1, resource identifier 2, resource identifier 3, or resource identifier 4, etc. The identifier of a resource used for transmitting a reference signal can be called a reference signal resource identifier.

[0117] The resource identified by the resource identifier can be an actual resource that is indicated or configured, or it can be a virtual resource. A virtual resource is a resource that is not directly configured to the terminal by the network side, but is only used to mark resources. For example, if the set of reference signal resources corresponding to all beams is set A (setA), and the resources configured to the terminal device by the network side are a subset B (set B) of the set of reference signal resources corresponding to all beams A (set A), then the reference signal resources in set A other than set B can be regarded as virtual resources.

[0118] When a resource includes a beam, the resource identifier can also be represented by a beam identifier, or in other words, the resource identifier can be replaced by a beam identifier. For example, the reference signal resource identifier can be a beam identifier.

[0119] 6. Beam

[0120] A beam is a communication resource. Beams can be wide beams, narrow beams, or other types. A wide beam refers to a beam with a relatively large radiation range for the transmitting or receiving antenna when transmitting or receiving signals. Wide beams are typically used in applications requiring broadcasting signals to a large area or providing wide coverage. They can provide a wider coverage area, but the signal strength is relatively weaker. A narrow beam refers to a beam with a relatively small radiation range for the transmitting or receiving antenna. Narrow beams are typically used in applications requiring focused signals on a specific target or area. They can provide higher signal strength and greater directivity, but the coverage area is relatively smaller.

[0121] Beamforming technology can be a beamforming technique or other techniques. Beamforming technology can specifically be digital beamforming, analog beamforming, or hybrid digital / analog beamforming. Different beams can be considered different resources. The same or different information can be transmitted through different beams. Optionally, multiple beams with the same or similar communication characteristics can be considered as a single beam. A beam can include one or more antenna ports for transmitting data channels, control channels, and detection signals, etc. For example, a transmit beam can refer to the signal strength distribution in different directions in space after a signal is transmitted through an antenna, and a receive beam can refer to the signal strength distribution in different directions in space of the wireless signal received from the antenna. One or more antenna ports forming a beam can also be considered as a set of antenna ports.

[0122] 7. Power

[0123] Power is divided into receiving power and transmitting power (or transmit power). Receiving power represents the power or energy of the received signal. Taking the reception of a reference signal as an example, the power of receiving the reference signal includes, for example, the reference signal receiving power (RSRP). Transmitting power represents the power or energy of the transmitted signal.

[0124] The power (such as transmit power or receive power) involved in the embodiments of this application is a linear value or a decibel (dB) value. When the power type is a decibel value, the unit of power can be decibel.

[0125] In this embodiment, the transmit power can be divided into measured receive power and predicted receive power. Measured receive power refers to the received power of the signal obtained by measurement (or scanning). Predicted receive power refers to the predicted received power of the signal, for example, the received power of the signal predicted by a model.

[0126] In addition, embodiments of this application also involve a reference power (also known as a reference value) and a power compensation value (also known as a compensation power, etc.). The reference power is a reference power value used for processing power; for example, the reference received power represents a reference power value used for processing received power. The power compensation value is used to compensate for power, for example, it can be used to compensate for received power, etc.

[0127] 8. Relative value

[0128] A relative value represents the comparison result of two parameters or their values, such as the degree of similarity or difference between the two parameters. For example, the relative value of A and B can be the result of subtracting A from B. This could include at least one of the following: the difference between A and B, the absolute value of the difference, or the square of the difference. The difference between A and B can be either A minus B or B minus A. Alternatively, the relative value of A and B can be the result of dividing A from B. This could include the result of dividing A from B and / or the rounded-down result of the division. The result of dividing A from B can be either A divided by B or B divided by A, without limitation. The rounded-down result can be either rounded up or rounded down.

[0129] The relative value of A and B can also be described as the relative value of A compared to (or relative to) B, or the relative value of B compared to (or relative to) A, or the comparison result of A and B, etc.

[0130] 9. First Information Set

[0131] The first information set may also be referred to as the first predicted received power information set, and its name is not specifically limited. The first information set includes at least one piece of first information. Alternatively, the first information set can also be described as at least one piece of first information. At least one piece of first information reflects or characterizes the inference result of the model, or can be described as at least one piece of first information being understandable as indicating (or used to determine, or correspond to) the predicted received power or content related to the predicted received power, or can be described as at least one piece of first information being determined based on the first predicted received power set. The first predicted received power set includes multiple predicted received powers. Wherein, each piece of first information is determined based on at least one predicted received power in the first predicted received power set, or can be described as each piece of first information corresponding to at least one predicted received power in the first predicted received power set, or can be described as each piece of first information corresponding to (or associated with) at least one predicted received power in the first predicted received power set. Wherein, the number of at least one piece of first information may be equal to or less than the number of predicted received powers in the first predicted received power set.

[0132] Optionally, the first predicted received power set can be the predicted received power of the signal on the first resource set, or it can be described as a one-to-one correspondence (or association) between the first predicted received power set and the first resource set, specifically, each predicted received power set in the first predicted received power set corresponds to each resource in the first resource set. Correspondingly, it can also be viewed as a correspondence between the first information set and the first resource set; for example, one piece of first information in the first information set corresponds to (or is associated with) at least one resource in the first resource set. The first predicted received power set can also be a compensation result for the predicted received power on the first resource set. The compensation result refers to the result after compensating the received power based on the power compensation value, and the compensation result for the predicted received power refers to the result after compensating the predicted received power based on the power compensation value. The first resource set can, for example, be part or all of the reference signal resource set of all beams; in other words, the first resource set is part or all of the resources used to transmit the reference signal.

[0133] Each of the first pieces of information includes, for example, information about a single predicted received power and / or statistical information about multiple predicted received powers. Information about a single predicted received power includes, for example, at least one of the following: normalized predicted received power, such as normalized predicted received power corresponding to a resource identifier, a single relative received power (e.g., the relative values ​​of predicted received powers corresponding to two resource identifiers), a single predicted received power ranking (e.g., the ranking of a resource identifier relative to one or more other resource identifiers, or the ranking of a predicted received power relative to one or more other predicted received powers), or a single predicted received power (e.g., the predicted received power corresponding to a single resource identifier).

[0134] The statistical information for multiple predicted received powers includes at least one of the following: the mean of the multiple predicted received powers, the variance of the multiple predicted received powers, the labeled difference of the multiple predicted received powers, the cumulative distribution function (CDF) of the multiple predicted received powers, or the predicted received power corresponding to the position where the CDF is X%. X is a real number. The mean may include, for example, the arithmetic mean and the weighted average.

[0135] In cases where each piece of first information includes multiple statistical information on predicted received power, then optionally, the first information may correspond to multiple resource identifiers corresponding to these multiple predicted powers. For example, if a piece of first information includes three statistical information on predicted received power, then the first information corresponds to three resource identifiers corresponding to these three predicted received powers.

[0136] The predicted received power values ​​corresponding to any two pieces of first information in at least one piece of first information may be the same or different, and no specific limitation is made in this regard. Any two pieces of first information in at least one piece of first information are of the same type.

[0137] For example, at least one type of first information includes one (or item, or class) of the following A1 to A4: A1, normalized predicted received power information (also referred to as normalized predicted received power information); A2, first relative received power information; A3, predicted received power ranking information; or, A4, predicted received power information. This can also be described as each of the at least one first information (or any first information) indicating normalized predicted received power, relative received power, predicted received power ranking, or predicted received power, or described as the type of at least one first information including one of the following based on prediction: normalized received power information, relative received power information, power ranking information, or received power information.

[0138] A1. Normalized predicted received power information, used to indicate the normalized predicted received power. For example, the normalized predicted received power information corresponds to (or indicates, or is used to determine) a relative value between a certain predicted received power and a first reference received power. The first reference received power may be preset, predefined, or preconfigured (such as protocol-defined), or indicated by the network side, or determined based on some or all of the first information in at least one piece of first information, and there is no limitation thereto.

[0139] A2. First relative received power information, used to indicate the relative value of a certain predicted received power with other received power (such as another predicted received power). For example, it can be the difference between a certain predicted received power and other received power, such as the difference between a certain predicted received power and other received power, or it can be the division between a certain predicted received power and other received power, such as the ratio between a certain predicted received power and other received power.

[0140] A3. Predicted received power sorting information, including sorting information for predicted received power or sorting information for resource identifiers corresponding to predicted received power. The sorting information for predicted received power corresponds to (or indicates, or is used to determine) the results of arranging predicted received power in a first order. Since in this case, it may not be possible to correspond to the resource identifiers corresponding to the predicted received power, optionally, the predicted received power indicated by the sorting information for predicted received power may also be associated with the resource identifiers corresponding to the predicted received power. The sorting information for resource identifiers corresponds to (or indicates, or is used to determine) the results of arranging resource identifiers corresponding to predicted received power in a first order. The first order is, for example, a descending order of received power or a ascending order of received power.

[0141] For example, the first predicted received power set includes three predicted received powers: 100dB, 80dB, and 70dB, and the resource identifiers corresponding to these three predicted received powers are 1, 3, and 2, respectively. Accordingly, the ordering information of the predicted received powers is, for example, (100dB; 80dB; 70dB) or (1, 100dB; 3, 80dB; 2, 70dB), and the ordering information of the resource identifiers is, for example, (1, 3, 2).

[0142] A4. Predicted received power information, corresponding to (or indicating, or used to determine) the predicted received power, or the compensation result of the predicted received power, etc. The compensation result can be referred to the previous content, and will not be listed here.

[0143] 10. Third Information Set

[0144] The third information set can also be referred to as the first measured received power information set, and its name is not specifically limited. The third information set includes at least one piece of third information. Alternatively, the third information set can also be described as at least one piece of third information. At least one piece of third information reflects or characterizes the truth value (or true result, or measurement result, etc.) corresponding to the inference result of the model, or can be described as at least one piece of third information being understandable as indicating (or used to determine, or correspond to) the measured received power or content related to the measured received power, or can be described as at least one piece of third information being determined based on the first measured received power set. The first measured received power includes multiple measured received powers. Wherein, each piece of third information is determined based on at least one measured received power in the first measured received power set, or can be described as each piece of third information corresponding to at least one measured received power in the first measured received power set, or can be described as each piece of third information corresponding to (or associated with) at least one measured received power in the first measured received power set. Wherein, the number of at least one piece of third information can be equal to or less than the number of measured received powers in the first measured received power set.

[0145] Optionally, the first measured received power set can be the received power of the signal on the measured first resource set, or it can be described as a one-to-one correspondence (or association) between the first measured received power set and the first resource set. Specifically, for example, each measured received power set in the first measured received power set corresponds to each resource in the first resource set. Correspondingly, it can also be regarded as a correspondence between the third information set and the first resource set. For example, one piece of third information in the third information set corresponds to (or is associated with) at least one resource in the first resource set. The first measured received power set can also be a compensation result of the measured received power on the first resource set. The compensation result of the measured received power can refer to the result after compensating the measured received power based on the power compensation value. The content of the first resource set can refer to the content of the first resource set above, and repeated parts will not be listed again.

[0146] One of the at least three pieces of information may correspond to some or all of the same resources in the first resource set as one of the at least one pieces of information, or in other words, the resource identifier corresponding to the one piece of information and the one piece of information are the same. In this case, the one piece of information and the one piece of information can be regarded as a pair of information (or a set of information). By analogy, the first information set and the third information set can be divided into at least a pair of information (or at least a set of information), wherein each pair of information includes one of the at least three pieces of information and at least one piece of information corresponding to the third piece of information.

[0147] For example, the third information set includes third information 1 and third information 2. Third information 1 corresponds to the first resource identifier and the second resource identifier, and third information 2 corresponds to the third resource identifier and the fourth resource identifier. The first information set includes first information 1 and first information 2. First information 1 corresponds to the third resource identifier and the fourth resource identifier, and first information 2 corresponds to the first resource identifier and the second resource identifier. Therefore, third information 1 and first information 2 correspond to the same resource identifier, and thus they are a pair of information. Similarly, third information 2 and first information 1 are also a pair of information.

[0148] Each of the at least one third piece of information includes, for example, information about a single measured received power and / or statistical information about multiple measured received powers. Information about a single measured received power includes, for example, at least one of the following: normalized measured received power, such as normalized measured received power corresponding to a resource identifier, a single relative received power (e.g., the relative values ​​of measured received powers corresponding to two resource identifiers), a single measured received power ranking (e.g., the ranking of two resource identifiers, or the ranking of two measured received powers), or a single measured received power (e.g., the measured received power corresponding to a single resource identifier). Statistical information about multiple measured received powers includes at least one of the following: the mean of multiple measured received powers, the variance of multiple measured received powers, the labeled difference of multiple measured received powers, the CDF of multiple measured received powers, or the measured received power corresponding to the position where the CDF is X% among the CDFs of multiple measured received powers. X is a real number.

[0149] In cases where each piece of third information includes multiple statistical information on measured received power, then optionally, the third information may correspond to multiple resource identifiers corresponding to these multiple measured powers. For example, if a piece of third information includes four statistical information on measured received power, then the third information corresponds to four resource identifiers corresponding to these four predicted received powers.

[0150] The measured received power values ​​corresponding to any two pieces of third information in at least one set of third information may be the same or different, and no specific limitation is made in this regard. Any two pieces of third information in at least one set of third information are of the same type.

[0151] For example, the type of at least one third piece of information includes one of the following B1 to B4: B1, normalized measured received power information; B2, second relative received power information; B3, measured received power ranking information; or, B4, measured received power information. This can also be described as each of the at least one third piece of information (or any third piece of information) indicating normalized measured received power, relative received power, measured received power ranking, or measured received power, or described as the type of at least one third piece of information including one of the following based on measurement measurements: normalized received power information, relative received power information, power ranking information, or received power information.

[0152] The type of at least one third piece of information includes one of the following based on measurement: normalized received power information, relative received power information, power ranking information, or received power information, and the type of at least one first piece of information includes one of the following based on prediction: normalized received power information, relative received power information, power ranking information, or received power information, in which case the type of at least one first piece of information is the same as the type of at least one third piece of information.

[0153] B1. Normalized measured received power information, used to indicate the normalized measured received power. For example, the normalized measured received power information corresponds to (or indicates, or is used to determine) a relative value between a certain measured received power and a second reference received power. The second reference received power may be preset, predefined, or preconfigured (such as protocol-defined), or indicated by the network side, or determined based on some or all of the third information in at least one third piece of information, without limitation.

[0154] If at least one type of first information is the information shown in A1 above (i.e., the normalized predicted received power information), then at least one type of third information is the information shown in B1 (i.e., the normalized measured received power information).

[0155] B2. Second relative received power information, used to indicate the relative value of a certain measured received power with other received power (such as another measured received power). For example, it can be the difference between a certain measured received power and other received power, such as the difference between a certain measured received power and other received power, or it can be the division between a certain measured received power and other received power, such as the ratio between a certain measured received power and other received power.

[0156] If at least one type of first information is the information shown in A2 above (i.e., first relative received power information), then at least one type of third information is the information shown in B2 (i.e., second relative received power information).

[0157] B3. Measured received power sorting information, including sorting information for the measured received power or sorting information for the resource identifiers corresponding to the measured received power. The sorting information for the measured received power corresponds to (or indicates, or is used to determine) the results of the measured received power in a first order. Since in this case, it may not be possible to correspond to the resource identifiers corresponding to the measured received power, optionally, the measured received power indicated by the sorting information for the measured received power may also be associated with the resource identifiers corresponding to the measured received power. The sorting information for the resource identifiers corresponds to (or indicates, or is used to determine) the results of the resource identifiers corresponding to the measured received power in a first order. The content of the first order can be referred to above and will not be listed here.

[0158] If at least one type of first information is the information shown in A3 above (predicted received power ranking information), then at least one type of third information is the information shown in B3 (i.e., measured received power ranking information).

[0159] B4. Measure received power information, corresponding to (or indicating, or used to determine) the measured received power, or the compensation result of the measured received power, etc. The compensation result of the measured received power refers to the result after compensating the measured received power based on power compensation values, etc.

[0160] If at least one type of first information is the information shown in A4 above (predicted received power information), then at least one type of third information is the information shown in B4 (i.e., measured received power information).

[0161] 11. First report information

[0162] The first reported information can also be referred to as the second information set, and the first reported information includes at least one second piece of information. The first reported information is related to the first information set, or in other words, the first reported information is determined based on the first information set.

[0163] Optionally, the first reported information may correspond to (or indicate, or be used to determine) the inference results of the model, such as the predicted received power or the compensation result of the predicted received power. Alternatively, the first reported information may correspond to (or indicate, or be used to determine) the monitoring results (or monitoring data, or monitoring performance, etc.) of the model. In this optional case, the first reported information may reflect at least one performance metric(s) of the model, for example, at least one of the model's accuracy, precision, or mean squared error. Correspondingly, the first data may include at least one of the model's accuracy, precision standard deviation, CDF, probability density function (PDF), or mean squared error, without specific limitations.

[0164] As standards continue to evolve, the names of the various terms listed above (such as the first information set, the first reported information, and the third information set) may change, and no specific restrictions are imposed on them.

[0165] In the various embodiments of this application, the number of nouns, unless otherwise specified, refers to "singular nouns or plural nouns," that is, "one or more." "At least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. For example, A / B means: A or B. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, or c means: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0166] In this application embodiment, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information to indicate A, it can be understood that the instruction information carries A, directly indicates A, or indirectly indicates A. In this application, the information indicated by the instruction information is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, wherein there is an association between the other information and the information to be instructed. It can also indicate only a part of the information to be instructed, while the other parts of the information to be instructed are known or agreed upon in advance. For example, the instruction of specific information can also be achieved by using the arrangement order of various information in advance (e.g., protocol stipulation), thereby reducing the instruction overhead to a certain extent. In addition, the information to be instructed can be sent as a whole or divided into multiple sub-information to be sent separately, and the sending period and / or sending time of these sub-information can be the same or different.

[0167] In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include direct transmission via the air interface or indirect transmission by other units or modules via the air interface. "Receive information from YY" can be understood as the source of the information being YY, which may include direct reception from YY via the air interface or indirect reception from YY by other units or modules via the air interface. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface. In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0168] To achieve model monitoring, this application provides a communication scheme. In this scheme, a first device can determine a first information set reflecting relevant information about the predicted received power, and determine first reporting information based on the first information set. Since the first information set reflects the normalized result of the predicted received power, the relative predicted received power, the ranking result of the predicted received power, or the predicted received power itself, it realizes the collection of relevant information about the model's predicted received power, processes and reports this information, enabling the network side to monitor the model based on the reported information. Thus, a model monitoring mechanism is provided. Furthermore, since the predicted received power of the model is normalized, relative, or ranked, it is equivalent to processing the overall predicted received power to a certain extent, which can reduce the impact of errors in individual predicted received power on model monitoring, improve the accuracy of the first reporting information, and thus improve the accuracy of model monitoring.

[0169] The solution provided in this application can be applied to various communication systems including a first device and a second device. Both the first device and the second device have communication functions. The device can also be replaced by an entity, network entity, apparatus, communication equipment, communication module, network element, node, or communication node, etc., and there is no limitation thereto.

[0170] The first type of device includes, for example, a terminal device, or a chip system (such as a chip) or other functional module or component within a terminal device, or a device with a deployed model (such as an AI entity), such as an OTT device or a server. The second type of device includes, for example, a network device, or a chip system (such as a chip) or other functional module or component within a network device, or a device with a deployed model, such as an OTT device or a server.

[0171] A terminal device is a device or module that can access a communication system and has corresponding communication functions. A terminal device can be considered a device with wireless transceiver capabilities, and can be a fixed device, mobile device, handheld device, wearable device, vehicle-mounted device, or a wireless device (e.g., a communication module or chip system) built into the aforementioned devices. Terminal devices typically contain communication modules, circuits, or chips that perform the corresponding communication functions. Terminal devices may also be configured with program instructions for performing these communication functions.

[0172] The terminal devices are used to connect people, things, machines, etc., and can be widely used in various scenarios, including but not limited to the following: cellular communication, device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine / machine-type communications (M2M / MTC) communication, Internet of Things (IoT), virtual reality (VR), augmented reality (AR), industrial control, self-driving, remote medical care, smart grid, smart furniture, smart office, smart wearables, smart transportation, smart city, drones, robots, and other scenarios. For example, terminal equipment includes mobile stations (MS), subscriber units, cellular phones, smartphones, wireless data cards, personal digital assistant (PDA) computers, tablet computers, wireless modems, handsets, laptop computers, machine-type communication (MTC) terminals, tags, transportation vehicles with wireless communication capabilities (such as intelligent vehicles), communication modules, and roadside units (RSUs) with terminal functions. These terminal devices may sometimes be referred to as user equipment (UE), terminals, access stations, UE stations, remote stations, wireless communication equipment, or user devices.

[0173] Network equipment includes, for example, access network equipment (or, referred to as access network device / access network element) and / or core network equipment (or, referred to as core network device / core network element).

[0174] Access network equipment is a device with wireless transceiver capabilities used to communicate with the terminal equipment. The access network equipment includes, but is not limited to, base stations (BTS, Node B, eNodeB / eNB, or gNodeB / gNB), transmission reception points (TRPs), 3GPP later-evolved base stations, access nodes in wireless fidelity (WiFi) systems, wireless relay nodes, wireless backhaul nodes, satellites, or drones, etc. The TRP can be a device or module located on the network side of the communication system and possessing corresponding communication functions. The TRP typically contains communication modules, circuits, or chips that perform the corresponding communication functions. The TRP also contains program instructions for performing the corresponding communication functions and corresponding program instructions. The base station can be: a macro base station, a micro base station, a pico base station, a small cell, a relay station, etc. Multiple base stations can support networks using the same access technology mentioned above, or they can support networks using different access technologies mentioned above. A base station can contain one or more co-located or non-co-located transmission and reception points. Access network equipment can also include wireless controllers, NodeBs, evolved NodeBs (eNBs), next-generation NodeBs (gNBs), relay stations, access points, transmitting and receiving points (TRPs), transmitting points (TPs), master stations, auxiliary stations, motor slide retainers (MSRs), home base stations, network controllers, access nodes, wireless nodes, access points (APs), transmission nodes, transceiver nodes, baseband units (BBUs), remote radio units (RRUs), active antenna units (AAUs), remote radio heads (RRHs), central units (CUs), distributed units (DUs), radio units (RUs), and positioning nodes in cloud radio access network (C(R)AN) scenarios. Access network equipment can also include servers, wearable devices, or vehicle-mounted equipment. For example, the access network equipment in V2X technology can be an RSU (Remote Service Unit). The following explanation uses a base station as an example to illustrate the access network equipment. Multiple access network devices in the communication system can be base stations of the same type or different types.Base stations can communicate directly with terminal devices, or they can communicate with terminal devices through relay stations. Terminal devices can communicate with multiple base stations using different access technologies.

[0175] Access network equipment includes CU, DU, CU-CP, CU-UP, and RU, which can be considered a classification of access network equipment from a logical functional perspective. CU and DU can be physically separate or deployed together. For example, CU and DU can be included in the same network element, such as a building base band unit (BBU). One CU can connect to one DU, or multiple DUs can share one CU. RU can be included in radio frequency equipment or radio frequency units, such as in an RRH, active antenna unit (AAU), or RRU.

[0176] The CU and DU can be segmented according to the protocol stack. One possible approach is to deploy the Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), and Packet Data Convergence Protocol (PDCP) layers on the CU, while deploying the remaining Radio Link Control (RLC), Media Access Control (MAC), and physical layers on the DU. This application does not completely limit the CU and DU to the above protocol stack segmentation; other segmentation methods are also possible, such as segmentation according to service type.

[0177] The CU-CP is responsible for control plane functions, mainly including RRC and the PDCP control plane (control, C) (which can be abbreviated as PDCP-C). PDCP-C is mainly responsible for control plane data encryption / decryption, integrity protection, and data transmission. The CU-UP is responsible for user plane functions, mainly including SDAP and PDCP-U. SDAP is mainly responsible for processing core network data and mapping flows to bearers. PDCP-U is mainly responsible for data plane encryption / decryption, integrity protection, header compression, sequence number maintenance, and data transmission.

[0178] Access network equipment can support one or more types of fronthaul interfaces. Different types of fronthaul interfaces correspond to DUs and RUs with different functions. If the fronthaul interface between the DU and RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and RU is another interface relative to CPRI, then the RU can be used to implement some downlink and / or uplink baseband functions. For example, for downlink, the RU can implement precoding, digital beamforming (BF), inverse fast Fourier transform (IFFT), or adding one or more cyclic prefixes (CP). For uplink, the RU can also implement one or more of the following: digital beamforming (BF), fast Fourier transform (FFT), or removing cyclic prefixes (CP). In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the splitting method between the DU and RU is different, corresponding to different categories (Cat) of eCPRI, such as eCPRI CatA, B, C, D, E, and F.

[0179] Taking eCPRI Cat A as an example, for downlink transmission, layer mapping is used as the dividing point. DU is configured to implement one or more functions preceding layer mapping (such as coding, rate matching, scrambling, modulation, and one or more of layer mapping functions), while other functions following layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) or adding a cyclic prefix (CP)) can be implemented in RU. For uplink transmission, de-RE mapping is used as the dividing point. DU is configured to implement one or more functions preceding de-mapping (i.e., decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and one or more of de-RE mapping functions), while other functions following de-mapping (e.g., digital BF or fast Fourier transform (FFT) / CP removal) are implemented in RU.

[0180] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0181] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in the embodiments of this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0182] Core network equipment is used to implement at least one of the functions of mobility management, data processing, session management, policy and charging. The names of the equipment implementing core network functions may differ in systems using different access technologies, and this application does not limit this. Taking a 5G system as an example, the core network equipment includes: access and mobility management function (AMF), session management function (SMF), or user plane function (UPF), etc.

[0183] The embodiments of this application provide solutions applicable to various communication systems, including Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, and 5G (5G) systems. th Generation (5G) (such as new radio (NR) systems), wireless local area network (WLAN) systems, satellite communication systems, side link (SL) communication systems, future evolution communication systems, or integrated systems of multiple communication systems, etc., are not limited to these. SL can also be called side link, side link, direct link, edge link, or auxiliary link, etc. SL includes vehicle-to-everything (V2X) communication, etc. V2X communication can include: vehicle-to-vehicle (V2V) communication, vehicle-to-infrastructure (V2I) communication, vehicle-to-pedestrian (V2P) communication, vehicle-to-network (V2N) communication, etc., without specific limitations.

[0184] The following description, in conjunction with the accompanying drawings, illustrates a schematic diagram of a communication system applicable to the embodiments of this application.

[0185] Please refer to Figure 4, which is a schematic diagram of a communication system applicable to an embodiment of this application. As shown in Figure 4, the communication system includes terminal devices and network devices. Figure 4 is an example with two terminal devices and one network device, but the actual number of terminal devices and network devices is not limited.

[0186] Network devices can send downlink signals to terminal devices, and / or terminal devices can send uplink signals to network devices. Optionally, terminal devices can deploy models, and network devices can monitor these models through interaction with the terminal devices. Alternatively, the model can be deployed in other devices that communicate with the terminal devices. In this case, network devices can also monitor the models through interaction with the terminal devices.

[0187] Please refer to Figure 5, which is a schematic diagram of a communication system applicable to an embodiment of this application. Compared to the communication system shown in Figure 4, the communication system shown in Figure 5 also includes AI network elements (or AI entities, AI devices, AI apparatuses, etc.). AI network elements are used to perform AI-related operations, such as building training datasets or training AI models.

[0188] For example, network devices can send data related to the training of AI models to AI network elements, which then construct training datasets and train the models. For instance, data related to model training may include data reported by terminal devices. AI network elements can send the results of AI model-related operations to network devices, which then forward them to terminal devices. For instance, the results of model-related operations may include at least one of the following: the trained model, model evaluation results, or test results.

[0189] Optionally, part of the trained AI model can be deployed on a network device, and another part on a terminal device. Alternatively, the trained AI model can be deployed on a network device. Alternatively, the trained AI model can be deployed on a terminal device. Alternatively, the AI ​​network element can also be set as a module in a network device, terminal device, OTT device, or server, for example, in the network device or terminal device shown in Figure 4.

[0190] Figure 4 illustrates the example of an AI network element directly connected to a network device. In other scenarios, the AI ​​network element can also be connected to a terminal device. Alternatively, the AI ​​network element can be connected to both a network device and a terminal device simultaneously. Furthermore, the AI ​​network element can also be connected to a network device through a third-party network element. This application does not limit the connection relationship between the AI ​​network element and other network elements.

[0191] Figures 4 and 5 are simplified illustrations for ease of understanding only. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 4 and 5.

[0192] The architecture of access network equipment will be illustrated below with reference to the structural diagrams of the communication system shown in Figures 6 and 7.

[0193] As shown in Figure 6, devices in a communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These devices, such as core network devices, access network nodes (e.g., RAN devices), terminal devices, or one or more devices in the operation, administration, and maintenance (OAM) systems, are equipped with one or more AI modules. Figure 6 illustrates one device with one AI module, but the actual number of AI modules is not limited. An access network node can be a single RAN node or can include multiple RAN nodes, such as CUs and DUs. The CU and / or DU can also be equipped with one or more AI modules. The CU or DU core network devices or access network nodes (RAN nodes) shown in Figure 6 can be considered as an example of network devices. Optionally, a CU can be further divided into CU-CP and CU-UP. One or more AI models are configured in the CU-CP and / or CU-UP.

[0194] The AI ​​module is used to implement corresponding functions. The AI ​​modules deployed on any two devices in one or more devices can be completely identical, partially identical, or completely different; this application embodiment does not specifically limit this. The AI ​​module is used to implement corresponding AI functions. The AI ​​modules deployed on different devices can be the same or different. Depending on the different parameter configurations, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The bias in the activation function can also be referred to as the bias of the neural network.

[0195] An AI module may include one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0196] In one possible implementation, the AI ​​module can be a RAN intelligent controller (RIC), such as a near-real-time RIC (near-RT RIC) or a non-real-time RIC (non-RT RIC). For example, a near-real-time RIC is located in a RAN node (e.g., in a CU and / or DU), while a non-real-time RIC is located in an OAM, a cloud server, a core network device, or other network device. The RIC can obtain subsets from multiple end devices from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU), reassemble them into a training dataset, and train the model based on the training dataset.

[0197] For example, near real-time RIC and non-real-time RIC can also be set up as separate network elements.

[0198] As shown in Figure 7, the communication system includes a Resource Interchange (RIC). For example, an RIC can be an AI module as shown in Figure 6, used to implement AI-related functions. The RIC includes near-real-time RICs and non-real-time RICs. Near-real-time RICs and / or non-real-time RICs can serve as examples of network devices. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency on the order of tens of milliseconds. Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency on the order of seconds.

[0199] Near real-time (NRT) RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. NRT RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminal devices. This information can be used as training data or inference data. Optionally, the NRT RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, the NRT RIC delivers inference results to a DU, which then forwards them to an RU.

[0200] Non-real-time RICs are also used for model training and inference. For example, they can be used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers inference results to a DU, which then forwards them to an RU.

[0201] Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Alternatively, near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in RAN nodes (e.g., CUs and / or DUs), while non-real-time RICs can be set in OAMs, cloud servers, core network devices, or other network devices.

[0202] Figures 4 to 7 above are examples of communication systems used in the embodiments of this application, and do not actually limit the communication systems that can be applied to the embodiments of this application.

[0203] The communication scheme provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0204] In the accompanying drawings corresponding to the various embodiments of this application, the steps indicated by dashed lines are all optional steps. Furthermore, the first device involved in the various embodiments of this application is, for example, any of the terminal devices involved in Figures 4 to 7. The second device involved in the various embodiments of this application is, for example, one or more of the network device involved in Figure 4, the network device involved in Figure 5, the CU, DU, core network device, access network node, or OAM involved in Figure 6, or one or more of the non-real-time RIC, near-real-time RIC, CU, DU, CU-CP, or RU involved in Figure 7. Alternatively, one of the first and second devices involved in the various embodiments of this application can also be an AI network element, such as the AI ​​network element on the network device side or the terminal device side involved in the description corresponding to Figure 5. In addition, as standards continue to evolve, the names and / or functions of devices may change, which is not limited.

[0205] Please refer to Figure 8, which illustrates a communication method provided in an embodiment of this application. The steps shown in Figure 8 are described below.

[0206] S801, The first device determines the first information set.

[0207] For example, the first information set includes at least one piece of first information. The type of at least one piece of first information includes: normalized predicted received power information, relative received power information, predicted received power ranking information, or predicted received power information, that is, one of A1 to A4 above. The content of the normalized predicted received power information, relative received power information, predicted received power ranking information, or predicted received power information can refer to the content discussed above, and the repeated parts will not be listed here.

[0208] The first device can obtain the first information set from other devices, such as AI network elements or other first devices, which is equivalent to the first device determining the first information set. Alternatively, the first device can determine the first information set itself. Since the type of at least one piece of first information differs, the way the first device determines at least one piece of first information will also differ. The following sections describe cases D1 to D4.

[0209] D1. At least one type of first information is the information shown in A1 above (i.e., normalized predicted received power information).

[0210] Under D1, at least one piece of first information corresponds to (or indicates, or is used to determine) a relative value between a portion or all of the predicted received power in a first predicted received power set and a first reference received power. Each piece of first information in the at least one set of first information may correspond to (or indicate, or is used to determine) a relative value between the predicted received power and the first reference received power. For example, each piece of first information in the at least one set of first information explicitly or implicitly indicates a relative value between the predicted received power and the first reference received power corresponding to each piece of first information. For example, one piece of first information indicates the predicted received power, the first reference received power, and a function for determining the relative value. Thus, the relative value between the predicted received power and the first reference received power can be determined based on this first information. For example, a portion of the predicted received power in the first predicted received power set may be the predicted received power ranked by the top K positions, where K is a positive integer. Alternatively, a portion of the predicted received power in the first predicted received power set may be a portion of the predicted received power corresponding to a portion of the measured received power in the first measured received power set, for example, the resources corresponding to the portion of the measured received power and the portion of the predicted received power are the same. In this application, a portion of the measured received power can be the measured received power ranked in the top M positions, where M is a positive integer. Specifically, in this embodiment, ranking in the top K or top M positions means that the power is sorted from largest to smallest, and the top K or top M positions refer to the top K or top M positions with the largest power.

[0211] The following describes how the content of determining the first information under D1 is illustrated using one of the at least one first information as an example. For ease of explanation, the first information will be referred to as first information #1, which can be any of the at least one first information. Taking, for example, at least one predicted received power in the set of first predicted received power corresponding to first information #1 being the first predicted received power.

[0212] In one possible approach, the first device measures a signal (such as a reference signal) on a second resource set to obtain a second measured received power set. Alternatively, the first device may obtain the second measured received power set from other devices (such as AI network elements). The first device inputs the second measured received power set into a first model to obtain a first predicted received power set corresponding to the first resource set output by the first model. The first model can be deployed on the first device or on a device or network element (such as an AI network element) capable of communicating with the first device; there is no specific limitation on this. Each resource in the first resource set can correspond to a predicted received power in the first predicted received power set.

[0213] The second resource set may be configured by the second device for the first device, or it may be determined by the first device from the first resource set. The second resource set may be, for example, a subset of the resources in the first resource set (or it can be described as a subset of the first resource set), or it may not belong to the first resource set. For example, the first resource set may include narrow beams, and the second resource set may include wide beams. The first resource set is configured by the second device for the first device to receive a first type of reference signal, such as CSI-RS, and the second resource set is configured by the second device for the first device to receive a second type of reference signal, such as SSB. For example, the spatial information of the first and second resource sets may correspond; for instance, a narrow beam may be within the coverage area of ​​a wide beam.

[0214] Optionally, the first resource set may include all beams or reference signal resources corresponding to all beams used for receiving reference signals. This is equivalent to taking into account the predicted received power of the first model on all beams, which is beneficial for more comprehensive monitoring of the first model and improves the accuracy of the first model monitoring.

[0215] After the first device obtains the first predicted received power set, it can also obtain the first predicted received power. The first device can obtain normalized predicted received power information based on the first predicted received power and the first reference received power. For example, the first device determines the relative value between the first predicted received power and the first reference received power.

[0216] For example, the first device performs a subtraction operation between the first predicted received power and the first reference received power, such as subtracting the first reference received power from the first predicted received power; or, it performs a division operation between the first predicted received power and the first reference received power, such as dividing the first predicted received power by the first reference received power. In this way, the normalization processing of the first predicted received power is achieved, thereby determining the first information #1.

[0217] The methods for determining at least one first piece of information other than first information #1 can all refer to the methods for determining the content of first information #1, and will not be listed one by one here. By analogy, the first device can determine the set of first information.

[0218] In one possible design, the first device may preset a first reference received power, pre-configured or pre-defined (such as protocol-predefined) first reference received power, or obtain the first reference received power from the second device. In this implementation, each piece of first information in the first information set corresponds to the relative value of the predicted received power and the first reference received power corresponding to each piece of first information.

[0219] In another possible design, the first device may be determined based on some or all of the first information in at least one set of first information, or the first device may be determined based on some or all of the preset set of first predicted received power in the first predicted received power set.

[0220] For example, the first device determines the first reference received power as the largest received power, the smallest received power, the kth largest received power, the kth smallest received power, or the average of at least one predicted received power in the first predicted received power set. k is a positive integer, such as 1, 2, 3, etc., and the value of k is preset or pre-configured, without limitation. The average of the first predicted received power set can be, for example, an arithmetic mean or a weighted average.

[0221] When the mean of the first predicted received power set is a weighted average, the first device can determine the weighted average corresponding to the first predicted received power set based on the first weight set. The first weight set can be understood as the weight corresponding to each resource in the first resource set, or the weight of each predicted received power set in the first predicted received power set. For example, the larger the predicted received power, the larger its weight in the first weight set; or, the smaller the predicted received power, the smaller its weight in the first weight set. Alternatively, the better the resource in the first weight set, the larger its corresponding weight. A better resource could be, for example, a resource with better signal quality.

[0222] Since the first resource set includes more resources, it is equivalent to considering the model's prediction results for more resources, which is equivalent to considering the model's prediction situation more comprehensively and is conducive to more accurate monitoring of the model.

[0223] Optionally, if the predicted received power corresponding to a certain first information (such as referred to as the first reference information) in at least one first information is the first reference received power, then the first information #1 can be any first information other than the first reference information in at least one first information.

[0224] For example, please refer to Figure 9, which is a schematic diagram of determining the first predicted received power set according to an embodiment of this application. Figure 9 is an example where the first resource set includes beams 1 to N, the second resource set includes beams 1 to W, the second resource set is a part of the first resource set, and the received power is RSRP. N is a positive integer greater than 1, and W is a positive integer less than N.

[0225] As shown in Figure 9, the first device can measure the received power of signals on beams 1 to W, i.e., the second set of measured received power, specifically S_RSRP1, S_RSRP2…S_RSRPW-1, and S_RSRPW as shown in Figure 9. In Figure 9 and subsequent figures, “…” indicates elements that are not fully listed; for example, “…” in Figure 9 indicates an incomplete list of S_RSRP. The first device can input the second set of measured received power into the first model to obtain the first set of predicted received power, specifically P_RSRP1, P_RSRP2…P_RSRPN-1, and P_RSRPN as shown in Figure 9. The first predicted received power can be, for example, a predicted power of a specific beam within the first set of predicted received power, such as P_RSRP2.

[0226] For example, the first predicted received power set includes three predicted received powers, namely 100dB, 108dB, and 90dB. The first reference power can be, for example, the maximum value of these three predicted received powers, namely 108dB. Then at least one first piece of information can indicate: 100 / 108, 1, 90 / 108, where " / " represents division.

[0227] In another possible approach, the first device can directly output the relative value between the first predicted received power and the first reference power through the first model to obtain first information #1, and then obtain the first information set, etc. For example, the first device inputs the second measured received power set into the first model, and the first model directly outputs the relative value of each predicted received power in the first predicted received power set relative to the first reference received power to determine the first information set.

[0228] Under D1, since the first predicted received power set is normalized based on the first reference received power, this can reduce the possibility of large deviations in some predicted received power in the first predicted received power set due to environmental changes (such as large-scale attenuation), which is beneficial for a more accurate monitoring model in the future.

[0229] D2. At least one type of first information is the information shown in A2 above (i.e., first relative received power information).

[0230] Under D2, at least one first piece of information corresponds to (or indicates, or is used to determine) the relative value of at least two predicted received powers in a portion or all of the predicted received powers in the first predicted received power set, for example, the relative value of two predicted received powers. Each of the at least one first piece of information may correspond to (or indicates, or is used to determine) the relative value of a predicted received power with other received powers. For example, each of the at least one first piece of information explicitly or implicitly indicates the relative value of the predicted received power with other received powers. For example, a portion of the predicted received powers in the first predicted received power set may be the predicted received powers ranked in the top K positions, where K is a positive integer. Alternatively, a portion of the predicted received powers in the first predicted received power set may be a portion of the predicted received powers corresponding to a portion of the measured received powers in the first measured received power set, for example, the portion of the measured received powers corresponds to the same resource as the portion of the predicted received powers. Here, a portion of the measured received powers may be the measured received powers ranked in the top M positions, where M is a positive integer. In this embodiment of the application, the sorting as the first K or the first M positions means that the power is sorted from largest to smallest, and the first K or the first M positions refer to the first K or the first M positions with larger power.

[0231] The following describes the determination of the first information under D2, using one of the at least one first information as an example. For ease of explanation, the first information will be referred to as first information #2, which can be any of the at least one first information. The following example illustrates the determination of at least one predicted received power in the first predicted received power set corresponding to first information #2, including both the first predicted received power and the second predicted received power.

[0232] In one possible approach, the first device obtains a first predicted received power set, the contents of which can be obtained as described in D1. The first device can determine a first predicted received power and a second predicted received power within the first predicted received power set, and determine the relative value between the first predicted received power and the second predicted received power. For example, the first device can determine the difference between the first predicted received power and the second predicted received power, the absolute value of the difference, the square of the difference, etc. Alternatively, the first device can determine the ratio between the first predicted received power and the second predicted received power. In this way, the first device can obtain first information #2.

[0233] The methods for determining at least one first piece of information other than first information #2 can all be referenced to determining the content of first information #2, and will not be listed here one by one. By analogy, the set of first information can be determined.

[0234] Wherein, the first predicted received power corresponds to the first resource identifier, and the second predicted received power corresponds to the second resource identifier. Optionally, the second resource identifier may be a resource identifier in the resource identifiers of the first resource set that satisfies a first condition. The first condition may include, for example, that the first resource identifier and the second resource identifier may be two adjacent resource identifiers, or that the second resource identifier may be the resource identifier in the identifiers of the first resource set with the smallest difference from the first resource identifier.

[0235] There may be more than one resource identifier satisfying the first condition in the first resource set. In this case, optionally, the first device can select one of the resource identifiers satisfying the first condition as the second resource identifier, or the first device can also determine multiple relative values, that is, the first information #2 can correspond to multiple relative values, such as a function of these multiple relative values, such as the average value. The multiple relative values ​​are the relative values ​​between the first predicted received power corresponding to the first resource identifier and the predicted received power corresponding to the multiple resource identifiers satisfying the first condition.

[0236] In this way, it is equivalent to selecting the predicted received power with similar resource identifiers for relative value calculation. Since the resource identifiers are similar, it means that the time and frequency locations of the resources are similar, which can reduce the impact of received power offset and fluctuation caused by sudden changes or changes in channel conditions due to the environment to a certain extent, thus facilitating a more accurate monitoring model.

[0237] For example, the identifiers of the first resource sets are 1, 2, 3, and 4, and the first predicted received power sets corresponding to the first resource sets include 108 dB, 100 dB, 90 dB, and 80 dB, respectively. The first device can determine the relative value of the predicted received power corresponding to resource 1 and resource 2, for example, 108 - 100 = 8, and the relative value of the predicted received power corresponding to resource 3 and resource 4, for example, 90 - 80 = 10. At least one piece of first information can indicate the relative value 8, and the relative value 10, etc. Alternatively, the first device can determine the relative value of the predicted received power corresponding to resource 1 and resource 2, for example, 8, the relative value of the predicted received power of resource 2 and resource 3, for example, 10, and the relative value of the predicted received power of resource 3 and resource 4, for example, 10.

[0238] In another possible approach, the first device can directly output the relative values ​​of the first predicted received power and the second predicted received power through the first model to obtain first information #1, and then obtain the first information set, etc. For example, the first device inputs the second measured received power set into the first model, and the first model outputs the relative values ​​of the two predicted received powers in the first predicted received power set to determine the first information set.

[0239] In D2, the predicted received power is compared with the predicted received power to obtain the difference result. This can reduce the impact of predicted received power offset and fluctuation caused by changes in power output or channel conditions due to the environment, which is beneficial for more accurate monitoring of the model in the future.

[0240] D3. At least one type of first information is the information shown in A3 above (i.e., predicted received power ranking information).

[0241] Under D3, at least one first piece of information corresponds to (or indicates, or is used to determine) the ranking result of some or all of the predicted received powers in the first predicted received power set, or corresponds to the ranking result of resource identifiers corresponding to some or all of the resources in the first resource set based on the predicted received powers. Each of the at least one first piece of information may correspond to (or indicate, or is used to determine) the measured received power ranking information. For example, each of the at least one first piece of information explicitly or implicitly indicates at least one ranking information of the predicted received powers. For example, a portion of the predicted received powers in the first predicted received power set may be the predicted received powers ranked in the top K positions, where K is a positive integer. Alternatively, a portion of the predicted received powers in the first predicted received power set may be a portion of the predicted received powers corresponding to a portion of the measured received powers in the first measured received power set, for example, the portion of the measured received powers corresponds to the same resource as the portion of the predicted received powers. Here, a portion of the measured received powers may be the measured received powers ranked in the top M positions, where M is a positive integer. In this embodiment of the application, the sorting as the first K or the first M positions means that the power is sorted from largest to smallest, and the first K or the first M positions refer to the first K or the first M positions with larger power.

[0242] The following describes the determination of the first information under D3, using one of the at least one first information as an example. For ease of explanation, the first information will be referred to as first information #3, which can be any of the at least one first information. The following example illustrates that at least one predicted received power in the first predicted received power set corresponding to first information #3 includes a third predicted received power and one or more fourth predicted received powers. The one or more fourth predicted received powers can be some or all of the predicted received powers in the first predicted received power set, excluding the third predicted received power.

[0243] In the first possible design, if the predicted received power ranking information includes the ranking information of the predicted received power, then the first information #3 corresponds to the ranking information of the third predicted received power relative to one or more fourth predicted received powers. The ranking information of the third predicted received power relative to one or more fourth predicted received powers can indicate the ranking result of the third predicted received power with one or more fourth predicted received powers, or it can indicate the ranking result of the third predicted received power among the third predicted received power and one or more fourth predicted received powers (such as sequence number or ranking position).

[0244] For example, if the sorting information for the predicted received power corresponds to (or indicates, or is used to determine) the results of arranging the predicted received power in a first order, then the first device determines the result of sorting the third predicted received power and one or more fourth predicted received powers in the first order, and determines first information #3, which corresponds to (or indicates, or is used to determine) the sorting information of the third predicted received power relative to one or more fourth predicted received powers. Optionally, the first information #3 also indicates the resource identifiers associated with the third predicted received power and one or more fourth predicted received powers, respectively. Wherein, the resource identifier corresponding to the third predicted received power is a third resource identifier, and the resource identifiers corresponding to one or more fourth predicted received powers are one or more fourth resource identifiers.

[0245] In the second possible design, if the predicted received power ranking information includes the ranking information of resource identifiers corresponding to the measured received power, then the first device can determine first information #3 based on the result of arranging the third resource identifier and one or more fourth resource identifiers in a first order. First information #3 corresponds to (or indicates, or is used to determine) the ranking information of the third resource identifier relative to one or more fourth resource identifiers. The ranking information of the third resource identifier relative to one or more fourth resource identifiers can indicate the ranking result of the third resource identifier with respect to one or more fourth resource identifiers, or it can indicate the ranking result of the third resource identifier among the third resource identifier and one or more fourth resource identifiers, such as a sequence number, which can be called an index.

[0246] The methods for determining at least one piece of first information other than first information #3 can all refer to the methods for determining the content of first information #3, and will not be listed one by one here. By analogy, the first device can determine the set of first information.

[0247] For example, the third predicted received power is 100dB, a fourth predicted received power is 20dB, the third resource identifier is 3, and a fourth resource identifier corresponds to 4.

[0248] The first information #3 can correspond to (3,4), meaning the third resource identifier precedes the fourth resource identifier; or the first information #3 can correspond to (100,20) or (3,100; 4,20), meaning the third predicted received power precedes a fourth predicted received power. Alternatively, the first information #3 can correspond to (4,3), meaning the third resource identifier follows a fourth resource identifier; or the first information #3 can correspond to (4,20; 3,100), meaning the third predicted received power follows a fourth predicted received power.

[0249] For example, the third predicted received power is 100dB, and the two fourth predicted received powers are 20dB and 10dB respectively. The third resource identifier is 3, and the two fourth resource identifiers correspond to 4 and 5.

[0250] The first information #3 can correspond to or indicate index 1. For example, it can include index 1, indicating that the third predicted received power is ranked first among the third predicted received power and one or more fourth predicted received powers in descending order of predicted received power, or that the third resource identifier is ranked first among the third resource identifier and one or more fourth resource identifiers in descending order of predicted received power. The first information #3 can also correspond to or indicate index 3. For example, it can include index 3, indicating that the third predicted received power is ranked third among the third predicted received power and one or more fourth predicted received powers in ascending order of predicted received power, or that the third resource identifier is ranked third among the third resource identifier and one or more fourth resource identifiers in ascending order of predicted received power.

[0251] In D3, the predicted received power is sorted. This avoids focusing too much on the magnitude of the power itself, reduces the impact of some predicted received power with large errors, and is conducive to more accurate monitoring of the model in the future.

[0252] D4. At least one type of first information is the information shown in A4 above (i.e., predicted received power information).

[0253] Under D4, at least one first piece of information corresponds to (or indicates, or is used to determine) a portion or all of the predicted received power in the first predicted received power set. Each of the at least one first piece of information may correspond to (or indicate, or is used to determine) one or more predicted received power information. For example, each of the at least one first piece of information explicitly or implicitly indicates at least one predicted received power, or a compensation result of at least one predicted received power. For example, a portion of the predicted received power in the first predicted received power set may be the predicted received power ranked in the top K positions, where K is a positive integer; or, a portion of the predicted received power in the first predicted received power set may be a portion of the predicted received power corresponding to a portion of the measured received power in the first measured received power set, for example, the resources corresponding to the portion of the measured received power and the portion of the predicted received power are the same. A portion of the measured received power may be the measured received power ranked in the top M positions, where M is a positive integer. In the embodiments of this application, ranking in the top K or top M positions means that the power is sorted from largest to smallest, and the top K or top M positions refer to the top K or top M positions with larger power.

[0254] If each piece of information in at least one first piece of information corresponds to at least one predicted received power, then the first device determines the first set of information after determining the first set of predicted received power.

[0255] If each piece of information in at least one set of first information corresponds to at least one compensation result for a predicted received power, then the first device can compensate for each predicted received power in the first set of predicted received power based on a first power compensation value. For example, the first device can subtract the first power compensation value from each predicted received power in the first set of predicted received power, or add the first power compensation value to each predicted received power, to obtain the first set of information. Alternatively, the first device can also obtain at least one set of first information by outputting the compensation result for each set of predicted received power in the first set of predicted received power through a first model.

[0256] The first device may have a pre-stored first power compensation value, or may obtain the first power compensation value from the second device. For example, the first device may obtain first indication information from the second device, which is used to determine the first power compensation value. For example, the first indication information may explicitly or implicitly indicate the first power compensation value.

[0257] For example, the first indication information indicates other information, and the first device determines the first power compensation value based on the other information. Specifically, for example, the first indication information indicates the actual transmission power of the signal of the second device, and the first device determines the first power compensation value based on the actual transmission power and the transmission power predicted by the first model. The actual transmission power information may include, for example, the synchronization signal-physical broadcasting channel-block power (SS-PBCH-BlockPower) and / or the power control offset synchronization signal (PowerControlOffsetSS). For example, if the transmission power information predicted by the first model is X dBm, and the transmission power information of the second device is Y dBm, then the first power compensation value is (YX) dBm.

[0258] In one possible implementation, under any of the scenarios shown in D1 to D3 above, before determining any first information, the first device can compensate for each predicted received power in the predicted received power of the signal corresponding to the first resource set predicted by the first model based on the first power compensation value, to obtain a first predicted received power set. That is, the first predicted received power set can be the result of compensation based on the first power compensation value. The first device can determine any of the first information sets in D1 to D3 based on the first predicted received power set. The content of the first power compensation value and the method of compensating for the predicted received power can refer to the content of the first power compensation value and the content of compensating for the predicted received power discussed in D4, and will not be listed here.

[0259] To monitor the model more comprehensively, the first device may optionally determine a third set of information. The content of the third set of information can be referenced from the previously discussed content of the third set of information; any repetitions will not be listed here.

[0260] The first device may also obtain the third information set from other devices (such as other first devices), or determine the third information set itself. The method by which the first device determines the third information set differs depending on the type of at least one piece of third information included in the third information set. These methods will be described below in conjunction with E1 to E4.

[0261] E1, at least one third piece of information is of the type shown in B1 above (i.e., normalized measured received power information).

[0262] Under E1, at least one third piece of information corresponds to (or indicates, or is used to determine) a relative value between a portion or all of the measured received power in the first set of measured received power and a second reference received power. Each of the at least one third piece of information may correspond to (or indicate, or is used to determine) a relative value between the measured received power and the second reference received power. For example, each of the at least one third piece of information explicitly or implicitly indicates a relative value between the predicted received power and the second reference received power corresponding to each of the third pieces of information. For example, a portion of the measured received power in the first set of measured received power may be the measured received power on a resource corresponding to a portion of the predicted received power in the first set of predicted received power. For example, a portion of the predicted received power in the first set of predicted received power may be the predicted received power ranked in the top K positions, where K is a positive integer. Alternatively, a portion of the measured received power in the first set of measured received power may be the measured received power ranked in the top M positions, where M is a positive integer. In this embodiment of the application, the sorting as the first K or the first M positions means that the power is sorted from largest to smallest, and the first K or the first M positions refer to the first K or the first M positions with larger power.

[0263] The following describes how the content of the third information is determined under E1, using one of the at least one third information as an example. For ease of explanation, the third information will be referred to as third information #1, which can be any of the at least one third information. Taking the example that at least one measured received power in the first measured received power set corresponding to third information #1 is the first measured received power.

[0264] For example, the first device measures a signal on a first resource set to obtain a first measured received power set. The contents of the first resource set can refer to the contents of the first resource set discussed above, and will not be repeated here. The first device can determine the relative value between the first measured received power and the second reference received power in the first measured received power set to obtain third information #1. The method for determining the relative value between the first measured received power and the second reference received power can refer to the content of determining the relative value between the first predicted received power and the first reference received power discussed above, and will not be repeated here.

[0265] The methods for determining any third information other than third information #1 can be the same as those for determining the content of third information #1, and will not be listed here one by one. Similarly, the first device can determine the set of third information.

[0266] In one possible design, the second reference received power can be preset, preconfigured, or predefined (e.g., protocol-predefined), or indicated by the second device to the first device. In this implementation, each piece of third information in the third information set corresponds to the relative value between the predicted received power and the second reference received power corresponding to each piece of third information.

[0267] In another possible design, the second reference received power may be determined by the first device based on some or all of the third information in at least one third information (or first information set) pair, or it may be determined by the first device based on some or all of the measured received power set in the first measured received power set.

[0268] For example, the second reference received power is the largest received power, the smallest received power, the j-th largest received power, the j-th smallest received power, or the average of at least one measured received power in the first set of measured received power. j is a positive integer, such as 1, 2, 3, etc. The value of j is preset or pre-configured and is not limited.

[0269] If the mean of the first set of measured received power is a weighted average, the first device can also use a second set of weights to determine the weighted average corresponding to the first set of measured received power. The content of the second set of weights can refer to the content of the first set of weights mentioned above, and will not be listed here again. The second set of weights and the first set of weights can be the same.

[0270] If the measured received power corresponding to a certain third information (such as referred to as the second reference information) in at least one of the first information is the second reference received power, then the third information #1 can be any third information other than the second reference information in at least one of the third information.

[0271] For example, the first set of measured received power includes three measured received power values ​​of 99dB, 100dB, and 85dB. The second reference power can be, for example, the maximum value of these three measured received power values, i.e., 100dB. Then at least one third piece of information can indicate: 90 / 100, 1, 85 / 100, where " / " represents division.

[0272] Under E1, since the first measured received power set is normalized based on the second reference received power, this reduces the possibility of large deviations in some measured received power values ​​within the first measured received power set due to environmental changes (such as large-scale attenuation). Furthermore, the first resource set includes all beams or reference signal resources used for receiving reference signals, which is equivalent to considering the predicted received power of the first model on all beams, as well as the corresponding measured predicted received power. This facilitates more comprehensive monitoring of the first model and improves the accuracy of first model monitoring.

[0273] E2, at least one third piece of information is of the type shown in B2 above (i.e., second relative received power information).

[0274] Under E2, at least one third piece of information corresponds to (or indicates, or is used to determine) the relative value of at least two measured received powers in a portion or all of the measured received powers in the first set of measured received powers. Each of the at least one third piece of information may correspond to (or indicate, or is used to determine) the relative value of a measured received power with other received powers. For example, each of the at least one third piece of information explicitly or implicitly indicates the relative value of one measured received power with another measured received power. The content of the relative value can be referred to the content of relative values ​​above, and will not be listed here. For example, a portion of the measured received powers in the first set of measured received powers may be the measured received powers on the resource corresponding to a portion of the predicted received powers in the first set of predicted received powers. For example, a portion of the predicted received powers in the first set of predicted received powers may be the predicted received powers ranked in the top K positions, where K is a positive integer. Alternatively, a portion of the measured received powers in the first set of measured received powers may be the measured received powers ranked in the top M positions, where M is a positive integer. In this application, the sorting as the first K or first M positions refers to the power being sorted from largest to smallest, and the first K or first M positions refer to the first K or first M positions with the larger power.

[0275] The following describes how the content of the third information is determined under E2, using one of the at least one third information as an example. For ease of explanation, the third information will be referred to as third information #2, which can be any of the at least one third information. Taking the example that at least one measured received power in the first measured received power set corresponding to third information #2 is the first measured received power and the second measured received power.

[0276] The first device obtains a first set of measured received power values. The content of this first set of measured received power values ​​can be found in section E1. The first device can determine the relative value between the first measured received power and the second measured received power in the first set of measured received power values, thus determining the third information #2. The methods for determining any third information other than third information #2 can be referenced to determining the content of third information #2, and will not be listed here individually. By analogy, the set of third information values ​​can be determined.

[0277] Optionally, the first measured received power corresponds to the first resource identifier, and the second measured received power corresponds to the second resource identifier. The contents of the first and second resource identifiers can be referred to the contents of the first and second resource identifiers discussed in D2 above. In the case where the first information #2 corresponds to multiple relative values, the third information #2 also corresponds to multiple relative values. These multiple relative values ​​are the relative values ​​between the first measured received power corresponding to the first resource identifier and the measured received power corresponding to the multiple resource identifiers that meet the first condition.

[0278] For example, if the identifiers of the first resource set are 1, 2, 3, and 4, and the first measured received power sets corresponding to the first resource set include 100dB, 107dB, 90dB, and 88dB respectively, then the first device can determine the relative value of the measured received power corresponding to resource 1 and resource 2, for example, 100-107=-7, and the relative value of the measured received power corresponding to resource 3 and resource 4, for example, 90-88=2. At least one third piece of information can indicate the relative value 7, and the relative value 2, etc. Alternatively, at least one third piece of information can indicate the relative value of the measured received power corresponding to resource 1 and resource 2, the relative value of the measured received power corresponding to resource 2 and resource 3, and the relative value of the measured received power corresponding to resource 3 and resource 4.

[0279] E3, at least one third piece of information is of the type shown in B3 above (i.e., measured received power sorting information).

[0280] Under E3, at least one third piece of information corresponds to (or indicates, or is used to determine) the ranking result of some or all of the measured received powers in the first measured received power set, or corresponds to the ranking result of resource identifiers corresponding to some or all resources in the first resource set based on the measured received power. Each of the at least one third piece of information may correspond to (or indicate, or is used to determine) the measured received power ranking information. For example, each of the at least one third piece of information explicitly or implicitly indicates at least one ranking information of the measured received power. For example, a portion of the measured received power in the first measured received power set may be the measured received power on the resource corresponding to a portion of the predicted received power in the first predicted received power set. For example, a portion of the predicted received power in the first predicted received power may be the predicted received power ranked in the top K positions, where K is a positive integer. Alternatively, a portion of the measured received power in the first measured received power set may be the measured received power ranked in the top M positions, where M is a positive integer. In the embodiments of this application, ranking in the top K or top M positions means that the power is ranked from largest to smallest, and the top K or top M positions refer to the top K or top M positions with larger power.

[0281] The following describes how the content of the third information is determined under E2, using one of the at least one third information as an example. For ease of explanation, the third information will be referred to as third information #3, which can be any of the at least one third information. Taking the example that at least one measured received power in the first measured received power set corresponding to third information #3 is a third measured received power and one or more fourth measured received powers, the one or more fourth predicted received powers can be some or all of the predicted received powers in the first predicted received power set, excluding the third predicted received power.

[0282] In the first possible design, if the measured received power sorting information includes the sorting information of the measured received power, then the first information #3 corresponds to the sorting information of the third measured received power relative to one or more fourth measured received powers. The sorting information of the third measured received power relative to one or more fourth measured received powers can indicate the sorting result of the third measured received power with one or more fourth measured received powers, or it can indicate the sorting result of the third measured received power among the third measured received power and one or more fourth measured received powers (such as sequence number or sorting position).

[0283] For example, if the sorting information for the measured received power corresponds to (or indicates, or is used to determine) the results of arranging the measured received power in a first order, then the first device sorts the third measured received power and one or more fourth measured received powers in the first order, and determines third information #3. Third information #3 corresponds to (or indicates, or is used to determine) the sorting information of the third measured received power relative to the one or more fourth measured received powers. Optionally, third information #3 also indicates the resource identifiers associated with the third measured received power and the one or more fourth measured received powers, respectively. Wherein, the resource identifier corresponding to the third measured received power is a third resource identifier, and the resource identifiers corresponding to the one or more fourth measured received powers are one or more fourth resource identifiers.

[0284] In the second possible design, if the sequence information for measured received power includes the sequence information of resource identifiers corresponding to the measured received power, then the first device can determine third information #3 by sorting the third resource identifier and one or more fourth resource identifiers according to a first order. Third information #3 corresponds to (or indicates, or is used to determine) the sequence information of the third resource identifier relative to one or more fourth resource identifiers, determined based on the second order. The sequence information of the third resource identifier relative to one or more fourth resource identifiers can indicate the sequence result of the third resource identifier and one or more fourth resource identifiers, or it can indicate the sequence result of the third resource identifier among the third resource identifier and one or more fourth resource identifiers (e.g., a sequence number).

[0285] The methods for determining any third information other than third information #3 can be the same as those for determining the content of third information #3, and will not be listed here one by one. Similarly, the first device can determine the set of third information.

[0286] For example, if the third measured received power is 109 dB, a fourth measured received power is 20 dB, the third resource identifier is 3, and the fourth resource identifier is 4, then the third information #3 can correspond to (3,4), meaning the third resource identifier precedes one or more fourth resource identifiers; or the third information #3 can correspond to (109,20) or (3,109; 4,20), meaning the third measured received power precedes a fourth measured received power. Alternatively, the third information #3 can correspond to (4,3), meaning the third resource identifier follows a fourth resource identifier; or the third information #3 can correspond to (4,20; 3,109), meaning the third measured received power follows a fourth measured received power.

[0287] Alternatively, for example, the third measured received power is 109 dB, one or more fourth measured received powers are 20 dB and 5 dB respectively, the third resource identifier is 3, and one or more fourth resource identifiers are 4 and 5 respectively. Third information #3 can correspond to or indicate index 1, such as including index 1, meaning the third measured received power is ranked first among the third measured received power and one or more fourth measured received powers in descending order of measured received power, or the third resource identifier is ranked first among the third resource identifier and one or more fourth resource identifiers in descending order of measured received power. Third information #3 can correspond to or indicate index 3, such as including index 3, meaning the third measured received power is ranked third among the third measured received power and one or more fourth measured received powers in ascending order of measured received power, or the third resource identifier is ranked third among the third resource identifier and one or more fourth resource identifiers in ascending order of measured received power.

[0288] E4. At least one third piece of information is of the type shown in B4 above (i.e., measured received power information).

[0289] Under E4, at least one third piece of information corresponds to (or indicates, or is used to determine) a portion or all of the measured received power in the first measured received power set. Each of the at least one third piece of information may correspond to (or indicate, or is used to determine) measured received power information. For example, each of the at least one third piece of information explicitly or implicitly indicates at least one measured received power, or a compensation result for at least one measured received power. For example, a portion of the measured received power in the first measured received power set may be the measured received power on the resource corresponding to a portion of the predicted received power in the first predicted received power set. For example, a portion of the predicted received power in the first predicted received power may be the predicted received power ranked in the top K positions, where K is a positive integer. Alternatively, a portion of the measured received power in the first measured received power set may be the measured received power ranked in the top M positions, where M is a positive integer. In the embodiments of this application, being ranked in the top K or top M positions means that the power is sorted from largest to smallest, and the top K or top M positions refer to the top K or top M positions with the largest power.

[0290] If each piece of information in at least one third piece of information corresponds to or is used to determine at least one measured received power, then after the first device determines the first set of measured received power, it can also determine the set of third information.

[0291] If each piece of information in at least one set of third information corresponds to a compensation result for at least one measured received power, then the first device can compensate for each measured received power in the first set of measured received power based on the second power compensation value. For example, subtracting the second power compensation value from each measured received power, or adding the second power compensation value to each measured received power, etc., to obtain the third set of information.

[0292] For example, if a measured received power in the first set of measured received power is the fifth measured received power, then the measured received power indicated by the third information in the third set (such as the sixth measured received power) differs from the fifth measured received power by a second power compensation value.

[0293] The first device may have a second power compensation value pre-stored, or may obtain the second power compensation value from the second device. For example, the first device may obtain second indication information from the second device, which is used to determine the second power compensation value. For example, the second indication information may explicitly or implicitly indicate the second power compensation value, without specific limitation. The second power compensation value may be the same as or different from the first power compensation value, without limitation.

[0294] S802, The first device determines the first reporting information based on the first information set.

[0295] The content of the first reported information can be referred to the previous discussion, and the repetitions will not be listed again. The following is an introduction to the method of determining the first reported information.

[0296] F1. The first reported information is determined based on the first information set.

[0297] In one possible design, the first reported information includes a first information set. Under this design, the contents of the first information set are the same as the contents of the corresponding first reported information, which will not be listed here.

[0298] In another possible design, the first reported information is obtained by processing the first information set, as illustrated below.

[0299] For example, if the first information set includes at least one first information indicating the first predicted received power set, then the first device can compensate the first predicted received power set based on the first power compensation value to obtain the first reported information, that is, the first reported information indicates the compensation result of the first predicted received power set.

[0300] For example, the first reported information may include at least one second piece of information that corresponds one-to-one with at least one first piece of information. Specifically, one of the at least one second piece of information is used to indicate the compensation result of the predicted received power corresponding to a certain first piece of information. It can also be described as the difference between the received power corresponding to a second piece of information and the predicted received power corresponding to the first piece of information being a first power compensation value. Correspondingly, in this case, the resource identifier corresponding to the second piece of information is the same as the resource identifier corresponding to the first piece of information.

[0301] In F1, the first reported information can be the inference result of the corresponding (or indication, or used to determine) model.

[0302] For example, the inference results included in the first reported information can be all or part of the model's total inference information (i.e., prediction information). For instance, it could be the top K1 inference results from the model's inference results, i.e., the inference results, such as the inference information of the top K1 values ​​with the largest RSRP values. For example, the inference information can include the inference results and information about the resources corresponding to the inference results, such as resource identifiers. The inference results can be the aforementioned predicted received power. K1 is a positive integer.

[0303] F2. The first reported information is determined based on the first information set and the third information set. Alternatively, it can be described as the first reported information being associated with the first information set and the third information set.

[0304] For example, the first reported information indicates (or is used to determine) a first information set and a third information set, etc. For example, the first reported information includes a first information set and a second information set.

[0305] Alternatively, the first reported information indicates (or is used to determine) the degree of difference between the first information set and the third information set. This can also be described as the degree of difference between each pair of information in at least one pair of information, or it can be understood as the degree of difference between the predicted received power corresponding to the first information in each pair of information and the measured received power corresponding to the third information in each pair of information. The content of the at least one pair of information can refer to the content of the at least one pair of information discussed above, and repetitions will not be listed again. For example, one pair of information in the at least one pair of information includes first information #1 and third information #1; or, one pair of information in the at least one pair of information includes first information #2 and third information #2; or, one pair of information in the at least one pair of information includes first information #3 and third information #3.

[0306] Alternatively, the first reported information indicates (or is used to determine) the degree of similarity (or similarity) between the first information set and the third information set. This can also be described as the degree of similarity between each pair of information in at least one pair of information, or it can be understood as the degree of similarity between the predicted received power corresponding to the first information in each pair of information and the measured received power corresponding to the third information in each pair of information.

[0307] The following provides an example of the content of the first reported information. The first reported information may include at least one of the following G1 to G4. Alternatively, G1 to G4 can also be considered as several ways to determine the first reported information.

[0308] G1. The first reported information corresponds to (indicates or is used to determine) at least one of the following: the difference, the absolute value of the difference, the square of the difference, or the compensation result of the difference for each pair of at least one pair of information. For example, each second piece of information in the first reported information indicates or is used to determine at least one of the following: the difference, the absolute value of the difference, or the square of the difference for each pair of at least one pair of information. Alternatively, the first reported information is obtained based on, or related to, the difference in each pair of at least one pair of information.

[0309] For example, at least one pair of information may be at least one pair of information consisting of all predicted received power in the first predicted received power set and all measured received power in the first measured received power set, or at least one pair of information consisting of a portion of the predicted received power in the first predicted received power set and a portion of the measured received power in the first measured received power set.

[0310] The difference between each pair of information refers to the difference between the content indicated by the first information in the pair and the content indicated by the third information in the pair. The following example illustrates this using at least one pair of information including first information #4 and third information #4. Here, first information #4 is any one of at least one first information, and third information #4 is at least one third information corresponding to the first information #4.

[0311] G1-1, the type of the first information #4 is the information shown in A1 above (i.e., the normalized predicted received power information), and the type of the third information #4 is the information shown in B1 above (i.e., the normalized measured received power information). Then the difference between the first information #4 and the third information #4 can be the difference between the normalized predicted received power indicated by the first information #4 and the normalized measured received power indicated by the third information #4.

[0312] For example, please refer to Figure 10, which is a schematic diagram of determining the first reported information according to an embodiment of this application. As shown in Figure 10, the first measured received power set includes the measured received power corresponding to beam 1 to beam N, as shown in Figure 10 as S_RSRP1, S_RSRP2...S_RSRPN-1, S_RSRPN. The first predicted received power set includes the measured received power corresponding to beam 1 to beam N, as shown in Figure 10 as P_RSRP1, P_RSRP2...P_RSRPN-1, P_RSRPN. In Figure 10, "VS" represents a comparison operation, such as difference calculation.

[0313] The first device normalizes the first measured received power set to obtain at least one third piece of information. This third piece of information may indicate the normalized first measured received power set, such as N_S_RSRP1, N_S_RSRP2...N_S_RSRPN-1, N_S_RSRPN as shown in Figure 10. Similarly, the first device normalizes the first predicted received power set to obtain at least one first piece of information. This first piece of information may indicate the normalized first predicted received power set, such as N_P_RSRP1, N_P_RSRP2...N_P_RSRPN-1, N_P_RSRPN as shown in Figure 10. The first reported information may then indicate the difference between N_S_RSRP1 and N_P_RSRP1, the difference between N_S_RSRP2 and N_P_RSRP2, etc.

[0314] G1-2, the type of the first information #4 is the information shown in A2 above (i.e., the first relative received power information), and the type of the third information #4 is the information shown in B2 above (i.e., the second relative received power information). Then the difference between the first information #4 and the third information #4 can be the difference between the relative received power indicated by the first information #4 and the relative received power indicated by the third information #4.

[0315] For example, please refer to Figure 11, which is a schematic diagram of determining the first reported information according to an embodiment of this application. As shown in Figure 11, the first measured received power set includes the measured received power corresponding to beam 1 to beam N, as shown in Figure 11 as S_RSRP1, S_RSRP2...S_RSRPN-1, S_RSRPN. The first predicted received power set includes the measured received power corresponding to beam 1 to beam N, as shown in Figure 11 as P_RSRP1, P_RSRP2...P_RSRPN-1, P_RSRPN. In Figure 11, "VS" represents a comparison operation, such as difference calculation.

[0316] The first device determines the difference in measured received power between two adjacent resource identifiers in a first set of measured received power, obtaining at least one piece of first information. This is exemplified by determining the difference in measured received power between a resource identifier and a resource identifier greater than and adjacent to that resource identifier (e.g., the difference in measured received power between beam 1 and beam 2, the difference in received power between beam 3 and beam 4, and so on). At least one piece of third information indicates, for example, multiple relative received powers. For instance, the first device determines the differences between S_RSRP1 and S_RSRP2, and between S_RSRP3 and S_RSRP4, and between S_RSRPN-3 and S_RSRPN-2, and between S_RSRPN-1 and S_RSRPN, and so on, obtaining Δs1, Δs2…ΔsM-1 and ΔsM as shown in Figure 11. M is a positive integer. Similarly, the first device determines the difference in predicted received power between two adjacent resource identifiers in a first set of predicted received power. This example illustrates determining the difference in predicted received power between a given resource identifier and an adjacent resource identifier (e.g., the difference in predicted received power between beam 1 and beam 2, beam 3 and beam 4, and so on). For instance, the first device determines the differences between P_RSRP1 and P_RSRP2, P_RSRP3 and P_RSRP4, P_RSRPN-3 and P_RSRPN-2, P_RSRPN-1 and P_RSRPN, and so on, obtaining at least one piece of first information. This first piece of first information may indicate Δp1, Δp2, ..., ΔpM-1 and ΔpM. The first reported information could then indicate the difference between Δs1 and Δp1, the difference between Δs2 and Δp2, etc.

[0317] G1-3, the type of the first information #4 is the information shown in A3 above (i.e., predicted received power ranking information), and the type of the third information #4 is the information shown in B3 above (i.e., measured received power ranking information). Then the difference between the first information #4 and the third information #4 can be the difference between the ranking indicated by the first information #4 and the ranking indicated by the third information #4.

[0318] For example, if the sorting result of the predicted received power corresponding to the first information #4 is the same as the sorting result of the measured received power corresponding to the third information #4, then the difference between the sorting indicated by the first information #4 and the sorting indicated by the third information #4 can be 0. If there are U different sorting results between the sorting result of the predicted received power corresponding to the first information #4 and the sorting result of the measured received power corresponding to the third information #4, then the difference between the sorting indicated by the first information #4 and the sorting indicated by the third information #4 can be U, where U is a positive integer. U can also be understood as the number of different sorting positions of the received power corresponding to the same resource identifier.

[0319] For example, the predicted received power order for the first information #4 is (1, 100; 2, 200), meaning the predicted received power for resource identifier 1 is 100, and the predicted received power for resource identifier 2 is 200. The predicted received power order for the third information #4 is (2, 101; 1, 202), meaning the predicted received power for resource identifier 2 is 101, and the predicted received power for resource identifier 1 is 202. Therefore, there are two different ordering results for the first and third information #4, meaning the difference between the first and third information #4 is 2.

[0320] G1-4, the type of the first information #4 is the information shown in A4 above (i.e., predicted received power information), and the type of the third information #4 is the information shown in B4 above (i.e., measured received power information). Then the difference between the first information #4 and the third information #4 can be the difference between the predicted received power indicated by the first information #4 and the measured received power indicated by the third information #4 (as referred to as the first difference).

[0321] In one possible implementation, the first device can compensate for the difference determined by any of the methods G1-1 to G1-4 above based on the third power compensation value, to obtain a compensation result for the difference. This compensation result is used to determine the first reporting information. The method by which the first device obtains the third power compensation value can also refer to the method by which the first device obtains the first power compensation value, and will not be listed here.

[0322] For example, under G1-4, after determining the first difference, the first device can compensate for the first difference based on the third power compensation value to obtain the first reported information. For example, the first reported information corresponds to the sum of the first difference and the third power compensation value, or the difference between the first difference and the third power compensation value, etc.

[0323] G2. The first reported information indicates or is used to determine statistical information such as the mean, variance, and standard deviation of multiple differences. These multiple differences include the difference between each pair of information in at least one pair, where at least one pair includes two or more pairs. Alternatively, the first reported information is derived from, or related to, statistical information about multiple differences.

[0324] For example, at least one pair of information may be at least one pair of information consisting of all predicted received power in the first predicted received power set and all measured received power in the first measured received power set, or at least one pair of information consisting of a portion of the predicted received power in the first predicted received power set and a portion of the measured received power in the first measured received power set.

[0325] G2 can be understood as the first device performing further statistical processing on the difference between each pair of information in at least one pair of information shown in G1 to obtain the first reported information.

[0326] Continuing with the example shown in Figure 10, the first reported information can indicate the difference between N_S_RSRP1 and N_P_RSRP1, and the statistical information corresponding to the difference between N_S_RSRP2 and N_P_RSRP2.

[0327] The first reported information under G1 or G2 can be regarded as indicating the degree of difference between the first information set and the third information set.

[0328] G3. The first reported information indicates or is used to determine the degree of matching, i.e., the degree of similarity, or the degree of difference, of each pair of information in at least one pair of information. In other words, the first reported information is obtained based on the degree of matching of each pair of information in at least one pair of information, or is related to the degree of matching of each pair of information in at least one pair of information.

[0329] For example, at least one pair of information may be at least one pair of information consisting of all predicted received power in the first predicted received power set and all measured received power in the first measured received power set, or at least one pair of information consisting of a portion of the predicted received power in the first predicted received power set and a portion of the measured received power in the first measured received power set.

[0330] The following is an example of how to determine the first reported information under G3.

[0331] G3-1, the type of the first information #4 is the information shown in A1 above (i.e., the normalized predicted received power information), and the type of the third information #4 is the information shown in B1 above (i.e., the normalized measured received power information).

[0332] The first device can determine the difference between the first information #4 and the third information #4, for example, the difference between the normalized predicted received power indicated by the first information #4 and the normalized measured received power indicated by the third information #4.

[0333] The degree of matching can be expressed directly as the difference. Alternatively, if the difference is greater than a first threshold, the degree of matching between the first information #4 and the third information #4 can be considered to be 1; or, if the difference is less than or equal to the first threshold, the degree of matching between the first information #4 and the third information #4 can be considered to be 0. Alternatively, the degree of matching can be the ratio of the difference to the normalized predicted received power indicated by the first information #4. Alternatively, the degree of matching can be the ratio of the difference to the mean, which is, for example, the mean of the normalized predicted received power indicated by the first information #4 and the normalized predicted received power indicated by the third information #4.

[0334] G3-2, the type of the first information #4 is the information shown in A2 above (i.e., the first relative received power information), and the type of the third information #4 is the information shown in B2 above (i.e., the second relative received power information).

[0335] The first device determines the difference between the first information #4 and the third information #4, for example, the difference between the relative received power indicated by the first information #4 and the relative received power indicated by the third information #4. The method for determining the degree of matching based on this difference can refer to the content on determining the degree of matching based on the difference discussed in G3-1 above.

[0336] G3-3, the type of the first information #4 is the information shown in A3 above (i.e., predicted received power ranking information), and the type of the third information #4 is the information shown in B3 above (i.e., measured received power ranking information).

[0337] The first device determines that the difference between the first information #4 and the third information #4 can be the difference between the order indicated by the first information #4 and the order indicated by the third information #4. The method for determining the degree of matching based on this difference can refer to the content on determining the degree of matching based on the difference discussed in G3-1 above. Optionally, if the order indicated by the first information #4 is the same as the order indicated by the third information #4, then the degree of matching between the first information #4 and the third information #4 can be considered to be 1; if the order indicated by the first information #4 is different from the order indicated by the third information #4, then the degree of matching between the first information #4 and the third information #4 can be considered to be 0.

[0338] G3-4, the first information #4 is of the type shown in A4 above (i.e., predicted received power information), and the third information #4 is of the type shown in B4 above (i.e., measured received power information).

[0339] The first device determines that the difference between the first information #4 and the third information #4 can be the difference between the predicted received power indicated by the first information #4 and the measured received power indicated by the third information #4. The method for determining the degree of matching based on this difference can refer to the discussion on determining the degree of matching based on the difference in section G3-1 above.

[0340] G4. The first reported information indicates or is used to determine multiple matching degrees. Multiple matching degrees here include the matching degree of each pair of information in at least one pair, where at least one pair of information includes two or more pairs of information. Alternatively, the first reported information is based on multiple matching degrees, such as statistical information on multiple matching degrees, or is related to multiple matching degrees and statistical information on multiple matching degrees.

[0341] For example, at least one pair of information can be at least one pair of information consisting of all predicted received powers in the first predicted received power set and all measured received powers in the first measured received power set, or at least one pair of information consisting of a portion of the predicted received powers in the first predicted received power set and a portion of the measured received powers in the first measured received power set. G4 can be understood as the first device performing further statistical processing on the matching degree of each pair of information in at least one pair of information shown in G3 to obtain first reported information. For example, the first reported information indicates the matching rate of at least one pair of information, which can be the number of matched information pairs divided by the total number of at least one pair of information.

[0342] Continuing with the example shown in Figure 11, the first reported information can indicate the statistical information corresponding to the difference between Δs1 and Δp1, and the difference between Δs2 and Δp2.

[0343] In one possible implementation, if the type of the first information #4 is the information shown in A3 above (i.e., predicted received power sorting information) and the type of the third information #4 is the information shown in B3 above (i.e., measured received power sorting information), the first device can determine a first number of elements in the first sequence that have a different logical order from those in the second sequence, and determine the first reporting information based on the first number.

[0344] The first sequence can be, for example, the result of sorting the identifiers of the second resource set based on a first order of the first predicted received power set. The second sequence can be, for example, the result of sorting the identifiers of the second resource set based on a first order of the first measured received power set. The content of the first order can be referred to the previous discussion and will not be repeated here. Different logical orders can be understood as the position of the first element in the first sequence being different from the position of the first element in the second sequence, or it can be understood as the position of the first element in the first sequence being different from the position of the first element in the second sequence, and the adjacent elements of the first element in the first sequence being different from the adjacent elements of the first element in the second sequence.

[0345] For example, the resource identifiers corresponding to the second resource set are 1, 2, 3, 5, and 9. The first predicted received power sets corresponding to the second resource set include 80dB, 110dB, 60dB, 113dB, and 109dB, respectively, and the first measured received power sets corresponding to the second resource set include 81dB, 114dB, 115dB, 118dB, and 111dB, respectively. Arranging the first device in descending order of the first predicted received power sets yields the first sequence, 5, 2, 9, 1, 3. Arranging the first device in descending order of the first measured received power sets yields the second sequence, 5, 3, 2, 9, 1. Thus, it can be seen that the adjacent elements of element 3 in the first sequence are all different from the adjacent elements of element 3 in the second sequence, and their positions are also different; therefore, the first quantity is 1.

[0346] For example, please refer to Figure 12, which is a schematic diagram of determining the first reported information according to an embodiment of this application. As shown in Figure 12, the second resource set includes beams 1 to N, and the first measured received power set includes the measured received power corresponding to beams 1 to N, such as S_RSRP1, S_RSRP2...S_RSRPN-1, S_RSRPN as shown in Figure 12. The first predicted received power set includes the measured received power corresponding to beams 1 to N, such as P_RSRP1, P_RSRP2...P_RSRPN-1, P_RSRPN as shown in Figure 12. "VS" in Figure 12 represents a comparison operation, such as difference calculation.

[0347] The first device can arrange the second resource set in descending order of measured received power to obtain the second sequence shown in Figure 12, which includes beams M, 3...K and 1 in sequence. Then, it can arrange the second resource set in descending order of predicted received power to obtain the first sequence, which includes beams M, 2...K and 1 in sequence. The first device can count the first quantity corresponding to the first and second sequences to determine the first reporting information.

[0348] The first reported information under G3 or G4 above can be regarded as indicating the degree of similarity between the first information set and the third information set.

[0349] Before determining the first reported information for any of G1 to G4 mentioned above, the first device can, based on the third weight set, perform weighted processing on each pair of information in at least one pair to obtain the first reported information. The value of the third weight set can be referred to the discussion of the value of the first weight set above, and will not be repeated here. In this way, the proportion of the more important received power can be increased, and more targeted first reported information can be obtained.

[0350] For example, if the matching degree between each pair of information in at least one pair is 0, 100, and 50 respectively, and the third weight set corresponding to at least one pair of information is 0.4, 0.5, and 0.1 respectively, then the statistical result of the matching degree of at least one pair of information can be: 0.4*0 + 0.5*100 + 0.1*50 = 55. Accordingly, the first reported information can indicate that the matching degree of at least one pair of information is 55.

[0351] Under F2, the first reported information can be the monitoring results that correspond to (or indicate, or are used to determine) the model.

[0352] In any of the G1 to G4 methods described above, the first device considers not only the first information set but also the second information set to determine the first reported information. This allows the first reported information to reflect the differences between the model's inference results and the measurement results, thus enabling more comprehensive and accurate model monitoring. Furthermore, when determining the first reported information, normalization, relative comparison processing, difference processing, or compensation processing are performed on either the first or second information set. This helps reduce the impact of individual power errors on the model's monitoring results and improves the accuracy of model monitoring. Moreover, when the first resource set includes multiple resources (e.g., all beams used for signal transmission), the first reported information effectively reflects the differences or similarities between the model's predictions and measurement results across all resources. This is equivalent to global monitoring of the first model, improving the comprehensiveness and accuracy of the first model's monitoring.

[0353] S803, the first device sends a first reporting message to the second device. Correspondingly, the second device receives the first reporting message from the first device.

[0354] The first device may send the first reporting information to the second device periodically or irregularly, without limitation. The first reporting information may be included in the CSI report or other messages.

[0355] The first device can send the first reporting information to the second device, or send the first reporting information to the second device through other devices; there are no limitations on this. For example, if the first device is an OTT device or a server, then the first device can send the first reporting information to the second device through a terminal device, or the first device can send the first reporting information directly to the second device. Alternatively, for example, if the second device is an OTT device or a server, then the first device can send the first reporting information to the second device through a network device (such as an access network device), or the first device can send the first reporting information directly to the second device.

[0356] Optionally, the first device may also send at least one transmission power information corresponding to the first information to the second device, whereby the transmission power information can be referred to as the first transmission power information. This transmission power corresponds to the transmission power of the training data used to train the first model. In this way, the second device can determine a power compensation value based on the first transmission power information and the actual transmission power of the second device, such as determining the first power compensation value mentioned above.

[0357] After receiving the first reported information, the second device can determine a strategy for managing the first model based on that information. For example, if the first reported information shows a significant difference between the first information set and the third information set, the second device can decide to switch to or update the first model. Conversely, if the first reported information shows a small difference between the first and third information sets, the second device can decide to continue using the first model.

[0358] This application provides a communication device. Figures 13 to 15 are schematic diagrams of possible structures of the communication device provided in the embodiments of this application. These communication devices can be used to implement the functions of the first device or the second device in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments. In the embodiments of this application, the communication device can be any of the terminal devices involved in Figures 4 to 7, the network devices involved in Figure 4 or Figure 5, the AI ​​network element involved in Figure 5, the CU, DU, core network device, access network node or OAM involved in Figure 6, or the non-real-time RIC, near-real-time RIC, CU, DU, CU-CP or RU involved in Figure 7, etc.

[0359] The communication device shown in Figure 13 will now be described. As shown in Figure 13, the communication device 1300 may include modules or units for implementing the methods described above. In one possible design, the communication device 1300 includes a processing unit 1310 and a communication unit 1320. The communication unit 1320 is used to perform transmit and receive operations, such as functions related to sending and receiving; the communication unit 1320 may be referred to as a transceiver unit; optionally, the communication unit 1320 includes a receiving unit and a transmitting unit. The processing unit 1310 is used to perform processing operations. Alternatively, the communication unit 1320 may be a transmitter and a receiver, or a transmitter and a receiver. Optionally, the communication device 1300 may also include a storage unit 1330. The storage unit 1330 is used to store the device's program code or data. The storage unit 1330 is indicated by a dashed box in Figure 13 as an optional unit.

[0360] In the first embodiment, the communication device 1300 can be the first device in the above embodiments, such as the communication module in the first device, or the circuit or chip in the first device responsible for communication functions.

[0361] For example, the communication device 1300 can implement the functions of the first device in the method implementation shown in FIG8 above.

[0362] In the above embodiments, the processing unit 1310 is used to determine the first information set and the first reporting information, and the communication unit 1320 is used to send the first reporting information.

[0363] For example, the processing unit 1310 is used to execute the steps of S801 and S802, and the communication unit 1320 is used to execute the content of sending the first reporting information involved in S803.

[0364] The communication device 1300 can also perform other steps executed by the first device in the method implementation shown in Figure 8 above, which will not be listed here one by one.

[0365] In the second embodiment, the communication device 1300 can be the second device in the above embodiments, such as the communication module in the second device, or the circuit or chip in the second device responsible for communication functions.

[0366] For example, the communication device 1300 can implement the functions of the second device in the method implementation shown in Figure 8 above.

[0367] In the above embodiment, the communication unit 1320 is used to receive the first reported information.

[0368] For example, the processing unit 1310 is used to execute the content of receiving the first reported information involved in S803.

[0369] The communication device 1300 can also perform other steps executed by the second device in the method implementation shown in Figure 8 above, which will not be listed here one by one.

[0370] In one possible design, when the communication device 1300 is an OTT device, server, terminal device, communication module in a terminal device, access network device, or communication module in an access network device, the function of the processing unit 1310 can be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-a-chip (SoC) chip or SIP chip containing a modem core. The function of the communication unit 1320 can be implemented by transceiver circuitry.

[0371] In one possible design, when the communication device 1300 is a circuit or chip responsible for communication functions in a terminal device, or a circuit or chip responsible for communication functions in an access network device, such as a modem chip or a system-on-a-chip (SoC) chip or SIP chip containing a modem core, the function of the processing unit 1310 can be implemented by a circuit system including one or more processors or processor cores in the aforementioned chip. The function of the communication unit 1320 can be implemented by the interface circuit or data transceiver circuit on the aforementioned chip.

[0372] It is understood that the division of units in the above-described device is merely a logical functional division. Each function can correspond to a functional unit, or two or more functions can be integrated into one functional unit. In actual implementation, all or some units can be integrated into a single physical entity, or they can be distributed across different physical entities. Furthermore, the aforementioned functional units can be implemented in hardware, software, or a combination of both. Whether a function is executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0373] In one example, the functional unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as: one or more application-specific integrated circuits (ASICs), or one or more central processing units (CPUs), one or more microcontroller units (MCUs), one or more DSPs, or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0374] In one example, storage unit 1330 may include random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory and / or registers, etc.

[0375] The communication device shown in Figure 14 will now be described. As shown in Figure 14, the communication device 1400 includes a processor 1410. Optionally, the communication device 1400 also includes an interface circuit 1420 and a memory 1430. The processor 1410 and the interface circuit 1420 are coupled to each other. It is understood that the interface circuit 1420 can be a transceiver or an input / output interface. The memory 1430 is used to store instructions executed by the processor 1410, or to store input data required by the processor 1410 to execute instructions, or to store data generated after the processor 1410 executes instructions. The interface circuit 1420 and the memory 1430 are optional modules and are shown in Figure 14 with dashed boxes. In addition, Figure 14 shows an example with one processor 1410 and one memory 1430, but the number of processors 1410 and memory 1430 is not actually limited.

[0376] The communication device 1400 is used to implement the method embodiment shown in FIG8. Optionally, the processor 1410 is used to implement the functions of the processing unit 1310, and the interface circuit 1420 is used to implement the functions of the communication unit 1320.

[0377] When the communication device 1400 is a chip applied to a device (such as the first or second device mentioned above), the chip implements the functions of the device in the above method embodiments. The chip receives information from other modules (such as radio frequency modules or antennas) in the device, which is information sent to the device by other devices; or, the chip sends information to other modules (such as radio frequency modules or antennas) in the device, which is information sent by the device to other devices. Here, the communication device 1400 can be a baseband chip of a device, or a DU or other modules. The DU can be a DU under an open radio access network (O-RAN) architecture.

[0378] The processor 1410 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor can be a microprocessor or any conventional processor. Furthermore, the memory involved in the various embodiments of this application can include volatile memory, such as random access memory (RAM). The memory can also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drives (HDDs), or solid-state drives (SSDs).

[0379] In one possible embodiment, the communication device 1400 may be a first device or a processor (circuit) or chip of the first device. The communication device can be used to perform the operations performed by the first device in the above method embodiments. For example, the communication device can be used to implement the functions of the first device in the method implementation shown in FIG8.

[0380] For example, processor 1410 is used to execute steps S801 and S802, and interface circuit 1420 is used to execute step S803 involving sending the first reporting information.

[0381] In another possible embodiment, the communication device 1400 may be a second device or a processor (circuit) or chip of the second device. The communication device can be used to perform operations performed by the second device in the above method embodiments. For example, the communication device can be used to implement the functions of the second device in the method implementation shown in FIG8.

[0382] For example, interface circuit 1420 is used to perform the step of receiving the first reported information involved in S803.

[0383] As shown in Figure 15, the communication device 1500 includes a processor 1510 and a transceiver 1530. The processor 1510 can also be referred to as a processing unit, processing board, processing module, or processing device. The transceiver 1530 can also be referred to as a transceiver unit, transceiver, or transceiver device. The transceiver 1530 includes a transmitter 1531, a receiver 1532, and an antenna 1533. Optionally, the transceiver 1530 may also include radio frequency circuitry and input / output devices, etc., without specific limitations.

[0384] Optionally, the device in transceiver 1530 used to implement the receiving function is considered a receiving module, and the device in transceiver 1530 used to implement the transmitting function is considered a transmitting module. That is, transceiver 1530 includes a receiver and a transmitter. A transceiver may sometimes be called a transceiver unit, transceiver module, or transceiver circuit, etc. A receiver may sometimes be called a receiver unit, receiving module, or receiving circuit, etc. A transmitter may sometimes be called a transmitter, transmitting module, or transmitting circuit, etc.

[0385] Optionally, the communication device 1500 may also include a memory 1520, which may store computer program code and / or data.

[0386] The processor 1510 is mainly used for processing communication protocols and data, controlling the communication device 1500, executing software programs, and processing software program data. The memory 1520 is mainly used for storing software programs and data. The radio frequency (RF) circuit is mainly used for converting baseband signals to RF signals and processing RF signals. The antenna 1533 is mainly used for transmitting and receiving RF signals in the form of electromagnetic waves. Input / output devices, such as touchscreens, displays, and keyboards, are mainly used for receiving user input data and outputting data to the user.

[0387] When data needs to be transmitted, the processor 1510 performs baseband processing on the data to be transmitted and outputs a baseband signal to the radio frequency (RF) circuit. The RF circuit then processes the baseband signal and transmits it outward as an electromagnetic wave through the antenna. When data is sent to the communication device 1500, the RF circuit receives the RF signal through the antenna, converts it into a baseband signal, and outputs the baseband signal to the processor. The processor 1510 converts the baseband signal back into data and processes it. For ease of explanation, Figure 15 only shows one memory 1520, processor 1510, and transceiver 1530. In actual terminal products, there may be one or more processors 1510 and one or more memories 1520. The memory 1520 may also be referred to as a storage medium or storage device. The memory 1520 may be independent of the processor 1510 or integrated with it; there is no limitation on this.

[0388] In this embodiment, the antenna and radio frequency circuit with transceiver functions are considered as communication units of the communication device 1500, and the processor with processing functions is considered as processing units of the communication device 1500. The processor 1510 is used to execute the processing actions on the first or second device side in the above embodiments, and the transceiver 1530 is used to execute the transceiver actions on the first or second device side in the above embodiments.

[0389] For example, processor 1510 is used to execute steps S801 and S802, and transceiver 1530 is used to execute step S803 involving sending the first reporting information.

[0390] For example, transceiver 1530 is used to perform the step of receiving the first reported information involved in S803.

[0391] When the communication device 1500 is a chip, the chip includes a processor and a transceiver. The transceiver can be an input / output circuit or a communication interface; the processor can be a processing module integrated on the chip, a microprocessor, or an integrated circuit. Optionally, the chip may also include a memory. In the above method embodiments, the transmitting operation of the first or second device can be understood as the output of the chip, and the receiving operation of the first or second device in the above method embodiments can be understood as the input of the chip.

[0392] This application provides a communication system. The communication system includes a first device and a second device. The first device can implement the functions of the first device in the method embodiment shown in FIG8, and the second device can implement the functions of the second device in the method embodiment shown in FIG8.

[0393] This application provides a chip system comprising a processor and an interface. The processor is used to call and execute instructions from the interface, and when the processor executes the instructions, it implements the method shown in Figure 8 above.

[0394] This application provides a computer-readable storage medium for storing computer programs or instructions that, when run, implement the method embodiment shown in FIG8.

[0395] This application provides a program product that, when run on a computer, implements the method embodiment shown in FIG8. The program product may include, for example, instructions and / or computer program products.

[0396] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0397] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0398] The various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers described above does not imply the order of execution; the execution order of each process should be based on its function and internal logic.

Claims

1. A communication method, characterized in that, The method includes: A first information set is determined, the first information set including at least one first piece of information, the type of the at least one first piece of information including one of the following: normalized predicted received power information, first relative received power information, predicted received power ranking information, or predicted received power information; The first reported information is determined based on the first information set; Send the first reported information.

2. The method according to claim 1, characterized in that, The type of the at least one first piece of information includes normalized predicted received power information; One of the at least one pieces of first information corresponds to the relative value between the predicted received power and the first reference received power.

3. The method according to claim 1, characterized in that, The type of at least one first piece of information includes first relative received power information; One of the at least one pieces of first information corresponds to the relative value of a first predicted received power and a second predicted received power, wherein the first predicted received power corresponds to a first resource identifier and the second predicted received power corresponds to a second resource identifier.

4. The method according to claim 1, characterized in that, The type of at least one first piece of information includes predicted received power ranking information; One of the first pieces of information includes sorting information of the third predicted received power relative to one or more fourth predicted received powers; or, One of the first pieces of information includes sorting information of a third resource identifier relative to one or more fourth resource identifiers, wherein the sorting of the third resource identifier relative to the one or more fourth resource identifiers is determined by the magnitude of the third predicted received power corresponding to the third resource identifier and the one or more fourth predicted received power corresponding to the one or more fourth resource identifiers.

5. The method according to claim 1, characterized in that, The type of at least one first piece of information includes predicted received power information; The first reported information includes at least one second piece of information, one of the second pieces of information corresponds to one of the first pieces of information, and the received power corresponding to the second piece of information differs from the predicted received power corresponding to the first piece of information by a first power compensation value.

6. The method according to claim 5, characterized in that, The method further includes: Receive first indication information, wherein the first indication information is used to determine the first power compensation value.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: A third information set is determined, the third information set including at least one third information, the type of the at least one third information including: normalized measured received power information, second relative received power information, measured received power sorting information, or measured received power information; Determining the first reported information based on the first information set includes: determining the first reported information based on the first information set and the third information set, wherein the first reported information is determined based on the degree of similarity or difference between the at least one first piece of information and the at least one third piece of information.

8. The method according to claim 7, characterized in that, The type of the at least one first piece of information includes normalized predicted received power information, and the type of the at least one third piece of information includes normalized predicted received power information; One of the at least three pieces of information corresponds to the relative value between the measured received power and the second reference received power.

9. The method according to claim 7, characterized in that, The type of the at least one first piece of information includes first relative received power information, and the type of the at least one third piece of information includes second relative received power information; One of the at least one third pieces of information corresponds to the relative value of the first measured received power and the second measured received power, wherein the first measured received power corresponds to the first resource identifier and the second measured received power corresponds to the second resource identifier.

10. The method according to claim 7, characterized in that, The type of the at least one first piece of information includes predicted power ranking information, and the type of the at least one third piece of information includes measured power ranking information; One of the at least one third pieces of information includes sorting information of the third measured received power relative to one or more fourth measured received powers; or, One of the at least three pieces of information includes sorting information of a third resource identifier relative to one or more fourth resource identifiers, wherein the sorting of the third resource identifier relative to one or more fourth resource identifiers is determined by the magnitude of the third measurement received power corresponding to the third resource identifier and the magnitude of the one or more fourth measurement received power corresponding to the one or more fourth resource identifiers.

11. The method according to claim 7, characterized in that, The type of the at least one first piece of information includes predicted received power information, and the type of the at least one third piece of information includes measured received power information; The measured received power corresponding to one of the at least three pieces of information differs from the fifth measured received power by a second power compensation value, wherein the fifth measured received power is the received power obtained by measuring the resource associated with the resource identifier corresponding to the one piece of information.

12. The method according to claim 11, characterized in that, The method further includes: Receive second indication information, wherein the second indication information is used to determine the second power compensation value.

13. The method according to claim 7, characterized in that, The type of the at least one first piece of information includes predicted received power information, and the type of the at least one third piece of information includes measured received power information; The first reported information is determined based on a first difference and a third power compensation value, wherein the first difference is the difference between the predicted received power corresponding to a first piece of information and the measured received power corresponding to a third piece of information; The first piece of information belongs to the at least one first piece of information, and the third piece of information is the measured received power information that corresponds to the first piece of information among the at least one third piece of information.

14. The method according to any one of claims 1-13, characterized in that, The type of the at least one first piece of information includes predicted received power information, and the method further includes... The transmission power information corresponding to the at least one first piece of information is transmitted, wherein the transmission power information is the transmission power corresponding to the training data used to train the first model, and the at least one first piece of information is determined according to the first model.

15. A communication method, characterized in that, The method includes: Receive first reported information, which is related to a first information set. The first information set includes at least one first piece of information, and the type of the at least one first piece of information includes one of the following: normalized predicted received power information, first relative received power information, predicted received power ranking information, or predicted received power information.

16. The method according to claim 15, characterized in that, The type of the at least one first piece of information includes normalized predicted received power information; One of the at least one pieces of first information corresponds to the relative value between the predicted received power and the first reference received power.

17. The method according to claim 15, characterized in that, The type of at least one first piece of information includes first relative received power information; One of the at least one pieces of first information corresponds to the relative value of a first predicted received power and a second predicted received power, wherein the first predicted received power corresponds to a first resource identifier and the second predicted received power corresponds to a second resource identifier.

18. The method according to claim 15, characterized in that, The type of at least one first piece of information includes predicted received power ranking information; One of the first pieces of information includes sorting information of the third predicted received power relative to one or more fourth predicted received powers; or, One of the first pieces of information includes sorting information of a third resource identifier relative to one or more fourth resource identifiers, wherein the sorting of the third resource identifier relative to the one or more fourth resource identifiers is determined by the magnitude of the third predicted received power corresponding to the third resource identifier and the one or more fourth predicted received power corresponding to the one or more fourth resource identifiers.

19. The method according to claim 15, characterized in that, The type of at least one first piece of information includes predicted received power information; The first reported information includes at least one second piece of information, one of the second pieces of information corresponds to one of the first pieces of information, and the received power corresponding to the second piece of information differs from the predicted received power corresponding to the first piece of information by a first power compensation value.

20. The method according to claim 19, characterized in that, The method further includes: Receive first indication information, wherein the first indication information is used to determine the first power compensation value.

21. The method according to any one of claims 15-20, characterized in that, The first reported information is determined based on the degree of similarity or difference between the at least one first piece of information and at least one third piece of information in the set of at least one third piece of information, wherein the type of the at least one third piece of information includes: normalized measured received power information, second relative received power information, measured received power ranking information, or measured received power information.

22. The method according to claim 21, characterized in that, The type of the at least one first piece of information includes normalized predicted received power information, and the type of the at least one third piece of information includes normalized predicted received power information; One of the at least three pieces of information corresponds to the relative value between the measured received power and the second reference received power.

23. The method according to claim 21, characterized in that, The type of the at least one first piece of information includes first relative received power information, and the type of the at least one third piece of information includes second relative received power information; One of the at least one third pieces of information corresponds to the relative value of the first measured received power and the second measured received power, wherein the first measured received power corresponds to the first resource identifier and the second measured received power corresponds to the second resource identifier.

24. The method according to claim 21, characterized in that, The type of the at least one first piece of information includes predicted power ranking information, and the type of the at least one third piece of information includes measured power ranking information; One of the at least one third pieces of information includes sorting information of the third measured received power relative to one or more fourth measured received powers; or, One of the at least three pieces of information includes sorting information of a third resource identifier relative to one or more fourth resource identifiers, wherein the sorting of the third resource identifier relative to one or more fourth resource identifiers is determined by the magnitude of the third measurement received power corresponding to the third resource identifier and the magnitude of the one or more fourth measurement received power corresponding to the one or more fourth resource identifiers.

25. The method according to claim 21, characterized in that, The type of the at least one first piece of information includes predicted received power information, and the type of the at least one third piece of information includes measured received power information; The measured received power corresponding to one of the at least three pieces of information differs from the fifth measured received power by a second power compensation value, wherein the fifth measured received power is the received power obtained by measuring the resource associated with the resource identifier corresponding to the one piece of information.

26. The method according to claim 25, characterized in that, The method further includes: Send a second indication message, wherein the second indication message is used to determine the second power compensation value.

27. The method according to claim 21, characterized in that, The type of the at least one first piece of information includes predicted received power information, and the type of the at least one third piece of information includes measured received power information; The first reported information is determined based on a first difference and a third power compensation value, wherein the first difference is the difference between the predicted received power corresponding to a first piece of information and the measured received power corresponding to a third piece of information; The first piece of information belongs to the at least one first piece of information, and the third piece of information is the measured received power information that corresponds to the first piece of information among the at least one third piece of information.

28. The method according to any one of claims 15-27, characterized in that, The type of the at least one first piece of information includes predicted received power information, and the method further includes... The system receives transmission power information corresponding to at least one first piece of information, wherein the transmission power information is the transmission power corresponding to the training data used to train the first model, and the at least one first piece of information is determined according to the first model.

29. A communication device, characterized in that, The device includes: A module for performing the method as described in any one of claims 1-14; or, A module for performing the method as described in any one of claims 15-28.

30. A communication device, characterized in that, The device includes one or more processors, which are configured to execute computer programs or instructions in memory, such that the communication device implements the method as claimed in any one of claims 1-14 or the method as claimed in any one of claims 15-28.

31. A readable storage medium, characterized in that, Used to store instructions, which, when executed, perform the method as described in any one of claims 1-28.

32. A computer program product, characterized in that, Includes instructions, when which the method is performed as described in any one of claims 1-28.

33. A communication system, characterized in that, Includes means for performing the method as claimed in any one of claims 1-14 and means for performing the method as claimed in any one of claims 15-28.

Images